Upload Phase3 QLoRA adapter
Browse files- .gitattributes +3 -0
- README.md +202 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- checkpoint-13396/README.md +202 -0
- checkpoint-13396/adapter_config.json +39 -0
- checkpoint-13396/adapter_model.safetensors +3 -0
- checkpoint-13396/optimizer.pt +3 -0
- checkpoint-13396/rng_state.pth +3 -0
- checkpoint-13396/scheduler.pt +3 -0
- checkpoint-13396/special_tokens_map.json +17 -0
- checkpoint-13396/tokenizer.json +3 -0
- checkpoint-13396/tokenizer_config.json +2063 -0
- checkpoint-13396/trainer_state.json +3779 -0
- checkpoint-13396/training_args.bin +3 -0
- checkpoint-6698/README.md +202 -0
- checkpoint-6698/adapter_config.json +39 -0
- checkpoint-6698/adapter_model.safetensors +3 -0
- checkpoint-6698/optimizer.pt +3 -0
- checkpoint-6698/rng_state.pth +3 -0
- checkpoint-6698/scheduler.pt +3 -0
- checkpoint-6698/special_tokens_map.json +17 -0
- checkpoint-6698/tokenizer.json +3 -0
- checkpoint-6698/tokenizer_config.json +2063 -0
- checkpoint-6698/trainer_state.json +1903 -0
- checkpoint-6698/training_args.bin +3 -0
- runs/Apr29_04-40-07_sg238/events.out.tfevents.1745926808.sg238.3949072.0 +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-13396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-6698/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-3B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 32,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2eeff804972b0a0f1e29b91d0def6715e90f7642dfe2d382e6bc84ee843fe4
|
| 3 |
+
size 194563400
|
checkpoint-13396/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-3B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
checkpoint-13396/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 32,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-13396/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2eeff804972b0a0f1e29b91d0def6715e90f7642dfe2d382e6bc84ee843fe4
|
| 3 |
+
size 194563400
|
checkpoint-13396/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4df6db305ad9f202bb72227874f515f1ad3edb3d7056bcf48ee5a433bd4f7af6
|
| 3 |
+
size 389352298
|
checkpoint-13396/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:139073485977a5422638ab0c9fa5461bec1c22cb87d137c972feaf3b153065f6
|
| 3 |
+
size 14244
|
checkpoint-13396/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:461cb458ab19c8e296bfeb272112eef240ce4075123156f827151f22ed257cd7
|
| 3 |
+
size 1064
|
checkpoint-13396/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
+
}
|
checkpoint-13396/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-13396/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|end_of_text|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2063 |
+
}
|
checkpoint-13396/trainer_state.json
ADDED
|
@@ -0,0 +1,3779 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 13396,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0037324574499850703,
|
| 14 |
+
"grad_norm": 2.1287152767181396,
|
| 15 |
+
"learning_rate": 1.2468827930174565e-06,
|
| 16 |
+
"loss": 2.5876,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0074649148999701405,
|
| 21 |
+
"grad_norm": 1.5928611755371094,
|
| 22 |
+
"learning_rate": 2.493765586034913e-06,
|
| 23 |
+
"loss": 2.4586,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.011197372349955211,
|
| 28 |
+
"grad_norm": 2.13069748878479,
|
| 29 |
+
"learning_rate": 3.7406483790523696e-06,
|
| 30 |
+
"loss": 2.3632,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.014929829799940281,
|
| 35 |
+
"grad_norm": 4.3777875900268555,
|
| 36 |
+
"learning_rate": 4.987531172069826e-06,
|
| 37 |
+
"loss": 2.0385,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01866228724992535,
|
| 42 |
+
"grad_norm": 1.8015117645263672,
|
| 43 |
+
"learning_rate": 6.234413965087282e-06,
|
| 44 |
+
"loss": 1.7473,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.022394744699910422,
|
| 49 |
+
"grad_norm": 2.9806246757507324,
|
| 50 |
+
"learning_rate": 7.481296758104739e-06,
|
| 51 |
+
"loss": 1.6573,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02612720214989549,
|
| 56 |
+
"grad_norm": 2.6732096672058105,
|
| 57 |
+
"learning_rate": 8.728179551122195e-06,
|
| 58 |
+
"loss": 1.5128,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.029859659599880562,
|
| 63 |
+
"grad_norm": 2.345278024673462,
|
| 64 |
+
"learning_rate": 9.975062344139652e-06,
|
| 65 |
+
"loss": 1.5679,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03359211704986563,
|
| 70 |
+
"grad_norm": 1.6303949356079102,
|
| 71 |
+
"learning_rate": 1.122194513715711e-05,
|
| 72 |
+
"loss": 1.6128,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0373245744998507,
|
| 77 |
+
"grad_norm": 1.976975917816162,
|
| 78 |
+
"learning_rate": 1.2468827930174564e-05,
|
| 79 |
+
"loss": 1.473,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04105703194983577,
|
| 84 |
+
"grad_norm": 1.7693899869918823,
|
| 85 |
+
"learning_rate": 1.3715710723192021e-05,
|
| 86 |
+
"loss": 1.441,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.044789489399820845,
|
| 91 |
+
"grad_norm": 3.1766514778137207,
|
| 92 |
+
"learning_rate": 1.4962593516209478e-05,
|
| 93 |
+
"loss": 1.4022,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04852194684980591,
|
| 98 |
+
"grad_norm": 1.5538763999938965,
|
| 99 |
+
"learning_rate": 1.6209476309226934e-05,
|
| 100 |
+
"loss": 1.3989,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05225440429979098,
|
| 105 |
+
"grad_norm": 1.815725326538086,
|
| 106 |
+
"learning_rate": 1.745635910224439e-05,
|
| 107 |
+
"loss": 1.3802,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05598686174977605,
|
| 112 |
+
"grad_norm": 2.7508153915405273,
|
| 113 |
+
"learning_rate": 1.8703241895261847e-05,
|
| 114 |
+
"loss": 1.4179,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.059719319199761124,
|
| 119 |
+
"grad_norm": 1.0810010433197021,
|
| 120 |
+
"learning_rate": 1.9950124688279304e-05,
|
| 121 |
+
"loss": 1.2646,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06345177664974619,
|
| 126 |
+
"grad_norm": 1.8426517248153687,
|
| 127 |
+
"learning_rate": 1.9999831678944005e-05,
|
| 128 |
+
"loss": 1.3424,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06718423409973126,
|
| 133 |
+
"grad_norm": 2.5106186866760254,
|
| 134 |
+
"learning_rate": 1.9999298376279043e-05,
|
| 135 |
+
"loss": 1.4793,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07091669154971633,
|
| 140 |
+
"grad_norm": 2.054409980773926,
|
| 141 |
+
"learning_rate": 1.999839981926073e-05,
|
| 142 |
+
"loss": 1.3784,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0746491489997014,
|
| 147 |
+
"grad_norm": 1.7603126764297485,
|
| 148 |
+
"learning_rate": 1.9997136040711548e-05,
|
| 149 |
+
"loss": 1.3707,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07838160644968648,
|
| 154 |
+
"grad_norm": 3.026569128036499,
|
| 155 |
+
"learning_rate": 1.99955070867948e-05,
|
| 156 |
+
"loss": 1.3515,
|
| 157 |
+
"step": 525
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08211406389967155,
|
| 161 |
+
"grad_norm": 1.8115179538726807,
|
| 162 |
+
"learning_rate": 1.9993513017012914e-05,
|
| 163 |
+
"loss": 1.2936,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08584652134965662,
|
| 168 |
+
"grad_norm": 1.5803134441375732,
|
| 169 |
+
"learning_rate": 1.999115390420526e-05,
|
| 170 |
+
"loss": 1.3345,
|
| 171 |
+
"step": 575
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08957897879964169,
|
| 175 |
+
"grad_norm": 1.7329767942428589,
|
| 176 |
+
"learning_rate": 1.9988429834545516e-05,
|
| 177 |
+
"loss": 1.2807,
|
| 178 |
+
"step": 600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09331143624962675,
|
| 182 |
+
"grad_norm": 1.9004117250442505,
|
| 183 |
+
"learning_rate": 1.998534090753849e-05,
|
| 184 |
+
"loss": 1.3161,
|
| 185 |
+
"step": 625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.09704389369961182,
|
| 189 |
+
"grad_norm": 2.8287253379821777,
|
| 190 |
+
"learning_rate": 1.99818872360165e-05,
|
| 191 |
+
"loss": 1.3086,
|
| 192 |
+
"step": 650
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.10077635114959689,
|
| 196 |
+
"grad_norm": 1.6014684438705444,
|
| 197 |
+
"learning_rate": 1.9978068946135253e-05,
|
| 198 |
+
"loss": 1.3899,
|
| 199 |
+
"step": 675
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.10450880859958196,
|
| 203 |
+
"grad_norm": 1.3626344203948975,
|
| 204 |
+
"learning_rate": 1.9973886177369238e-05,
|
| 205 |
+
"loss": 1.3327,
|
| 206 |
+
"step": 700
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.10824126604956703,
|
| 210 |
+
"grad_norm": 1.674828052520752,
|
| 211 |
+
"learning_rate": 1.9969339082506622e-05,
|
| 212 |
+
"loss": 1.3386,
|
| 213 |
+
"step": 725
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1119737234995521,
|
| 217 |
+
"grad_norm": 1.8585690259933472,
|
| 218 |
+
"learning_rate": 1.996442782764368e-05,
|
| 219 |
+
"loss": 1.3538,
|
| 220 |
+
"step": 750
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11570618094953718,
|
| 224 |
+
"grad_norm": 2.4924845695495605,
|
| 225 |
+
"learning_rate": 1.9959152592178723e-05,
|
| 226 |
+
"loss": 1.3291,
|
| 227 |
+
"step": 775
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.11943863839952225,
|
| 231 |
+
"grad_norm": 1.6198917627334595,
|
| 232 |
+
"learning_rate": 1.995351356880554e-05,
|
| 233 |
+
"loss": 1.1865,
|
| 234 |
+
"step": 800
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12317109584950732,
|
| 238 |
+
"grad_norm": 1.76533842086792,
|
| 239 |
+
"learning_rate": 1.994751096350637e-05,
|
| 240 |
+
"loss": 1.3401,
|
| 241 |
+
"step": 825
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12690355329949238,
|
| 245 |
+
"grad_norm": 1.99082612991333,
|
| 246 |
+
"learning_rate": 1.994114499554436e-05,
|
| 247 |
+
"loss": 1.2676,
|
| 248 |
+
"step": 850
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13063601074947745,
|
| 252 |
+
"grad_norm": 1.4129736423492432,
|
| 253 |
+
"learning_rate": 1.9934415897455586e-05,
|
| 254 |
+
"loss": 1.3497,
|
| 255 |
+
"step": 875
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13436846819946252,
|
| 259 |
+
"grad_norm": 1.4906266927719116,
|
| 260 |
+
"learning_rate": 1.9927323915040526e-05,
|
| 261 |
+
"loss": 1.2567,
|
| 262 |
+
"step": 900
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1381009256494476,
|
| 266 |
+
"grad_norm": 1.525483250617981,
|
| 267 |
+
"learning_rate": 1.9919869307355104e-05,
|
| 268 |
+
"loss": 1.2826,
|
| 269 |
+
"step": 925
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14183338309943266,
|
| 273 |
+
"grad_norm": 2.0674450397491455,
|
| 274 |
+
"learning_rate": 1.9912052346701215e-05,
|
| 275 |
+
"loss": 1.2984,
|
| 276 |
+
"step": 950
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.14556584054941774,
|
| 280 |
+
"grad_norm": 1.3082191944122314,
|
| 281 |
+
"learning_rate": 1.9903873318616783e-05,
|
| 282 |
+
"loss": 1.3463,
|
| 283 |
+
"step": 975
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.1492982979994028,
|
| 287 |
+
"grad_norm": 1.1901448965072632,
|
| 288 |
+
"learning_rate": 1.9895332521865334e-05,
|
| 289 |
+
"loss": 1.2979,
|
| 290 |
+
"step": 1000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15303075544938788,
|
| 294 |
+
"grad_norm": 1.5535725355148315,
|
| 295 |
+
"learning_rate": 1.988643026842507e-05,
|
| 296 |
+
"loss": 1.243,
|
| 297 |
+
"step": 1025
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15676321289937295,
|
| 301 |
+
"grad_norm": 1.5167412757873535,
|
| 302 |
+
"learning_rate": 1.98771668834775e-05,
|
| 303 |
+
"loss": 1.2642,
|
| 304 |
+
"step": 1050
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16049567034935802,
|
| 308 |
+
"grad_norm": 1.1971468925476074,
|
| 309 |
+
"learning_rate": 1.986754270539552e-05,
|
| 310 |
+
"loss": 1.2216,
|
| 311 |
+
"step": 1075
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.1642281277993431,
|
| 315 |
+
"grad_norm": 2.145617723464966,
|
| 316 |
+
"learning_rate": 1.98575580857311e-05,
|
| 317 |
+
"loss": 1.31,
|
| 318 |
+
"step": 1100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.16796058524932816,
|
| 322 |
+
"grad_norm": 1.7136638164520264,
|
| 323 |
+
"learning_rate": 1.9847213389202407e-05,
|
| 324 |
+
"loss": 1.3125,
|
| 325 |
+
"step": 1125
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.17169304269931324,
|
| 329 |
+
"grad_norm": 1.0633866786956787,
|
| 330 |
+
"learning_rate": 1.9836508993680494e-05,
|
| 331 |
+
"loss": 1.2653,
|
| 332 |
+
"step": 1150
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1754255001492983,
|
| 336 |
+
"grad_norm": 1.4107152223587036,
|
| 337 |
+
"learning_rate": 1.982544529017551e-05,
|
| 338 |
+
"loss": 1.3267,
|
| 339 |
+
"step": 1175
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17915795759928338,
|
| 343 |
+
"grad_norm": 1.7887978553771973,
|
| 344 |
+
"learning_rate": 1.981402268282238e-05,
|
| 345 |
+
"loss": 1.3425,
|
| 346 |
+
"step": 1200
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18289041504926845,
|
| 350 |
+
"grad_norm": 1.6244795322418213,
|
| 351 |
+
"learning_rate": 1.9802241588866104e-05,
|
| 352 |
+
"loss": 1.2189,
|
| 353 |
+
"step": 1225
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1866228724992535,
|
| 357 |
+
"grad_norm": 2.4690091609954834,
|
| 358 |
+
"learning_rate": 1.979010243864645e-05,
|
| 359 |
+
"loss": 1.2242,
|
| 360 |
+
"step": 1250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19035532994923857,
|
| 364 |
+
"grad_norm": 1.7802854776382446,
|
| 365 |
+
"learning_rate": 1.977760567558228e-05,
|
| 366 |
+
"loss": 1.2209,
|
| 367 |
+
"step": 1275
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.19408778739922364,
|
| 371 |
+
"grad_norm": 0.9973099827766418,
|
| 372 |
+
"learning_rate": 1.976475175615533e-05,
|
| 373 |
+
"loss": 1.2717,
|
| 374 |
+
"step": 1300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.1978202448492087,
|
| 378 |
+
"grad_norm": 1.479239821434021,
|
| 379 |
+
"learning_rate": 1.9751541149893553e-05,
|
| 380 |
+
"loss": 1.3293,
|
| 381 |
+
"step": 1325
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.20155270229919378,
|
| 385 |
+
"grad_norm": 2.492645025253296,
|
| 386 |
+
"learning_rate": 1.9737974339353944e-05,
|
| 387 |
+
"loss": 1.2891,
|
| 388 |
+
"step": 1350
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.20528515974917885,
|
| 392 |
+
"grad_norm": 1.1490769386291504,
|
| 393 |
+
"learning_rate": 1.9724051820104935e-05,
|
| 394 |
+
"loss": 1.3399,
|
| 395 |
+
"step": 1375
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.20901761719916392,
|
| 399 |
+
"grad_norm": 1.0268490314483643,
|
| 400 |
+
"learning_rate": 1.9709774100708285e-05,
|
| 401 |
+
"loss": 1.2535,
|
| 402 |
+
"step": 1400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.212750074649149,
|
| 406 |
+
"grad_norm": 2.1317245960235596,
|
| 407 |
+
"learning_rate": 1.9695141702700508e-05,
|
| 408 |
+
"loss": 1.2751,
|
| 409 |
+
"step": 1425
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.21648253209913407,
|
| 413 |
+
"grad_norm": 2.0975019931793213,
|
| 414 |
+
"learning_rate": 1.9680155160573803e-05,
|
| 415 |
+
"loss": 1.293,
|
| 416 |
+
"step": 1450
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.22021498954911914,
|
| 420 |
+
"grad_norm": 1.1691114902496338,
|
| 421 |
+
"learning_rate": 1.9664815021756563e-05,
|
| 422 |
+
"loss": 1.3222,
|
| 423 |
+
"step": 1475
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2239474469991042,
|
| 427 |
+
"grad_norm": 2.5722885131835938,
|
| 428 |
+
"learning_rate": 1.9649121846593346e-05,
|
| 429 |
+
"loss": 1.2455,
|
| 430 |
+
"step": 1500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.22767990444908928,
|
| 434 |
+
"grad_norm": 1.5031440258026123,
|
| 435 |
+
"learning_rate": 1.9633076208324427e-05,
|
| 436 |
+
"loss": 1.2319,
|
| 437 |
+
"step": 1525
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23141236189907435,
|
| 441 |
+
"grad_norm": 1.3974519968032837,
|
| 442 |
+
"learning_rate": 1.961667869306486e-05,
|
| 443 |
+
"loss": 1.3008,
|
| 444 |
+
"step": 1550
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.23514481934905943,
|
| 448 |
+
"grad_norm": 1.469709038734436,
|
| 449 |
+
"learning_rate": 1.959992989978304e-05,
|
| 450 |
+
"loss": 1.2394,
|
| 451 |
+
"step": 1575
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2388772767990445,
|
| 455 |
+
"grad_norm": 1.490043044090271,
|
| 456 |
+
"learning_rate": 1.958283044027887e-05,
|
| 457 |
+
"loss": 1.3695,
|
| 458 |
+
"step": 1600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.24260973424902957,
|
| 462 |
+
"grad_norm": 1.4141137599945068,
|
| 463 |
+
"learning_rate": 1.956538093916137e-05,
|
| 464 |
+
"loss": 1.2551,
|
| 465 |
+
"step": 1625
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.24634219169901464,
|
| 469 |
+
"grad_norm": 1.017072081565857,
|
| 470 |
+
"learning_rate": 1.9547582033825888e-05,
|
| 471 |
+
"loss": 1.2362,
|
| 472 |
+
"step": 1650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2500746491489997,
|
| 476 |
+
"grad_norm": 0.8914686441421509,
|
| 477 |
+
"learning_rate": 1.9529434374430805e-05,
|
| 478 |
+
"loss": 1.3,
|
| 479 |
+
"step": 1675
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.25380710659898476,
|
| 483 |
+
"grad_norm": 1.0766717195510864,
|
| 484 |
+
"learning_rate": 1.9510938623873793e-05,
|
| 485 |
+
"loss": 1.3152,
|
| 486 |
+
"step": 1700
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2575395640489698,
|
| 490 |
+
"grad_norm": 1.336647391319275,
|
| 491 |
+
"learning_rate": 1.949209545776759e-05,
|
| 492 |
+
"loss": 1.3164,
|
| 493 |
+
"step": 1725
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2612720214989549,
|
| 497 |
+
"grad_norm": 1.2256617546081543,
|
| 498 |
+
"learning_rate": 1.9472905564415344e-05,
|
| 499 |
+
"loss": 1.2771,
|
| 500 |
+
"step": 1750
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.26500447894893997,
|
| 504 |
+
"grad_norm": 1.1724133491516113,
|
| 505 |
+
"learning_rate": 1.945336964478544e-05,
|
| 506 |
+
"loss": 1.2033,
|
| 507 |
+
"step": 1775
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.26873693639892504,
|
| 511 |
+
"grad_norm": 1.3075248003005981,
|
| 512 |
+
"learning_rate": 1.943348841248592e-05,
|
| 513 |
+
"loss": 1.1953,
|
| 514 |
+
"step": 1800
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2724693938489101,
|
| 518 |
+
"grad_norm": 1.7785544395446777,
|
| 519 |
+
"learning_rate": 1.9413262593738392e-05,
|
| 520 |
+
"loss": 1.2611,
|
| 521 |
+
"step": 1825
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2762018512988952,
|
| 525 |
+
"grad_norm": 1.3955777883529663,
|
| 526 |
+
"learning_rate": 1.9392692927351535e-05,
|
| 527 |
+
"loss": 1.3405,
|
| 528 |
+
"step": 1850
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.27993430874888026,
|
| 532 |
+
"grad_norm": 2.070401430130005,
|
| 533 |
+
"learning_rate": 1.9371780164694086e-05,
|
| 534 |
+
"loss": 1.2554,
|
| 535 |
+
"step": 1875
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.2836667661988653,
|
| 539 |
+
"grad_norm": 2.1829886436462402,
|
| 540 |
+
"learning_rate": 1.93505250696674e-05,
|
| 541 |
+
"loss": 1.3218,
|
| 542 |
+
"step": 1900
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2873992236488504,
|
| 546 |
+
"grad_norm": 1.010029911994934,
|
| 547 |
+
"learning_rate": 1.9328928418677554e-05,
|
| 548 |
+
"loss": 1.2459,
|
| 549 |
+
"step": 1925
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.29113168109883547,
|
| 553 |
+
"grad_norm": 1.444607138633728,
|
| 554 |
+
"learning_rate": 1.930699100060697e-05,
|
| 555 |
+
"loss": 1.2065,
|
| 556 |
+
"step": 1950
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.29486413854882054,
|
| 560 |
+
"grad_norm": 1.3134291172027588,
|
| 561 |
+
"learning_rate": 1.9284713616785625e-05,
|
| 562 |
+
"loss": 1.2659,
|
| 563 |
+
"step": 1975
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.2985965959988056,
|
| 567 |
+
"grad_norm": 1.726757526397705,
|
| 568 |
+
"learning_rate": 1.926209708096175e-05,
|
| 569 |
+
"loss": 1.2167,
|
| 570 |
+
"step": 2000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3023290534487907,
|
| 574 |
+
"grad_norm": 1.0370910167694092,
|
| 575 |
+
"learning_rate": 1.9239142219272126e-05,
|
| 576 |
+
"loss": 1.3228,
|
| 577 |
+
"step": 2025
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.30606151089877576,
|
| 581 |
+
"grad_norm": 1.231990098953247,
|
| 582 |
+
"learning_rate": 1.9215849870211903e-05,
|
| 583 |
+
"loss": 1.2452,
|
| 584 |
+
"step": 2050
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.30979396834876083,
|
| 588 |
+
"grad_norm": 1.2131986618041992,
|
| 589 |
+
"learning_rate": 1.919222088460396e-05,
|
| 590 |
+
"loss": 1.2628,
|
| 591 |
+
"step": 2075
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3135264257987459,
|
| 595 |
+
"grad_norm": 1.881930947303772,
|
| 596 |
+
"learning_rate": 1.916825612556785e-05,
|
| 597 |
+
"loss": 1.2626,
|
| 598 |
+
"step": 2100
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.31725888324873097,
|
| 602 |
+
"grad_norm": 1.3210067749023438,
|
| 603 |
+
"learning_rate": 1.9143956468488243e-05,
|
| 604 |
+
"loss": 1.2584,
|
| 605 |
+
"step": 2125
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.32099134069871604,
|
| 609 |
+
"grad_norm": 1.635605812072754,
|
| 610 |
+
"learning_rate": 1.9119322800982973e-05,
|
| 611 |
+
"loss": 1.2587,
|
| 612 |
+
"step": 2150
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3247237981487011,
|
| 616 |
+
"grad_norm": 1.3837544918060303,
|
| 617 |
+
"learning_rate": 1.90943560228706e-05,
|
| 618 |
+
"loss": 1.2959,
|
| 619 |
+
"step": 2175
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3284562555986862,
|
| 623 |
+
"grad_norm": 1.366673469543457,
|
| 624 |
+
"learning_rate": 1.9069057046137552e-05,
|
| 625 |
+
"loss": 1.2247,
|
| 626 |
+
"step": 2200
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.33218871304867126,
|
| 630 |
+
"grad_norm": 1.0182894468307495,
|
| 631 |
+
"learning_rate": 1.9043426794904804e-05,
|
| 632 |
+
"loss": 1.3071,
|
| 633 |
+
"step": 2225
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.33592117049865633,
|
| 637 |
+
"grad_norm": 1.2455936670303345,
|
| 638 |
+
"learning_rate": 1.901746620539413e-05,
|
| 639 |
+
"loss": 1.2189,
|
| 640 |
+
"step": 2250
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3396536279486414,
|
| 644 |
+
"grad_norm": 1.3316103219985962,
|
| 645 |
+
"learning_rate": 1.8991176225893895e-05,
|
| 646 |
+
"loss": 1.1764,
|
| 647 |
+
"step": 2275
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3433860853986265,
|
| 651 |
+
"grad_norm": 1.165073275566101,
|
| 652 |
+
"learning_rate": 1.8964557816724428e-05,
|
| 653 |
+
"loss": 1.2441,
|
| 654 |
+
"step": 2300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.34711854284861154,
|
| 658 |
+
"grad_norm": 2.3722586631774902,
|
| 659 |
+
"learning_rate": 1.893761195020293e-05,
|
| 660 |
+
"loss": 1.2145,
|
| 661 |
+
"step": 2325
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.3508510002985966,
|
| 665 |
+
"grad_norm": 1.5098875761032104,
|
| 666 |
+
"learning_rate": 1.8910339610607963e-05,
|
| 667 |
+
"loss": 1.2289,
|
| 668 |
+
"step": 2350
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.3545834577485817,
|
| 672 |
+
"grad_norm": 1.7946386337280273,
|
| 673 |
+
"learning_rate": 1.8882741794143502e-05,
|
| 674 |
+
"loss": 1.2414,
|
| 675 |
+
"step": 2375
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.35831591519856676,
|
| 679 |
+
"grad_norm": 1.4160943031311035,
|
| 680 |
+
"learning_rate": 1.8854819508902538e-05,
|
| 681 |
+
"loss": 1.2507,
|
| 682 |
+
"step": 2400
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.36204837264855183,
|
| 686 |
+
"grad_norm": 1.667029857635498,
|
| 687 |
+
"learning_rate": 1.8826573774830256e-05,
|
| 688 |
+
"loss": 1.3307,
|
| 689 |
+
"step": 2425
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3657808300985369,
|
| 693 |
+
"grad_norm": 2.139542579650879,
|
| 694 |
+
"learning_rate": 1.879800562368678e-05,
|
| 695 |
+
"loss": 1.2979,
|
| 696 |
+
"step": 2450
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.369513287548522,
|
| 700 |
+
"grad_norm": 1.7116003036499023,
|
| 701 |
+
"learning_rate": 1.8769116099009485e-05,
|
| 702 |
+
"loss": 1.3246,
|
| 703 |
+
"step": 2475
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.373245744998507,
|
| 707 |
+
"grad_norm": 1.9875051975250244,
|
| 708 |
+
"learning_rate": 1.8739906256074875e-05,
|
| 709 |
+
"loss": 1.3063,
|
| 710 |
+
"step": 2500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.37697820244849206,
|
| 714 |
+
"grad_norm": 1.4133434295654297,
|
| 715 |
+
"learning_rate": 1.8710377161860044e-05,
|
| 716 |
+
"loss": 1.2403,
|
| 717 |
+
"step": 2525
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.38071065989847713,
|
| 721 |
+
"grad_norm": 2.0674993991851807,
|
| 722 |
+
"learning_rate": 1.868052989500369e-05,
|
| 723 |
+
"loss": 1.249,
|
| 724 |
+
"step": 2550
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.3844431173484622,
|
| 728 |
+
"grad_norm": 1.3384236097335815,
|
| 729 |
+
"learning_rate": 1.8650365545766724e-05,
|
| 730 |
+
"loss": 1.2225,
|
| 731 |
+
"step": 2575
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.3881755747984473,
|
| 735 |
+
"grad_norm": 1.7959239482879639,
|
| 736 |
+
"learning_rate": 1.8619885215992446e-05,
|
| 737 |
+
"loss": 1.2747,
|
| 738 |
+
"step": 2600
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.39190803224843235,
|
| 742 |
+
"grad_norm": 1.415369987487793,
|
| 743 |
+
"learning_rate": 1.8589090019066285e-05,
|
| 744 |
+
"loss": 1.1303,
|
| 745 |
+
"step": 2625
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.3956404896984174,
|
| 749 |
+
"grad_norm": 1.4702545404434204,
|
| 750 |
+
"learning_rate": 1.8557981079875138e-05,
|
| 751 |
+
"loss": 1.2383,
|
| 752 |
+
"step": 2650
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.3993729471484025,
|
| 756 |
+
"grad_norm": 1.1834770441055298,
|
| 757 |
+
"learning_rate": 1.852655953476628e-05,
|
| 758 |
+
"loss": 1.1785,
|
| 759 |
+
"step": 2675
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.40310540459838756,
|
| 763 |
+
"grad_norm": 1.6196682453155518,
|
| 764 |
+
"learning_rate": 1.8494826531505862e-05,
|
| 765 |
+
"loss": 1.2132,
|
| 766 |
+
"step": 2700
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.40683786204837263,
|
| 770 |
+
"grad_norm": 1.7983671426773071,
|
| 771 |
+
"learning_rate": 1.8462783229236964e-05,
|
| 772 |
+
"loss": 1.252,
|
| 773 |
+
"step": 2725
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4105703194983577,
|
| 777 |
+
"grad_norm": 1.32036292552948,
|
| 778 |
+
"learning_rate": 1.8430430798437272e-05,
|
| 779 |
+
"loss": 1.2476,
|
| 780 |
+
"step": 2750
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4143027769483428,
|
| 784 |
+
"grad_norm": 1.2666844129562378,
|
| 785 |
+
"learning_rate": 1.839777042087633e-05,
|
| 786 |
+
"loss": 1.2617,
|
| 787 |
+
"step": 2775
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.41803523439832785,
|
| 791 |
+
"grad_norm": 1.4495422840118408,
|
| 792 |
+
"learning_rate": 1.8364803289572347e-05,
|
| 793 |
+
"loss": 1.2137,
|
| 794 |
+
"step": 2800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4217676918483129,
|
| 798 |
+
"grad_norm": 1.2833021879196167,
|
| 799 |
+
"learning_rate": 1.8331530608748635e-05,
|
| 800 |
+
"loss": 1.2164,
|
| 801 |
+
"step": 2825
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.425500149298298,
|
| 805 |
+
"grad_norm": 1.4636069536209106,
|
| 806 |
+
"learning_rate": 1.829795359378962e-05,
|
| 807 |
+
"loss": 1.2561,
|
| 808 |
+
"step": 2850
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.42923260674828306,
|
| 812 |
+
"grad_norm": 2.463801145553589,
|
| 813 |
+
"learning_rate": 1.826407347119645e-05,
|
| 814 |
+
"loss": 1.2825,
|
| 815 |
+
"step": 2875
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.43296506419826813,
|
| 819 |
+
"grad_norm": 2.269793748855591,
|
| 820 |
+
"learning_rate": 1.8229891478542182e-05,
|
| 821 |
+
"loss": 1.25,
|
| 822 |
+
"step": 2900
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.4366975216482532,
|
| 826 |
+
"grad_norm": 1.1336036920547485,
|
| 827 |
+
"learning_rate": 1.8195408864426576e-05,
|
| 828 |
+
"loss": 1.277,
|
| 829 |
+
"step": 2925
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4404299790982383,
|
| 833 |
+
"grad_norm": 1.261833667755127,
|
| 834 |
+
"learning_rate": 1.8160626888430505e-05,
|
| 835 |
+
"loss": 1.2,
|
| 836 |
+
"step": 2950
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.44416243654822335,
|
| 840 |
+
"grad_norm": 1.607729434967041,
|
| 841 |
+
"learning_rate": 1.8125546821069924e-05,
|
| 842 |
+
"loss": 1.248,
|
| 843 |
+
"step": 2975
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4478948939982084,
|
| 847 |
+
"grad_norm": 1.5860254764556885,
|
| 848 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 849 |
+
"loss": 1.2422,
|
| 850 |
+
"step": 3000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4516273514481935,
|
| 854 |
+
"grad_norm": 1.2062890529632568,
|
| 855 |
+
"learning_rate": 1.8054497548715668e-05,
|
| 856 |
+
"loss": 1.1927,
|
| 857 |
+
"step": 3025
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.45535980889817856,
|
| 861 |
+
"grad_norm": 1.3773223161697388,
|
| 862 |
+
"learning_rate": 1.8018530939009682e-05,
|
| 863 |
+
"loss": 1.1484,
|
| 864 |
+
"step": 3050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.45909226634816364,
|
| 868 |
+
"grad_norm": 1.697527289390564,
|
| 869 |
+
"learning_rate": 1.798227142841978e-05,
|
| 870 |
+
"loss": 1.2343,
|
| 871 |
+
"step": 3075
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.4628247237981487,
|
| 875 |
+
"grad_norm": 1.2200244665145874,
|
| 876 |
+
"learning_rate": 1.7945720341433297e-05,
|
| 877 |
+
"loss": 1.268,
|
| 878 |
+
"step": 3100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.4665571812481338,
|
| 882 |
+
"grad_norm": 1.3417649269104004,
|
| 883 |
+
"learning_rate": 1.7908879013188272e-05,
|
| 884 |
+
"loss": 1.2212,
|
| 885 |
+
"step": 3125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.47028963869811885,
|
| 889 |
+
"grad_norm": 1.720186471939087,
|
| 890 |
+
"learning_rate": 1.787174878942468e-05,
|
| 891 |
+
"loss": 1.2134,
|
| 892 |
+
"step": 3150
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4740220961481039,
|
| 896 |
+
"grad_norm": 1.9250013828277588,
|
| 897 |
+
"learning_rate": 1.7834331026435266e-05,
|
| 898 |
+
"loss": 1.2258,
|
| 899 |
+
"step": 3175
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.477754553598089,
|
| 903 |
+
"grad_norm": 1.9136689901351929,
|
| 904 |
+
"learning_rate": 1.7796627091016013e-05,
|
| 905 |
+
"loss": 1.1845,
|
| 906 |
+
"step": 3200
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.48148701104807407,
|
| 910 |
+
"grad_norm": 1.3587361574172974,
|
| 911 |
+
"learning_rate": 1.7758638360416202e-05,
|
| 912 |
+
"loss": 1.1483,
|
| 913 |
+
"step": 3225
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.48521946849805914,
|
| 917 |
+
"grad_norm": 1.691744089126587,
|
| 918 |
+
"learning_rate": 1.7720366222288124e-05,
|
| 919 |
+
"loss": 1.2432,
|
| 920 |
+
"step": 3250
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.4889519259480442,
|
| 924 |
+
"grad_norm": 1.2485105991363525,
|
| 925 |
+
"learning_rate": 1.768181207463637e-05,
|
| 926 |
+
"loss": 1.2696,
|
| 927 |
+
"step": 3275
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.4926843833980293,
|
| 931 |
+
"grad_norm": 1.2822153568267822,
|
| 932 |
+
"learning_rate": 1.764297732576678e-05,
|
| 933 |
+
"loss": 1.2322,
|
| 934 |
+
"step": 3300
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.49641684084801435,
|
| 938 |
+
"grad_norm": 1.0677824020385742,
|
| 939 |
+
"learning_rate": 1.760386339423498e-05,
|
| 940 |
+
"loss": 1.2366,
|
| 941 |
+
"step": 3325
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5001492982979994,
|
| 945 |
+
"grad_norm": 1.0575954914093018,
|
| 946 |
+
"learning_rate": 1.7564471708794607e-05,
|
| 947 |
+
"loss": 1.2628,
|
| 948 |
+
"step": 3350
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5038817557479844,
|
| 952 |
+
"grad_norm": 1.2826817035675049,
|
| 953 |
+
"learning_rate": 1.7524803708345065e-05,
|
| 954 |
+
"loss": 1.2282,
|
| 955 |
+
"step": 3375
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5076142131979695,
|
| 959 |
+
"grad_norm": 1.4431601762771606,
|
| 960 |
+
"learning_rate": 1.7484860841879016e-05,
|
| 961 |
+
"loss": 1.2144,
|
| 962 |
+
"step": 3400
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5113466706479546,
|
| 966 |
+
"grad_norm": 1.3346613645553589,
|
| 967 |
+
"learning_rate": 1.74446445684294e-05,
|
| 968 |
+
"loss": 1.2159,
|
| 969 |
+
"step": 3425
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5150791280979397,
|
| 973 |
+
"grad_norm": 1.4220223426818848,
|
| 974 |
+
"learning_rate": 1.7404156357016196e-05,
|
| 975 |
+
"loss": 1.2159,
|
| 976 |
+
"step": 3450
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5188115855479247,
|
| 980 |
+
"grad_norm": 1.5507416725158691,
|
| 981 |
+
"learning_rate": 1.7363397686592712e-05,
|
| 982 |
+
"loss": 1.1986,
|
| 983 |
+
"step": 3475
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5225440429979098,
|
| 987 |
+
"grad_norm": 1.8560044765472412,
|
| 988 |
+
"learning_rate": 1.7322370045991592e-05,
|
| 989 |
+
"loss": 1.1887,
|
| 990 |
+
"step": 3500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5262765004478949,
|
| 994 |
+
"grad_norm": 0.9891431331634521,
|
| 995 |
+
"learning_rate": 1.7281074933870418e-05,
|
| 996 |
+
"loss": 1.2561,
|
| 997 |
+
"step": 3525
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5300089578978799,
|
| 1001 |
+
"grad_norm": 1.8725615739822388,
|
| 1002 |
+
"learning_rate": 1.723951385865697e-05,
|
| 1003 |
+
"loss": 1.2103,
|
| 1004 |
+
"step": 3550
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.533741415347865,
|
| 1008 |
+
"grad_norm": 1.6701029539108276,
|
| 1009 |
+
"learning_rate": 1.719768833849413e-05,
|
| 1010 |
+
"loss": 1.2575,
|
| 1011 |
+
"step": 3575
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5374738727978501,
|
| 1015 |
+
"grad_norm": 1.1404553651809692,
|
| 1016 |
+
"learning_rate": 1.7155599901184427e-05,
|
| 1017 |
+
"loss": 1.2533,
|
| 1018 |
+
"step": 3600
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5412063302478352,
|
| 1022 |
+
"grad_norm": 1.3595733642578125,
|
| 1023 |
+
"learning_rate": 1.7113250084134225e-05,
|
| 1024 |
+
"loss": 1.2169,
|
| 1025 |
+
"step": 3625
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5449387876978202,
|
| 1029 |
+
"grad_norm": 1.5469706058502197,
|
| 1030 |
+
"learning_rate": 1.707064043429756e-05,
|
| 1031 |
+
"loss": 1.234,
|
| 1032 |
+
"step": 3650
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5486712451478053,
|
| 1036 |
+
"grad_norm": 1.28376305103302,
|
| 1037 |
+
"learning_rate": 1.702777250811966e-05,
|
| 1038 |
+
"loss": 1.2091,
|
| 1039 |
+
"step": 3675
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5524037025977904,
|
| 1043 |
+
"grad_norm": 1.1762385368347168,
|
| 1044 |
+
"learning_rate": 1.6984647871480038e-05,
|
| 1045 |
+
"loss": 1.2603,
|
| 1046 |
+
"step": 3700
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5561361600477754,
|
| 1050 |
+
"grad_norm": 1.7015496492385864,
|
| 1051 |
+
"learning_rate": 1.6941268099635356e-05,
|
| 1052 |
+
"loss": 1.2189,
|
| 1053 |
+
"step": 3725
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5598686174977605,
|
| 1057 |
+
"grad_norm": 1.4737459421157837,
|
| 1058 |
+
"learning_rate": 1.689763477716184e-05,
|
| 1059 |
+
"loss": 1.2567,
|
| 1060 |
+
"step": 3750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5636010749477456,
|
| 1064 |
+
"grad_norm": 1.0501235723495483,
|
| 1065 |
+
"learning_rate": 1.6853749497897417e-05,
|
| 1066 |
+
"loss": 1.2647,
|
| 1067 |
+
"step": 3775
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5673335323977307,
|
| 1071 |
+
"grad_norm": 1.793992519378662,
|
| 1072 |
+
"learning_rate": 1.6809613864883484e-05,
|
| 1073 |
+
"loss": 1.1963,
|
| 1074 |
+
"step": 3800
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5710659898477157,
|
| 1078 |
+
"grad_norm": 1.3824703693389893,
|
| 1079 |
+
"learning_rate": 1.6765229490306376e-05,
|
| 1080 |
+
"loss": 1.1961,
|
| 1081 |
+
"step": 3825
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5747984472977008,
|
| 1085 |
+
"grad_norm": 1.2093158960342407,
|
| 1086 |
+
"learning_rate": 1.672059799543844e-05,
|
| 1087 |
+
"loss": 1.3218,
|
| 1088 |
+
"step": 3850
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5785309047476859,
|
| 1092 |
+
"grad_norm": 1.4345468282699585,
|
| 1093 |
+
"learning_rate": 1.667572101057885e-05,
|
| 1094 |
+
"loss": 1.2929,
|
| 1095 |
+
"step": 3875
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.5822633621976709,
|
| 1099 |
+
"grad_norm": 1.790346384048462,
|
| 1100 |
+
"learning_rate": 1.663060017499402e-05,
|
| 1101 |
+
"loss": 1.2416,
|
| 1102 |
+
"step": 3900
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.585995819647656,
|
| 1106 |
+
"grad_norm": 1.126421570777893,
|
| 1107 |
+
"learning_rate": 1.6585237136857762e-05,
|
| 1108 |
+
"loss": 1.1753,
|
| 1109 |
+
"step": 3925
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.5897282770976411,
|
| 1113 |
+
"grad_norm": 2.123781204223633,
|
| 1114 |
+
"learning_rate": 1.653963355319104e-05,
|
| 1115 |
+
"loss": 1.2442,
|
| 1116 |
+
"step": 3950
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.5934607345476262,
|
| 1120 |
+
"grad_norm": 1.4365142583847046,
|
| 1121 |
+
"learning_rate": 1.6493791089801488e-05,
|
| 1122 |
+
"loss": 1.1901,
|
| 1123 |
+
"step": 3975
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.5971931919976112,
|
| 1127 |
+
"grad_norm": 0.9638050198554993,
|
| 1128 |
+
"learning_rate": 1.6447711421222524e-05,
|
| 1129 |
+
"loss": 1.2474,
|
| 1130 |
+
"step": 4000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6009256494475963,
|
| 1134 |
+
"grad_norm": 1.3598357439041138,
|
| 1135 |
+
"learning_rate": 1.64013962306522e-05,
|
| 1136 |
+
"loss": 1.2294,
|
| 1137 |
+
"step": 4025
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6046581068975814,
|
| 1141 |
+
"grad_norm": 1.4392117261886597,
|
| 1142 |
+
"learning_rate": 1.6354847209891715e-05,
|
| 1143 |
+
"loss": 1.185,
|
| 1144 |
+
"step": 4050
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6083905643475664,
|
| 1148 |
+
"grad_norm": 1.8003793954849243,
|
| 1149 |
+
"learning_rate": 1.6308066059283617e-05,
|
| 1150 |
+
"loss": 1.2059,
|
| 1151 |
+
"step": 4075
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6121230217975515,
|
| 1155 |
+
"grad_norm": 1.2645149230957031,
|
| 1156 |
+
"learning_rate": 1.626105448764969e-05,
|
| 1157 |
+
"loss": 1.2035,
|
| 1158 |
+
"step": 4100
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6158554792475366,
|
| 1162 |
+
"grad_norm": 2.2808313369750977,
|
| 1163 |
+
"learning_rate": 1.6213814212228542e-05,
|
| 1164 |
+
"loss": 1.2203,
|
| 1165 |
+
"step": 4125
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6195879366975217,
|
| 1169 |
+
"grad_norm": 1.444287896156311,
|
| 1170 |
+
"learning_rate": 1.6166346958612872e-05,
|
| 1171 |
+
"loss": 1.2243,
|
| 1172 |
+
"step": 4150
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6233203941475067,
|
| 1176 |
+
"grad_norm": 1.2230594158172607,
|
| 1177 |
+
"learning_rate": 1.611865446068643e-05,
|
| 1178 |
+
"loss": 1.2306,
|
| 1179 |
+
"step": 4175
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6270528515974918,
|
| 1183 |
+
"grad_norm": 1.4247676134109497,
|
| 1184 |
+
"learning_rate": 1.6070738460560703e-05,
|
| 1185 |
+
"loss": 1.2,
|
| 1186 |
+
"step": 4200
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6307853090474769,
|
| 1190 |
+
"grad_norm": 1.3539576530456543,
|
| 1191 |
+
"learning_rate": 1.602260070851125e-05,
|
| 1192 |
+
"loss": 1.222,
|
| 1193 |
+
"step": 4225
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6345177664974619,
|
| 1197 |
+
"grad_norm": 1.4188202619552612,
|
| 1198 |
+
"learning_rate": 1.59742429629138e-05,
|
| 1199 |
+
"loss": 1.2525,
|
| 1200 |
+
"step": 4250
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.638250223947447,
|
| 1204 |
+
"grad_norm": 4.922667026519775,
|
| 1205 |
+
"learning_rate": 1.5925666990179997e-05,
|
| 1206 |
+
"loss": 1.2556,
|
| 1207 |
+
"step": 4275
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6419826813974321,
|
| 1211 |
+
"grad_norm": 1.7935903072357178,
|
| 1212 |
+
"learning_rate": 1.587687456469288e-05,
|
| 1213 |
+
"loss": 1.2192,
|
| 1214 |
+
"step": 4300
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6457151388474172,
|
| 1218 |
+
"grad_norm": 1.1644890308380127,
|
| 1219 |
+
"learning_rate": 1.5827867468742088e-05,
|
| 1220 |
+
"loss": 1.2647,
|
| 1221 |
+
"step": 4325
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6494475962974022,
|
| 1225 |
+
"grad_norm": 1.1731319427490234,
|
| 1226 |
+
"learning_rate": 1.5778647492458735e-05,
|
| 1227 |
+
"loss": 1.1913,
|
| 1228 |
+
"step": 4350
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6531800537473873,
|
| 1232 |
+
"grad_norm": 1.4858598709106445,
|
| 1233 |
+
"learning_rate": 1.5729216433750023e-05,
|
| 1234 |
+
"loss": 1.2086,
|
| 1235 |
+
"step": 4375
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6569125111973724,
|
| 1239 |
+
"grad_norm": 1.705950140953064,
|
| 1240 |
+
"learning_rate": 1.567957609823358e-05,
|
| 1241 |
+
"loss": 1.1848,
|
| 1242 |
+
"step": 4400
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6606449686473574,
|
| 1246 |
+
"grad_norm": 1.615257740020752,
|
| 1247 |
+
"learning_rate": 1.5629728299171495e-05,
|
| 1248 |
+
"loss": 1.2117,
|
| 1249 |
+
"step": 4425
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6643774260973425,
|
| 1253 |
+
"grad_norm": 2.1554055213928223,
|
| 1254 |
+
"learning_rate": 1.5579674857404078e-05,
|
| 1255 |
+
"loss": 1.1318,
|
| 1256 |
+
"step": 4450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6681098835473276,
|
| 1260 |
+
"grad_norm": 1.1841500997543335,
|
| 1261 |
+
"learning_rate": 1.552941760128337e-05,
|
| 1262 |
+
"loss": 1.2348,
|
| 1263 |
+
"step": 4475
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6718423409973127,
|
| 1267 |
+
"grad_norm": 1.6528973579406738,
|
| 1268 |
+
"learning_rate": 1.5478958366606323e-05,
|
| 1269 |
+
"loss": 1.1943,
|
| 1270 |
+
"step": 4500
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6755747984472977,
|
| 1274 |
+
"grad_norm": 1.7715898752212524,
|
| 1275 |
+
"learning_rate": 1.5428298996547778e-05,
|
| 1276 |
+
"loss": 1.1289,
|
| 1277 |
+
"step": 4525
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.6793072558972828,
|
| 1281 |
+
"grad_norm": 1.4920035600662231,
|
| 1282 |
+
"learning_rate": 1.5377441341593116e-05,
|
| 1283 |
+
"loss": 1.1901,
|
| 1284 |
+
"step": 4550
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.6830397133472679,
|
| 1288 |
+
"grad_norm": 1.339840054512024,
|
| 1289 |
+
"learning_rate": 1.532638725947066e-05,
|
| 1290 |
+
"loss": 1.2306,
|
| 1291 |
+
"step": 4575
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.686772170797253,
|
| 1295 |
+
"grad_norm": 1.212212085723877,
|
| 1296 |
+
"learning_rate": 1.5275138615083843e-05,
|
| 1297 |
+
"loss": 1.1593,
|
| 1298 |
+
"step": 4600
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.690504628247238,
|
| 1302 |
+
"grad_norm": 1.667057991027832,
|
| 1303 |
+
"learning_rate": 1.5223697280443044e-05,
|
| 1304 |
+
"loss": 1.165,
|
| 1305 |
+
"step": 4625
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6942370856972231,
|
| 1309 |
+
"grad_norm": 1.502441644668579,
|
| 1310 |
+
"learning_rate": 1.517206513459725e-05,
|
| 1311 |
+
"loss": 1.1481,
|
| 1312 |
+
"step": 4650
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.6979695431472082,
|
| 1316 |
+
"grad_norm": 1.2989062070846558,
|
| 1317 |
+
"learning_rate": 1.5120244063565393e-05,
|
| 1318 |
+
"loss": 1.133,
|
| 1319 |
+
"step": 4675
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7017020005971932,
|
| 1323 |
+
"grad_norm": 1.3973162174224854,
|
| 1324 |
+
"learning_rate": 1.506823596026746e-05,
|
| 1325 |
+
"loss": 1.2839,
|
| 1326 |
+
"step": 4700
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7054344580471783,
|
| 1330 |
+
"grad_norm": 1.2941102981567383,
|
| 1331 |
+
"learning_rate": 1.501604272445536e-05,
|
| 1332 |
+
"loss": 1.2032,
|
| 1333 |
+
"step": 4725
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7091669154971634,
|
| 1337 |
+
"grad_norm": 1.8230595588684082,
|
| 1338 |
+
"learning_rate": 1.4963666262643517e-05,
|
| 1339 |
+
"loss": 1.2128,
|
| 1340 |
+
"step": 4750
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7128993729471484,
|
| 1344 |
+
"grad_norm": 1.251273274421692,
|
| 1345 |
+
"learning_rate": 1.4911108488039233e-05,
|
| 1346 |
+
"loss": 1.2268,
|
| 1347 |
+
"step": 4775
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7166318303971335,
|
| 1351 |
+
"grad_norm": 1.185001254081726,
|
| 1352 |
+
"learning_rate": 1.4858371320472807e-05,
|
| 1353 |
+
"loss": 1.1763,
|
| 1354 |
+
"step": 4800
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7203642878471186,
|
| 1358 |
+
"grad_norm": 1.127736210823059,
|
| 1359 |
+
"learning_rate": 1.4805456686327404e-05,
|
| 1360 |
+
"loss": 1.2929,
|
| 1361 |
+
"step": 4825
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7240967452971037,
|
| 1365 |
+
"grad_norm": 1.849836826324463,
|
| 1366 |
+
"learning_rate": 1.4752366518468684e-05,
|
| 1367 |
+
"loss": 1.2721,
|
| 1368 |
+
"step": 4850
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7278292027470887,
|
| 1372 |
+
"grad_norm": 1.5276362895965576,
|
| 1373 |
+
"learning_rate": 1.4699102756174207e-05,
|
| 1374 |
+
"loss": 1.2126,
|
| 1375 |
+
"step": 4875
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7315616601970738,
|
| 1379 |
+
"grad_norm": 1.338534951210022,
|
| 1380 |
+
"learning_rate": 1.4645667345062584e-05,
|
| 1381 |
+
"loss": 1.2524,
|
| 1382 |
+
"step": 4900
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7352941176470589,
|
| 1386 |
+
"grad_norm": 2.3885657787323,
|
| 1387 |
+
"learning_rate": 1.4592062237022419e-05,
|
| 1388 |
+
"loss": 1.2397,
|
| 1389 |
+
"step": 4925
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.739026575097044,
|
| 1393 |
+
"grad_norm": 1.712269902229309,
|
| 1394 |
+
"learning_rate": 1.4538289390141005e-05,
|
| 1395 |
+
"loss": 1.1817,
|
| 1396 |
+
"step": 4950
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.742759032547029,
|
| 1400 |
+
"grad_norm": 1.3213021755218506,
|
| 1401 |
+
"learning_rate": 1.4484350768632795e-05,
|
| 1402 |
+
"loss": 1.1884,
|
| 1403 |
+
"step": 4975
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.746491489997014,
|
| 1407 |
+
"grad_norm": 1.7047327756881714,
|
| 1408 |
+
"learning_rate": 1.4430248342767661e-05,
|
| 1409 |
+
"loss": 1.158,
|
| 1410 |
+
"step": 5000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.750223947446999,
|
| 1414 |
+
"grad_norm": 1.3052529096603394,
|
| 1415 |
+
"learning_rate": 1.437598408879892e-05,
|
| 1416 |
+
"loss": 1.1679,
|
| 1417 |
+
"step": 5025
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7539564048969841,
|
| 1421 |
+
"grad_norm": 1.8056520223617554,
|
| 1422 |
+
"learning_rate": 1.4321559988891143e-05,
|
| 1423 |
+
"loss": 1.2433,
|
| 1424 |
+
"step": 5050
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7576888623469692,
|
| 1428 |
+
"grad_norm": 1.0514063835144043,
|
| 1429 |
+
"learning_rate": 1.4266978031047756e-05,
|
| 1430 |
+
"loss": 1.1839,
|
| 1431 |
+
"step": 5075
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7614213197969543,
|
| 1435 |
+
"grad_norm": 1.5641283988952637,
|
| 1436 |
+
"learning_rate": 1.421224020903842e-05,
|
| 1437 |
+
"loss": 1.1845,
|
| 1438 |
+
"step": 5100
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7651537772469393,
|
| 1442 |
+
"grad_norm": 0.9585388898849487,
|
| 1443 |
+
"learning_rate": 1.4157348522326193e-05,
|
| 1444 |
+
"loss": 1.1198,
|
| 1445 |
+
"step": 5125
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7688862346969244,
|
| 1449 |
+
"grad_norm": 1.113794207572937,
|
| 1450 |
+
"learning_rate": 1.4102304975994518e-05,
|
| 1451 |
+
"loss": 1.2197,
|
| 1452 |
+
"step": 5150
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7726186921469095,
|
| 1456 |
+
"grad_norm": 1.5784218311309814,
|
| 1457 |
+
"learning_rate": 1.4047111580673955e-05,
|
| 1458 |
+
"loss": 1.1592,
|
| 1459 |
+
"step": 5175
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.7763511495968946,
|
| 1463 |
+
"grad_norm": 1.339924693107605,
|
| 1464 |
+
"learning_rate": 1.3991770352468753e-05,
|
| 1465 |
+
"loss": 1.2009,
|
| 1466 |
+
"step": 5200
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.7800836070468796,
|
| 1470 |
+
"grad_norm": 1.5128077268600464,
|
| 1471 |
+
"learning_rate": 1.3936283312883192e-05,
|
| 1472 |
+
"loss": 1.2504,
|
| 1473 |
+
"step": 5225
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7838160644968647,
|
| 1477 |
+
"grad_norm": 1.5745166540145874,
|
| 1478 |
+
"learning_rate": 1.3880652488747756e-05,
|
| 1479 |
+
"loss": 1.1723,
|
| 1480 |
+
"step": 5250
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.7875485219468498,
|
| 1484 |
+
"grad_norm": 2.238532066345215,
|
| 1485 |
+
"learning_rate": 1.38248799121451e-05,
|
| 1486 |
+
"loss": 1.1674,
|
| 1487 |
+
"step": 5275
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.7912809793968348,
|
| 1491 |
+
"grad_norm": 1.1808812618255615,
|
| 1492 |
+
"learning_rate": 1.3768967620335791e-05,
|
| 1493 |
+
"loss": 1.218,
|
| 1494 |
+
"step": 5300
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.7950134368468199,
|
| 1498 |
+
"grad_norm": 2.038313865661621,
|
| 1499 |
+
"learning_rate": 1.371291765568393e-05,
|
| 1500 |
+
"loss": 1.2065,
|
| 1501 |
+
"step": 5325
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.798745894296805,
|
| 1505 |
+
"grad_norm": 1.5826561450958252,
|
| 1506 |
+
"learning_rate": 1.3656732065582529e-05,
|
| 1507 |
+
"loss": 1.1006,
|
| 1508 |
+
"step": 5350
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.80247835174679,
|
| 1512 |
+
"grad_norm": 1.3146427869796753,
|
| 1513 |
+
"learning_rate": 1.360041290237872e-05,
|
| 1514 |
+
"loss": 1.1637,
|
| 1515 |
+
"step": 5375
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8062108091967751,
|
| 1519 |
+
"grad_norm": 1.2641507387161255,
|
| 1520 |
+
"learning_rate": 1.3543962223298799e-05,
|
| 1521 |
+
"loss": 1.1175,
|
| 1522 |
+
"step": 5400
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8099432666467602,
|
| 1526 |
+
"grad_norm": 1.886314034461975,
|
| 1527 |
+
"learning_rate": 1.348738209037307e-05,
|
| 1528 |
+
"loss": 1.2644,
|
| 1529 |
+
"step": 5425
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8136757240967453,
|
| 1533 |
+
"grad_norm": 2.5574333667755127,
|
| 1534 |
+
"learning_rate": 1.3430674570360528e-05,
|
| 1535 |
+
"loss": 1.2805,
|
| 1536 |
+
"step": 5450
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8174081815467303,
|
| 1540 |
+
"grad_norm": 1.5606664419174194,
|
| 1541 |
+
"learning_rate": 1.3373841734673366e-05,
|
| 1542 |
+
"loss": 1.1581,
|
| 1543 |
+
"step": 5475
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8211406389967154,
|
| 1547 |
+
"grad_norm": 1.60868501663208,
|
| 1548 |
+
"learning_rate": 1.3316885659301298e-05,
|
| 1549 |
+
"loss": 1.1639,
|
| 1550 |
+
"step": 5500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8248730964467005,
|
| 1554 |
+
"grad_norm": 1.3898091316223145,
|
| 1555 |
+
"learning_rate": 1.3259808424735754e-05,
|
| 1556 |
+
"loss": 1.1757,
|
| 1557 |
+
"step": 5525
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8286055538966856,
|
| 1561 |
+
"grad_norm": 1.1681030988693237,
|
| 1562 |
+
"learning_rate": 1.320261211589385e-05,
|
| 1563 |
+
"loss": 1.2276,
|
| 1564 |
+
"step": 5550
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8323380113466706,
|
| 1568 |
+
"grad_norm": 1.813833236694336,
|
| 1569 |
+
"learning_rate": 1.3145298822042255e-05,
|
| 1570 |
+
"loss": 1.1826,
|
| 1571 |
+
"step": 5575
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8360704687966557,
|
| 1575 |
+
"grad_norm": 2.5199103355407715,
|
| 1576 |
+
"learning_rate": 1.308787063672087e-05,
|
| 1577 |
+
"loss": 1.2587,
|
| 1578 |
+
"step": 5600
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8398029262466408,
|
| 1582 |
+
"grad_norm": 2.014720916748047,
|
| 1583 |
+
"learning_rate": 1.3030329657666339e-05,
|
| 1584 |
+
"loss": 1.1934,
|
| 1585 |
+
"step": 5625
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8435353836966258,
|
| 1589 |
+
"grad_norm": 1.3772430419921875,
|
| 1590 |
+
"learning_rate": 1.2972677986735449e-05,
|
| 1591 |
+
"loss": 1.2342,
|
| 1592 |
+
"step": 5650
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8472678411466109,
|
| 1596 |
+
"grad_norm": 1.337478756904602,
|
| 1597 |
+
"learning_rate": 1.2914917729828331e-05,
|
| 1598 |
+
"loss": 1.1866,
|
| 1599 |
+
"step": 5675
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.851000298596596,
|
| 1603 |
+
"grad_norm": 1.9738775491714478,
|
| 1604 |
+
"learning_rate": 1.2857050996811548e-05,
|
| 1605 |
+
"loss": 1.1844,
|
| 1606 |
+
"step": 5700
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.854732756046581,
|
| 1610 |
+
"grad_norm": 1.9654030799865723,
|
| 1611 |
+
"learning_rate": 1.2799079901441021e-05,
|
| 1612 |
+
"loss": 1.1876,
|
| 1613 |
+
"step": 5725
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8584652134965661,
|
| 1617 |
+
"grad_norm": 1.7116689682006836,
|
| 1618 |
+
"learning_rate": 1.2741006561284812e-05,
|
| 1619 |
+
"loss": 1.2034,
|
| 1620 |
+
"step": 5750
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8621976709465512,
|
| 1624 |
+
"grad_norm": 1.231316089630127,
|
| 1625 |
+
"learning_rate": 1.26828330976458e-05,
|
| 1626 |
+
"loss": 1.1424,
|
| 1627 |
+
"step": 5775
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8659301283965363,
|
| 1631 |
+
"grad_norm": 1.4150484800338745,
|
| 1632 |
+
"learning_rate": 1.2624561635484152e-05,
|
| 1633 |
+
"loss": 1.1775,
|
| 1634 |
+
"step": 5800
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8696625858465213,
|
| 1638 |
+
"grad_norm": 1.6012908220291138,
|
| 1639 |
+
"learning_rate": 1.2566194303339738e-05,
|
| 1640 |
+
"loss": 1.1916,
|
| 1641 |
+
"step": 5825
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.8733950432965064,
|
| 1645 |
+
"grad_norm": 1.2136471271514893,
|
| 1646 |
+
"learning_rate": 1.2507733233254362e-05,
|
| 1647 |
+
"loss": 1.1952,
|
| 1648 |
+
"step": 5850
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.8771275007464915,
|
| 1652 |
+
"grad_norm": 1.2161729335784912,
|
| 1653 |
+
"learning_rate": 1.2449180560693888e-05,
|
| 1654 |
+
"loss": 1.1532,
|
| 1655 |
+
"step": 5875
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.8808599581964766,
|
| 1659 |
+
"grad_norm": 0.9797784090042114,
|
| 1660 |
+
"learning_rate": 1.239053842447024e-05,
|
| 1661 |
+
"loss": 1.2634,
|
| 1662 |
+
"step": 5900
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.8845924156464616,
|
| 1666 |
+
"grad_norm": 1.0139834880828857,
|
| 1667 |
+
"learning_rate": 1.233180896666326e-05,
|
| 1668 |
+
"loss": 1.2226,
|
| 1669 |
+
"step": 5925
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.8883248730964467,
|
| 1673 |
+
"grad_norm": 1.7537201642990112,
|
| 1674 |
+
"learning_rate": 1.227299433254248e-05,
|
| 1675 |
+
"loss": 1.3035,
|
| 1676 |
+
"step": 5950
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.8920573305464318,
|
| 1680 |
+
"grad_norm": 1.4647903442382812,
|
| 1681 |
+
"learning_rate": 1.2214096670488753e-05,
|
| 1682 |
+
"loss": 1.2201,
|
| 1683 |
+
"step": 5975
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.8957897879964168,
|
| 1687 |
+
"grad_norm": 1.5560133457183838,
|
| 1688 |
+
"learning_rate": 1.215511813191577e-05,
|
| 1689 |
+
"loss": 1.1134,
|
| 1690 |
+
"step": 6000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.8995222454464019,
|
| 1694 |
+
"grad_norm": 1.3168470859527588,
|
| 1695 |
+
"learning_rate": 1.2096060871191492e-05,
|
| 1696 |
+
"loss": 1.1175,
|
| 1697 |
+
"step": 6025
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.903254702896387,
|
| 1701 |
+
"grad_norm": 1.569739818572998,
|
| 1702 |
+
"learning_rate": 1.2036927045559426e-05,
|
| 1703 |
+
"loss": 1.1893,
|
| 1704 |
+
"step": 6050
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9069871603463721,
|
| 1708 |
+
"grad_norm": 1.5962868928909302,
|
| 1709 |
+
"learning_rate": 1.197771881505985e-05,
|
| 1710 |
+
"loss": 1.1658,
|
| 1711 |
+
"step": 6075
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9107196177963571,
|
| 1715 |
+
"grad_norm": 1.5586867332458496,
|
| 1716 |
+
"learning_rate": 1.191843834245091e-05,
|
| 1717 |
+
"loss": 1.2502,
|
| 1718 |
+
"step": 6100
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9144520752463422,
|
| 1722 |
+
"grad_norm": 1.9700677394866943,
|
| 1723 |
+
"learning_rate": 1.185908779312959e-05,
|
| 1724 |
+
"loss": 1.254,
|
| 1725 |
+
"step": 6125
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9181845326963273,
|
| 1729 |
+
"grad_norm": 4.636424541473389,
|
| 1730 |
+
"learning_rate": 1.1799669335052668e-05,
|
| 1731 |
+
"loss": 1.1341,
|
| 1732 |
+
"step": 6150
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9219169901463123,
|
| 1736 |
+
"grad_norm": 1.5172594785690308,
|
| 1737 |
+
"learning_rate": 1.1740185138657461e-05,
|
| 1738 |
+
"loss": 1.1326,
|
| 1739 |
+
"step": 6175
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9256494475962974,
|
| 1743 |
+
"grad_norm": 1.9873288869857788,
|
| 1744 |
+
"learning_rate": 1.16806373767826e-05,
|
| 1745 |
+
"loss": 1.2313,
|
| 1746 |
+
"step": 6200
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9293819050462825,
|
| 1750 |
+
"grad_norm": 1.6878819465637207,
|
| 1751 |
+
"learning_rate": 1.1621028224588617e-05,
|
| 1752 |
+
"loss": 1.2502,
|
| 1753 |
+
"step": 6225
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9331143624962676,
|
| 1757 |
+
"grad_norm": 1.5390180349349976,
|
| 1758 |
+
"learning_rate": 1.156135985947852e-05,
|
| 1759 |
+
"loss": 1.2216,
|
| 1760 |
+
"step": 6250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9368468199462526,
|
| 1764 |
+
"grad_norm": 1.386735439300537,
|
| 1765 |
+
"learning_rate": 1.1501634461018249e-05,
|
| 1766 |
+
"loss": 1.1471,
|
| 1767 |
+
"step": 6275
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9405792773962377,
|
| 1771 |
+
"grad_norm": 1.200641393661499,
|
| 1772 |
+
"learning_rate": 1.1441854210857047e-05,
|
| 1773 |
+
"loss": 1.222,
|
| 1774 |
+
"step": 6300
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.9443117348462228,
|
| 1778 |
+
"grad_norm": 1.2502779960632324,
|
| 1779 |
+
"learning_rate": 1.1382021292647789e-05,
|
| 1780 |
+
"loss": 1.1901,
|
| 1781 |
+
"step": 6325
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9480441922962078,
|
| 1785 |
+
"grad_norm": 1.8482311964035034,
|
| 1786 |
+
"learning_rate": 1.1322137891967202e-05,
|
| 1787 |
+
"loss": 1.1126,
|
| 1788 |
+
"step": 6350
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9517766497461929,
|
| 1792 |
+
"grad_norm": 3.107370138168335,
|
| 1793 |
+
"learning_rate": 1.1262206196236041e-05,
|
| 1794 |
+
"loss": 1.2232,
|
| 1795 |
+
"step": 6375
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.955509107196178,
|
| 1799 |
+
"grad_norm": 1.6704610586166382,
|
| 1800 |
+
"learning_rate": 1.1202228394639185e-05,
|
| 1801 |
+
"loss": 1.2805,
|
| 1802 |
+
"step": 6400
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9592415646461631,
|
| 1806 |
+
"grad_norm": 1.9674614667892456,
|
| 1807 |
+
"learning_rate": 1.1142206678045659e-05,
|
| 1808 |
+
"loss": 1.2271,
|
| 1809 |
+
"step": 6425
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9629740220961481,
|
| 1813 |
+
"grad_norm": 1.4267408847808838,
|
| 1814 |
+
"learning_rate": 1.1082143238928627e-05,
|
| 1815 |
+
"loss": 1.1858,
|
| 1816 |
+
"step": 6450
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9667064795461332,
|
| 1820 |
+
"grad_norm": 1.3559452295303345,
|
| 1821 |
+
"learning_rate": 1.102204027128528e-05,
|
| 1822 |
+
"loss": 1.1946,
|
| 1823 |
+
"step": 6475
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9704389369961183,
|
| 1827 |
+
"grad_norm": 1.2451636791229248,
|
| 1828 |
+
"learning_rate": 1.0961899970556714e-05,
|
| 1829 |
+
"loss": 1.2767,
|
| 1830 |
+
"step": 6500
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.9741713944461033,
|
| 1834 |
+
"grad_norm": 1.0592637062072754,
|
| 1835 |
+
"learning_rate": 1.0901724533547732e-05,
|
| 1836 |
+
"loss": 1.2102,
|
| 1837 |
+
"step": 6525
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.9779038518960884,
|
| 1841 |
+
"grad_norm": 1.5661903619766235,
|
| 1842 |
+
"learning_rate": 1.0841516158346585e-05,
|
| 1843 |
+
"loss": 1.323,
|
| 1844 |
+
"step": 6550
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.9816363093460735,
|
| 1848 |
+
"grad_norm": 1.1508394479751587,
|
| 1849 |
+
"learning_rate": 1.0781277044244702e-05,
|
| 1850 |
+
"loss": 1.1423,
|
| 1851 |
+
"step": 6575
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.9853687667960586,
|
| 1855 |
+
"grad_norm": 1.777511477470398,
|
| 1856 |
+
"learning_rate": 1.0721009391656331e-05,
|
| 1857 |
+
"loss": 1.171,
|
| 1858 |
+
"step": 6600
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.9891012242460436,
|
| 1862 |
+
"grad_norm": 1.3769773244857788,
|
| 1863 |
+
"learning_rate": 1.0660715402038178e-05,
|
| 1864 |
+
"loss": 1.1406,
|
| 1865 |
+
"step": 6625
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.9928336816960287,
|
| 1869 |
+
"grad_norm": 1.7429224252700806,
|
| 1870 |
+
"learning_rate": 1.0600397277808996e-05,
|
| 1871 |
+
"loss": 1.1783,
|
| 1872 |
+
"step": 6650
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.9965661391460138,
|
| 1876 |
+
"grad_norm": 3.171079397201538,
|
| 1877 |
+
"learning_rate": 1.054005722226911e-05,
|
| 1878 |
+
"loss": 1.1792,
|
| 1879 |
+
"step": 6675
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.0002985965959987,
|
| 1883 |
+
"grad_norm": 1.426594614982605,
|
| 1884 |
+
"learning_rate": 1.047969743951997e-05,
|
| 1885 |
+
"loss": 1.2918,
|
| 1886 |
+
"step": 6700
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.0040310540459838,
|
| 1890 |
+
"grad_norm": 1.8872315883636475,
|
| 1891 |
+
"learning_rate": 1.0419320134383608e-05,
|
| 1892 |
+
"loss": 1.1895,
|
| 1893 |
+
"step": 6725
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.0077635114959689,
|
| 1897 |
+
"grad_norm": 1.3219560384750366,
|
| 1898 |
+
"learning_rate": 1.0358927512322119e-05,
|
| 1899 |
+
"loss": 1.198,
|
| 1900 |
+
"step": 6750
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.011495968945954,
|
| 1904 |
+
"grad_norm": 1.5500373840332031,
|
| 1905 |
+
"learning_rate": 1.02985217793571e-05,
|
| 1906 |
+
"loss": 1.1774,
|
| 1907 |
+
"step": 6775
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.015228426395939,
|
| 1911 |
+
"grad_norm": 1.7060877084732056,
|
| 1912 |
+
"learning_rate": 1.0238105141989053e-05,
|
| 1913 |
+
"loss": 1.0923,
|
| 1914 |
+
"step": 6800
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.018960883845924,
|
| 1918 |
+
"grad_norm": 1.2694035768508911,
|
| 1919 |
+
"learning_rate": 1.0177679807116803e-05,
|
| 1920 |
+
"loss": 1.1555,
|
| 1921 |
+
"step": 6825
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.0226933412959092,
|
| 1925 |
+
"grad_norm": 1.6255228519439697,
|
| 1926 |
+
"learning_rate": 1.011724798195687e-05,
|
| 1927 |
+
"loss": 1.1586,
|
| 1928 |
+
"step": 6850
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.0264257987458942,
|
| 1932 |
+
"grad_norm": 1.0839436054229736,
|
| 1933 |
+
"learning_rate": 1.0056811873962862e-05,
|
| 1934 |
+
"loss": 1.1479,
|
| 1935 |
+
"step": 6875
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.0301582561958793,
|
| 1939 |
+
"grad_norm": 1.5991156101226807,
|
| 1940 |
+
"learning_rate": 9.996373690744824e-06,
|
| 1941 |
+
"loss": 1.1523,
|
| 1942 |
+
"step": 6900
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.0338907136458644,
|
| 1946 |
+
"grad_norm": 1.5178261995315552,
|
| 1947 |
+
"learning_rate": 9.935935639988601e-06,
|
| 1948 |
+
"loss": 1.1006,
|
| 1949 |
+
"step": 6925
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.0376231710958495,
|
| 1953 |
+
"grad_norm": 1.4072154760360718,
|
| 1954 |
+
"learning_rate": 9.875499929375208e-06,
|
| 1955 |
+
"loss": 1.2102,
|
| 1956 |
+
"step": 6950
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.0413556285458345,
|
| 1960 |
+
"grad_norm": 2.050013780593872,
|
| 1961 |
+
"learning_rate": 9.815068766500178e-06,
|
| 1962 |
+
"loss": 1.1656,
|
| 1963 |
+
"step": 6975
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.0450880859958196,
|
| 1967 |
+
"grad_norm": 1.9359312057495117,
|
| 1968 |
+
"learning_rate": 9.754644358792914e-06,
|
| 1969 |
+
"loss": 1.1416,
|
| 1970 |
+
"step": 7000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.0488205434458047,
|
| 1974 |
+
"grad_norm": 1.5673409700393677,
|
| 1975 |
+
"learning_rate": 9.694228913436078e-06,
|
| 1976 |
+
"loss": 1.142,
|
| 1977 |
+
"step": 7025
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.0525530008957897,
|
| 1981 |
+
"grad_norm": 1.1554819345474243,
|
| 1982 |
+
"learning_rate": 9.633824637284945e-06,
|
| 1983 |
+
"loss": 1.1354,
|
| 1984 |
+
"step": 7050
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.0562854583457748,
|
| 1988 |
+
"grad_norm": 1.1798933744430542,
|
| 1989 |
+
"learning_rate": 9.573433736786816e-06,
|
| 1990 |
+
"loss": 1.0835,
|
| 1991 |
+
"step": 7075
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.0600179157957599,
|
| 1995 |
+
"grad_norm": 1.336529016494751,
|
| 1996 |
+
"learning_rate": 9.513058417900395e-06,
|
| 1997 |
+
"loss": 1.0847,
|
| 1998 |
+
"step": 7100
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.063750373245745,
|
| 2002 |
+
"grad_norm": 2.0378334522247314,
|
| 2003 |
+
"learning_rate": 9.45270088601522e-06,
|
| 2004 |
+
"loss": 1.165,
|
| 2005 |
+
"step": 7125
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.06748283069573,
|
| 2009 |
+
"grad_norm": 1.8982287645339966,
|
| 2010 |
+
"learning_rate": 9.392363345871109e-06,
|
| 2011 |
+
"loss": 1.1124,
|
| 2012 |
+
"step": 7150
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.071215288145715,
|
| 2016 |
+
"grad_norm": 1.4027245044708252,
|
| 2017 |
+
"learning_rate": 9.33204800147762e-06,
|
| 2018 |
+
"loss": 1.2012,
|
| 2019 |
+
"step": 7175
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.0749477455957002,
|
| 2023 |
+
"grad_norm": 1.3875622749328613,
|
| 2024 |
+
"learning_rate": 9.271757056033551e-06,
|
| 2025 |
+
"loss": 1.0709,
|
| 2026 |
+
"step": 7200
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.0786802030456852,
|
| 2030 |
+
"grad_norm": 2.0866403579711914,
|
| 2031 |
+
"learning_rate": 9.21149271184645e-06,
|
| 2032 |
+
"loss": 1.1476,
|
| 2033 |
+
"step": 7225
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.0824126604956703,
|
| 2037 |
+
"grad_norm": 1.427161693572998,
|
| 2038 |
+
"learning_rate": 9.15125717025217e-06,
|
| 2039 |
+
"loss": 1.1209,
|
| 2040 |
+
"step": 7250
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.0861451179456554,
|
| 2044 |
+
"grad_norm": 1.1774548292160034,
|
| 2045 |
+
"learning_rate": 9.09105263153447e-06,
|
| 2046 |
+
"loss": 1.1531,
|
| 2047 |
+
"step": 7275
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.0898775753956405,
|
| 2051 |
+
"grad_norm": 1.5583891868591309,
|
| 2052 |
+
"learning_rate": 9.030881294844632e-06,
|
| 2053 |
+
"loss": 1.1557,
|
| 2054 |
+
"step": 7300
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.0936100328456255,
|
| 2058 |
+
"grad_norm": 2.1019532680511475,
|
| 2059 |
+
"learning_rate": 8.970745358121138e-06,
|
| 2060 |
+
"loss": 1.2222,
|
| 2061 |
+
"step": 7325
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.0973424902956106,
|
| 2065 |
+
"grad_norm": 1.4941744804382324,
|
| 2066 |
+
"learning_rate": 8.91064701800938e-06,
|
| 2067 |
+
"loss": 1.1338,
|
| 2068 |
+
"step": 7350
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.1010749477455957,
|
| 2072 |
+
"grad_norm": 1.6256505250930786,
|
| 2073 |
+
"learning_rate": 8.850588469781413e-06,
|
| 2074 |
+
"loss": 1.0977,
|
| 2075 |
+
"step": 7375
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.1048074051955807,
|
| 2079 |
+
"grad_norm": 1.286529779434204,
|
| 2080 |
+
"learning_rate": 8.790571907255786e-06,
|
| 2081 |
+
"loss": 1.2127,
|
| 2082 |
+
"step": 7400
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.1085398626455658,
|
| 2086 |
+
"grad_norm": 2.218416213989258,
|
| 2087 |
+
"learning_rate": 8.730599522717382e-06,
|
| 2088 |
+
"loss": 1.1587,
|
| 2089 |
+
"step": 7425
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.1122723200955509,
|
| 2093 |
+
"grad_norm": 2.030414581298828,
|
| 2094 |
+
"learning_rate": 8.670673506837364e-06,
|
| 2095 |
+
"loss": 1.0577,
|
| 2096 |
+
"step": 7450
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.116004777545536,
|
| 2100 |
+
"grad_norm": 1.4240121841430664,
|
| 2101 |
+
"learning_rate": 8.610796048593133e-06,
|
| 2102 |
+
"loss": 1.0681,
|
| 2103 |
+
"step": 7475
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.119737234995521,
|
| 2107 |
+
"grad_norm": 2.0933725833892822,
|
| 2108 |
+
"learning_rate": 8.550969335188373e-06,
|
| 2109 |
+
"loss": 1.0996,
|
| 2110 |
+
"step": 7500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.123469692445506,
|
| 2114 |
+
"grad_norm": 2.4245800971984863,
|
| 2115 |
+
"learning_rate": 8.491195551973168e-06,
|
| 2116 |
+
"loss": 1.1281,
|
| 2117 |
+
"step": 7525
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.1272021498954912,
|
| 2121 |
+
"grad_norm": 1.6084437370300293,
|
| 2122 |
+
"learning_rate": 8.431476882364162e-06,
|
| 2123 |
+
"loss": 1.1423,
|
| 2124 |
+
"step": 7550
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.1309346073454762,
|
| 2128 |
+
"grad_norm": 1.5444978475570679,
|
| 2129 |
+
"learning_rate": 8.371815507764816e-06,
|
| 2130 |
+
"loss": 1.0604,
|
| 2131 |
+
"step": 7575
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.1346670647954613,
|
| 2135 |
+
"grad_norm": 2.020827531814575,
|
| 2136 |
+
"learning_rate": 8.31221360748572e-06,
|
| 2137 |
+
"loss": 1.1431,
|
| 2138 |
+
"step": 7600
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.1383995222454464,
|
| 2142 |
+
"grad_norm": 2.264282703399658,
|
| 2143 |
+
"learning_rate": 8.252673358664972e-06,
|
| 2144 |
+
"loss": 1.22,
|
| 2145 |
+
"step": 7625
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.1421319796954315,
|
| 2149 |
+
"grad_norm": 1.6863064765930176,
|
| 2150 |
+
"learning_rate": 8.193196936188681e-06,
|
| 2151 |
+
"loss": 1.0738,
|
| 2152 |
+
"step": 7650
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.1458644371454165,
|
| 2156 |
+
"grad_norm": 1.8547500371932983,
|
| 2157 |
+
"learning_rate": 8.133786512611499e-06,
|
| 2158 |
+
"loss": 1.1273,
|
| 2159 |
+
"step": 7675
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.1495968945954016,
|
| 2163 |
+
"grad_norm": 2.0477960109710693,
|
| 2164 |
+
"learning_rate": 8.074444258077277e-06,
|
| 2165 |
+
"loss": 1.1476,
|
| 2166 |
+
"step": 7700
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.1533293520453867,
|
| 2170 |
+
"grad_norm": 1.6225486993789673,
|
| 2171 |
+
"learning_rate": 8.015172340239783e-06,
|
| 2172 |
+
"loss": 1.1621,
|
| 2173 |
+
"step": 7725
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.1570618094953717,
|
| 2177 |
+
"grad_norm": 2.2358946800231934,
|
| 2178 |
+
"learning_rate": 7.955972924183522e-06,
|
| 2179 |
+
"loss": 1.1086,
|
| 2180 |
+
"step": 7750
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.1607942669453568,
|
| 2184 |
+
"grad_norm": 1.4182322025299072,
|
| 2185 |
+
"learning_rate": 7.896848172344662e-06,
|
| 2186 |
+
"loss": 1.2202,
|
| 2187 |
+
"step": 7775
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.1645267243953419,
|
| 2191 |
+
"grad_norm": 1.8966310024261475,
|
| 2192 |
+
"learning_rate": 7.837800244432031e-06,
|
| 2193 |
+
"loss": 1.1745,
|
| 2194 |
+
"step": 7800
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.168259181845327,
|
| 2198 |
+
"grad_norm": 1.9122511148452759,
|
| 2199 |
+
"learning_rate": 7.77883129734824e-06,
|
| 2200 |
+
"loss": 1.1819,
|
| 2201 |
+
"step": 7825
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.171991639295312,
|
| 2205 |
+
"grad_norm": 1.4847153425216675,
|
| 2206 |
+
"learning_rate": 7.71994348511088e-06,
|
| 2207 |
+
"loss": 1.1829,
|
| 2208 |
+
"step": 7850
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.175724096745297,
|
| 2212 |
+
"grad_norm": 2.047247886657715,
|
| 2213 |
+
"learning_rate": 7.661138958773853e-06,
|
| 2214 |
+
"loss": 1.105,
|
| 2215 |
+
"step": 7875
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.1794565541952822,
|
| 2219 |
+
"grad_norm": 1.442701816558838,
|
| 2220 |
+
"learning_rate": 7.6024198663487905e-06,
|
| 2221 |
+
"loss": 1.1524,
|
| 2222 |
+
"step": 7900
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.1831890116452672,
|
| 2226 |
+
"grad_norm": 1.3216183185577393,
|
| 2227 |
+
"learning_rate": 7.543788352726596e-06,
|
| 2228 |
+
"loss": 1.1517,
|
| 2229 |
+
"step": 7925
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.1869214690952523,
|
| 2233 |
+
"grad_norm": 1.8324280977249146,
|
| 2234 |
+
"learning_rate": 7.4852465595990996e-06,
|
| 2235 |
+
"loss": 1.0995,
|
| 2236 |
+
"step": 7950
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.1906539265452374,
|
| 2240 |
+
"grad_norm": 1.9671550989151,
|
| 2241 |
+
"learning_rate": 7.426796625380816e-06,
|
| 2242 |
+
"loss": 1.1162,
|
| 2243 |
+
"step": 7975
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.1943863839952225,
|
| 2247 |
+
"grad_norm": 2.0152297019958496,
|
| 2248 |
+
"learning_rate": 7.368440685130837e-06,
|
| 2249 |
+
"loss": 1.1783,
|
| 2250 |
+
"step": 8000
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.1981188414452075,
|
| 2254 |
+
"grad_norm": 2.0338809490203857,
|
| 2255 |
+
"learning_rate": 7.3101808704748435e-06,
|
| 2256 |
+
"loss": 1.1305,
|
| 2257 |
+
"step": 8025
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.2018512988951926,
|
| 2261 |
+
"grad_norm": 1.4223659038543701,
|
| 2262 |
+
"learning_rate": 7.2520193095272406e-06,
|
| 2263 |
+
"loss": 1.168,
|
| 2264 |
+
"step": 8050
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.2055837563451777,
|
| 2268 |
+
"grad_norm": 2.2649288177490234,
|
| 2269 |
+
"learning_rate": 7.193958126813429e-06,
|
| 2270 |
+
"loss": 1.2133,
|
| 2271 |
+
"step": 8075
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.2093162137951627,
|
| 2275 |
+
"grad_norm": 2.082691192626953,
|
| 2276 |
+
"learning_rate": 7.135999443192186e-06,
|
| 2277 |
+
"loss": 1.1571,
|
| 2278 |
+
"step": 8100
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.2130486712451478,
|
| 2282 |
+
"grad_norm": 1.5287214517593384,
|
| 2283 |
+
"learning_rate": 7.078145375778202e-06,
|
| 2284 |
+
"loss": 1.1652,
|
| 2285 |
+
"step": 8125
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.2167811286951329,
|
| 2289 |
+
"grad_norm": 1.9839378595352173,
|
| 2290 |
+
"learning_rate": 7.020398037864747e-06,
|
| 2291 |
+
"loss": 1.1832,
|
| 2292 |
+
"step": 8150
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.220513586145118,
|
| 2296 |
+
"grad_norm": 1.330376148223877,
|
| 2297 |
+
"learning_rate": 6.962759538846484e-06,
|
| 2298 |
+
"loss": 1.1326,
|
| 2299 |
+
"step": 8175
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.224246043595103,
|
| 2303 |
+
"grad_norm": 1.392379879951477,
|
| 2304 |
+
"learning_rate": 6.9052319841423985e-06,
|
| 2305 |
+
"loss": 1.1295,
|
| 2306 |
+
"step": 8200
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.227978501045088,
|
| 2310 |
+
"grad_norm": 1.452363133430481,
|
| 2311 |
+
"learning_rate": 6.847817475118911e-06,
|
| 2312 |
+
"loss": 1.0618,
|
| 2313 |
+
"step": 8225
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.2317109584950732,
|
| 2317 |
+
"grad_norm": 2.00919771194458,
|
| 2318 |
+
"learning_rate": 6.7905181090131e-06,
|
| 2319 |
+
"loss": 1.0486,
|
| 2320 |
+
"step": 8250
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.2354434159450582,
|
| 2324 |
+
"grad_norm": 1.6396093368530273,
|
| 2325 |
+
"learning_rate": 6.733335978856108e-06,
|
| 2326 |
+
"loss": 1.1697,
|
| 2327 |
+
"step": 8275
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.2391758733950433,
|
| 2331 |
+
"grad_norm": 1.666356086730957,
|
| 2332 |
+
"learning_rate": 6.67627317339669e-06,
|
| 2333 |
+
"loss": 1.0609,
|
| 2334 |
+
"step": 8300
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.2429083308450284,
|
| 2338 |
+
"grad_norm": 1.3906646966934204,
|
| 2339 |
+
"learning_rate": 6.619331777024901e-06,
|
| 2340 |
+
"loss": 1.1236,
|
| 2341 |
+
"step": 8325
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.2466407882950135,
|
| 2345 |
+
"grad_norm": 2.39345121383667,
|
| 2346 |
+
"learning_rate": 6.562513869695967e-06,
|
| 2347 |
+
"loss": 1.1077,
|
| 2348 |
+
"step": 8350
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.2503732457449985,
|
| 2352 |
+
"grad_norm": 1.6149343252182007,
|
| 2353 |
+
"learning_rate": 6.505821526854302e-06,
|
| 2354 |
+
"loss": 1.134,
|
| 2355 |
+
"step": 8375
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.2541057031949836,
|
| 2359 |
+
"grad_norm": 2.2569212913513184,
|
| 2360 |
+
"learning_rate": 6.449256819357706e-06,
|
| 2361 |
+
"loss": 1.0531,
|
| 2362 |
+
"step": 8400
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.2578381606449687,
|
| 2366 |
+
"grad_norm": 1.6592438220977783,
|
| 2367 |
+
"learning_rate": 6.3928218134017175e-06,
|
| 2368 |
+
"loss": 1.1663,
|
| 2369 |
+
"step": 8425
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.2615706180949537,
|
| 2373 |
+
"grad_norm": 1.553542137145996,
|
| 2374 |
+
"learning_rate": 6.336518570444132e-06,
|
| 2375 |
+
"loss": 1.1776,
|
| 2376 |
+
"step": 8450
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.2653030755449388,
|
| 2380 |
+
"grad_norm": 1.2993265390396118,
|
| 2381 |
+
"learning_rate": 6.280349147129711e-06,
|
| 2382 |
+
"loss": 1.1804,
|
| 2383 |
+
"step": 8475
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.2690355329949239,
|
| 2387 |
+
"grad_norm": 1.5138100385665894,
|
| 2388 |
+
"learning_rate": 6.2243155952150445e-06,
|
| 2389 |
+
"loss": 1.0547,
|
| 2390 |
+
"step": 8500
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.272767990444909,
|
| 2394 |
+
"grad_norm": 1.947925090789795,
|
| 2395 |
+
"learning_rate": 6.168419961493618e-06,
|
| 2396 |
+
"loss": 1.1109,
|
| 2397 |
+
"step": 8525
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.276500447894894,
|
| 2401 |
+
"grad_norm": 2.3967175483703613,
|
| 2402 |
+
"learning_rate": 6.112664287721047e-06,
|
| 2403 |
+
"loss": 1.0756,
|
| 2404 |
+
"step": 8550
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.280232905344879,
|
| 2408 |
+
"grad_norm": 2.8286006450653076,
|
| 2409 |
+
"learning_rate": 6.057050610540478e-06,
|
| 2410 |
+
"loss": 1.1191,
|
| 2411 |
+
"step": 8575
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.2839653627948642,
|
| 2415 |
+
"grad_norm": 1.5493801832199097,
|
| 2416 |
+
"learning_rate": 6.0015809614082175e-06,
|
| 2417 |
+
"loss": 1.1326,
|
| 2418 |
+
"step": 8600
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.2876978202448492,
|
| 2422 |
+
"grad_norm": 2.070044755935669,
|
| 2423 |
+
"learning_rate": 5.9462573665195055e-06,
|
| 2424 |
+
"loss": 1.1442,
|
| 2425 |
+
"step": 8625
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.2914302776948343,
|
| 2429 |
+
"grad_norm": 1.602590560913086,
|
| 2430 |
+
"learning_rate": 5.891081846734519e-06,
|
| 2431 |
+
"loss": 1.1736,
|
| 2432 |
+
"step": 8650
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.2951627351448194,
|
| 2436 |
+
"grad_norm": 1.58939528465271,
|
| 2437 |
+
"learning_rate": 5.83605641750455e-06,
|
| 2438 |
+
"loss": 1.1332,
|
| 2439 |
+
"step": 8675
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.2988951925948045,
|
| 2443 |
+
"grad_norm": 2.3203682899475098,
|
| 2444 |
+
"learning_rate": 5.7811830887983754e-06,
|
| 2445 |
+
"loss": 1.0441,
|
| 2446 |
+
"step": 8700
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.3026276500447895,
|
| 2450 |
+
"grad_norm": 1.6625529527664185,
|
| 2451 |
+
"learning_rate": 5.72646386502886e-06,
|
| 2452 |
+
"loss": 1.0532,
|
| 2453 |
+
"step": 8725
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.3063601074947746,
|
| 2457 |
+
"grad_norm": 2.119262456893921,
|
| 2458 |
+
"learning_rate": 5.671900744979697e-06,
|
| 2459 |
+
"loss": 1.1607,
|
| 2460 |
+
"step": 8750
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.3100925649447597,
|
| 2464 |
+
"grad_norm": 1.253125786781311,
|
| 2465 |
+
"learning_rate": 5.617495721732445e-06,
|
| 2466 |
+
"loss": 1.1638,
|
| 2467 |
+
"step": 8775
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.3138250223947447,
|
| 2471 |
+
"grad_norm": 1.5370473861694336,
|
| 2472 |
+
"learning_rate": 5.563250782593701e-06,
|
| 2473 |
+
"loss": 1.1022,
|
| 2474 |
+
"step": 8800
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.3175574798447298,
|
| 2478 |
+
"grad_norm": 1.874109148979187,
|
| 2479 |
+
"learning_rate": 5.509167909022499e-06,
|
| 2480 |
+
"loss": 1.0875,
|
| 2481 |
+
"step": 8825
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.321289937294715,
|
| 2485 |
+
"grad_norm": 1.6128805875778198,
|
| 2486 |
+
"learning_rate": 5.4552490765579555e-06,
|
| 2487 |
+
"loss": 1.0155,
|
| 2488 |
+
"step": 8850
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.3250223947447,
|
| 2492 |
+
"grad_norm": 1.8262598514556885,
|
| 2493 |
+
"learning_rate": 5.401496254747081e-06,
|
| 2494 |
+
"loss": 1.1788,
|
| 2495 |
+
"step": 8875
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.328754852194685,
|
| 2499 |
+
"grad_norm": 2.1879348754882812,
|
| 2500 |
+
"learning_rate": 5.347911407072862e-06,
|
| 2501 |
+
"loss": 1.1587,
|
| 2502 |
+
"step": 8900
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.33248730964467,
|
| 2506 |
+
"grad_norm": 1.4473679065704346,
|
| 2507 |
+
"learning_rate": 5.2944964908825106e-06,
|
| 2508 |
+
"loss": 1.139,
|
| 2509 |
+
"step": 8925
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.3362197670946552,
|
| 2513 |
+
"grad_norm": 1.9233894348144531,
|
| 2514 |
+
"learning_rate": 5.241253457315996e-06,
|
| 2515 |
+
"loss": 1.1275,
|
| 2516 |
+
"step": 8950
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.3399522245446402,
|
| 2520 |
+
"grad_norm": 1.3463555574417114,
|
| 2521 |
+
"learning_rate": 5.188184251234758e-06,
|
| 2522 |
+
"loss": 1.1071,
|
| 2523 |
+
"step": 8975
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.3436846819946253,
|
| 2527 |
+
"grad_norm": 1.7632958889007568,
|
| 2528 |
+
"learning_rate": 5.135290811150656e-06,
|
| 2529 |
+
"loss": 1.0742,
|
| 2530 |
+
"step": 9000
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.3474171394446104,
|
| 2534 |
+
"grad_norm": 1.586159348487854,
|
| 2535 |
+
"learning_rate": 5.082575069155174e-06,
|
| 2536 |
+
"loss": 1.0873,
|
| 2537 |
+
"step": 9025
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.3511495968945955,
|
| 2541 |
+
"grad_norm": 2.366755247116089,
|
| 2542 |
+
"learning_rate": 5.03003895084885e-06,
|
| 2543 |
+
"loss": 1.1684,
|
| 2544 |
+
"step": 9050
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.3548820543445805,
|
| 2548 |
+
"grad_norm": 2.0446362495422363,
|
| 2549 |
+
"learning_rate": 4.97768437527091e-06,
|
| 2550 |
+
"loss": 1.1631,
|
| 2551 |
+
"step": 9075
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.3586145117945656,
|
| 2555 |
+
"grad_norm": 1.790091633796692,
|
| 2556 |
+
"learning_rate": 4.925513254829209e-06,
|
| 2557 |
+
"loss": 1.169,
|
| 2558 |
+
"step": 9100
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.3623469692445507,
|
| 2562 |
+
"grad_norm": 1.2629742622375488,
|
| 2563 |
+
"learning_rate": 4.873527495230332e-06,
|
| 2564 |
+
"loss": 1.108,
|
| 2565 |
+
"step": 9125
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.3660794266945357,
|
| 2569 |
+
"grad_norm": 2.121185302734375,
|
| 2570 |
+
"learning_rate": 4.821728995410022e-06,
|
| 2571 |
+
"loss": 1.1191,
|
| 2572 |
+
"step": 9150
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.3698118841445208,
|
| 2576 |
+
"grad_norm": 1.7731324434280396,
|
| 2577 |
+
"learning_rate": 4.77011964746378e-06,
|
| 2578 |
+
"loss": 1.1217,
|
| 2579 |
+
"step": 9175
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.373544341594506,
|
| 2583 |
+
"grad_norm": 1.7735278606414795,
|
| 2584 |
+
"learning_rate": 4.7187013365777815e-06,
|
| 2585 |
+
"loss": 1.1551,
|
| 2586 |
+
"step": 9200
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.377276799044491,
|
| 2590 |
+
"grad_norm": 1.352729082107544,
|
| 2591 |
+
"learning_rate": 4.667475940959998e-06,
|
| 2592 |
+
"loss": 1.1701,
|
| 2593 |
+
"step": 9225
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.381009256494476,
|
| 2597 |
+
"grad_norm": 1.7144463062286377,
|
| 2598 |
+
"learning_rate": 4.616445331771587e-06,
|
| 2599 |
+
"loss": 1.1293,
|
| 2600 |
+
"step": 9250
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.384741713944461,
|
| 2604 |
+
"grad_norm": 1.1307408809661865,
|
| 2605 |
+
"learning_rate": 4.565611373058545e-06,
|
| 2606 |
+
"loss": 1.1125,
|
| 2607 |
+
"step": 9275
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.3884741713944462,
|
| 2611 |
+
"grad_norm": 1.4697372913360596,
|
| 2612 |
+
"learning_rate": 4.514975921683631e-06,
|
| 2613 |
+
"loss": 1.0857,
|
| 2614 |
+
"step": 9300
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.3922066288444312,
|
| 2618 |
+
"grad_norm": 2.0420682430267334,
|
| 2619 |
+
"learning_rate": 4.4645408272585265e-06,
|
| 2620 |
+
"loss": 1.1061,
|
| 2621 |
+
"step": 9325
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.3959390862944163,
|
| 2625 |
+
"grad_norm": 2.240722417831421,
|
| 2626 |
+
"learning_rate": 4.4143079320762675e-06,
|
| 2627 |
+
"loss": 1.0921,
|
| 2628 |
+
"step": 9350
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.3996715437444014,
|
| 2632 |
+
"grad_norm": 1.8340919017791748,
|
| 2633 |
+
"learning_rate": 4.364279071043955e-06,
|
| 2634 |
+
"loss": 1.1458,
|
| 2635 |
+
"step": 9375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.4034040011943865,
|
| 2639 |
+
"grad_norm": 2.2173268795013428,
|
| 2640 |
+
"learning_rate": 4.314456071615747e-06,
|
| 2641 |
+
"loss": 1.1657,
|
| 2642 |
+
"step": 9400
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.4071364586443715,
|
| 2646 |
+
"grad_norm": 1.6073921918869019,
|
| 2647 |
+
"learning_rate": 4.264840753726066e-06,
|
| 2648 |
+
"loss": 1.072,
|
| 2649 |
+
"step": 9425
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.4108689160943566,
|
| 2653 |
+
"grad_norm": 1.6717661619186401,
|
| 2654 |
+
"learning_rate": 4.215434929723165e-06,
|
| 2655 |
+
"loss": 1.1181,
|
| 2656 |
+
"step": 9450
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.4146013735443415,
|
| 2660 |
+
"grad_norm": 2.7145605087280273,
|
| 2661 |
+
"learning_rate": 4.1662404043028935e-06,
|
| 2662 |
+
"loss": 1.0869,
|
| 2663 |
+
"step": 9475
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.4183338309943267,
|
| 2667 |
+
"grad_norm": 1.4944945573806763,
|
| 2668 |
+
"learning_rate": 4.117258974442789e-06,
|
| 2669 |
+
"loss": 1.1613,
|
| 2670 |
+
"step": 9500
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.4220662884443116,
|
| 2674 |
+
"grad_norm": 2.4273176193237305,
|
| 2675 |
+
"learning_rate": 4.06849242933643e-06,
|
| 2676 |
+
"loss": 1.1624,
|
| 2677 |
+
"step": 9525
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.425798745894297,
|
| 2681 |
+
"grad_norm": 1.472550392150879,
|
| 2682 |
+
"learning_rate": 4.019942550328095e-06,
|
| 2683 |
+
"loss": 1.1275,
|
| 2684 |
+
"step": 9550
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.4295312033442817,
|
| 2688 |
+
"grad_norm": 1.120005488395691,
|
| 2689 |
+
"learning_rate": 3.971611110847678e-06,
|
| 2690 |
+
"loss": 1.1263,
|
| 2691 |
+
"step": 9575
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.433263660794267,
|
| 2695 |
+
"grad_norm": 2.124173641204834,
|
| 2696 |
+
"learning_rate": 3.923499876345913e-06,
|
| 2697 |
+
"loss": 1.0929,
|
| 2698 |
+
"step": 9600
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.4369961182442519,
|
| 2702 |
+
"grad_norm": 2.039698600769043,
|
| 2703 |
+
"learning_rate": 3.875610604229886e-06,
|
| 2704 |
+
"loss": 1.1147,
|
| 2705 |
+
"step": 9625
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.4407285756942372,
|
| 2709 |
+
"grad_norm": 2.226929187774658,
|
| 2710 |
+
"learning_rate": 3.82794504379885e-06,
|
| 2711 |
+
"loss": 1.0798,
|
| 2712 |
+
"step": 9650
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.444461033144222,
|
| 2716 |
+
"grad_norm": 1.7479681968688965,
|
| 2717 |
+
"learning_rate": 3.7805049361803047e-06,
|
| 2718 |
+
"loss": 1.1117,
|
| 2719 |
+
"step": 9675
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.4481934905942073,
|
| 2723 |
+
"grad_norm": 1.8305010795593262,
|
| 2724 |
+
"learning_rate": 3.733292014266422e-06,
|
| 2725 |
+
"loss": 1.1188,
|
| 2726 |
+
"step": 9700
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.4519259480441922,
|
| 2730 |
+
"grad_norm": 1.6707849502563477,
|
| 2731 |
+
"learning_rate": 3.6863080026507316e-06,
|
| 2732 |
+
"loss": 1.1041,
|
| 2733 |
+
"step": 9725
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.4556584054941775,
|
| 2737 |
+
"grad_norm": 1.8863219022750854,
|
| 2738 |
+
"learning_rate": 3.639554617565123e-06,
|
| 2739 |
+
"loss": 1.1363,
|
| 2740 |
+
"step": 9750
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.4593908629441623,
|
| 2744 |
+
"grad_norm": 1.9603029489517212,
|
| 2745 |
+
"learning_rate": 3.5930335668171612e-06,
|
| 2746 |
+
"loss": 1.0795,
|
| 2747 |
+
"step": 9775
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.4631233203941476,
|
| 2751 |
+
"grad_norm": 1.2171770334243774,
|
| 2752 |
+
"learning_rate": 3.5467465497277098e-06,
|
| 2753 |
+
"loss": 1.1738,
|
| 2754 |
+
"step": 9800
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.4668557778441325,
|
| 2758 |
+
"grad_norm": 1.4534763097763062,
|
| 2759 |
+
"learning_rate": 3.500695257068848e-06,
|
| 2760 |
+
"loss": 1.1413,
|
| 2761 |
+
"step": 9825
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.4705882352941178,
|
| 2765 |
+
"grad_norm": 1.8603515625,
|
| 2766 |
+
"learning_rate": 3.45488137100211e-06,
|
| 2767 |
+
"loss": 1.1065,
|
| 2768 |
+
"step": 9850
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.4743206927441026,
|
| 2772 |
+
"grad_norm": 1.5301094055175781,
|
| 2773 |
+
"learning_rate": 3.409306565017042e-06,
|
| 2774 |
+
"loss": 1.15,
|
| 2775 |
+
"step": 9875
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.478053150194088,
|
| 2779 |
+
"grad_norm": 1.9820491075515747,
|
| 2780 |
+
"learning_rate": 3.363972503870082e-06,
|
| 2781 |
+
"loss": 1.1335,
|
| 2782 |
+
"step": 9900
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.4817856076440727,
|
| 2786 |
+
"grad_norm": 1.562347650527954,
|
| 2787 |
+
"learning_rate": 3.3188808435237295e-06,
|
| 2788 |
+
"loss": 1.126,
|
| 2789 |
+
"step": 9925
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.485518065094058,
|
| 2793 |
+
"grad_norm": 1.440078854560852,
|
| 2794 |
+
"learning_rate": 3.2740332310860758e-06,
|
| 2795 |
+
"loss": 1.0951,
|
| 2796 |
+
"step": 9950
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.4892505225440429,
|
| 2800 |
+
"grad_norm": 1.8323134183883667,
|
| 2801 |
+
"learning_rate": 3.229431304750633e-06,
|
| 2802 |
+
"loss": 1.1655,
|
| 2803 |
+
"step": 9975
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 1.4929829799940282,
|
| 2807 |
+
"grad_norm": 2.663576126098633,
|
| 2808 |
+
"learning_rate": 3.185076693736483e-06,
|
| 2809 |
+
"loss": 1.1957,
|
| 2810 |
+
"step": 10000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.496715437444013,
|
| 2814 |
+
"grad_norm": 1.9912225008010864,
|
| 2815 |
+
"learning_rate": 3.1409710182287757e-06,
|
| 2816 |
+
"loss": 1.1006,
|
| 2817 |
+
"step": 10025
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 1.5004478948939983,
|
| 2821 |
+
"grad_norm": 3.2061407566070557,
|
| 2822 |
+
"learning_rate": 3.09711588931955e-06,
|
| 2823 |
+
"loss": 1.1886,
|
| 2824 |
+
"step": 10050
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 1.5041803523439832,
|
| 2828 |
+
"grad_norm": 1.6869685649871826,
|
| 2829 |
+
"learning_rate": 3.0535129089488813e-06,
|
| 2830 |
+
"loss": 1.085,
|
| 2831 |
+
"step": 10075
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 1.5079128097939685,
|
| 2835 |
+
"grad_norm": 1.1851885318756104,
|
| 2836 |
+
"learning_rate": 3.0101636698463556e-06,
|
| 2837 |
+
"loss": 1.1252,
|
| 2838 |
+
"step": 10100
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 1.5116452672439533,
|
| 2842 |
+
"grad_norm": 1.8176482915878296,
|
| 2843 |
+
"learning_rate": 2.967069755472899e-06,
|
| 2844 |
+
"loss": 1.0895,
|
| 2845 |
+
"step": 10125
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.5153777246939386,
|
| 2849 |
+
"grad_norm": 1.722021460533142,
|
| 2850 |
+
"learning_rate": 2.9242327399629445e-06,
|
| 2851 |
+
"loss": 1.1318,
|
| 2852 |
+
"step": 10150
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 1.5191101821439235,
|
| 2856 |
+
"grad_norm": 1.7580561637878418,
|
| 2857 |
+
"learning_rate": 2.8816541880669145e-06,
|
| 2858 |
+
"loss": 1.0428,
|
| 2859 |
+
"step": 10175
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.5228426395939088,
|
| 2863 |
+
"grad_norm": 1.8136518001556396,
|
| 2864 |
+
"learning_rate": 2.8393356550940778e-06,
|
| 2865 |
+
"loss": 1.1525,
|
| 2866 |
+
"step": 10200
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.5265750970438936,
|
| 2870 |
+
"grad_norm": 1.3077131509780884,
|
| 2871 |
+
"learning_rate": 2.7972786868557365e-06,
|
| 2872 |
+
"loss": 1.1932,
|
| 2873 |
+
"step": 10225
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 1.530307554493879,
|
| 2877 |
+
"grad_norm": 2.2732295989990234,
|
| 2878 |
+
"learning_rate": 2.7554848196087493e-06,
|
| 2879 |
+
"loss": 1.1529,
|
| 2880 |
+
"step": 10250
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 1.5340400119438637,
|
| 2884 |
+
"grad_norm": 2.207001209259033,
|
| 2885 |
+
"learning_rate": 2.7139555799994198e-06,
|
| 2886 |
+
"loss": 1.1333,
|
| 2887 |
+
"step": 10275
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 1.537772469393849,
|
| 2891 |
+
"grad_norm": 1.7305580377578735,
|
| 2892 |
+
"learning_rate": 2.672692485007744e-06,
|
| 2893 |
+
"loss": 1.1834,
|
| 2894 |
+
"step": 10300
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 1.541504926843834,
|
| 2898 |
+
"grad_norm": 1.3060213327407837,
|
| 2899 |
+
"learning_rate": 2.631697041891984e-06,
|
| 2900 |
+
"loss": 1.1016,
|
| 2901 |
+
"step": 10325
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 1.5452373842938192,
|
| 2905 |
+
"grad_norm": 1.4190231561660767,
|
| 2906 |
+
"learning_rate": 2.590970748133611e-06,
|
| 2907 |
+
"loss": 1.0844,
|
| 2908 |
+
"step": 10350
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 1.548969841743804,
|
| 2912 |
+
"grad_norm": 1.52984619140625,
|
| 2913 |
+
"learning_rate": 2.5505150913826084e-06,
|
| 2914 |
+
"loss": 1.1215,
|
| 2915 |
+
"step": 10375
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.5527022991937893,
|
| 2919 |
+
"grad_norm": 2.1748387813568115,
|
| 2920 |
+
"learning_rate": 2.510331549403139e-06,
|
| 2921 |
+
"loss": 1.0668,
|
| 2922 |
+
"step": 10400
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 1.5564347566437742,
|
| 2926 |
+
"grad_norm": 1.3061221837997437,
|
| 2927 |
+
"learning_rate": 2.470421590019548e-06,
|
| 2928 |
+
"loss": 1.1091,
|
| 2929 |
+
"step": 10425
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 1.5601672140937595,
|
| 2933 |
+
"grad_norm": 1.638881802558899,
|
| 2934 |
+
"learning_rate": 2.4307866710627636e-06,
|
| 2935 |
+
"loss": 1.1703,
|
| 2936 |
+
"step": 10450
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 1.5638996715437443,
|
| 2940 |
+
"grad_norm": 1.3871835470199585,
|
| 2941 |
+
"learning_rate": 2.3914282403170385e-06,
|
| 2942 |
+
"loss": 1.1998,
|
| 2943 |
+
"step": 10475
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 1.5676321289937296,
|
| 2947 |
+
"grad_norm": 1.460083246231079,
|
| 2948 |
+
"learning_rate": 2.3523477354670586e-06,
|
| 2949 |
+
"loss": 1.1087,
|
| 2950 |
+
"step": 10500
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 1.5713645864437145,
|
| 2954 |
+
"grad_norm": 1.4515403509140015,
|
| 2955 |
+
"learning_rate": 2.313546584045432e-06,
|
| 2956 |
+
"loss": 1.0663,
|
| 2957 |
+
"step": 10525
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 1.5750970438936998,
|
| 2961 |
+
"grad_norm": 1.5948618650436401,
|
| 2962 |
+
"learning_rate": 2.2750262033805513e-06,
|
| 2963 |
+
"loss": 1.0758,
|
| 2964 |
+
"step": 10550
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 1.5788295013436846,
|
| 2968 |
+
"grad_norm": 1.943331003189087,
|
| 2969 |
+
"learning_rate": 2.236788000544817e-06,
|
| 2970 |
+
"loss": 1.0956,
|
| 2971 |
+
"step": 10575
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 1.58256195879367,
|
| 2975 |
+
"grad_norm": 1.8953666687011719,
|
| 2976 |
+
"learning_rate": 2.198833372303233e-06,
|
| 2977 |
+
"loss": 1.1122,
|
| 2978 |
+
"step": 10600
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 1.5862944162436547,
|
| 2982 |
+
"grad_norm": 2.3364477157592773,
|
| 2983 |
+
"learning_rate": 2.1611637050623866e-06,
|
| 2984 |
+
"loss": 1.1121,
|
| 2985 |
+
"step": 10625
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 1.59002687369364,
|
| 2989 |
+
"grad_norm": 2.5381453037261963,
|
| 2990 |
+
"learning_rate": 2.1237803748198238e-06,
|
| 2991 |
+
"loss": 1.1065,
|
| 2992 |
+
"step": 10650
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 1.593759331143625,
|
| 2996 |
+
"grad_norm": 1.718410849571228,
|
| 2997 |
+
"learning_rate": 2.0866847471137588e-06,
|
| 2998 |
+
"loss": 1.1232,
|
| 2999 |
+
"step": 10675
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 1.5974917885936102,
|
| 3003 |
+
"grad_norm": 2.0576751232147217,
|
| 3004 |
+
"learning_rate": 2.049878176973218e-06,
|
| 3005 |
+
"loss": 1.0853,
|
| 3006 |
+
"step": 10700
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 1.601224246043595,
|
| 3010 |
+
"grad_norm": 2.394857406616211,
|
| 3011 |
+
"learning_rate": 2.0133620088685314e-06,
|
| 3012 |
+
"loss": 1.1566,
|
| 3013 |
+
"step": 10725
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 1.6049567034935803,
|
| 3017 |
+
"grad_norm": 1.7517675161361694,
|
| 3018 |
+
"learning_rate": 1.9771375766622227e-06,
|
| 3019 |
+
"loss": 1.0626,
|
| 3020 |
+
"step": 10750
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 1.6086891609435652,
|
| 3024 |
+
"grad_norm": 1.7681195735931396,
|
| 3025 |
+
"learning_rate": 1.941206203560283e-06,
|
| 3026 |
+
"loss": 1.1656,
|
| 3027 |
+
"step": 10775
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 1.6124216183935505,
|
| 3031 |
+
"grad_norm": 1.3712217807769775,
|
| 3032 |
+
"learning_rate": 1.9055692020638471e-06,
|
| 3033 |
+
"loss": 1.1124,
|
| 3034 |
+
"step": 10800
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 1.6161540758435353,
|
| 3038 |
+
"grad_norm": 1.4817813634872437,
|
| 3039 |
+
"learning_rate": 1.8702278739212475e-06,
|
| 3040 |
+
"loss": 1.0707,
|
| 3041 |
+
"step": 10825
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 1.6198865332935206,
|
| 3045 |
+
"grad_norm": 3.1233913898468018,
|
| 3046 |
+
"learning_rate": 1.8351835100804515e-06,
|
| 3047 |
+
"loss": 1.1632,
|
| 3048 |
+
"step": 10850
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 1.6236189907435055,
|
| 3052 |
+
"grad_norm": 1.694852590560913,
|
| 3053 |
+
"learning_rate": 1.800437390641917e-06,
|
| 3054 |
+
"loss": 1.1411,
|
| 3055 |
+
"step": 10875
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 1.6273514481934908,
|
| 3059 |
+
"grad_norm": 2.072053909301758,
|
| 3060 |
+
"learning_rate": 1.7659907848118384e-06,
|
| 3061 |
+
"loss": 1.0997,
|
| 3062 |
+
"step": 10900
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 1.6310839056434756,
|
| 3066 |
+
"grad_norm": 2.4234817028045654,
|
| 3067 |
+
"learning_rate": 1.7318449508557679e-06,
|
| 3068 |
+
"loss": 1.1937,
|
| 3069 |
+
"step": 10925
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.634816363093461,
|
| 3073 |
+
"grad_norm": 2.134819746017456,
|
| 3074 |
+
"learning_rate": 1.6980011360526693e-06,
|
| 3075 |
+
"loss": 1.1062,
|
| 3076 |
+
"step": 10950
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 1.6385488205434457,
|
| 3080 |
+
"grad_norm": 1.728718638420105,
|
| 3081 |
+
"learning_rate": 1.6644605766493527e-06,
|
| 3082 |
+
"loss": 1.1053,
|
| 3083 |
+
"step": 10975
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 1.6422812779934308,
|
| 3087 |
+
"grad_norm": 1.7218749523162842,
|
| 3088 |
+
"learning_rate": 1.6312244978153103e-06,
|
| 3089 |
+
"loss": 1.0659,
|
| 3090 |
+
"step": 11000
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 1.646013735443416,
|
| 3094 |
+
"grad_norm": 1.8273673057556152,
|
| 3095 |
+
"learning_rate": 1.598294113597968e-06,
|
| 3096 |
+
"loss": 1.155,
|
| 3097 |
+
"step": 11025
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 1.649746192893401,
|
| 3101 |
+
"grad_norm": 1.3257777690887451,
|
| 3102 |
+
"learning_rate": 1.565670626878344e-06,
|
| 3103 |
+
"loss": 1.0923,
|
| 3104 |
+
"step": 11050
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 1.653478650343386,
|
| 3108 |
+
"grad_norm": 2.329346179962158,
|
| 3109 |
+
"learning_rate": 1.533355229327107e-06,
|
| 3110 |
+
"loss": 1.1995,
|
| 3111 |
+
"step": 11075
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 1.657211107793371,
|
| 3115 |
+
"grad_norm": 1.8972541093826294,
|
| 3116 |
+
"learning_rate": 1.5013491013610381e-06,
|
| 3117 |
+
"loss": 1.115,
|
| 3118 |
+
"step": 11100
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 1.6609435652433562,
|
| 3122 |
+
"grad_norm": 1.2541754245758057,
|
| 3123 |
+
"learning_rate": 1.4696534120999205e-06,
|
| 3124 |
+
"loss": 1.1326,
|
| 3125 |
+
"step": 11125
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 1.6646760226933413,
|
| 3129 |
+
"grad_norm": 1.7968276739120483,
|
| 3130 |
+
"learning_rate": 1.4382693193238406e-06,
|
| 3131 |
+
"loss": 1.1092,
|
| 3132 |
+
"step": 11150
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 1.6684084801433263,
|
| 3136 |
+
"grad_norm": 2.048880100250244,
|
| 3137 |
+
"learning_rate": 1.407197969430879e-06,
|
| 3138 |
+
"loss": 1.1347,
|
| 3139 |
+
"step": 11175
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 1.6721409375933114,
|
| 3143 |
+
"grad_norm": 1.6656211614608765,
|
| 3144 |
+
"learning_rate": 1.3764404973952517e-06,
|
| 3145 |
+
"loss": 1.1882,
|
| 3146 |
+
"step": 11200
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 1.6758733950432965,
|
| 3150 |
+
"grad_norm": 1.8330296277999878,
|
| 3151 |
+
"learning_rate": 1.3459980267258432e-06,
|
| 3152 |
+
"loss": 1.1001,
|
| 3153 |
+
"step": 11225
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 1.6796058524932815,
|
| 3157 |
+
"grad_norm": 2.6874196529388428,
|
| 3158 |
+
"learning_rate": 1.3158716694251695e-06,
|
| 3159 |
+
"loss": 1.1027,
|
| 3160 |
+
"step": 11250
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 1.6833383099432666,
|
| 3164 |
+
"grad_norm": 1.514073371887207,
|
| 3165 |
+
"learning_rate": 1.2860625259487503e-06,
|
| 3166 |
+
"loss": 1.0475,
|
| 3167 |
+
"step": 11275
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 1.6870707673932517,
|
| 3171 |
+
"grad_norm": 1.9588838815689087,
|
| 3172 |
+
"learning_rate": 1.2565716851649311e-06,
|
| 3173 |
+
"loss": 1.0807,
|
| 3174 |
+
"step": 11300
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 1.6908032248432368,
|
| 3178 |
+
"grad_norm": 1.3124940395355225,
|
| 3179 |
+
"learning_rate": 1.227400224315093e-06,
|
| 3180 |
+
"loss": 1.0948,
|
| 3181 |
+
"step": 11325
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 1.6945356822932218,
|
| 3185 |
+
"grad_norm": 2.254624605178833,
|
| 3186 |
+
"learning_rate": 1.1985492089743033e-06,
|
| 3187 |
+
"loss": 1.194,
|
| 3188 |
+
"step": 11350
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 1.698268139743207,
|
| 3192 |
+
"grad_norm": 2.042088508605957,
|
| 3193 |
+
"learning_rate": 1.1700196930123976e-06,
|
| 3194 |
+
"loss": 1.0444,
|
| 3195 |
+
"step": 11375
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 1.702000597193192,
|
| 3199 |
+
"grad_norm": 2.0678699016571045,
|
| 3200 |
+
"learning_rate": 1.141812718555486e-06,
|
| 3201 |
+
"loss": 1.2321,
|
| 3202 |
+
"step": 11400
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 1.705733054643177,
|
| 3206 |
+
"grad_norm": 2.074615955352783,
|
| 3207 |
+
"learning_rate": 1.1139293159478836e-06,
|
| 3208 |
+
"loss": 1.1151,
|
| 3209 |
+
"step": 11425
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 1.709465512093162,
|
| 3213 |
+
"grad_norm": 1.6156505346298218,
|
| 3214 |
+
"learning_rate": 1.086370503714469e-06,
|
| 3215 |
+
"loss": 1.1754,
|
| 3216 |
+
"step": 11450
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 1.7131979695431472,
|
| 3220 |
+
"grad_norm": 2.8018553256988525,
|
| 3221 |
+
"learning_rate": 1.0591372885234885e-06,
|
| 3222 |
+
"loss": 1.1344,
|
| 3223 |
+
"step": 11475
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 1.7169304269931323,
|
| 3227 |
+
"grad_norm": 2.0518441200256348,
|
| 3228 |
+
"learning_rate": 1.032230665149777e-06,
|
| 3229 |
+
"loss": 1.0816,
|
| 3230 |
+
"step": 11500
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 1.7206628844431173,
|
| 3234 |
+
"grad_norm": 1.9642572402954102,
|
| 3235 |
+
"learning_rate": 1.0056516164384234e-06,
|
| 3236 |
+
"loss": 1.1712,
|
| 3237 |
+
"step": 11525
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 1.7243953418931024,
|
| 3241 |
+
"grad_norm": 1.679519772529602,
|
| 3242 |
+
"learning_rate": 9.79401113268874e-07,
|
| 3243 |
+
"loss": 1.0824,
|
| 3244 |
+
"step": 11550
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 1.7281277993430875,
|
| 3248 |
+
"grad_norm": 1.6319055557250977,
|
| 3249 |
+
"learning_rate": 9.534801145194638e-07,
|
| 3250 |
+
"loss": 1.0335,
|
| 3251 |
+
"step": 11575
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 1.7318602567930725,
|
| 3255 |
+
"grad_norm": 1.6553189754486084,
|
| 3256 |
+
"learning_rate": 9.278895670323873e-07,
|
| 3257 |
+
"loss": 1.1526,
|
| 3258 |
+
"step": 11600
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 1.7355927142430576,
|
| 3262 |
+
"grad_norm": 2.050332546234131,
|
| 3263 |
+
"learning_rate": 9.026304055791157e-07,
|
| 3264 |
+
"loss": 1.1082,
|
| 3265 |
+
"step": 11625
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 1.7393251716930427,
|
| 3269 |
+
"grad_norm": 2.3540430068969727,
|
| 3270 |
+
"learning_rate": 8.777035528262568e-07,
|
| 3271 |
+
"loss": 1.1494,
|
| 3272 |
+
"step": 11650
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 1.7430576291430278,
|
| 3276 |
+
"grad_norm": 1.6769859790802002,
|
| 3277 |
+
"learning_rate": 8.531099193018433e-07,
|
| 3278 |
+
"loss": 1.1348,
|
| 3279 |
+
"step": 11675
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 1.7467900865930128,
|
| 3283 |
+
"grad_norm": 5.018988609313965,
|
| 3284 |
+
"learning_rate": 8.288504033620748e-07,
|
| 3285 |
+
"loss": 1.1647,
|
| 3286 |
+
"step": 11700
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 1.750522544042998,
|
| 3290 |
+
"grad_norm": 2.353095293045044,
|
| 3291 |
+
"learning_rate": 8.049258911585111e-07,
|
| 3292 |
+
"loss": 1.0927,
|
| 3293 |
+
"step": 11725
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 1.754255001492983,
|
| 3297 |
+
"grad_norm": 2.0205836296081543,
|
| 3298 |
+
"learning_rate": 7.813372566056876e-07,
|
| 3299 |
+
"loss": 1.1419,
|
| 3300 |
+
"step": 11750
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 1.757987458942968,
|
| 3304 |
+
"grad_norm": 2.0935847759246826,
|
| 3305 |
+
"learning_rate": 7.580853613492045e-07,
|
| 3306 |
+
"loss": 1.1403,
|
| 3307 |
+
"step": 11775
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 1.7617199163929531,
|
| 3311 |
+
"grad_norm": 2.269958972930908,
|
| 3312 |
+
"learning_rate": 7.351710547342527e-07,
|
| 3313 |
+
"loss": 1.1325,
|
| 3314 |
+
"step": 11800
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 1.7654523738429382,
|
| 3318 |
+
"grad_norm": 1.559847116470337,
|
| 3319 |
+
"learning_rate": 7.125951737745851e-07,
|
| 3320 |
+
"loss": 1.077,
|
| 3321 |
+
"step": 11825
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 1.7691848312929233,
|
| 3325 |
+
"grad_norm": 1.7500661611557007,
|
| 3326 |
+
"learning_rate": 6.903585431219384e-07,
|
| 3327 |
+
"loss": 1.1374,
|
| 3328 |
+
"step": 11850
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 1.7729172887429083,
|
| 3332 |
+
"grad_norm": 1.6666224002838135,
|
| 3333 |
+
"learning_rate": 6.684619750359189e-07,
|
| 3334 |
+
"loss": 1.1507,
|
| 3335 |
+
"step": 11875
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 1.7766497461928934,
|
| 3339 |
+
"grad_norm": 1.5856088399887085,
|
| 3340 |
+
"learning_rate": 6.469062693543249e-07,
|
| 3341 |
+
"loss": 1.0852,
|
| 3342 |
+
"step": 11900
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 1.7803822036428785,
|
| 3346 |
+
"grad_norm": 2.088207483291626,
|
| 3347 |
+
"learning_rate": 6.256922134639399e-07,
|
| 3348 |
+
"loss": 1.086,
|
| 3349 |
+
"step": 11925
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 1.7841146610928635,
|
| 3353 |
+
"grad_norm": 1.4074583053588867,
|
| 3354 |
+
"learning_rate": 6.048205822717568e-07,
|
| 3355 |
+
"loss": 1.0726,
|
| 3356 |
+
"step": 11950
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 1.7878471185428486,
|
| 3360 |
+
"grad_norm": 2.0588154792785645,
|
| 3361 |
+
"learning_rate": 5.84292138176682e-07,
|
| 3362 |
+
"loss": 1.114,
|
| 3363 |
+
"step": 11975
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 1.7915795759928337,
|
| 3367 |
+
"grad_norm": 2.760040760040283,
|
| 3368 |
+
"learning_rate": 5.641076310416871e-07,
|
| 3369 |
+
"loss": 1.1694,
|
| 3370 |
+
"step": 12000
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 1.7953120334428188,
|
| 3374 |
+
"grad_norm": 1.4084038734436035,
|
| 3375 |
+
"learning_rate": 5.442677981664102e-07,
|
| 3376 |
+
"loss": 1.1006,
|
| 3377 |
+
"step": 12025
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 1.7990444908928038,
|
| 3381 |
+
"grad_norm": 1.3373968601226807,
|
| 3382 |
+
"learning_rate": 5.247733642602326e-07,
|
| 3383 |
+
"loss": 1.189,
|
| 3384 |
+
"step": 12050
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 1.802776948342789,
|
| 3388 |
+
"grad_norm": 1.83051335811615,
|
| 3389 |
+
"learning_rate": 5.056250414158037e-07,
|
| 3390 |
+
"loss": 1.1739,
|
| 3391 |
+
"step": 12075
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 1.806509405792774,
|
| 3395 |
+
"grad_norm": 1.5041176080703735,
|
| 3396 |
+
"learning_rate": 4.868235290830247e-07,
|
| 3397 |
+
"loss": 1.1253,
|
| 3398 |
+
"step": 12100
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 1.810241863242759,
|
| 3402 |
+
"grad_norm": 1.787211298942566,
|
| 3403 |
+
"learning_rate": 4.6836951404350297e-07,
|
| 3404 |
+
"loss": 1.0491,
|
| 3405 |
+
"step": 12125
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 1.8139743206927441,
|
| 3409 |
+
"grad_norm": 1.642086386680603,
|
| 3410 |
+
"learning_rate": 4.502636703854701e-07,
|
| 3411 |
+
"loss": 1.2168,
|
| 3412 |
+
"step": 12150
|
| 3413 |
+
},
|
| 3414 |
+
{
|
| 3415 |
+
"epoch": 1.8177067781427292,
|
| 3416 |
+
"grad_norm": 1.6135952472686768,
|
| 3417 |
+
"learning_rate": 4.325066594791494e-07,
|
| 3418 |
+
"loss": 1.0452,
|
| 3419 |
+
"step": 12175
|
| 3420 |
+
},
|
| 3421 |
+
{
|
| 3422 |
+
"epoch": 1.8214392355927143,
|
| 3423 |
+
"grad_norm": 2.309962511062622,
|
| 3424 |
+
"learning_rate": 4.1509912995260525e-07,
|
| 3425 |
+
"loss": 1.1534,
|
| 3426 |
+
"step": 12200
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 1.8251716930426993,
|
| 3430 |
+
"grad_norm": 1.8272658586502075,
|
| 3431 |
+
"learning_rate": 3.980417176680429e-07,
|
| 3432 |
+
"loss": 1.1599,
|
| 3433 |
+
"step": 12225
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 1.8289041504926844,
|
| 3437 |
+
"grad_norm": 2.4274184703826904,
|
| 3438 |
+
"learning_rate": 3.813350456985898e-07,
|
| 3439 |
+
"loss": 1.1665,
|
| 3440 |
+
"step": 12250
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 1.8326366079426695,
|
| 3444 |
+
"grad_norm": 1.7932881116867065,
|
| 3445 |
+
"learning_rate": 3.6497972430552974e-07,
|
| 3446 |
+
"loss": 1.1777,
|
| 3447 |
+
"step": 12275
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 1.8363690653926545,
|
| 3451 |
+
"grad_norm": 1.7765918970108032,
|
| 3452 |
+
"learning_rate": 3.4897635091601265e-07,
|
| 3453 |
+
"loss": 1.0802,
|
| 3454 |
+
"step": 12300
|
| 3455 |
+
},
|
| 3456 |
+
{
|
| 3457 |
+
"epoch": 1.8401015228426396,
|
| 3458 |
+
"grad_norm": 2.2067999839782715,
|
| 3459 |
+
"learning_rate": 3.333255101012356e-07,
|
| 3460 |
+
"loss": 1.162,
|
| 3461 |
+
"step": 12325
|
| 3462 |
+
},
|
| 3463 |
+
{
|
| 3464 |
+
"epoch": 1.8438339802926247,
|
| 3465 |
+
"grad_norm": 1.8501057624816895,
|
| 3466 |
+
"learning_rate": 3.1802777355508294e-07,
|
| 3467 |
+
"loss": 1.139,
|
| 3468 |
+
"step": 12350
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 1.8475664377426098,
|
| 3472 |
+
"grad_norm": 2.841785430908203,
|
| 3473 |
+
"learning_rate": 3.030837000732456e-07,
|
| 3474 |
+
"loss": 1.1007,
|
| 3475 |
+
"step": 12375
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 1.8512988951925948,
|
| 3479 |
+
"grad_norm": 2.5297131538391113,
|
| 3480 |
+
"learning_rate": 2.8849383553281596e-07,
|
| 3481 |
+
"loss": 1.1666,
|
| 3482 |
+
"step": 12400
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 1.85503135264258,
|
| 3486 |
+
"grad_norm": 2.378845691680908,
|
| 3487 |
+
"learning_rate": 2.742587128723417e-07,
|
| 3488 |
+
"loss": 1.1507,
|
| 3489 |
+
"step": 12425
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 1.858763810092565,
|
| 3493 |
+
"grad_norm": 2.067227840423584,
|
| 3494 |
+
"learning_rate": 2.603788520723549e-07,
|
| 3495 |
+
"loss": 1.0886,
|
| 3496 |
+
"step": 12450
|
| 3497 |
+
},
|
| 3498 |
+
{
|
| 3499 |
+
"epoch": 1.86249626754255,
|
| 3500 |
+
"grad_norm": 2.217111349105835,
|
| 3501 |
+
"learning_rate": 2.468547601363858e-07,
|
| 3502 |
+
"loss": 1.1039,
|
| 3503 |
+
"step": 12475
|
| 3504 |
+
},
|
| 3505 |
+
{
|
| 3506 |
+
"epoch": 1.8662287249925351,
|
| 3507 |
+
"grad_norm": 1.1246284246444702,
|
| 3508 |
+
"learning_rate": 2.3368693107244433e-07,
|
| 3509 |
+
"loss": 1.1889,
|
| 3510 |
+
"step": 12500
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"epoch": 1.8699611824425202,
|
| 3514 |
+
"grad_norm": 1.749080777168274,
|
| 3515 |
+
"learning_rate": 2.2087584587496269e-07,
|
| 3516 |
+
"loss": 1.1952,
|
| 3517 |
+
"step": 12525
|
| 3518 |
+
},
|
| 3519 |
+
{
|
| 3520 |
+
"epoch": 1.8736936398925053,
|
| 3521 |
+
"grad_norm": 1.6620442867279053,
|
| 3522 |
+
"learning_rate": 2.0842197250724228e-07,
|
| 3523 |
+
"loss": 1.125,
|
| 3524 |
+
"step": 12550
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 1.8774260973424903,
|
| 3528 |
+
"grad_norm": 1.9476419687271118,
|
| 3529 |
+
"learning_rate": 1.9632576588434539e-07,
|
| 3530 |
+
"loss": 1.0906,
|
| 3531 |
+
"step": 12575
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 1.8811585547924754,
|
| 3535 |
+
"grad_norm": 2.474914312362671,
|
| 3536 |
+
"learning_rate": 1.8458766785648617e-07,
|
| 3537 |
+
"loss": 1.1787,
|
| 3538 |
+
"step": 12600
|
| 3539 |
+
},
|
| 3540 |
+
{
|
| 3541 |
+
"epoch": 1.8848910122424605,
|
| 3542 |
+
"grad_norm": 2.5472021102905273,
|
| 3543 |
+
"learning_rate": 1.7320810719288927e-07,
|
| 3544 |
+
"loss": 1.1172,
|
| 3545 |
+
"step": 12625
|
| 3546 |
+
},
|
| 3547 |
+
{
|
| 3548 |
+
"epoch": 1.8886234696924455,
|
| 3549 |
+
"grad_norm": 2.045405864715576,
|
| 3550 |
+
"learning_rate": 1.6218749956612546e-07,
|
| 3551 |
+
"loss": 1.2075,
|
| 3552 |
+
"step": 12650
|
| 3553 |
+
},
|
| 3554 |
+
{
|
| 3555 |
+
"epoch": 1.8923559271424306,
|
| 3556 |
+
"grad_norm": 1.4525920152664185,
|
| 3557 |
+
"learning_rate": 1.5152624753693056e-07,
|
| 3558 |
+
"loss": 1.0744,
|
| 3559 |
+
"step": 12675
|
| 3560 |
+
},
|
| 3561 |
+
{
|
| 3562 |
+
"epoch": 1.8960883845924157,
|
| 3563 |
+
"grad_norm": 1.578680396080017,
|
| 3564 |
+
"learning_rate": 1.4122474053950176e-07,
|
| 3565 |
+
"loss": 1.0693,
|
| 3566 |
+
"step": 12700
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 1.8998208420424008,
|
| 3570 |
+
"grad_norm": 1.826701283454895,
|
| 3571 |
+
"learning_rate": 1.312833548672654e-07,
|
| 3572 |
+
"loss": 1.0635,
|
| 3573 |
+
"step": 12725
|
| 3574 |
+
},
|
| 3575 |
+
{
|
| 3576 |
+
"epoch": 1.9035532994923858,
|
| 3577 |
+
"grad_norm": 2.093668222427368,
|
| 3578 |
+
"learning_rate": 1.2170245365914269e-07,
|
| 3579 |
+
"loss": 1.1203,
|
| 3580 |
+
"step": 12750
|
| 3581 |
+
},
|
| 3582 |
+
{
|
| 3583 |
+
"epoch": 1.907285756942371,
|
| 3584 |
+
"grad_norm": 2.742335557937622,
|
| 3585 |
+
"learning_rate": 1.1248238688627344e-07,
|
| 3586 |
+
"loss": 1.1201,
|
| 3587 |
+
"step": 12775
|
| 3588 |
+
},
|
| 3589 |
+
{
|
| 3590 |
+
"epoch": 1.911018214392356,
|
| 3591 |
+
"grad_norm": 2.9583375453948975,
|
| 3592 |
+
"learning_rate": 1.0362349133924087e-07,
|
| 3593 |
+
"loss": 1.1284,
|
| 3594 |
+
"step": 12800
|
| 3595 |
+
},
|
| 3596 |
+
{
|
| 3597 |
+
"epoch": 1.914750671842341,
|
| 3598 |
+
"grad_norm": 1.8587770462036133,
|
| 3599 |
+
"learning_rate": 9.512609061576805e-08,
|
| 3600 |
+
"loss": 1.1556,
|
| 3601 |
+
"step": 12825
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 1.9184831292923261,
|
| 3605 |
+
"grad_norm": 1.5821772813796997,
|
| 3606 |
+
"learning_rate": 8.69904951088918e-08,
|
| 3607 |
+
"loss": 1.0839,
|
| 3608 |
+
"step": 12850
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 1.9222155867423112,
|
| 3612 |
+
"grad_norm": 1.4884095191955566,
|
| 3613 |
+
"learning_rate": 7.921700199562843e-08,
|
| 3614 |
+
"loss": 1.182,
|
| 3615 |
+
"step": 12875
|
| 3616 |
+
},
|
| 3617 |
+
{
|
| 3618 |
+
"epoch": 1.9259480441922963,
|
| 3619 |
+
"grad_norm": 1.558162808418274,
|
| 3620 |
+
"learning_rate": 7.180589522612358e-08,
|
| 3621 |
+
"loss": 1.0976,
|
| 3622 |
+
"step": 12900
|
| 3623 |
+
},
|
| 3624 |
+
{
|
| 3625 |
+
"epoch": 1.9296805016422813,
|
| 3626 |
+
"grad_norm": 1.8147116899490356,
|
| 3627 |
+
"learning_rate": 6.475744551327268e-08,
|
| 3628 |
+
"loss": 1.1314,
|
| 3629 |
+
"step": 12925
|
| 3630 |
+
},
|
| 3631 |
+
{
|
| 3632 |
+
"epoch": 1.9334129590922664,
|
| 3633 |
+
"grad_norm": 1.5404441356658936,
|
| 3634 |
+
"learning_rate": 5.8071910322831106e-08,
|
| 3635 |
+
"loss": 1.0939,
|
| 3636 |
+
"step": 12950
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"epoch": 1.9371454165422515,
|
| 3640 |
+
"grad_norm": 2.331568717956543,
|
| 3641 |
+
"learning_rate": 5.174953386401949e-08,
|
| 3642 |
+
"loss": 1.171,
|
| 3643 |
+
"step": 12975
|
| 3644 |
+
},
|
| 3645 |
+
{
|
| 3646 |
+
"epoch": 1.9408778739922363,
|
| 3647 |
+
"grad_norm": 2.340298652648926,
|
| 3648 |
+
"learning_rate": 4.579054708059194e-08,
|
| 3649 |
+
"loss": 1.1533,
|
| 3650 |
+
"step": 13000
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 1.9446103314422216,
|
| 3654 |
+
"grad_norm": 1.5086429119110107,
|
| 3655 |
+
"learning_rate": 4.019516764240727e-08,
|
| 3656 |
+
"loss": 1.0505,
|
| 3657 |
+
"step": 13025
|
| 3658 |
+
},
|
| 3659 |
+
{
|
| 3660 |
+
"epoch": 1.9483427888922065,
|
| 3661 |
+
"grad_norm": 2.9765470027923584,
|
| 3662 |
+
"learning_rate": 3.496359993747645e-08,
|
| 3663 |
+
"loss": 1.074,
|
| 3664 |
+
"step": 13050
|
| 3665 |
+
},
|
| 3666 |
+
{
|
| 3667 |
+
"epoch": 1.9520752463421918,
|
| 3668 |
+
"grad_norm": 2.2466864585876465,
|
| 3669 |
+
"learning_rate": 3.009603506449521e-08,
|
| 3670 |
+
"loss": 1.1127,
|
| 3671 |
+
"step": 13075
|
| 3672 |
+
},
|
| 3673 |
+
{
|
| 3674 |
+
"epoch": 1.9558077037921766,
|
| 3675 |
+
"grad_norm": 2.2559330463409424,
|
| 3676 |
+
"learning_rate": 2.559265082586526e-08,
|
| 3677 |
+
"loss": 1.2065,
|
| 3678 |
+
"step": 13100
|
| 3679 |
+
},
|
| 3680 |
+
{
|
| 3681 |
+
"epoch": 1.959540161242162,
|
| 3682 |
+
"grad_norm": 1.564339280128479,
|
| 3683 |
+
"learning_rate": 2.1453611721196088e-08,
|
| 3684 |
+
"loss": 1.0338,
|
| 3685 |
+
"step": 13125
|
| 3686 |
+
},
|
| 3687 |
+
{
|
| 3688 |
+
"epoch": 1.9632726186921468,
|
| 3689 |
+
"grad_norm": 1.9360361099243164,
|
| 3690 |
+
"learning_rate": 1.7679068941302e-08,
|
| 3691 |
+
"loss": 1.131,
|
| 3692 |
+
"step": 13150
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 1.967005076142132,
|
| 3696 |
+
"grad_norm": 2.1053478717803955,
|
| 3697 |
+
"learning_rate": 1.4269160362675449e-08,
|
| 3698 |
+
"loss": 1.105,
|
| 3699 |
+
"step": 13175
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 1.970737533592117,
|
| 3703 |
+
"grad_norm": 1.6952719688415527,
|
| 3704 |
+
"learning_rate": 1.1224010542451037e-08,
|
| 3705 |
+
"loss": 1.0709,
|
| 3706 |
+
"step": 13200
|
| 3707 |
+
},
|
| 3708 |
+
{
|
| 3709 |
+
"epoch": 1.9744699910421022,
|
| 3710 |
+
"grad_norm": 1.3267275094985962,
|
| 3711 |
+
"learning_rate": 8.543730713854725e-09,
|
| 3712 |
+
"loss": 1.0402,
|
| 3713 |
+
"step": 13225
|
| 3714 |
+
},
|
| 3715 |
+
{
|
| 3716 |
+
"epoch": 1.978202448492087,
|
| 3717 |
+
"grad_norm": 1.4626907110214233,
|
| 3718 |
+
"learning_rate": 6.228418782143752e-09,
|
| 3719 |
+
"loss": 1.1153,
|
| 3720 |
+
"step": 13250
|
| 3721 |
+
},
|
| 3722 |
+
{
|
| 3723 |
+
"epoch": 1.9819349059420723,
|
| 3724 |
+
"grad_norm": 2.1010468006134033,
|
| 3725 |
+
"learning_rate": 4.2781593210283744e-09,
|
| 3726 |
+
"loss": 1.1109,
|
| 3727 |
+
"step": 13275
|
| 3728 |
+
},
|
| 3729 |
+
{
|
| 3730 |
+
"epoch": 1.9856673633920572,
|
| 3731 |
+
"grad_norm": 1.494059681892395,
|
| 3732 |
+
"learning_rate": 2.6930235695832307e-09,
|
| 3733 |
+
"loss": 1.0881,
|
| 3734 |
+
"step": 13300
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 1.9893998208420425,
|
| 3738 |
+
"grad_norm": 1.9556529521942139,
|
| 3739 |
+
"learning_rate": 1.4730694296438697e-09,
|
| 3740 |
+
"loss": 1.0646,
|
| 3741 |
+
"step": 13325
|
| 3742 |
+
},
|
| 3743 |
+
{
|
| 3744 |
+
"epoch": 1.9931322782920273,
|
| 3745 |
+
"grad_norm": 1.674444556236267,
|
| 3746 |
+
"learning_rate": 6.183414636928842e-10,
|
| 3747 |
+
"loss": 1.0772,
|
| 3748 |
+
"step": 13350
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 1.9968647357420126,
|
| 3752 |
+
"grad_norm": 1.3396408557891846,
|
| 3753 |
+
"learning_rate": 1.288708932323246e-10,
|
| 3754 |
+
"loss": 1.0856,
|
| 3755 |
+
"step": 13375
|
| 3756 |
+
}
|
| 3757 |
+
],
|
| 3758 |
+
"logging_steps": 25,
|
| 3759 |
+
"max_steps": 13396,
|
| 3760 |
+
"num_input_tokens_seen": 0,
|
| 3761 |
+
"num_train_epochs": 2,
|
| 3762 |
+
"save_steps": 500,
|
| 3763 |
+
"stateful_callbacks": {
|
| 3764 |
+
"TrainerControl": {
|
| 3765 |
+
"args": {
|
| 3766 |
+
"should_epoch_stop": false,
|
| 3767 |
+
"should_evaluate": false,
|
| 3768 |
+
"should_log": false,
|
| 3769 |
+
"should_save": true,
|
| 3770 |
+
"should_training_stop": true
|
| 3771 |
+
},
|
| 3772 |
+
"attributes": {}
|
| 3773 |
+
}
|
| 3774 |
+
},
|
| 3775 |
+
"total_flos": 4.436325915256013e+17,
|
| 3776 |
+
"train_batch_size": 8,
|
| 3777 |
+
"trial_name": null,
|
| 3778 |
+
"trial_params": null
|
| 3779 |
+
}
|
checkpoint-13396/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7faed4b619c396df51af330c0f854c7ab9439405c1297639dbb684514dc8760
|
| 3 |
+
size 5368
|
checkpoint-6698/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-3B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
checkpoint-6698/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 32,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"o_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-6698/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424be5b3e908b0f8ff040441a8b8b86265e97658e4eb1d03e07ec7c5b3a1ee13
|
| 3 |
+
size 194563400
|
checkpoint-6698/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9bd32960d6c26c3a9001710e36cbefa93f32e774506ab12672f89c0e382f416
|
| 3 |
+
size 389352298
|
checkpoint-6698/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e3255f615ee71b6f16ca0b93619079691b0cd119e6785951864aecab59cb9cd
|
| 3 |
+
size 14244
|
checkpoint-6698/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18dabd18d61db528528570ec32df0cdb4e2da9fb307e11ae13ab5fea150d3036
|
| 3 |
+
size 1064
|
checkpoint-6698/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
+
}
|
checkpoint-6698/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-6698/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|end_of_text|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2063 |
+
}
|
checkpoint-6698/trainer_state.json
ADDED
|
@@ -0,0 +1,1903 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 6698,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0037324574499850703,
|
| 14 |
+
"grad_norm": 2.1287152767181396,
|
| 15 |
+
"learning_rate": 1.2468827930174565e-06,
|
| 16 |
+
"loss": 2.5876,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0074649148999701405,
|
| 21 |
+
"grad_norm": 1.5928611755371094,
|
| 22 |
+
"learning_rate": 2.493765586034913e-06,
|
| 23 |
+
"loss": 2.4586,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.011197372349955211,
|
| 28 |
+
"grad_norm": 2.13069748878479,
|
| 29 |
+
"learning_rate": 3.7406483790523696e-06,
|
| 30 |
+
"loss": 2.3632,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.014929829799940281,
|
| 35 |
+
"grad_norm": 4.3777875900268555,
|
| 36 |
+
"learning_rate": 4.987531172069826e-06,
|
| 37 |
+
"loss": 2.0385,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01866228724992535,
|
| 42 |
+
"grad_norm": 1.8015117645263672,
|
| 43 |
+
"learning_rate": 6.234413965087282e-06,
|
| 44 |
+
"loss": 1.7473,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.022394744699910422,
|
| 49 |
+
"grad_norm": 2.9806246757507324,
|
| 50 |
+
"learning_rate": 7.481296758104739e-06,
|
| 51 |
+
"loss": 1.6573,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02612720214989549,
|
| 56 |
+
"grad_norm": 2.6732096672058105,
|
| 57 |
+
"learning_rate": 8.728179551122195e-06,
|
| 58 |
+
"loss": 1.5128,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.029859659599880562,
|
| 63 |
+
"grad_norm": 2.345278024673462,
|
| 64 |
+
"learning_rate": 9.975062344139652e-06,
|
| 65 |
+
"loss": 1.5679,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03359211704986563,
|
| 70 |
+
"grad_norm": 1.6303949356079102,
|
| 71 |
+
"learning_rate": 1.122194513715711e-05,
|
| 72 |
+
"loss": 1.6128,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0373245744998507,
|
| 77 |
+
"grad_norm": 1.976975917816162,
|
| 78 |
+
"learning_rate": 1.2468827930174564e-05,
|
| 79 |
+
"loss": 1.473,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04105703194983577,
|
| 84 |
+
"grad_norm": 1.7693899869918823,
|
| 85 |
+
"learning_rate": 1.3715710723192021e-05,
|
| 86 |
+
"loss": 1.441,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.044789489399820845,
|
| 91 |
+
"grad_norm": 3.1766514778137207,
|
| 92 |
+
"learning_rate": 1.4962593516209478e-05,
|
| 93 |
+
"loss": 1.4022,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04852194684980591,
|
| 98 |
+
"grad_norm": 1.5538763999938965,
|
| 99 |
+
"learning_rate": 1.6209476309226934e-05,
|
| 100 |
+
"loss": 1.3989,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05225440429979098,
|
| 105 |
+
"grad_norm": 1.815725326538086,
|
| 106 |
+
"learning_rate": 1.745635910224439e-05,
|
| 107 |
+
"loss": 1.3802,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05598686174977605,
|
| 112 |
+
"grad_norm": 2.7508153915405273,
|
| 113 |
+
"learning_rate": 1.8703241895261847e-05,
|
| 114 |
+
"loss": 1.4179,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.059719319199761124,
|
| 119 |
+
"grad_norm": 1.0810010433197021,
|
| 120 |
+
"learning_rate": 1.9950124688279304e-05,
|
| 121 |
+
"loss": 1.2646,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06345177664974619,
|
| 126 |
+
"grad_norm": 1.8426517248153687,
|
| 127 |
+
"learning_rate": 1.9999831678944005e-05,
|
| 128 |
+
"loss": 1.3424,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06718423409973126,
|
| 133 |
+
"grad_norm": 2.5106186866760254,
|
| 134 |
+
"learning_rate": 1.9999298376279043e-05,
|
| 135 |
+
"loss": 1.4793,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07091669154971633,
|
| 140 |
+
"grad_norm": 2.054409980773926,
|
| 141 |
+
"learning_rate": 1.999839981926073e-05,
|
| 142 |
+
"loss": 1.3784,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0746491489997014,
|
| 147 |
+
"grad_norm": 1.7603126764297485,
|
| 148 |
+
"learning_rate": 1.9997136040711548e-05,
|
| 149 |
+
"loss": 1.3707,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07838160644968648,
|
| 154 |
+
"grad_norm": 3.026569128036499,
|
| 155 |
+
"learning_rate": 1.99955070867948e-05,
|
| 156 |
+
"loss": 1.3515,
|
| 157 |
+
"step": 525
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08211406389967155,
|
| 161 |
+
"grad_norm": 1.8115179538726807,
|
| 162 |
+
"learning_rate": 1.9993513017012914e-05,
|
| 163 |
+
"loss": 1.2936,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08584652134965662,
|
| 168 |
+
"grad_norm": 1.5803134441375732,
|
| 169 |
+
"learning_rate": 1.999115390420526e-05,
|
| 170 |
+
"loss": 1.3345,
|
| 171 |
+
"step": 575
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08957897879964169,
|
| 175 |
+
"grad_norm": 1.7329767942428589,
|
| 176 |
+
"learning_rate": 1.9988429834545516e-05,
|
| 177 |
+
"loss": 1.2807,
|
| 178 |
+
"step": 600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09331143624962675,
|
| 182 |
+
"grad_norm": 1.9004117250442505,
|
| 183 |
+
"learning_rate": 1.998534090753849e-05,
|
| 184 |
+
"loss": 1.3161,
|
| 185 |
+
"step": 625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.09704389369961182,
|
| 189 |
+
"grad_norm": 2.8287253379821777,
|
| 190 |
+
"learning_rate": 1.99818872360165e-05,
|
| 191 |
+
"loss": 1.3086,
|
| 192 |
+
"step": 650
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.10077635114959689,
|
| 196 |
+
"grad_norm": 1.6014684438705444,
|
| 197 |
+
"learning_rate": 1.9978068946135253e-05,
|
| 198 |
+
"loss": 1.3899,
|
| 199 |
+
"step": 675
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.10450880859958196,
|
| 203 |
+
"grad_norm": 1.3626344203948975,
|
| 204 |
+
"learning_rate": 1.9973886177369238e-05,
|
| 205 |
+
"loss": 1.3327,
|
| 206 |
+
"step": 700
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.10824126604956703,
|
| 210 |
+
"grad_norm": 1.674828052520752,
|
| 211 |
+
"learning_rate": 1.9969339082506622e-05,
|
| 212 |
+
"loss": 1.3386,
|
| 213 |
+
"step": 725
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1119737234995521,
|
| 217 |
+
"grad_norm": 1.8585690259933472,
|
| 218 |
+
"learning_rate": 1.996442782764368e-05,
|
| 219 |
+
"loss": 1.3538,
|
| 220 |
+
"step": 750
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11570618094953718,
|
| 224 |
+
"grad_norm": 2.4924845695495605,
|
| 225 |
+
"learning_rate": 1.9959152592178723e-05,
|
| 226 |
+
"loss": 1.3291,
|
| 227 |
+
"step": 775
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.11943863839952225,
|
| 231 |
+
"grad_norm": 1.6198917627334595,
|
| 232 |
+
"learning_rate": 1.995351356880554e-05,
|
| 233 |
+
"loss": 1.1865,
|
| 234 |
+
"step": 800
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12317109584950732,
|
| 238 |
+
"grad_norm": 1.76533842086792,
|
| 239 |
+
"learning_rate": 1.994751096350637e-05,
|
| 240 |
+
"loss": 1.3401,
|
| 241 |
+
"step": 825
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12690355329949238,
|
| 245 |
+
"grad_norm": 1.99082612991333,
|
| 246 |
+
"learning_rate": 1.994114499554436e-05,
|
| 247 |
+
"loss": 1.2676,
|
| 248 |
+
"step": 850
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13063601074947745,
|
| 252 |
+
"grad_norm": 1.4129736423492432,
|
| 253 |
+
"learning_rate": 1.9934415897455586e-05,
|
| 254 |
+
"loss": 1.3497,
|
| 255 |
+
"step": 875
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13436846819946252,
|
| 259 |
+
"grad_norm": 1.4906266927719116,
|
| 260 |
+
"learning_rate": 1.9927323915040526e-05,
|
| 261 |
+
"loss": 1.2567,
|
| 262 |
+
"step": 900
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1381009256494476,
|
| 266 |
+
"grad_norm": 1.525483250617981,
|
| 267 |
+
"learning_rate": 1.9919869307355104e-05,
|
| 268 |
+
"loss": 1.2826,
|
| 269 |
+
"step": 925
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.14183338309943266,
|
| 273 |
+
"grad_norm": 2.0674450397491455,
|
| 274 |
+
"learning_rate": 1.9912052346701215e-05,
|
| 275 |
+
"loss": 1.2984,
|
| 276 |
+
"step": 950
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.14556584054941774,
|
| 280 |
+
"grad_norm": 1.3082191944122314,
|
| 281 |
+
"learning_rate": 1.9903873318616783e-05,
|
| 282 |
+
"loss": 1.3463,
|
| 283 |
+
"step": 975
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.1492982979994028,
|
| 287 |
+
"grad_norm": 1.1901448965072632,
|
| 288 |
+
"learning_rate": 1.9895332521865334e-05,
|
| 289 |
+
"loss": 1.2979,
|
| 290 |
+
"step": 1000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.15303075544938788,
|
| 294 |
+
"grad_norm": 1.5535725355148315,
|
| 295 |
+
"learning_rate": 1.988643026842507e-05,
|
| 296 |
+
"loss": 1.243,
|
| 297 |
+
"step": 1025
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15676321289937295,
|
| 301 |
+
"grad_norm": 1.5167412757873535,
|
| 302 |
+
"learning_rate": 1.98771668834775e-05,
|
| 303 |
+
"loss": 1.2642,
|
| 304 |
+
"step": 1050
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.16049567034935802,
|
| 308 |
+
"grad_norm": 1.1971468925476074,
|
| 309 |
+
"learning_rate": 1.986754270539552e-05,
|
| 310 |
+
"loss": 1.2216,
|
| 311 |
+
"step": 1075
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.1642281277993431,
|
| 315 |
+
"grad_norm": 2.145617723464966,
|
| 316 |
+
"learning_rate": 1.98575580857311e-05,
|
| 317 |
+
"loss": 1.31,
|
| 318 |
+
"step": 1100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.16796058524932816,
|
| 322 |
+
"grad_norm": 1.7136638164520264,
|
| 323 |
+
"learning_rate": 1.9847213389202407e-05,
|
| 324 |
+
"loss": 1.3125,
|
| 325 |
+
"step": 1125
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.17169304269931324,
|
| 329 |
+
"grad_norm": 1.0633866786956787,
|
| 330 |
+
"learning_rate": 1.9836508993680494e-05,
|
| 331 |
+
"loss": 1.2653,
|
| 332 |
+
"step": 1150
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1754255001492983,
|
| 336 |
+
"grad_norm": 1.4107152223587036,
|
| 337 |
+
"learning_rate": 1.982544529017551e-05,
|
| 338 |
+
"loss": 1.3267,
|
| 339 |
+
"step": 1175
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17915795759928338,
|
| 343 |
+
"grad_norm": 1.7887978553771973,
|
| 344 |
+
"learning_rate": 1.981402268282238e-05,
|
| 345 |
+
"loss": 1.3425,
|
| 346 |
+
"step": 1200
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.18289041504926845,
|
| 350 |
+
"grad_norm": 1.6244795322418213,
|
| 351 |
+
"learning_rate": 1.9802241588866104e-05,
|
| 352 |
+
"loss": 1.2189,
|
| 353 |
+
"step": 1225
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1866228724992535,
|
| 357 |
+
"grad_norm": 2.4690091609954834,
|
| 358 |
+
"learning_rate": 1.979010243864645e-05,
|
| 359 |
+
"loss": 1.2242,
|
| 360 |
+
"step": 1250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19035532994923857,
|
| 364 |
+
"grad_norm": 1.7802854776382446,
|
| 365 |
+
"learning_rate": 1.977760567558228e-05,
|
| 366 |
+
"loss": 1.2209,
|
| 367 |
+
"step": 1275
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.19408778739922364,
|
| 371 |
+
"grad_norm": 0.9973099827766418,
|
| 372 |
+
"learning_rate": 1.976475175615533e-05,
|
| 373 |
+
"loss": 1.2717,
|
| 374 |
+
"step": 1300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.1978202448492087,
|
| 378 |
+
"grad_norm": 1.479239821434021,
|
| 379 |
+
"learning_rate": 1.9751541149893553e-05,
|
| 380 |
+
"loss": 1.3293,
|
| 381 |
+
"step": 1325
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.20155270229919378,
|
| 385 |
+
"grad_norm": 2.492645025253296,
|
| 386 |
+
"learning_rate": 1.9737974339353944e-05,
|
| 387 |
+
"loss": 1.2891,
|
| 388 |
+
"step": 1350
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.20528515974917885,
|
| 392 |
+
"grad_norm": 1.1490769386291504,
|
| 393 |
+
"learning_rate": 1.9724051820104935e-05,
|
| 394 |
+
"loss": 1.3399,
|
| 395 |
+
"step": 1375
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.20901761719916392,
|
| 399 |
+
"grad_norm": 1.0268490314483643,
|
| 400 |
+
"learning_rate": 1.9709774100708285e-05,
|
| 401 |
+
"loss": 1.2535,
|
| 402 |
+
"step": 1400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.212750074649149,
|
| 406 |
+
"grad_norm": 2.1317245960235596,
|
| 407 |
+
"learning_rate": 1.9695141702700508e-05,
|
| 408 |
+
"loss": 1.2751,
|
| 409 |
+
"step": 1425
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.21648253209913407,
|
| 413 |
+
"grad_norm": 2.0975019931793213,
|
| 414 |
+
"learning_rate": 1.9680155160573803e-05,
|
| 415 |
+
"loss": 1.293,
|
| 416 |
+
"step": 1450
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.22021498954911914,
|
| 420 |
+
"grad_norm": 1.1691114902496338,
|
| 421 |
+
"learning_rate": 1.9664815021756563e-05,
|
| 422 |
+
"loss": 1.3222,
|
| 423 |
+
"step": 1475
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2239474469991042,
|
| 427 |
+
"grad_norm": 2.5722885131835938,
|
| 428 |
+
"learning_rate": 1.9649121846593346e-05,
|
| 429 |
+
"loss": 1.2455,
|
| 430 |
+
"step": 1500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.22767990444908928,
|
| 434 |
+
"grad_norm": 1.5031440258026123,
|
| 435 |
+
"learning_rate": 1.9633076208324427e-05,
|
| 436 |
+
"loss": 1.2319,
|
| 437 |
+
"step": 1525
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.23141236189907435,
|
| 441 |
+
"grad_norm": 1.3974519968032837,
|
| 442 |
+
"learning_rate": 1.961667869306486e-05,
|
| 443 |
+
"loss": 1.3008,
|
| 444 |
+
"step": 1550
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.23514481934905943,
|
| 448 |
+
"grad_norm": 1.469709038734436,
|
| 449 |
+
"learning_rate": 1.959992989978304e-05,
|
| 450 |
+
"loss": 1.2394,
|
| 451 |
+
"step": 1575
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2388772767990445,
|
| 455 |
+
"grad_norm": 1.490043044090271,
|
| 456 |
+
"learning_rate": 1.958283044027887e-05,
|
| 457 |
+
"loss": 1.3695,
|
| 458 |
+
"step": 1600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.24260973424902957,
|
| 462 |
+
"grad_norm": 1.4141137599945068,
|
| 463 |
+
"learning_rate": 1.956538093916137e-05,
|
| 464 |
+
"loss": 1.2551,
|
| 465 |
+
"step": 1625
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.24634219169901464,
|
| 469 |
+
"grad_norm": 1.017072081565857,
|
| 470 |
+
"learning_rate": 1.9547582033825888e-05,
|
| 471 |
+
"loss": 1.2362,
|
| 472 |
+
"step": 1650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2500746491489997,
|
| 476 |
+
"grad_norm": 0.8914686441421509,
|
| 477 |
+
"learning_rate": 1.9529434374430805e-05,
|
| 478 |
+
"loss": 1.3,
|
| 479 |
+
"step": 1675
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.25380710659898476,
|
| 483 |
+
"grad_norm": 1.0766717195510864,
|
| 484 |
+
"learning_rate": 1.9510938623873793e-05,
|
| 485 |
+
"loss": 1.3152,
|
| 486 |
+
"step": 1700
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2575395640489698,
|
| 490 |
+
"grad_norm": 1.336647391319275,
|
| 491 |
+
"learning_rate": 1.949209545776759e-05,
|
| 492 |
+
"loss": 1.3164,
|
| 493 |
+
"step": 1725
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2612720214989549,
|
| 497 |
+
"grad_norm": 1.2256617546081543,
|
| 498 |
+
"learning_rate": 1.9472905564415344e-05,
|
| 499 |
+
"loss": 1.2771,
|
| 500 |
+
"step": 1750
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.26500447894893997,
|
| 504 |
+
"grad_norm": 1.1724133491516113,
|
| 505 |
+
"learning_rate": 1.945336964478544e-05,
|
| 506 |
+
"loss": 1.2033,
|
| 507 |
+
"step": 1775
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.26873693639892504,
|
| 511 |
+
"grad_norm": 1.3075248003005981,
|
| 512 |
+
"learning_rate": 1.943348841248592e-05,
|
| 513 |
+
"loss": 1.1953,
|
| 514 |
+
"step": 1800
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2724693938489101,
|
| 518 |
+
"grad_norm": 1.7785544395446777,
|
| 519 |
+
"learning_rate": 1.9413262593738392e-05,
|
| 520 |
+
"loss": 1.2611,
|
| 521 |
+
"step": 1825
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2762018512988952,
|
| 525 |
+
"grad_norm": 1.3955777883529663,
|
| 526 |
+
"learning_rate": 1.9392692927351535e-05,
|
| 527 |
+
"loss": 1.3405,
|
| 528 |
+
"step": 1850
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.27993430874888026,
|
| 532 |
+
"grad_norm": 2.070401430130005,
|
| 533 |
+
"learning_rate": 1.9371780164694086e-05,
|
| 534 |
+
"loss": 1.2554,
|
| 535 |
+
"step": 1875
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.2836667661988653,
|
| 539 |
+
"grad_norm": 2.1829886436462402,
|
| 540 |
+
"learning_rate": 1.93505250696674e-05,
|
| 541 |
+
"loss": 1.3218,
|
| 542 |
+
"step": 1900
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2873992236488504,
|
| 546 |
+
"grad_norm": 1.010029911994934,
|
| 547 |
+
"learning_rate": 1.9328928418677554e-05,
|
| 548 |
+
"loss": 1.2459,
|
| 549 |
+
"step": 1925
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.29113168109883547,
|
| 553 |
+
"grad_norm": 1.444607138633728,
|
| 554 |
+
"learning_rate": 1.930699100060697e-05,
|
| 555 |
+
"loss": 1.2065,
|
| 556 |
+
"step": 1950
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.29486413854882054,
|
| 560 |
+
"grad_norm": 1.3134291172027588,
|
| 561 |
+
"learning_rate": 1.9284713616785625e-05,
|
| 562 |
+
"loss": 1.2659,
|
| 563 |
+
"step": 1975
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.2985965959988056,
|
| 567 |
+
"grad_norm": 1.726757526397705,
|
| 568 |
+
"learning_rate": 1.926209708096175e-05,
|
| 569 |
+
"loss": 1.2167,
|
| 570 |
+
"step": 2000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3023290534487907,
|
| 574 |
+
"grad_norm": 1.0370910167694092,
|
| 575 |
+
"learning_rate": 1.9239142219272126e-05,
|
| 576 |
+
"loss": 1.3228,
|
| 577 |
+
"step": 2025
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.30606151089877576,
|
| 581 |
+
"grad_norm": 1.231990098953247,
|
| 582 |
+
"learning_rate": 1.9215849870211903e-05,
|
| 583 |
+
"loss": 1.2452,
|
| 584 |
+
"step": 2050
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.30979396834876083,
|
| 588 |
+
"grad_norm": 1.2131986618041992,
|
| 589 |
+
"learning_rate": 1.919222088460396e-05,
|
| 590 |
+
"loss": 1.2628,
|
| 591 |
+
"step": 2075
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3135264257987459,
|
| 595 |
+
"grad_norm": 1.881930947303772,
|
| 596 |
+
"learning_rate": 1.916825612556785e-05,
|
| 597 |
+
"loss": 1.2626,
|
| 598 |
+
"step": 2100
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.31725888324873097,
|
| 602 |
+
"grad_norm": 1.3210067749023438,
|
| 603 |
+
"learning_rate": 1.9143956468488243e-05,
|
| 604 |
+
"loss": 1.2584,
|
| 605 |
+
"step": 2125
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.32099134069871604,
|
| 609 |
+
"grad_norm": 1.635605812072754,
|
| 610 |
+
"learning_rate": 1.9119322800982973e-05,
|
| 611 |
+
"loss": 1.2587,
|
| 612 |
+
"step": 2150
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3247237981487011,
|
| 616 |
+
"grad_norm": 1.3837544918060303,
|
| 617 |
+
"learning_rate": 1.90943560228706e-05,
|
| 618 |
+
"loss": 1.2959,
|
| 619 |
+
"step": 2175
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3284562555986862,
|
| 623 |
+
"grad_norm": 1.366673469543457,
|
| 624 |
+
"learning_rate": 1.9069057046137552e-05,
|
| 625 |
+
"loss": 1.2247,
|
| 626 |
+
"step": 2200
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.33218871304867126,
|
| 630 |
+
"grad_norm": 1.0182894468307495,
|
| 631 |
+
"learning_rate": 1.9043426794904804e-05,
|
| 632 |
+
"loss": 1.3071,
|
| 633 |
+
"step": 2225
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.33592117049865633,
|
| 637 |
+
"grad_norm": 1.2455936670303345,
|
| 638 |
+
"learning_rate": 1.901746620539413e-05,
|
| 639 |
+
"loss": 1.2189,
|
| 640 |
+
"step": 2250
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3396536279486414,
|
| 644 |
+
"grad_norm": 1.3316103219985962,
|
| 645 |
+
"learning_rate": 1.8991176225893895e-05,
|
| 646 |
+
"loss": 1.1764,
|
| 647 |
+
"step": 2275
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3433860853986265,
|
| 651 |
+
"grad_norm": 1.165073275566101,
|
| 652 |
+
"learning_rate": 1.8964557816724428e-05,
|
| 653 |
+
"loss": 1.2441,
|
| 654 |
+
"step": 2300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.34711854284861154,
|
| 658 |
+
"grad_norm": 2.3722586631774902,
|
| 659 |
+
"learning_rate": 1.893761195020293e-05,
|
| 660 |
+
"loss": 1.2145,
|
| 661 |
+
"step": 2325
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.3508510002985966,
|
| 665 |
+
"grad_norm": 1.5098875761032104,
|
| 666 |
+
"learning_rate": 1.8910339610607963e-05,
|
| 667 |
+
"loss": 1.2289,
|
| 668 |
+
"step": 2350
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.3545834577485817,
|
| 672 |
+
"grad_norm": 1.7946386337280273,
|
| 673 |
+
"learning_rate": 1.8882741794143502e-05,
|
| 674 |
+
"loss": 1.2414,
|
| 675 |
+
"step": 2375
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.35831591519856676,
|
| 679 |
+
"grad_norm": 1.4160943031311035,
|
| 680 |
+
"learning_rate": 1.8854819508902538e-05,
|
| 681 |
+
"loss": 1.2507,
|
| 682 |
+
"step": 2400
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.36204837264855183,
|
| 686 |
+
"grad_norm": 1.667029857635498,
|
| 687 |
+
"learning_rate": 1.8826573774830256e-05,
|
| 688 |
+
"loss": 1.3307,
|
| 689 |
+
"step": 2425
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3657808300985369,
|
| 693 |
+
"grad_norm": 2.139542579650879,
|
| 694 |
+
"learning_rate": 1.879800562368678e-05,
|
| 695 |
+
"loss": 1.2979,
|
| 696 |
+
"step": 2450
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.369513287548522,
|
| 700 |
+
"grad_norm": 1.7116003036499023,
|
| 701 |
+
"learning_rate": 1.8769116099009485e-05,
|
| 702 |
+
"loss": 1.3246,
|
| 703 |
+
"step": 2475
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.373245744998507,
|
| 707 |
+
"grad_norm": 1.9875051975250244,
|
| 708 |
+
"learning_rate": 1.8739906256074875e-05,
|
| 709 |
+
"loss": 1.3063,
|
| 710 |
+
"step": 2500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.37697820244849206,
|
| 714 |
+
"grad_norm": 1.4133434295654297,
|
| 715 |
+
"learning_rate": 1.8710377161860044e-05,
|
| 716 |
+
"loss": 1.2403,
|
| 717 |
+
"step": 2525
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.38071065989847713,
|
| 721 |
+
"grad_norm": 2.0674993991851807,
|
| 722 |
+
"learning_rate": 1.868052989500369e-05,
|
| 723 |
+
"loss": 1.249,
|
| 724 |
+
"step": 2550
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.3844431173484622,
|
| 728 |
+
"grad_norm": 1.3384236097335815,
|
| 729 |
+
"learning_rate": 1.8650365545766724e-05,
|
| 730 |
+
"loss": 1.2225,
|
| 731 |
+
"step": 2575
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.3881755747984473,
|
| 735 |
+
"grad_norm": 1.7959239482879639,
|
| 736 |
+
"learning_rate": 1.8619885215992446e-05,
|
| 737 |
+
"loss": 1.2747,
|
| 738 |
+
"step": 2600
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.39190803224843235,
|
| 742 |
+
"grad_norm": 1.415369987487793,
|
| 743 |
+
"learning_rate": 1.8589090019066285e-05,
|
| 744 |
+
"loss": 1.1303,
|
| 745 |
+
"step": 2625
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.3956404896984174,
|
| 749 |
+
"grad_norm": 1.4702545404434204,
|
| 750 |
+
"learning_rate": 1.8557981079875138e-05,
|
| 751 |
+
"loss": 1.2383,
|
| 752 |
+
"step": 2650
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.3993729471484025,
|
| 756 |
+
"grad_norm": 1.1834770441055298,
|
| 757 |
+
"learning_rate": 1.852655953476628e-05,
|
| 758 |
+
"loss": 1.1785,
|
| 759 |
+
"step": 2675
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.40310540459838756,
|
| 763 |
+
"grad_norm": 1.6196682453155518,
|
| 764 |
+
"learning_rate": 1.8494826531505862e-05,
|
| 765 |
+
"loss": 1.2132,
|
| 766 |
+
"step": 2700
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.40683786204837263,
|
| 770 |
+
"grad_norm": 1.7983671426773071,
|
| 771 |
+
"learning_rate": 1.8462783229236964e-05,
|
| 772 |
+
"loss": 1.252,
|
| 773 |
+
"step": 2725
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4105703194983577,
|
| 777 |
+
"grad_norm": 1.32036292552948,
|
| 778 |
+
"learning_rate": 1.8430430798437272e-05,
|
| 779 |
+
"loss": 1.2476,
|
| 780 |
+
"step": 2750
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4143027769483428,
|
| 784 |
+
"grad_norm": 1.2666844129562378,
|
| 785 |
+
"learning_rate": 1.839777042087633e-05,
|
| 786 |
+
"loss": 1.2617,
|
| 787 |
+
"step": 2775
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.41803523439832785,
|
| 791 |
+
"grad_norm": 1.4495422840118408,
|
| 792 |
+
"learning_rate": 1.8364803289572347e-05,
|
| 793 |
+
"loss": 1.2137,
|
| 794 |
+
"step": 2800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4217676918483129,
|
| 798 |
+
"grad_norm": 1.2833021879196167,
|
| 799 |
+
"learning_rate": 1.8331530608748635e-05,
|
| 800 |
+
"loss": 1.2164,
|
| 801 |
+
"step": 2825
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.425500149298298,
|
| 805 |
+
"grad_norm": 1.4636069536209106,
|
| 806 |
+
"learning_rate": 1.829795359378962e-05,
|
| 807 |
+
"loss": 1.2561,
|
| 808 |
+
"step": 2850
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.42923260674828306,
|
| 812 |
+
"grad_norm": 2.463801145553589,
|
| 813 |
+
"learning_rate": 1.826407347119645e-05,
|
| 814 |
+
"loss": 1.2825,
|
| 815 |
+
"step": 2875
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.43296506419826813,
|
| 819 |
+
"grad_norm": 2.269793748855591,
|
| 820 |
+
"learning_rate": 1.8229891478542182e-05,
|
| 821 |
+
"loss": 1.25,
|
| 822 |
+
"step": 2900
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.4366975216482532,
|
| 826 |
+
"grad_norm": 1.1336036920547485,
|
| 827 |
+
"learning_rate": 1.8195408864426576e-05,
|
| 828 |
+
"loss": 1.277,
|
| 829 |
+
"step": 2925
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4404299790982383,
|
| 833 |
+
"grad_norm": 1.261833667755127,
|
| 834 |
+
"learning_rate": 1.8160626888430505e-05,
|
| 835 |
+
"loss": 1.2,
|
| 836 |
+
"step": 2950
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.44416243654822335,
|
| 840 |
+
"grad_norm": 1.607729434967041,
|
| 841 |
+
"learning_rate": 1.8125546821069924e-05,
|
| 842 |
+
"loss": 1.248,
|
| 843 |
+
"step": 2975
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4478948939982084,
|
| 847 |
+
"grad_norm": 1.5860254764556885,
|
| 848 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 849 |
+
"loss": 1.2422,
|
| 850 |
+
"step": 3000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4516273514481935,
|
| 854 |
+
"grad_norm": 1.2062890529632568,
|
| 855 |
+
"learning_rate": 1.8054497548715668e-05,
|
| 856 |
+
"loss": 1.1927,
|
| 857 |
+
"step": 3025
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.45535980889817856,
|
| 861 |
+
"grad_norm": 1.3773223161697388,
|
| 862 |
+
"learning_rate": 1.8018530939009682e-05,
|
| 863 |
+
"loss": 1.1484,
|
| 864 |
+
"step": 3050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.45909226634816364,
|
| 868 |
+
"grad_norm": 1.697527289390564,
|
| 869 |
+
"learning_rate": 1.798227142841978e-05,
|
| 870 |
+
"loss": 1.2343,
|
| 871 |
+
"step": 3075
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.4628247237981487,
|
| 875 |
+
"grad_norm": 1.2200244665145874,
|
| 876 |
+
"learning_rate": 1.7945720341433297e-05,
|
| 877 |
+
"loss": 1.268,
|
| 878 |
+
"step": 3100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.4665571812481338,
|
| 882 |
+
"grad_norm": 1.3417649269104004,
|
| 883 |
+
"learning_rate": 1.7908879013188272e-05,
|
| 884 |
+
"loss": 1.2212,
|
| 885 |
+
"step": 3125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.47028963869811885,
|
| 889 |
+
"grad_norm": 1.720186471939087,
|
| 890 |
+
"learning_rate": 1.787174878942468e-05,
|
| 891 |
+
"loss": 1.2134,
|
| 892 |
+
"step": 3150
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4740220961481039,
|
| 896 |
+
"grad_norm": 1.9250013828277588,
|
| 897 |
+
"learning_rate": 1.7834331026435266e-05,
|
| 898 |
+
"loss": 1.2258,
|
| 899 |
+
"step": 3175
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.477754553598089,
|
| 903 |
+
"grad_norm": 1.9136689901351929,
|
| 904 |
+
"learning_rate": 1.7796627091016013e-05,
|
| 905 |
+
"loss": 1.1845,
|
| 906 |
+
"step": 3200
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.48148701104807407,
|
| 910 |
+
"grad_norm": 1.3587361574172974,
|
| 911 |
+
"learning_rate": 1.7758638360416202e-05,
|
| 912 |
+
"loss": 1.1483,
|
| 913 |
+
"step": 3225
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.48521946849805914,
|
| 917 |
+
"grad_norm": 1.691744089126587,
|
| 918 |
+
"learning_rate": 1.7720366222288124e-05,
|
| 919 |
+
"loss": 1.2432,
|
| 920 |
+
"step": 3250
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.4889519259480442,
|
| 924 |
+
"grad_norm": 1.2485105991363525,
|
| 925 |
+
"learning_rate": 1.768181207463637e-05,
|
| 926 |
+
"loss": 1.2696,
|
| 927 |
+
"step": 3275
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.4926843833980293,
|
| 931 |
+
"grad_norm": 1.2822153568267822,
|
| 932 |
+
"learning_rate": 1.764297732576678e-05,
|
| 933 |
+
"loss": 1.2322,
|
| 934 |
+
"step": 3300
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.49641684084801435,
|
| 938 |
+
"grad_norm": 1.0677824020385742,
|
| 939 |
+
"learning_rate": 1.760386339423498e-05,
|
| 940 |
+
"loss": 1.2366,
|
| 941 |
+
"step": 3325
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5001492982979994,
|
| 945 |
+
"grad_norm": 1.0575954914093018,
|
| 946 |
+
"learning_rate": 1.7564471708794607e-05,
|
| 947 |
+
"loss": 1.2628,
|
| 948 |
+
"step": 3350
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5038817557479844,
|
| 952 |
+
"grad_norm": 1.2826817035675049,
|
| 953 |
+
"learning_rate": 1.7524803708345065e-05,
|
| 954 |
+
"loss": 1.2282,
|
| 955 |
+
"step": 3375
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5076142131979695,
|
| 959 |
+
"grad_norm": 1.4431601762771606,
|
| 960 |
+
"learning_rate": 1.7484860841879016e-05,
|
| 961 |
+
"loss": 1.2144,
|
| 962 |
+
"step": 3400
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5113466706479546,
|
| 966 |
+
"grad_norm": 1.3346613645553589,
|
| 967 |
+
"learning_rate": 1.74446445684294e-05,
|
| 968 |
+
"loss": 1.2159,
|
| 969 |
+
"step": 3425
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5150791280979397,
|
| 973 |
+
"grad_norm": 1.4220223426818848,
|
| 974 |
+
"learning_rate": 1.7404156357016196e-05,
|
| 975 |
+
"loss": 1.2159,
|
| 976 |
+
"step": 3450
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5188115855479247,
|
| 980 |
+
"grad_norm": 1.5507416725158691,
|
| 981 |
+
"learning_rate": 1.7363397686592712e-05,
|
| 982 |
+
"loss": 1.1986,
|
| 983 |
+
"step": 3475
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5225440429979098,
|
| 987 |
+
"grad_norm": 1.8560044765472412,
|
| 988 |
+
"learning_rate": 1.7322370045991592e-05,
|
| 989 |
+
"loss": 1.1887,
|
| 990 |
+
"step": 3500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5262765004478949,
|
| 994 |
+
"grad_norm": 0.9891431331634521,
|
| 995 |
+
"learning_rate": 1.7281074933870418e-05,
|
| 996 |
+
"loss": 1.2561,
|
| 997 |
+
"step": 3525
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5300089578978799,
|
| 1001 |
+
"grad_norm": 1.8725615739822388,
|
| 1002 |
+
"learning_rate": 1.723951385865697e-05,
|
| 1003 |
+
"loss": 1.2103,
|
| 1004 |
+
"step": 3550
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.533741415347865,
|
| 1008 |
+
"grad_norm": 1.6701029539108276,
|
| 1009 |
+
"learning_rate": 1.719768833849413e-05,
|
| 1010 |
+
"loss": 1.2575,
|
| 1011 |
+
"step": 3575
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5374738727978501,
|
| 1015 |
+
"grad_norm": 1.1404553651809692,
|
| 1016 |
+
"learning_rate": 1.7155599901184427e-05,
|
| 1017 |
+
"loss": 1.2533,
|
| 1018 |
+
"step": 3600
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5412063302478352,
|
| 1022 |
+
"grad_norm": 1.3595733642578125,
|
| 1023 |
+
"learning_rate": 1.7113250084134225e-05,
|
| 1024 |
+
"loss": 1.2169,
|
| 1025 |
+
"step": 3625
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5449387876978202,
|
| 1029 |
+
"grad_norm": 1.5469706058502197,
|
| 1030 |
+
"learning_rate": 1.707064043429756e-05,
|
| 1031 |
+
"loss": 1.234,
|
| 1032 |
+
"step": 3650
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5486712451478053,
|
| 1036 |
+
"grad_norm": 1.28376305103302,
|
| 1037 |
+
"learning_rate": 1.702777250811966e-05,
|
| 1038 |
+
"loss": 1.2091,
|
| 1039 |
+
"step": 3675
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5524037025977904,
|
| 1043 |
+
"grad_norm": 1.1762385368347168,
|
| 1044 |
+
"learning_rate": 1.6984647871480038e-05,
|
| 1045 |
+
"loss": 1.2603,
|
| 1046 |
+
"step": 3700
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5561361600477754,
|
| 1050 |
+
"grad_norm": 1.7015496492385864,
|
| 1051 |
+
"learning_rate": 1.6941268099635356e-05,
|
| 1052 |
+
"loss": 1.2189,
|
| 1053 |
+
"step": 3725
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5598686174977605,
|
| 1057 |
+
"grad_norm": 1.4737459421157837,
|
| 1058 |
+
"learning_rate": 1.689763477716184e-05,
|
| 1059 |
+
"loss": 1.2567,
|
| 1060 |
+
"step": 3750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5636010749477456,
|
| 1064 |
+
"grad_norm": 1.0501235723495483,
|
| 1065 |
+
"learning_rate": 1.6853749497897417e-05,
|
| 1066 |
+
"loss": 1.2647,
|
| 1067 |
+
"step": 3775
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5673335323977307,
|
| 1071 |
+
"grad_norm": 1.793992519378662,
|
| 1072 |
+
"learning_rate": 1.6809613864883484e-05,
|
| 1073 |
+
"loss": 1.1963,
|
| 1074 |
+
"step": 3800
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5710659898477157,
|
| 1078 |
+
"grad_norm": 1.3824703693389893,
|
| 1079 |
+
"learning_rate": 1.6765229490306376e-05,
|
| 1080 |
+
"loss": 1.1961,
|
| 1081 |
+
"step": 3825
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5747984472977008,
|
| 1085 |
+
"grad_norm": 1.2093158960342407,
|
| 1086 |
+
"learning_rate": 1.672059799543844e-05,
|
| 1087 |
+
"loss": 1.3218,
|
| 1088 |
+
"step": 3850
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5785309047476859,
|
| 1092 |
+
"grad_norm": 1.4345468282699585,
|
| 1093 |
+
"learning_rate": 1.667572101057885e-05,
|
| 1094 |
+
"loss": 1.2929,
|
| 1095 |
+
"step": 3875
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.5822633621976709,
|
| 1099 |
+
"grad_norm": 1.790346384048462,
|
| 1100 |
+
"learning_rate": 1.663060017499402e-05,
|
| 1101 |
+
"loss": 1.2416,
|
| 1102 |
+
"step": 3900
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.585995819647656,
|
| 1106 |
+
"grad_norm": 1.126421570777893,
|
| 1107 |
+
"learning_rate": 1.6585237136857762e-05,
|
| 1108 |
+
"loss": 1.1753,
|
| 1109 |
+
"step": 3925
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.5897282770976411,
|
| 1113 |
+
"grad_norm": 2.123781204223633,
|
| 1114 |
+
"learning_rate": 1.653963355319104e-05,
|
| 1115 |
+
"loss": 1.2442,
|
| 1116 |
+
"step": 3950
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.5934607345476262,
|
| 1120 |
+
"grad_norm": 1.4365142583847046,
|
| 1121 |
+
"learning_rate": 1.6493791089801488e-05,
|
| 1122 |
+
"loss": 1.1901,
|
| 1123 |
+
"step": 3975
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.5971931919976112,
|
| 1127 |
+
"grad_norm": 0.9638050198554993,
|
| 1128 |
+
"learning_rate": 1.6447711421222524e-05,
|
| 1129 |
+
"loss": 1.2474,
|
| 1130 |
+
"step": 4000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6009256494475963,
|
| 1134 |
+
"grad_norm": 1.3598357439041138,
|
| 1135 |
+
"learning_rate": 1.64013962306522e-05,
|
| 1136 |
+
"loss": 1.2294,
|
| 1137 |
+
"step": 4025
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6046581068975814,
|
| 1141 |
+
"grad_norm": 1.4392117261886597,
|
| 1142 |
+
"learning_rate": 1.6354847209891715e-05,
|
| 1143 |
+
"loss": 1.185,
|
| 1144 |
+
"step": 4050
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6083905643475664,
|
| 1148 |
+
"grad_norm": 1.8003793954849243,
|
| 1149 |
+
"learning_rate": 1.6308066059283617e-05,
|
| 1150 |
+
"loss": 1.2059,
|
| 1151 |
+
"step": 4075
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6121230217975515,
|
| 1155 |
+
"grad_norm": 1.2645149230957031,
|
| 1156 |
+
"learning_rate": 1.626105448764969e-05,
|
| 1157 |
+
"loss": 1.2035,
|
| 1158 |
+
"step": 4100
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6158554792475366,
|
| 1162 |
+
"grad_norm": 2.2808313369750977,
|
| 1163 |
+
"learning_rate": 1.6213814212228542e-05,
|
| 1164 |
+
"loss": 1.2203,
|
| 1165 |
+
"step": 4125
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6195879366975217,
|
| 1169 |
+
"grad_norm": 1.444287896156311,
|
| 1170 |
+
"learning_rate": 1.6166346958612872e-05,
|
| 1171 |
+
"loss": 1.2243,
|
| 1172 |
+
"step": 4150
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6233203941475067,
|
| 1176 |
+
"grad_norm": 1.2230594158172607,
|
| 1177 |
+
"learning_rate": 1.611865446068643e-05,
|
| 1178 |
+
"loss": 1.2306,
|
| 1179 |
+
"step": 4175
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6270528515974918,
|
| 1183 |
+
"grad_norm": 1.4247676134109497,
|
| 1184 |
+
"learning_rate": 1.6070738460560703e-05,
|
| 1185 |
+
"loss": 1.2,
|
| 1186 |
+
"step": 4200
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6307853090474769,
|
| 1190 |
+
"grad_norm": 1.3539576530456543,
|
| 1191 |
+
"learning_rate": 1.602260070851125e-05,
|
| 1192 |
+
"loss": 1.222,
|
| 1193 |
+
"step": 4225
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6345177664974619,
|
| 1197 |
+
"grad_norm": 1.4188202619552612,
|
| 1198 |
+
"learning_rate": 1.59742429629138e-05,
|
| 1199 |
+
"loss": 1.2525,
|
| 1200 |
+
"step": 4250
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.638250223947447,
|
| 1204 |
+
"grad_norm": 4.922667026519775,
|
| 1205 |
+
"learning_rate": 1.5925666990179997e-05,
|
| 1206 |
+
"loss": 1.2556,
|
| 1207 |
+
"step": 4275
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6419826813974321,
|
| 1211 |
+
"grad_norm": 1.7935903072357178,
|
| 1212 |
+
"learning_rate": 1.587687456469288e-05,
|
| 1213 |
+
"loss": 1.2192,
|
| 1214 |
+
"step": 4300
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6457151388474172,
|
| 1218 |
+
"grad_norm": 1.1644890308380127,
|
| 1219 |
+
"learning_rate": 1.5827867468742088e-05,
|
| 1220 |
+
"loss": 1.2647,
|
| 1221 |
+
"step": 4325
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6494475962974022,
|
| 1225 |
+
"grad_norm": 1.1731319427490234,
|
| 1226 |
+
"learning_rate": 1.5778647492458735e-05,
|
| 1227 |
+
"loss": 1.1913,
|
| 1228 |
+
"step": 4350
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6531800537473873,
|
| 1232 |
+
"grad_norm": 1.4858598709106445,
|
| 1233 |
+
"learning_rate": 1.5729216433750023e-05,
|
| 1234 |
+
"loss": 1.2086,
|
| 1235 |
+
"step": 4375
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6569125111973724,
|
| 1239 |
+
"grad_norm": 1.705950140953064,
|
| 1240 |
+
"learning_rate": 1.567957609823358e-05,
|
| 1241 |
+
"loss": 1.1848,
|
| 1242 |
+
"step": 4400
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6606449686473574,
|
| 1246 |
+
"grad_norm": 1.615257740020752,
|
| 1247 |
+
"learning_rate": 1.5629728299171495e-05,
|
| 1248 |
+
"loss": 1.2117,
|
| 1249 |
+
"step": 4425
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6643774260973425,
|
| 1253 |
+
"grad_norm": 2.1554055213928223,
|
| 1254 |
+
"learning_rate": 1.5579674857404078e-05,
|
| 1255 |
+
"loss": 1.1318,
|
| 1256 |
+
"step": 4450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6681098835473276,
|
| 1260 |
+
"grad_norm": 1.1841500997543335,
|
| 1261 |
+
"learning_rate": 1.552941760128337e-05,
|
| 1262 |
+
"loss": 1.2348,
|
| 1263 |
+
"step": 4475
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6718423409973127,
|
| 1267 |
+
"grad_norm": 1.6528973579406738,
|
| 1268 |
+
"learning_rate": 1.5478958366606323e-05,
|
| 1269 |
+
"loss": 1.1943,
|
| 1270 |
+
"step": 4500
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6755747984472977,
|
| 1274 |
+
"grad_norm": 1.7715898752212524,
|
| 1275 |
+
"learning_rate": 1.5428298996547778e-05,
|
| 1276 |
+
"loss": 1.1289,
|
| 1277 |
+
"step": 4525
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.6793072558972828,
|
| 1281 |
+
"grad_norm": 1.4920035600662231,
|
| 1282 |
+
"learning_rate": 1.5377441341593116e-05,
|
| 1283 |
+
"loss": 1.1901,
|
| 1284 |
+
"step": 4550
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.6830397133472679,
|
| 1288 |
+
"grad_norm": 1.339840054512024,
|
| 1289 |
+
"learning_rate": 1.532638725947066e-05,
|
| 1290 |
+
"loss": 1.2306,
|
| 1291 |
+
"step": 4575
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.686772170797253,
|
| 1295 |
+
"grad_norm": 1.212212085723877,
|
| 1296 |
+
"learning_rate": 1.5275138615083843e-05,
|
| 1297 |
+
"loss": 1.1593,
|
| 1298 |
+
"step": 4600
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.690504628247238,
|
| 1302 |
+
"grad_norm": 1.667057991027832,
|
| 1303 |
+
"learning_rate": 1.5223697280443044e-05,
|
| 1304 |
+
"loss": 1.165,
|
| 1305 |
+
"step": 4625
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6942370856972231,
|
| 1309 |
+
"grad_norm": 1.502441644668579,
|
| 1310 |
+
"learning_rate": 1.517206513459725e-05,
|
| 1311 |
+
"loss": 1.1481,
|
| 1312 |
+
"step": 4650
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.6979695431472082,
|
| 1316 |
+
"grad_norm": 1.2989062070846558,
|
| 1317 |
+
"learning_rate": 1.5120244063565393e-05,
|
| 1318 |
+
"loss": 1.133,
|
| 1319 |
+
"step": 4675
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7017020005971932,
|
| 1323 |
+
"grad_norm": 1.3973162174224854,
|
| 1324 |
+
"learning_rate": 1.506823596026746e-05,
|
| 1325 |
+
"loss": 1.2839,
|
| 1326 |
+
"step": 4700
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7054344580471783,
|
| 1330 |
+
"grad_norm": 1.2941102981567383,
|
| 1331 |
+
"learning_rate": 1.501604272445536e-05,
|
| 1332 |
+
"loss": 1.2032,
|
| 1333 |
+
"step": 4725
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7091669154971634,
|
| 1337 |
+
"grad_norm": 1.8230595588684082,
|
| 1338 |
+
"learning_rate": 1.4963666262643517e-05,
|
| 1339 |
+
"loss": 1.2128,
|
| 1340 |
+
"step": 4750
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7128993729471484,
|
| 1344 |
+
"grad_norm": 1.251273274421692,
|
| 1345 |
+
"learning_rate": 1.4911108488039233e-05,
|
| 1346 |
+
"loss": 1.2268,
|
| 1347 |
+
"step": 4775
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7166318303971335,
|
| 1351 |
+
"grad_norm": 1.185001254081726,
|
| 1352 |
+
"learning_rate": 1.4858371320472807e-05,
|
| 1353 |
+
"loss": 1.1763,
|
| 1354 |
+
"step": 4800
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7203642878471186,
|
| 1358 |
+
"grad_norm": 1.127736210823059,
|
| 1359 |
+
"learning_rate": 1.4805456686327404e-05,
|
| 1360 |
+
"loss": 1.2929,
|
| 1361 |
+
"step": 4825
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7240967452971037,
|
| 1365 |
+
"grad_norm": 1.849836826324463,
|
| 1366 |
+
"learning_rate": 1.4752366518468684e-05,
|
| 1367 |
+
"loss": 1.2721,
|
| 1368 |
+
"step": 4850
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7278292027470887,
|
| 1372 |
+
"grad_norm": 1.5276362895965576,
|
| 1373 |
+
"learning_rate": 1.4699102756174207e-05,
|
| 1374 |
+
"loss": 1.2126,
|
| 1375 |
+
"step": 4875
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7315616601970738,
|
| 1379 |
+
"grad_norm": 1.338534951210022,
|
| 1380 |
+
"learning_rate": 1.4645667345062584e-05,
|
| 1381 |
+
"loss": 1.2524,
|
| 1382 |
+
"step": 4900
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7352941176470589,
|
| 1386 |
+
"grad_norm": 2.3885657787323,
|
| 1387 |
+
"learning_rate": 1.4592062237022419e-05,
|
| 1388 |
+
"loss": 1.2397,
|
| 1389 |
+
"step": 4925
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.739026575097044,
|
| 1393 |
+
"grad_norm": 1.712269902229309,
|
| 1394 |
+
"learning_rate": 1.4538289390141005e-05,
|
| 1395 |
+
"loss": 1.1817,
|
| 1396 |
+
"step": 4950
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.742759032547029,
|
| 1400 |
+
"grad_norm": 1.3213021755218506,
|
| 1401 |
+
"learning_rate": 1.4484350768632795e-05,
|
| 1402 |
+
"loss": 1.1884,
|
| 1403 |
+
"step": 4975
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.746491489997014,
|
| 1407 |
+
"grad_norm": 1.7047327756881714,
|
| 1408 |
+
"learning_rate": 1.4430248342767661e-05,
|
| 1409 |
+
"loss": 1.158,
|
| 1410 |
+
"step": 5000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.750223947446999,
|
| 1414 |
+
"grad_norm": 1.3052529096603394,
|
| 1415 |
+
"learning_rate": 1.437598408879892e-05,
|
| 1416 |
+
"loss": 1.1679,
|
| 1417 |
+
"step": 5025
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7539564048969841,
|
| 1421 |
+
"grad_norm": 1.8056520223617554,
|
| 1422 |
+
"learning_rate": 1.4321559988891143e-05,
|
| 1423 |
+
"loss": 1.2433,
|
| 1424 |
+
"step": 5050
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7576888623469692,
|
| 1428 |
+
"grad_norm": 1.0514063835144043,
|
| 1429 |
+
"learning_rate": 1.4266978031047756e-05,
|
| 1430 |
+
"loss": 1.1839,
|
| 1431 |
+
"step": 5075
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7614213197969543,
|
| 1435 |
+
"grad_norm": 1.5641283988952637,
|
| 1436 |
+
"learning_rate": 1.421224020903842e-05,
|
| 1437 |
+
"loss": 1.1845,
|
| 1438 |
+
"step": 5100
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7651537772469393,
|
| 1442 |
+
"grad_norm": 0.9585388898849487,
|
| 1443 |
+
"learning_rate": 1.4157348522326193e-05,
|
| 1444 |
+
"loss": 1.1198,
|
| 1445 |
+
"step": 5125
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7688862346969244,
|
| 1449 |
+
"grad_norm": 1.113794207572937,
|
| 1450 |
+
"learning_rate": 1.4102304975994518e-05,
|
| 1451 |
+
"loss": 1.2197,
|
| 1452 |
+
"step": 5150
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7726186921469095,
|
| 1456 |
+
"grad_norm": 1.5784218311309814,
|
| 1457 |
+
"learning_rate": 1.4047111580673955e-05,
|
| 1458 |
+
"loss": 1.1592,
|
| 1459 |
+
"step": 5175
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.7763511495968946,
|
| 1463 |
+
"grad_norm": 1.339924693107605,
|
| 1464 |
+
"learning_rate": 1.3991770352468753e-05,
|
| 1465 |
+
"loss": 1.2009,
|
| 1466 |
+
"step": 5200
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.7800836070468796,
|
| 1470 |
+
"grad_norm": 1.5128077268600464,
|
| 1471 |
+
"learning_rate": 1.3936283312883192e-05,
|
| 1472 |
+
"loss": 1.2504,
|
| 1473 |
+
"step": 5225
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7838160644968647,
|
| 1477 |
+
"grad_norm": 1.5745166540145874,
|
| 1478 |
+
"learning_rate": 1.3880652488747756e-05,
|
| 1479 |
+
"loss": 1.1723,
|
| 1480 |
+
"step": 5250
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.7875485219468498,
|
| 1484 |
+
"grad_norm": 2.238532066345215,
|
| 1485 |
+
"learning_rate": 1.38248799121451e-05,
|
| 1486 |
+
"loss": 1.1674,
|
| 1487 |
+
"step": 5275
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.7912809793968348,
|
| 1491 |
+
"grad_norm": 1.1808812618255615,
|
| 1492 |
+
"learning_rate": 1.3768967620335791e-05,
|
| 1493 |
+
"loss": 1.218,
|
| 1494 |
+
"step": 5300
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.7950134368468199,
|
| 1498 |
+
"grad_norm": 2.038313865661621,
|
| 1499 |
+
"learning_rate": 1.371291765568393e-05,
|
| 1500 |
+
"loss": 1.2065,
|
| 1501 |
+
"step": 5325
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.798745894296805,
|
| 1505 |
+
"grad_norm": 1.5826561450958252,
|
| 1506 |
+
"learning_rate": 1.3656732065582529e-05,
|
| 1507 |
+
"loss": 1.1006,
|
| 1508 |
+
"step": 5350
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.80247835174679,
|
| 1512 |
+
"grad_norm": 1.3146427869796753,
|
| 1513 |
+
"learning_rate": 1.360041290237872e-05,
|
| 1514 |
+
"loss": 1.1637,
|
| 1515 |
+
"step": 5375
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8062108091967751,
|
| 1519 |
+
"grad_norm": 1.2641507387161255,
|
| 1520 |
+
"learning_rate": 1.3543962223298799e-05,
|
| 1521 |
+
"loss": 1.1175,
|
| 1522 |
+
"step": 5400
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8099432666467602,
|
| 1526 |
+
"grad_norm": 1.886314034461975,
|
| 1527 |
+
"learning_rate": 1.348738209037307e-05,
|
| 1528 |
+
"loss": 1.2644,
|
| 1529 |
+
"step": 5425
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8136757240967453,
|
| 1533 |
+
"grad_norm": 2.5574333667755127,
|
| 1534 |
+
"learning_rate": 1.3430674570360528e-05,
|
| 1535 |
+
"loss": 1.2805,
|
| 1536 |
+
"step": 5450
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8174081815467303,
|
| 1540 |
+
"grad_norm": 1.5606664419174194,
|
| 1541 |
+
"learning_rate": 1.3373841734673366e-05,
|
| 1542 |
+
"loss": 1.1581,
|
| 1543 |
+
"step": 5475
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8211406389967154,
|
| 1547 |
+
"grad_norm": 1.60868501663208,
|
| 1548 |
+
"learning_rate": 1.3316885659301298e-05,
|
| 1549 |
+
"loss": 1.1639,
|
| 1550 |
+
"step": 5500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8248730964467005,
|
| 1554 |
+
"grad_norm": 1.3898091316223145,
|
| 1555 |
+
"learning_rate": 1.3259808424735754e-05,
|
| 1556 |
+
"loss": 1.1757,
|
| 1557 |
+
"step": 5525
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8286055538966856,
|
| 1561 |
+
"grad_norm": 1.1681030988693237,
|
| 1562 |
+
"learning_rate": 1.320261211589385e-05,
|
| 1563 |
+
"loss": 1.2276,
|
| 1564 |
+
"step": 5550
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8323380113466706,
|
| 1568 |
+
"grad_norm": 1.813833236694336,
|
| 1569 |
+
"learning_rate": 1.3145298822042255e-05,
|
| 1570 |
+
"loss": 1.1826,
|
| 1571 |
+
"step": 5575
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8360704687966557,
|
| 1575 |
+
"grad_norm": 2.5199103355407715,
|
| 1576 |
+
"learning_rate": 1.308787063672087e-05,
|
| 1577 |
+
"loss": 1.2587,
|
| 1578 |
+
"step": 5600
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8398029262466408,
|
| 1582 |
+
"grad_norm": 2.014720916748047,
|
| 1583 |
+
"learning_rate": 1.3030329657666339e-05,
|
| 1584 |
+
"loss": 1.1934,
|
| 1585 |
+
"step": 5625
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8435353836966258,
|
| 1589 |
+
"grad_norm": 1.3772430419921875,
|
| 1590 |
+
"learning_rate": 1.2972677986735449e-05,
|
| 1591 |
+
"loss": 1.2342,
|
| 1592 |
+
"step": 5650
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8472678411466109,
|
| 1596 |
+
"grad_norm": 1.337478756904602,
|
| 1597 |
+
"learning_rate": 1.2914917729828331e-05,
|
| 1598 |
+
"loss": 1.1866,
|
| 1599 |
+
"step": 5675
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.851000298596596,
|
| 1603 |
+
"grad_norm": 1.9738775491714478,
|
| 1604 |
+
"learning_rate": 1.2857050996811548e-05,
|
| 1605 |
+
"loss": 1.1844,
|
| 1606 |
+
"step": 5700
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.854732756046581,
|
| 1610 |
+
"grad_norm": 1.9654030799865723,
|
| 1611 |
+
"learning_rate": 1.2799079901441021e-05,
|
| 1612 |
+
"loss": 1.1876,
|
| 1613 |
+
"step": 5725
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8584652134965661,
|
| 1617 |
+
"grad_norm": 1.7116689682006836,
|
| 1618 |
+
"learning_rate": 1.2741006561284812e-05,
|
| 1619 |
+
"loss": 1.2034,
|
| 1620 |
+
"step": 5750
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8621976709465512,
|
| 1624 |
+
"grad_norm": 1.231316089630127,
|
| 1625 |
+
"learning_rate": 1.26828330976458e-05,
|
| 1626 |
+
"loss": 1.1424,
|
| 1627 |
+
"step": 5775
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8659301283965363,
|
| 1631 |
+
"grad_norm": 1.4150484800338745,
|
| 1632 |
+
"learning_rate": 1.2624561635484152e-05,
|
| 1633 |
+
"loss": 1.1775,
|
| 1634 |
+
"step": 5800
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8696625858465213,
|
| 1638 |
+
"grad_norm": 1.6012908220291138,
|
| 1639 |
+
"learning_rate": 1.2566194303339738e-05,
|
| 1640 |
+
"loss": 1.1916,
|
| 1641 |
+
"step": 5825
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.8733950432965064,
|
| 1645 |
+
"grad_norm": 1.2136471271514893,
|
| 1646 |
+
"learning_rate": 1.2507733233254362e-05,
|
| 1647 |
+
"loss": 1.1952,
|
| 1648 |
+
"step": 5850
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.8771275007464915,
|
| 1652 |
+
"grad_norm": 1.2161729335784912,
|
| 1653 |
+
"learning_rate": 1.2449180560693888e-05,
|
| 1654 |
+
"loss": 1.1532,
|
| 1655 |
+
"step": 5875
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.8808599581964766,
|
| 1659 |
+
"grad_norm": 0.9797784090042114,
|
| 1660 |
+
"learning_rate": 1.239053842447024e-05,
|
| 1661 |
+
"loss": 1.2634,
|
| 1662 |
+
"step": 5900
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.8845924156464616,
|
| 1666 |
+
"grad_norm": 1.0139834880828857,
|
| 1667 |
+
"learning_rate": 1.233180896666326e-05,
|
| 1668 |
+
"loss": 1.2226,
|
| 1669 |
+
"step": 5925
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.8883248730964467,
|
| 1673 |
+
"grad_norm": 1.7537201642990112,
|
| 1674 |
+
"learning_rate": 1.227299433254248e-05,
|
| 1675 |
+
"loss": 1.3035,
|
| 1676 |
+
"step": 5950
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.8920573305464318,
|
| 1680 |
+
"grad_norm": 1.4647903442382812,
|
| 1681 |
+
"learning_rate": 1.2214096670488753e-05,
|
| 1682 |
+
"loss": 1.2201,
|
| 1683 |
+
"step": 5975
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.8957897879964168,
|
| 1687 |
+
"grad_norm": 1.5560133457183838,
|
| 1688 |
+
"learning_rate": 1.215511813191577e-05,
|
| 1689 |
+
"loss": 1.1134,
|
| 1690 |
+
"step": 6000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.8995222454464019,
|
| 1694 |
+
"grad_norm": 1.3168470859527588,
|
| 1695 |
+
"learning_rate": 1.2096060871191492e-05,
|
| 1696 |
+
"loss": 1.1175,
|
| 1697 |
+
"step": 6025
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.903254702896387,
|
| 1701 |
+
"grad_norm": 1.569739818572998,
|
| 1702 |
+
"learning_rate": 1.2036927045559426e-05,
|
| 1703 |
+
"loss": 1.1893,
|
| 1704 |
+
"step": 6050
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9069871603463721,
|
| 1708 |
+
"grad_norm": 1.5962868928909302,
|
| 1709 |
+
"learning_rate": 1.197771881505985e-05,
|
| 1710 |
+
"loss": 1.1658,
|
| 1711 |
+
"step": 6075
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9107196177963571,
|
| 1715 |
+
"grad_norm": 1.5586867332458496,
|
| 1716 |
+
"learning_rate": 1.191843834245091e-05,
|
| 1717 |
+
"loss": 1.2502,
|
| 1718 |
+
"step": 6100
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9144520752463422,
|
| 1722 |
+
"grad_norm": 1.9700677394866943,
|
| 1723 |
+
"learning_rate": 1.185908779312959e-05,
|
| 1724 |
+
"loss": 1.254,
|
| 1725 |
+
"step": 6125
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.9181845326963273,
|
| 1729 |
+
"grad_norm": 4.636424541473389,
|
| 1730 |
+
"learning_rate": 1.1799669335052668e-05,
|
| 1731 |
+
"loss": 1.1341,
|
| 1732 |
+
"step": 6150
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.9219169901463123,
|
| 1736 |
+
"grad_norm": 1.5172594785690308,
|
| 1737 |
+
"learning_rate": 1.1740185138657461e-05,
|
| 1738 |
+
"loss": 1.1326,
|
| 1739 |
+
"step": 6175
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.9256494475962974,
|
| 1743 |
+
"grad_norm": 1.9873288869857788,
|
| 1744 |
+
"learning_rate": 1.16806373767826e-05,
|
| 1745 |
+
"loss": 1.2313,
|
| 1746 |
+
"step": 6200
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9293819050462825,
|
| 1750 |
+
"grad_norm": 1.6878819465637207,
|
| 1751 |
+
"learning_rate": 1.1621028224588617e-05,
|
| 1752 |
+
"loss": 1.2502,
|
| 1753 |
+
"step": 6225
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.9331143624962676,
|
| 1757 |
+
"grad_norm": 1.5390180349349976,
|
| 1758 |
+
"learning_rate": 1.156135985947852e-05,
|
| 1759 |
+
"loss": 1.2216,
|
| 1760 |
+
"step": 6250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.9368468199462526,
|
| 1764 |
+
"grad_norm": 1.386735439300537,
|
| 1765 |
+
"learning_rate": 1.1501634461018249e-05,
|
| 1766 |
+
"loss": 1.1471,
|
| 1767 |
+
"step": 6275
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9405792773962377,
|
| 1771 |
+
"grad_norm": 1.200641393661499,
|
| 1772 |
+
"learning_rate": 1.1441854210857047e-05,
|
| 1773 |
+
"loss": 1.222,
|
| 1774 |
+
"step": 6300
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.9443117348462228,
|
| 1778 |
+
"grad_norm": 1.2502779960632324,
|
| 1779 |
+
"learning_rate": 1.1382021292647789e-05,
|
| 1780 |
+
"loss": 1.1901,
|
| 1781 |
+
"step": 6325
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9480441922962078,
|
| 1785 |
+
"grad_norm": 1.8482311964035034,
|
| 1786 |
+
"learning_rate": 1.1322137891967202e-05,
|
| 1787 |
+
"loss": 1.1126,
|
| 1788 |
+
"step": 6350
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9517766497461929,
|
| 1792 |
+
"grad_norm": 3.107370138168335,
|
| 1793 |
+
"learning_rate": 1.1262206196236041e-05,
|
| 1794 |
+
"loss": 1.2232,
|
| 1795 |
+
"step": 6375
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.955509107196178,
|
| 1799 |
+
"grad_norm": 1.6704610586166382,
|
| 1800 |
+
"learning_rate": 1.1202228394639185e-05,
|
| 1801 |
+
"loss": 1.2805,
|
| 1802 |
+
"step": 6400
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9592415646461631,
|
| 1806 |
+
"grad_norm": 1.9674614667892456,
|
| 1807 |
+
"learning_rate": 1.1142206678045659e-05,
|
| 1808 |
+
"loss": 1.2271,
|
| 1809 |
+
"step": 6425
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9629740220961481,
|
| 1813 |
+
"grad_norm": 1.4267408847808838,
|
| 1814 |
+
"learning_rate": 1.1082143238928627e-05,
|
| 1815 |
+
"loss": 1.1858,
|
| 1816 |
+
"step": 6450
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9667064795461332,
|
| 1820 |
+
"grad_norm": 1.3559452295303345,
|
| 1821 |
+
"learning_rate": 1.102204027128528e-05,
|
| 1822 |
+
"loss": 1.1946,
|
| 1823 |
+
"step": 6475
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9704389369961183,
|
| 1827 |
+
"grad_norm": 1.2451636791229248,
|
| 1828 |
+
"learning_rate": 1.0961899970556714e-05,
|
| 1829 |
+
"loss": 1.2767,
|
| 1830 |
+
"step": 6500
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.9741713944461033,
|
| 1834 |
+
"grad_norm": 1.0592637062072754,
|
| 1835 |
+
"learning_rate": 1.0901724533547732e-05,
|
| 1836 |
+
"loss": 1.2102,
|
| 1837 |
+
"step": 6525
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.9779038518960884,
|
| 1841 |
+
"grad_norm": 1.5661903619766235,
|
| 1842 |
+
"learning_rate": 1.0841516158346585e-05,
|
| 1843 |
+
"loss": 1.323,
|
| 1844 |
+
"step": 6550
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.9816363093460735,
|
| 1848 |
+
"grad_norm": 1.1508394479751587,
|
| 1849 |
+
"learning_rate": 1.0781277044244702e-05,
|
| 1850 |
+
"loss": 1.1423,
|
| 1851 |
+
"step": 6575
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.9853687667960586,
|
| 1855 |
+
"grad_norm": 1.777511477470398,
|
| 1856 |
+
"learning_rate": 1.0721009391656331e-05,
|
| 1857 |
+
"loss": 1.171,
|
| 1858 |
+
"step": 6600
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.9891012242460436,
|
| 1862 |
+
"grad_norm": 1.3769773244857788,
|
| 1863 |
+
"learning_rate": 1.0660715402038178e-05,
|
| 1864 |
+
"loss": 1.1406,
|
| 1865 |
+
"step": 6625
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.9928336816960287,
|
| 1869 |
+
"grad_norm": 1.7429224252700806,
|
| 1870 |
+
"learning_rate": 1.0600397277808996e-05,
|
| 1871 |
+
"loss": 1.1783,
|
| 1872 |
+
"step": 6650
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.9965661391460138,
|
| 1876 |
+
"grad_norm": 3.171079397201538,
|
| 1877 |
+
"learning_rate": 1.054005722226911e-05,
|
| 1878 |
+
"loss": 1.1792,
|
| 1879 |
+
"step": 6675
|
| 1880 |
+
}
|
| 1881 |
+
],
|
| 1882 |
+
"logging_steps": 25,
|
| 1883 |
+
"max_steps": 13396,
|
| 1884 |
+
"num_input_tokens_seen": 0,
|
| 1885 |
+
"num_train_epochs": 2,
|
| 1886 |
+
"save_steps": 500,
|
| 1887 |
+
"stateful_callbacks": {
|
| 1888 |
+
"TrainerControl": {
|
| 1889 |
+
"args": {
|
| 1890 |
+
"should_epoch_stop": false,
|
| 1891 |
+
"should_evaluate": false,
|
| 1892 |
+
"should_log": false,
|
| 1893 |
+
"should_save": true,
|
| 1894 |
+
"should_training_stop": false
|
| 1895 |
+
},
|
| 1896 |
+
"attributes": {}
|
| 1897 |
+
}
|
| 1898 |
+
},
|
| 1899 |
+
"total_flos": 2.219269535028142e+17,
|
| 1900 |
+
"train_batch_size": 8,
|
| 1901 |
+
"trial_name": null,
|
| 1902 |
+
"trial_params": null
|
| 1903 |
+
}
|
checkpoint-6698/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08030c458813a63de631e045b9b695462154f661362deb23c1340aaf03a10920
|
| 3 |
+
size 5304
|
runs/Apr29_04-40-07_sg238/events.out.tfevents.1745926808.sg238.3949072.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:283ae0f7acb566c691e98b002faa7ead5f7d5eaf0a05bb3c044586be5c4e89e5
|
| 3 |
+
size 5255
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|end_of_text|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2063 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7faed4b619c396df51af330c0f854c7ab9439405c1297639dbb684514dc8760
|
| 3 |
+
size 5368
|