Hugging Face's logo

yezg
/
myqwenmodel

PEFT
Safetensors
qwen2
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
Community
yezg commited on
Commit
7f7733b
·
verified ·
1 Parent(s): d42c0ec

Upload LoRA adapter

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. .ipynb_checkpoints/README-checkpoint.md +137 -0
  3. README.md +137 -0
  4. adapter_config.json +40 -0
  5. adapter_model.safetensors +3 -0
  6. added_tokens.json +24 -0
  7. checkpoint-1375/README.md +202 -0
  8. checkpoint-1375/adapter_config.json +40 -0
  9. checkpoint-1375/adapter_model.safetensors +3 -0
  10. checkpoint-1375/added_tokens.json +24 -0
  11. checkpoint-1375/merges.txt +0 -0
  12. checkpoint-1375/optimizer.pt +3 -0
  13. checkpoint-1375/rng_state_0.pth +3 -0
  14. checkpoint-1375/rng_state_1.pth +3 -0
  15. checkpoint-1375/scaler.pt +3 -0
  16. checkpoint-1375/scheduler.pt +3 -0
  17. checkpoint-1375/special_tokens_map.json +31 -0
  18. checkpoint-1375/tokenizer.json +3 -0
  19. checkpoint-1375/tokenizer_config.json +208 -0
  20. checkpoint-1375/trainer_state.json +0 -0
  21. checkpoint-1375/training_args.bin +3 -0
  22. checkpoint-1375/vocab.json +0 -0
  23. checkpoint-459/README.md +202 -0
  24. checkpoint-459/adapter_config.json +40 -0
  25. checkpoint-459/adapter_model.safetensors +3 -0
  26. checkpoint-459/added_tokens.json +24 -0
  27. checkpoint-459/merges.txt +0 -0
  28. checkpoint-459/optimizer.pt +3 -0
  29. checkpoint-459/rng_state_0.pth +3 -0
  30. checkpoint-459/rng_state_1.pth +3 -0
  31. checkpoint-459/scaler.pt +3 -0
  32. checkpoint-459/scheduler.pt +3 -0
  33. checkpoint-459/special_tokens_map.json +31 -0
  34. checkpoint-459/tokenizer.json +3 -0
  35. checkpoint-459/tokenizer_config.json +208 -0
  36. checkpoint-459/trainer_state.json +3263 -0
  37. checkpoint-459/training_args.bin +3 -0
  38. checkpoint-459/vocab.json +0 -0
  39. checkpoint-918/README.md +202 -0
  40. checkpoint-918/adapter_config.json +40 -0
  41. checkpoint-918/adapter_model.safetensors +3 -0
  42. checkpoint-918/added_tokens.json +24 -0
  43. checkpoint-918/merges.txt +0 -0
  44. checkpoint-918/optimizer.pt +3 -0
  45. checkpoint-918/rng_state_0.pth +3 -0
  46. checkpoint-918/rng_state_1.pth +3 -0
  47. checkpoint-918/scaler.pt +3 -0
  48. checkpoint-918/scheduler.pt +3 -0
  49. checkpoint-918/special_tokens_map.json +31 -0
  50. checkpoint-918/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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-1375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-459/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-918/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-coder-3B
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets: []
8
+ model-index:
9
+ - name: outputs/qwen2.5-coder-3b-lora
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.10.0.dev0`
20
+ ```yaml
21
+ base_model: Qwen/Qwen2.5-coder-3B
22
+ model_type: AutoModelForCausalLM
23
+ tokenizer_type: AutoTokenizer
24
+ trust_remote_code: true
25
+ chat_template: qwen_25
26
+
27
+ adapter: qlora
28
+ lora_r: 8
29
+ lora_alpha: 32
30
+ lora_dropout: 0.05
31
+ lora_target_modules:
32
+ - c_attn
33
+ - c_proj
34
+ - w1
35
+ - w2
36
+ - q_proj
37
+ - v_proj
38
+ - k_proj
39
+ - o_proj
40
+
41
+ load_in_4bit: true
42
+ bnb_4bit_compute_dtype: float16
43
+ bnb_4bit_use_double_quant: true
44
+ bnb_4bit_quant_type: nf4
45
+
46
+ datasets:
47
+ - path: ./datasets/generic_formatted_data.jsonl
48
+ type: alpaca
49
+
50
+ val_set_size: 0.01
51
+ dataset_prepared_path:
52
+
53
+ sequence_len: 2048
54
+ pad_to_sequence_len: true
55
+
56
+ output_dir: ./outputs/qwen2.5-coder-3b-lora
57
+ num_epochs: 3
58
+ micro_batch_size: 2
59
+ gradient_accumulation_steps: 8
60
+ evals_per_epoch: 1
61
+ saves_per_epoch: 1
62
+ optimizer: adamw_bnb_8bit
63
+ learning_rate: 2e-5
64
+ lr_scheduler: cosine
65
+ warmup_steps: 50
66
+
67
+ gradient_checkpointing: true
68
+ fp16: true
69
+ bf16: false
70
+ tf32: true
71
+ flash_attention: true
72
+ eager_attention: false
73
+
74
+ logging_steps: 1
75
+ debug: true
76
+ wandb_project: qwen-coder
77
+ wandb_name: qwen2.5-coder-3b-lora
78
+ wandb_log_model: "false"
79
+ wandb_mode: disabled
80
+ ```
81
+
82
+ </details><br>
83
+
84
+ # outputs/qwen2.5-coder-3b-lora
85
+
86
+ This model is a fine-tuned version of [Qwen/Qwen2.5-coder-3B](https://huggingface.co/Qwen/Qwen2.5-coder-3B) on the ./datasets/generic_formatted_data.jsonl dataset.
87
+ It achieves the following results on the evaluation set:
88
+ - Loss: 0.0817
89
+
90
+ ## Model description
91
+
92
+ More information needed
93
+
94
+ ## Intended uses & limitations
95
+
96
+ More information needed
97
+
98
+ ## Training and evaluation data
99
+
100
+ More information needed
101
+
102
+ ## Training procedure
103
+
104
+ ### Training hyperparameters
105
+
106
+ The following hyperparameters were used during training:
107
+ - learning_rate: 2e-05
108
+ - train_batch_size: 2
109
+ - eval_batch_size: 2
110
+ - seed: 42
111
+ - distributed_type: multi-GPU
112
+ - num_devices: 2
113
+ - gradient_accumulation_steps: 8
114
+ - total_train_batch_size: 32
115
+ - total_eval_batch_size: 4
116
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
117
+ - lr_scheduler_type: cosine
118
+ - lr_scheduler_warmup_steps: 50
119
+ - training_steps: 1375
120
+ - mixed_precision_training: Native AMP
121
+
122
+ ### Training results
123
+
124
+ | Training Loss | Epoch | Step | Validation Loss |
125
+ |:-------------:|:------:|:----:|:---------------:|
126
+ | 1.0456 | 0.0022 | 1 | 0.9417 |
127
+ | 0.3029 | 1.0 | 459 | 0.1403 |
128
+ | 0.044 | 2.0 | 918 | 0.0817 |
129
+
130
+
131
+ ### Framework versions
132
+
133
+ - PEFT 0.15.2
134
+ - Transformers 4.51.3
135
+ - Pytorch 2.6.0+cu124
136
+ - Datasets 3.5.1
137
+ - Tokenizers 0.21.1
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-coder-3B
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets: []
8
+ model-index:
9
+ - name: outputs/qwen2.5-coder-3b-lora
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.10.0.dev0`
20
+ ```yaml
21
+ base_model: Qwen/Qwen2.5-coder-3B
22
+ model_type: AutoModelForCausalLM
23
+ tokenizer_type: AutoTokenizer
24
+ trust_remote_code: true
25
+ chat_template: qwen_25
26
+
27
+ adapter: qlora
28
+ lora_r: 8
29
+ lora_alpha: 32
30
+ lora_dropout: 0.05
31
+ lora_target_modules:
32
+ - c_attn
33
+ - c_proj
34
+ - w1
35
+ - w2
36
+ - q_proj
37
+ - v_proj
38
+ - k_proj
39
+ - o_proj
40
+
41
+ load_in_4bit: true
42
+ bnb_4bit_compute_dtype: float16
43
+ bnb_4bit_use_double_quant: true
44
+ bnb_4bit_quant_type: nf4
45
+
46
+ datasets:
47
+ - path: ./datasets/generic_formatted_data.jsonl
48
+ type: alpaca
49
+
50
+ val_set_size: 0.01
51
+ dataset_prepared_path:
52
+
53
+ sequence_len: 2048
54
+ pad_to_sequence_len: true
55
+
56
+ output_dir: ./outputs/qwen2.5-coder-3b-lora
57
+ num_epochs: 3
58
+ micro_batch_size: 2
59
+ gradient_accumulation_steps: 8
60
+ evals_per_epoch: 1
61
+ saves_per_epoch: 1
62
+ optimizer: adamw_bnb_8bit
63
+ learning_rate: 2e-5
64
+ lr_scheduler: cosine
65
+ warmup_steps: 50
66
+
67
+ gradient_checkpointing: true
68
+ fp16: true
69
+ bf16: false
70
+ tf32: true
71
+ flash_attention: true
72
+ eager_attention: false
73
+
74
+ logging_steps: 1
75
+ debug: true
76
+ wandb_project: qwen-coder
77
+ wandb_name: qwen2.5-coder-3b-lora
78
+ wandb_log_model: "false"
79
+ wandb_mode: disabled
80
+ ```
81
+
82
+ </details><br>
83
+
84
+ # outputs/qwen2.5-coder-3b-lora
85
+
86
+ This model is a fine-tuned version of [Qwen/Qwen2.5-coder-3B](https://huggingface.co/Qwen/Qwen2.5-coder-3B) on the ./datasets/generic_formatted_data.jsonl dataset.
87
+ It achieves the following results on the evaluation set:
88
+ - Loss: 0.0817
89
+
90
+ ## Model description
91
+
92
+ More information needed
93
+
94
+ ## Intended uses & limitations
95
+
96
+ More information needed
97
+
98
+ ## Training and evaluation data
99
+
100
+ More information needed
101
+
102
+ ## Training procedure
103
+
104
+ ### Training hyperparameters
105
+
106
+ The following hyperparameters were used during training:
107
+ - learning_rate: 2e-05
108
+ - train_batch_size: 2
109
+ - eval_batch_size: 2
110
+ - seed: 42
111
+ - distributed_type: multi-GPU
112
+ - num_devices: 2
113
+ - gradient_accumulation_steps: 8
114
+ - total_train_batch_size: 32
115
+ - total_eval_batch_size: 4
116
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
117
+ - lr_scheduler_type: cosine
118
+ - lr_scheduler_warmup_steps: 50
119
+ - training_steps: 1375
120
+ - mixed_precision_training: Native AMP
121
+
122
+ ### Training results
123
+
124
+ | Training Loss | Epoch | Step | Validation Loss |
125
+ |:-------------:|:------:|:----:|:---------------:|
126
+ | 1.0456 | 0.0022 | 1 | 0.9417 |
127
+ | 0.3029 | 1.0 | 459 | 0.1403 |
128
+ | 0.044 | 2.0 | 918 | 0.0817 |
129
+
130
+
131
+ ### Framework versions
132
+
133
+ - PEFT 0.15.2
134
+ - Transformers 4.51.3
135
+ - Pytorch 2.6.0+cu124
136
+ - Datasets 3.5.1
137
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-coder-3B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 32,
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": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "w1",
28
+ "v_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "o_proj",
32
+ "w2",
33
+ "c_proj",
34
+ "c_attn"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48ac54325a4c7785c9e06b893b342c6e171e277f5dde3612966a52982ec920a
3
+ size 14783648
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-1375/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-coder-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-1375/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-coder-3B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 32,
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": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "w1",
28
+ "v_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "o_proj",
32
+ "w2",
33
+ "c_proj",
34
+ "c_attn"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
checkpoint-1375/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48ac54325a4c7785c9e06b893b342c6e171e277f5dde3612966a52982ec920a
3
+ size 14783648
checkpoint-1375/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-1375/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6d9e8078816e7511852b1f72fcb669dc19f6a56915463bf52c059976047839
3
+ size 8663940
checkpoint-1375/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc31a8ca039d3507025cb6306c6eda51d4b2edbf3083da187042f32f13eb0de
3
+ size 14512
checkpoint-1375/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e4cda15bc59031d2cee5e06f4593d7e2158f897322af8bf690d7a711962f3f
3
+ size 14512
checkpoint-1375/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a2bbd5dd9e764edf2301d02a36cde2c338114bad37e9bffd604cea65cfe01e
3
+ size 988
checkpoint-1375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bf5b108d916bac514f3512650b729a55e24b4ab81e23cd6a93d67a16465117
3
+ size 1064
checkpoint-1375/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-1375/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-1375/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 32768,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-1375/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9782f3189b2775d8981fd1818051f75ea4e7ed0ea5d50644d78a1e3bfb534506
3
+ size 9144
checkpoint-1375/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-459/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-coder-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-459/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-coder-3B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 32,
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": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "w1",
28
+ "v_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "o_proj",
32
+ "w2",
33
+ "c_proj",
34
+ "c_attn"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
checkpoint-459/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee540540863e5b7457a6b658dc3f4ce9b31f2894419555e78421f85dfea742c
3
+ size 14783648
checkpoint-459/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-459/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-459/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0395c4f5ab34675ee30a2f6d7903d0848b8854198b2fcc38d712c481bee82c07
3
+ size 8663940
checkpoint-459/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335e2cc6a274327681e1d4937ab066aa1d472737c6fefd0ccce0da8cf252b156
3
+ size 14512
checkpoint-459/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839815f98dbb6e59904b9a84826ac34926937c4985fb1580af384cca73d8b4a8
3
+ size 14512
checkpoint-459/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fe83c05a65eb771c89e970e86b94914d213b21ceb1916de69afb794f6b88d9
3
+ size 988
checkpoint-459/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af00acb2185ccc1f2e983440ccf5eef2a8555a5a472b8617bd9ce957c7976d9
3
+ size 1064
checkpoint-459/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-459/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-459/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 32768,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-459/trainer_state.json ADDED
@@ -0,0 +1,3263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 459,
7
+ "global_step": 459,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002182214948172395,
14
+ "grad_norm": 1.4921265840530396,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.0456,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.002182214948172395,
21
+ "eval_loss": 0.9416840076446533,
22
+ "eval_runtime": 19.6642,
23
+ "eval_samples_per_second": 7.577,
24
+ "eval_steps_per_second": 1.932,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.00436442989634479,
29
+ "grad_norm": 1.959935188293457,
30
+ "learning_rate": 4.0000000000000003e-07,
31
+ "loss": 0.966,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.006546644844517185,
36
+ "grad_norm": 1.6094727516174316,
37
+ "learning_rate": 8.000000000000001e-07,
38
+ "loss": 0.9745,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.00872885979268958,
43
+ "grad_norm": 1.3938935995101929,
44
+ "learning_rate": 1.2000000000000002e-06,
45
+ "loss": 0.8823,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.010911074740861976,
50
+ "grad_norm": 1.8474189043045044,
51
+ "learning_rate": 1.6000000000000001e-06,
52
+ "loss": 0.9688,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.01309328968903437,
57
+ "grad_norm": 1.9620424509048462,
58
+ "learning_rate": 2.0000000000000003e-06,
59
+ "loss": 1.1181,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.015275504637206765,
64
+ "grad_norm": 1.3256500959396362,
65
+ "learning_rate": 2.4000000000000003e-06,
66
+ "loss": 1.0379,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.01745771958537916,
71
+ "grad_norm": 1.6532100439071655,
72
+ "learning_rate": 2.8000000000000003e-06,
73
+ "loss": 1.0999,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.019639934533551555,
78
+ "grad_norm": 1.9979885816574097,
79
+ "learning_rate": 3.2000000000000003e-06,
80
+ "loss": 0.8739,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.02182214948172395,
85
+ "grad_norm": 1.864553689956665,
86
+ "learning_rate": 3.6000000000000003e-06,
87
+ "loss": 0.8957,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.024004364429896344,
92
+ "grad_norm": 1.5396744012832642,
93
+ "learning_rate": 4.000000000000001e-06,
94
+ "loss": 0.8844,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.02618657937806874,
99
+ "grad_norm": 1.6357618570327759,
100
+ "learning_rate": 4.4e-06,
101
+ "loss": 0.9908,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.028368794326241134,
106
+ "grad_norm": 1.5768996477127075,
107
+ "learning_rate": 4.800000000000001e-06,
108
+ "loss": 0.9163,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.03055100927441353,
113
+ "grad_norm": 1.8592894077301025,
114
+ "learning_rate": 5.2e-06,
115
+ "loss": 1.177,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.03273322422258593,
120
+ "grad_norm": 1.8276045322418213,
121
+ "learning_rate": 5.600000000000001e-06,
122
+ "loss": 1.1037,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.03491543917075832,
127
+ "grad_norm": 1.9452946186065674,
128
+ "learning_rate": 6e-06,
129
+ "loss": 0.8114,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.03709765411893071,
134
+ "grad_norm": 1.5948249101638794,
135
+ "learning_rate": 6.4000000000000006e-06,
136
+ "loss": 0.9058,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.03927986906710311,
141
+ "grad_norm": 1.411731243133545,
142
+ "learning_rate": 6.800000000000001e-06,
143
+ "loss": 0.7237,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.041462084015275506,
148
+ "grad_norm": 1.7105116844177246,
149
+ "learning_rate": 7.2000000000000005e-06,
150
+ "loss": 0.7503,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.0436442989634479,
155
+ "grad_norm": 1.4265415668487549,
156
+ "learning_rate": 7.600000000000001e-06,
157
+ "loss": 0.8652,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.04582651391162029,
162
+ "grad_norm": 1.5991572141647339,
163
+ "learning_rate": 8.000000000000001e-06,
164
+ "loss": 0.9468,
165
+ "step": 21
166
+ },
167
+ {
168
+ "epoch": 0.04800872885979269,
169
+ "grad_norm": 1.5912425518035889,
170
+ "learning_rate": 8.400000000000001e-06,
171
+ "loss": 0.9793,
172
+ "step": 22
173
+ },
174
+ {
175
+ "epoch": 0.050190943807965085,
176
+ "grad_norm": 1.3830496072769165,
177
+ "learning_rate": 8.8e-06,
178
+ "loss": 0.7609,
179
+ "step": 23
180
+ },
181
+ {
182
+ "epoch": 0.05237315875613748,
183
+ "grad_norm": 1.2661924362182617,
184
+ "learning_rate": 9.200000000000002e-06,
185
+ "loss": 0.788,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 0.05455537370430987,
190
+ "grad_norm": 1.161792516708374,
191
+ "learning_rate": 9.600000000000001e-06,
192
+ "loss": 0.8404,
193
+ "step": 25
194
+ },
195
+ {
196
+ "epoch": 0.05673758865248227,
197
+ "grad_norm": 1.3503375053405762,
198
+ "learning_rate": 1e-05,
199
+ "loss": 0.8254,
200
+ "step": 26
201
+ },
202
+ {
203
+ "epoch": 0.058919803600654665,
204
+ "grad_norm": 1.156307578086853,
205
+ "learning_rate": 1.04e-05,
206
+ "loss": 0.6885,
207
+ "step": 27
208
+ },
209
+ {
210
+ "epoch": 0.06110201854882706,
211
+ "grad_norm": 1.2533096075057983,
212
+ "learning_rate": 1.0800000000000002e-05,
213
+ "loss": 0.8499,
214
+ "step": 28
215
+ },
216
+ {
217
+ "epoch": 0.06328423349699945,
218
+ "grad_norm": 1.3179517984390259,
219
+ "learning_rate": 1.1200000000000001e-05,
220
+ "loss": 0.7626,
221
+ "step": 29
222
+ },
223
+ {
224
+ "epoch": 0.06546644844517185,
225
+ "grad_norm": 1.179800033569336,
226
+ "learning_rate": 1.16e-05,
227
+ "loss": 0.7334,
228
+ "step": 30
229
+ },
230
+ {
231
+ "epoch": 0.06764866339334424,
232
+ "grad_norm": 1.2510403394699097,
233
+ "learning_rate": 1.2e-05,
234
+ "loss": 0.6933,
235
+ "step": 31
236
+ },
237
+ {
238
+ "epoch": 0.06983087834151663,
239
+ "grad_norm": 1.0884430408477783,
240
+ "learning_rate": 1.2400000000000002e-05,
241
+ "loss": 0.7441,
242
+ "step": 32
243
+ },
244
+ {
245
+ "epoch": 0.07201309328968904,
246
+ "grad_norm": 1.0181330442428589,
247
+ "learning_rate": 1.2800000000000001e-05,
248
+ "loss": 0.7369,
249
+ "step": 33
250
+ },
251
+ {
252
+ "epoch": 0.07419530823786143,
253
+ "grad_norm": 1.1634576320648193,
254
+ "learning_rate": 1.3200000000000002e-05,
255
+ "loss": 0.7186,
256
+ "step": 34
257
+ },
258
+ {
259
+ "epoch": 0.07637752318603383,
260
+ "grad_norm": 1.4808906316757202,
261
+ "learning_rate": 1.3600000000000002e-05,
262
+ "loss": 0.8053,
263
+ "step": 35
264
+ },
265
+ {
266
+ "epoch": 0.07855973813420622,
267
+ "grad_norm": 1.0586826801300049,
268
+ "learning_rate": 1.4e-05,
269
+ "loss": 0.8257,
270
+ "step": 36
271
+ },
272
+ {
273
+ "epoch": 0.08074195308237861,
274
+ "grad_norm": 1.0057055950164795,
275
+ "learning_rate": 1.4400000000000001e-05,
276
+ "loss": 0.7209,
277
+ "step": 37
278
+ },
279
+ {
280
+ "epoch": 0.08292416803055101,
281
+ "grad_norm": 1.0284557342529297,
282
+ "learning_rate": 1.48e-05,
283
+ "loss": 0.9696,
284
+ "step": 38
285
+ },
286
+ {
287
+ "epoch": 0.0851063829787234,
288
+ "grad_norm": 0.9222050309181213,
289
+ "learning_rate": 1.5200000000000002e-05,
290
+ "loss": 0.5902,
291
+ "step": 39
292
+ },
293
+ {
294
+ "epoch": 0.0872885979268958,
295
+ "grad_norm": 0.8478285074234009,
296
+ "learning_rate": 1.5600000000000003e-05,
297
+ "loss": 0.6501,
298
+ "step": 40
299
+ },
300
+ {
301
+ "epoch": 0.0894708128750682,
302
+ "grad_norm": 0.9614901542663574,
303
+ "learning_rate": 1.6000000000000003e-05,
304
+ "loss": 1.0219,
305
+ "step": 41
306
+ },
307
+ {
308
+ "epoch": 0.09165302782324058,
309
+ "grad_norm": 0.7026827931404114,
310
+ "learning_rate": 1.64e-05,
311
+ "loss": 0.6814,
312
+ "step": 42
313
+ },
314
+ {
315
+ "epoch": 0.09383524277141299,
316
+ "grad_norm": 0.6492002606391907,
317
+ "learning_rate": 1.6800000000000002e-05,
318
+ "loss": 0.8003,
319
+ "step": 43
320
+ },
321
+ {
322
+ "epoch": 0.09601745771958538,
323
+ "grad_norm": 0.6572920680046082,
324
+ "learning_rate": 1.72e-05,
325
+ "loss": 0.6363,
326
+ "step": 44
327
+ },
328
+ {
329
+ "epoch": 0.09819967266775777,
330
+ "grad_norm": 0.6610034108161926,
331
+ "learning_rate": 1.76e-05,
332
+ "loss": 0.4044,
333
+ "step": 45
334
+ },
335
+ {
336
+ "epoch": 0.10038188761593017,
337
+ "grad_norm": 0.7360779643058777,
338
+ "learning_rate": 1.8e-05,
339
+ "loss": 0.6865,
340
+ "step": 46
341
+ },
342
+ {
343
+ "epoch": 0.10256410256410256,
344
+ "grad_norm": 0.5434179306030273,
345
+ "learning_rate": 1.8400000000000003e-05,
346
+ "loss": 0.54,
347
+ "step": 47
348
+ },
349
+ {
350
+ "epoch": 0.10474631751227496,
351
+ "grad_norm": 0.6275272369384766,
352
+ "learning_rate": 1.88e-05,
353
+ "loss": 0.8565,
354
+ "step": 48
355
+ },
356
+ {
357
+ "epoch": 0.10692853246044735,
358
+ "grad_norm": 0.6033368110656738,
359
+ "learning_rate": 1.9200000000000003e-05,
360
+ "loss": 0.7129,
361
+ "step": 49
362
+ },
363
+ {
364
+ "epoch": 0.10911074740861974,
365
+ "grad_norm": 0.6621481776237488,
366
+ "learning_rate": 1.9600000000000002e-05,
367
+ "loss": 0.9844,
368
+ "step": 50
369
+ },
370
+ {
371
+ "epoch": 0.11129296235679215,
372
+ "grad_norm": 0.5725002884864807,
373
+ "learning_rate": 2e-05,
374
+ "loss": 0.7262,
375
+ "step": 51
376
+ },
377
+ {
378
+ "epoch": 0.11347517730496454,
379
+ "grad_norm": 0.5369328856468201,
380
+ "learning_rate": 1.999997189149227e-05,
381
+ "loss": 0.7641,
382
+ "step": 52
383
+ },
384
+ {
385
+ "epoch": 0.11565739225313694,
386
+ "grad_norm": 0.5427905917167664,
387
+ "learning_rate": 1.999988756612709e-05,
388
+ "loss": 0.6001,
389
+ "step": 53
390
+ },
391
+ {
392
+ "epoch": 0.11783960720130933,
393
+ "grad_norm": 0.5753054022789001,
394
+ "learning_rate": 1.9999747024378516e-05,
395
+ "loss": 0.6579,
396
+ "step": 54
397
+ },
398
+ {
399
+ "epoch": 0.12002182214948172,
400
+ "grad_norm": 0.692951500415802,
401
+ "learning_rate": 1.9999550267036634e-05,
402
+ "loss": 0.7786,
403
+ "step": 55
404
+ },
405
+ {
406
+ "epoch": 0.12220403709765412,
407
+ "grad_norm": 0.7742375731468201,
408
+ "learning_rate": 1.999929729520755e-05,
409
+ "loss": 0.8386,
410
+ "step": 56
411
+ },
412
+ {
413
+ "epoch": 0.12438625204582651,
414
+ "grad_norm": 0.6625115275382996,
415
+ "learning_rate": 1.99989881103134e-05,
416
+ "loss": 0.8797,
417
+ "step": 57
418
+ },
419
+ {
420
+ "epoch": 0.1265684669939989,
421
+ "grad_norm": 0.5346710085868835,
422
+ "learning_rate": 1.9998622714092328e-05,
423
+ "loss": 0.5483,
424
+ "step": 58
425
+ },
426
+ {
427
+ "epoch": 0.1287506819421713,
428
+ "grad_norm": 0.5811567306518555,
429
+ "learning_rate": 1.9998201108598477e-05,
430
+ "loss": 0.6895,
431
+ "step": 59
432
+ },
433
+ {
434
+ "epoch": 0.1309328968903437,
435
+ "grad_norm": 0.5905172824859619,
436
+ "learning_rate": 1.9997723296201997e-05,
437
+ "loss": 0.6995,
438
+ "step": 60
439
+ },
440
+ {
441
+ "epoch": 0.1331151118385161,
442
+ "grad_norm": 0.5894107818603516,
443
+ "learning_rate": 1.9997189279589003e-05,
444
+ "loss": 0.5713,
445
+ "step": 61
446
+ },
447
+ {
448
+ "epoch": 0.1352973267866885,
449
+ "grad_norm": 0.6387777328491211,
450
+ "learning_rate": 1.9996599061761575e-05,
451
+ "loss": 0.7275,
452
+ "step": 62
453
+ },
454
+ {
455
+ "epoch": 0.13747954173486088,
456
+ "grad_norm": 0.5308466553688049,
457
+ "learning_rate": 1.9995952646037743e-05,
458
+ "loss": 0.4408,
459
+ "step": 63
460
+ },
461
+ {
462
+ "epoch": 0.13966175668303327,
463
+ "grad_norm": 0.6239039897918701,
464
+ "learning_rate": 1.9995250036051462e-05,
465
+ "loss": 0.6457,
466
+ "step": 64
467
+ },
468
+ {
469
+ "epoch": 0.14184397163120568,
470
+ "grad_norm": 0.5327976942062378,
471
+ "learning_rate": 1.9994491235752595e-05,
472
+ "loss": 0.4673,
473
+ "step": 65
474
+ },
475
+ {
476
+ "epoch": 0.14402618657937807,
477
+ "grad_norm": 0.500877320766449,
478
+ "learning_rate": 1.9993676249406895e-05,
479
+ "loss": 0.548,
480
+ "step": 66
481
+ },
482
+ {
483
+ "epoch": 0.14620840152755046,
484
+ "grad_norm": 0.6878646016120911,
485
+ "learning_rate": 1.999280508159597e-05,
486
+ "loss": 0.7135,
487
+ "step": 67
488
+ },
489
+ {
490
+ "epoch": 0.14839061647572285,
491
+ "grad_norm": 0.6099561452865601,
492
+ "learning_rate": 1.999187773721726e-05,
493
+ "loss": 0.6922,
494
+ "step": 68
495
+ },
496
+ {
497
+ "epoch": 0.15057283142389524,
498
+ "grad_norm": 0.5138156414031982,
499
+ "learning_rate": 1.9990894221484027e-05,
500
+ "loss": 0.5143,
501
+ "step": 69
502
+ },
503
+ {
504
+ "epoch": 0.15275504637206766,
505
+ "grad_norm": 0.7398216724395752,
506
+ "learning_rate": 1.9989854539925296e-05,
507
+ "loss": 0.6775,
508
+ "step": 70
509
+ },
510
+ {
511
+ "epoch": 0.15493726132024005,
512
+ "grad_norm": 0.5672114491462708,
513
+ "learning_rate": 1.9988758698385854e-05,
514
+ "loss": 0.6343,
515
+ "step": 71
516
+ },
517
+ {
518
+ "epoch": 0.15711947626841244,
519
+ "grad_norm": 0.5795859098434448,
520
+ "learning_rate": 1.9987606703026187e-05,
521
+ "loss": 0.6327,
522
+ "step": 72
523
+ },
524
+ {
525
+ "epoch": 0.15930169121658483,
526
+ "grad_norm": 0.6178355813026428,
527
+ "learning_rate": 1.9986398560322476e-05,
528
+ "loss": 0.481,
529
+ "step": 73
530
+ },
531
+ {
532
+ "epoch": 0.16148390616475722,
533
+ "grad_norm": 0.48614248633384705,
534
+ "learning_rate": 1.9985134277066533e-05,
535
+ "loss": 0.3952,
536
+ "step": 74
537
+ },
538
+ {
539
+ "epoch": 0.16366612111292964,
540
+ "grad_norm": 0.6208723783493042,
541
+ "learning_rate": 1.998381386036578e-05,
542
+ "loss": 0.5589,
543
+ "step": 75
544
+ },
545
+ {
546
+ "epoch": 0.16584833606110203,
547
+ "grad_norm": 0.7473292350769043,
548
+ "learning_rate": 1.9982437317643218e-05,
549
+ "loss": 0.7363,
550
+ "step": 76
551
+ },
552
+ {
553
+ "epoch": 0.16803055100927441,
554
+ "grad_norm": 0.6796333193778992,
555
+ "learning_rate": 1.9981004656637344e-05,
556
+ "loss": 0.5746,
557
+ "step": 77
558
+ },
559
+ {
560
+ "epoch": 0.1702127659574468,
561
+ "grad_norm": 0.5245673656463623,
562
+ "learning_rate": 1.9979515885402156e-05,
563
+ "loss": 0.3753,
564
+ "step": 78
565
+ },
566
+ {
567
+ "epoch": 0.1723949809056192,
568
+ "grad_norm": 0.5480374097824097,
569
+ "learning_rate": 1.9977971012307085e-05,
570
+ "loss": 0.5468,
571
+ "step": 79
572
+ },
573
+ {
574
+ "epoch": 0.1745771958537916,
575
+ "grad_norm": 0.8852786421775818,
576
+ "learning_rate": 1.9976370046036947e-05,
577
+ "loss": 0.8742,
578
+ "step": 80
579
+ },
580
+ {
581
+ "epoch": 0.176759410801964,
582
+ "grad_norm": 0.5887808203697205,
583
+ "learning_rate": 1.9974712995591887e-05,
584
+ "loss": 0.5144,
585
+ "step": 81
586
+ },
587
+ {
588
+ "epoch": 0.1789416257501364,
589
+ "grad_norm": 0.5992124676704407,
590
+ "learning_rate": 1.9972999870287357e-05,
591
+ "loss": 0.6015,
592
+ "step": 82
593
+ },
594
+ {
595
+ "epoch": 0.18112384069830878,
596
+ "grad_norm": 0.5454561710357666,
597
+ "learning_rate": 1.997123067975404e-05,
598
+ "loss": 0.4939,
599
+ "step": 83
600
+ },
601
+ {
602
+ "epoch": 0.18330605564648117,
603
+ "grad_norm": 0.5829342603683472,
604
+ "learning_rate": 1.996940543393778e-05,
605
+ "loss": 0.5391,
606
+ "step": 84
607
+ },
608
+ {
609
+ "epoch": 0.1854882705946536,
610
+ "grad_norm": 0.6858181357383728,
611
+ "learning_rate": 1.9967524143099583e-05,
612
+ "loss": 0.6028,
613
+ "step": 85
614
+ },
615
+ {
616
+ "epoch": 0.18767048554282598,
617
+ "grad_norm": 0.5993210673332214,
618
+ "learning_rate": 1.9965586817815494e-05,
619
+ "loss": 0.4545,
620
+ "step": 86
621
+ },
622
+ {
623
+ "epoch": 0.18985270049099837,
624
+ "grad_norm": 0.5937272906303406,
625
+ "learning_rate": 1.9963593468976583e-05,
626
+ "loss": 0.3147,
627
+ "step": 87
628
+ },
629
+ {
630
+ "epoch": 0.19203491543917076,
631
+ "grad_norm": 0.7777706384658813,
632
+ "learning_rate": 1.9961544107788855e-05,
633
+ "loss": 0.5694,
634
+ "step": 88
635
+ },
636
+ {
637
+ "epoch": 0.19421713038734315,
638
+ "grad_norm": 0.5509026050567627,
639
+ "learning_rate": 1.9959438745773216e-05,
640
+ "loss": 0.378,
641
+ "step": 89
642
+ },
643
+ {
644
+ "epoch": 0.19639934533551553,
645
+ "grad_norm": 0.6026902198791504,
646
+ "learning_rate": 1.9957277394765377e-05,
647
+ "loss": 0.6189,
648
+ "step": 90
649
+ },
650
+ {
651
+ "epoch": 0.19858156028368795,
652
+ "grad_norm": 0.5900372266769409,
653
+ "learning_rate": 1.995506006691581e-05,
654
+ "loss": 0.4099,
655
+ "step": 91
656
+ },
657
+ {
658
+ "epoch": 0.20076377523186034,
659
+ "grad_norm": 0.6046119928359985,
660
+ "learning_rate": 1.9952786774689667e-05,
661
+ "loss": 0.5802,
662
+ "step": 92
663
+ },
664
+ {
665
+ "epoch": 0.20294599018003273,
666
+ "grad_norm": 0.9368590116500854,
667
+ "learning_rate": 1.9950457530866726e-05,
668
+ "loss": 0.7274,
669
+ "step": 93
670
+ },
671
+ {
672
+ "epoch": 0.20512820512820512,
673
+ "grad_norm": 0.7070465683937073,
674
+ "learning_rate": 1.9948072348541294e-05,
675
+ "loss": 0.6259,
676
+ "step": 94
677
+ },
678
+ {
679
+ "epoch": 0.2073104200763775,
680
+ "grad_norm": 0.7370465993881226,
681
+ "learning_rate": 1.9945631241122158e-05,
682
+ "loss": 0.5427,
683
+ "step": 95
684
+ },
685
+ {
686
+ "epoch": 0.20949263502454993,
687
+ "grad_norm": 0.6051648259162903,
688
+ "learning_rate": 1.9943134222332493e-05,
689
+ "loss": 0.4497,
690
+ "step": 96
691
+ },
692
+ {
693
+ "epoch": 0.21167484997272232,
694
+ "grad_norm": 0.6110167503356934,
695
+ "learning_rate": 1.994058130620979e-05,
696
+ "loss": 0.4722,
697
+ "step": 97
698
+ },
699
+ {
700
+ "epoch": 0.2138570649208947,
701
+ "grad_norm": 0.581550657749176,
702
+ "learning_rate": 1.9937972507105793e-05,
703
+ "loss": 0.5503,
704
+ "step": 98
705
+ },
706
+ {
707
+ "epoch": 0.2160392798690671,
708
+ "grad_norm": 0.775860607624054,
709
+ "learning_rate": 1.993530783968638e-05,
710
+ "loss": 0.6042,
711
+ "step": 99
712
+ },
713
+ {
714
+ "epoch": 0.2182214948172395,
715
+ "grad_norm": 0.7601407766342163,
716
+ "learning_rate": 1.993258731893152e-05,
717
+ "loss": 0.6493,
718
+ "step": 100
719
+ },
720
+ {
721
+ "epoch": 0.2204037097654119,
722
+ "grad_norm": 0.6188685297966003,
723
+ "learning_rate": 1.992981096013517e-05,
724
+ "loss": 0.2717,
725
+ "step": 101
726
+ },
727
+ {
728
+ "epoch": 0.2225859247135843,
729
+ "grad_norm": 0.7693493962287903,
730
+ "learning_rate": 1.9926978778905193e-05,
731
+ "loss": 0.4525,
732
+ "step": 102
733
+ },
734
+ {
735
+ "epoch": 0.22476813966175668,
736
+ "grad_norm": 0.5389944911003113,
737
+ "learning_rate": 1.992409079116326e-05,
738
+ "loss": 0.3065,
739
+ "step": 103
740
+ },
741
+ {
742
+ "epoch": 0.22695035460992907,
743
+ "grad_norm": 0.6077801585197449,
744
+ "learning_rate": 1.9921147013144782e-05,
745
+ "loss": 0.4387,
746
+ "step": 104
747
+ },
748
+ {
749
+ "epoch": 0.22913256955810146,
750
+ "grad_norm": 0.6960924863815308,
751
+ "learning_rate": 1.9918147461398796e-05,
752
+ "loss": 0.4472,
753
+ "step": 105
754
+ },
755
+ {
756
+ "epoch": 0.23131478450627388,
757
+ "grad_norm": 1.2546156644821167,
758
+ "learning_rate": 1.9915092152787888e-05,
759
+ "loss": 0.7705,
760
+ "step": 106
761
+ },
762
+ {
763
+ "epoch": 0.23349699945444627,
764
+ "grad_norm": 0.634672999382019,
765
+ "learning_rate": 1.991198110448809e-05,
766
+ "loss": 0.3372,
767
+ "step": 107
768
+ },
769
+ {
770
+ "epoch": 0.23567921440261866,
771
+ "grad_norm": 0.6426758170127869,
772
+ "learning_rate": 1.9908814333988794e-05,
773
+ "loss": 0.4316,
774
+ "step": 108
775
+ },
776
+ {
777
+ "epoch": 0.23786142935079105,
778
+ "grad_norm": 0.6639129519462585,
779
+ "learning_rate": 1.990559185909263e-05,
780
+ "loss": 0.3664,
781
+ "step": 109
782
+ },
783
+ {
784
+ "epoch": 0.24004364429896344,
785
+ "grad_norm": 1.1192857027053833,
786
+ "learning_rate": 1.9902313697915395e-05,
787
+ "loss": 0.6416,
788
+ "step": 110
789
+ },
790
+ {
791
+ "epoch": 0.24222585924713586,
792
+ "grad_norm": 0.8382490277290344,
793
+ "learning_rate": 1.9898979868885933e-05,
794
+ "loss": 0.6472,
795
+ "step": 111
796
+ },
797
+ {
798
+ "epoch": 0.24440807419530824,
799
+ "grad_norm": 0.6984851360321045,
800
+ "learning_rate": 1.989559039074603e-05,
801
+ "loss": 0.403,
802
+ "step": 112
803
+ },
804
+ {
805
+ "epoch": 0.24659028914348063,
806
+ "grad_norm": 0.6598736047744751,
807
+ "learning_rate": 1.989214528255033e-05,
808
+ "loss": 0.4084,
809
+ "step": 113
810
+ },
811
+ {
812
+ "epoch": 0.24877250409165302,
813
+ "grad_norm": 0.7741075158119202,
814
+ "learning_rate": 1.9888644563666194e-05,
815
+ "loss": 0.3484,
816
+ "step": 114
817
+ },
818
+ {
819
+ "epoch": 0.2509547190398254,
820
+ "grad_norm": 0.705927848815918,
821
+ "learning_rate": 1.9885088253773623e-05,
822
+ "loss": 0.5471,
823
+ "step": 115
824
+ },
825
+ {
826
+ "epoch": 0.2531369339879978,
827
+ "grad_norm": 0.7205896973609924,
828
+ "learning_rate": 1.988147637286513e-05,
829
+ "loss": 0.4697,
830
+ "step": 116
831
+ },
832
+ {
833
+ "epoch": 0.2553191489361702,
834
+ "grad_norm": 0.6812205910682678,
835
+ "learning_rate": 1.987780894124563e-05,
836
+ "loss": 0.4276,
837
+ "step": 117
838
+ },
839
+ {
840
+ "epoch": 0.2575013638843426,
841
+ "grad_norm": 0.774861216545105,
842
+ "learning_rate": 1.987408597953233e-05,
843
+ "loss": 0.3648,
844
+ "step": 118
845
+ },
846
+ {
847
+ "epoch": 0.259683578832515,
848
+ "grad_norm": 0.7321362495422363,
849
+ "learning_rate": 1.987030750865461e-05,
850
+ "loss": 0.443,
851
+ "step": 119
852
+ },
853
+ {
854
+ "epoch": 0.2618657937806874,
855
+ "grad_norm": 0.847510039806366,
856
+ "learning_rate": 1.9866473549853904e-05,
857
+ "loss": 0.4152,
858
+ "step": 120
859
+ },
860
+ {
861
+ "epoch": 0.2640480087288598,
862
+ "grad_norm": 0.7177504897117615,
863
+ "learning_rate": 1.9862584124683587e-05,
864
+ "loss": 0.3436,
865
+ "step": 121
866
+ },
867
+ {
868
+ "epoch": 0.2662302236770322,
869
+ "grad_norm": 0.8176891207695007,
870
+ "learning_rate": 1.9858639255008844e-05,
871
+ "loss": 0.4013,
872
+ "step": 122
873
+ },
874
+ {
875
+ "epoch": 0.2684124386252046,
876
+ "grad_norm": 0.785882830619812,
877
+ "learning_rate": 1.9854638963006552e-05,
878
+ "loss": 0.2927,
879
+ "step": 123
880
+ },
881
+ {
882
+ "epoch": 0.270594653573377,
883
+ "grad_norm": 0.697388768196106,
884
+ "learning_rate": 1.9850583271165166e-05,
885
+ "loss": 0.3406,
886
+ "step": 124
887
+ },
888
+ {
889
+ "epoch": 0.27277686852154936,
890
+ "grad_norm": 0.6818001866340637,
891
+ "learning_rate": 1.9846472202284574e-05,
892
+ "loss": 0.4685,
893
+ "step": 125
894
+ },
895
+ {
896
+ "epoch": 0.27495908346972175,
897
+ "grad_norm": 0.7736262679100037,
898
+ "learning_rate": 1.984230577947597e-05,
899
+ "loss": 0.4724,
900
+ "step": 126
901
+ },
902
+ {
903
+ "epoch": 0.27714129841789414,
904
+ "grad_norm": 0.6667208671569824,
905
+ "learning_rate": 1.9838084026161746e-05,
906
+ "loss": 0.2187,
907
+ "step": 127
908
+ },
909
+ {
910
+ "epoch": 0.27932351336606653,
911
+ "grad_norm": 0.9545671343803406,
912
+ "learning_rate": 1.9833806966075343e-05,
913
+ "loss": 0.5534,
914
+ "step": 128
915
+ },
916
+ {
917
+ "epoch": 0.281505728314239,
918
+ "grad_norm": 0.8926610946655273,
919
+ "learning_rate": 1.9829474623261106e-05,
920
+ "loss": 0.3542,
921
+ "step": 129
922
+ },
923
+ {
924
+ "epoch": 0.28368794326241137,
925
+ "grad_norm": 0.8170763850212097,
926
+ "learning_rate": 1.9825087022074182e-05,
927
+ "loss": 0.37,
928
+ "step": 130
929
+ },
930
+ {
931
+ "epoch": 0.28587015821058376,
932
+ "grad_norm": 0.7550498843193054,
933
+ "learning_rate": 1.9820644187180354e-05,
934
+ "loss": 0.4051,
935
+ "step": 131
936
+ },
937
+ {
938
+ "epoch": 0.28805237315875615,
939
+ "grad_norm": 1.2304673194885254,
940
+ "learning_rate": 1.981614614355591e-05,
941
+ "loss": 0.4746,
942
+ "step": 132
943
+ },
944
+ {
945
+ "epoch": 0.29023458810692854,
946
+ "grad_norm": 1.0370253324508667,
947
+ "learning_rate": 1.981159291648751e-05,
948
+ "loss": 0.5431,
949
+ "step": 133
950
+ },
951
+ {
952
+ "epoch": 0.2924168030551009,
953
+ "grad_norm": 0.9382657408714294,
954
+ "learning_rate": 1.9806984531572038e-05,
955
+ "loss": 0.4667,
956
+ "step": 134
957
+ },
958
+ {
959
+ "epoch": 0.2945990180032733,
960
+ "grad_norm": 0.9219065308570862,
961
+ "learning_rate": 1.9802321014716465e-05,
962
+ "loss": 0.4035,
963
+ "step": 135
964
+ },
965
+ {
966
+ "epoch": 0.2967812329514457,
967
+ "grad_norm": 0.9711424708366394,
968
+ "learning_rate": 1.9797602392137678e-05,
969
+ "loss": 0.427,
970
+ "step": 136
971
+ },
972
+ {
973
+ "epoch": 0.2989634478996181,
974
+ "grad_norm": 0.8940355181694031,
975
+ "learning_rate": 1.9792828690362377e-05,
976
+ "loss": 0.3718,
977
+ "step": 137
978
+ },
979
+ {
980
+ "epoch": 0.3011456628477905,
981
+ "grad_norm": 0.8118104934692383,
982
+ "learning_rate": 1.9787999936226877e-05,
983
+ "loss": 0.2609,
984
+ "step": 138
985
+ },
986
+ {
987
+ "epoch": 0.3033278777959629,
988
+ "grad_norm": 0.8110172152519226,
989
+ "learning_rate": 1.9783116156877008e-05,
990
+ "loss": 0.3901,
991
+ "step": 139
992
+ },
993
+ {
994
+ "epoch": 0.3055100927441353,
995
+ "grad_norm": 0.8195408582687378,
996
+ "learning_rate": 1.9778177379767903e-05,
997
+ "loss": 0.3611,
998
+ "step": 140
999
+ },
1000
+ {
1001
+ "epoch": 0.3076923076923077,
1002
+ "grad_norm": 1.0430301427841187,
1003
+ "learning_rate": 1.9773183632663907e-05,
1004
+ "loss": 0.4232,
1005
+ "step": 141
1006
+ },
1007
+ {
1008
+ "epoch": 0.3098745226404801,
1009
+ "grad_norm": 1.0248348712921143,
1010
+ "learning_rate": 1.9768134943638367e-05,
1011
+ "loss": 0.4167,
1012
+ "step": 142
1013
+ },
1014
+ {
1015
+ "epoch": 0.3120567375886525,
1016
+ "grad_norm": 0.7270126342773438,
1017
+ "learning_rate": 1.9763031341073512e-05,
1018
+ "loss": 0.2579,
1019
+ "step": 143
1020
+ },
1021
+ {
1022
+ "epoch": 0.3142389525368249,
1023
+ "grad_norm": 1.1630446910858154,
1024
+ "learning_rate": 1.9757872853660265e-05,
1025
+ "loss": 0.5389,
1026
+ "step": 144
1027
+ },
1028
+ {
1029
+ "epoch": 0.31642116748499727,
1030
+ "grad_norm": 0.8725171089172363,
1031
+ "learning_rate": 1.975265951039811e-05,
1032
+ "loss": 0.3441,
1033
+ "step": 145
1034
+ },
1035
+ {
1036
+ "epoch": 0.31860338243316966,
1037
+ "grad_norm": 1.4248993396759033,
1038
+ "learning_rate": 1.97473913405949e-05,
1039
+ "loss": 0.5818,
1040
+ "step": 146
1041
+ },
1042
+ {
1043
+ "epoch": 0.32078559738134205,
1044
+ "grad_norm": 1.2512569427490234,
1045
+ "learning_rate": 1.974206837386672e-05,
1046
+ "loss": 0.4038,
1047
+ "step": 147
1048
+ },
1049
+ {
1050
+ "epoch": 0.32296781232951444,
1051
+ "grad_norm": 1.2032068967819214,
1052
+ "learning_rate": 1.9736690640137696e-05,
1053
+ "loss": 0.4594,
1054
+ "step": 148
1055
+ },
1056
+ {
1057
+ "epoch": 0.3251500272776868,
1058
+ "grad_norm": 0.8411722183227539,
1059
+ "learning_rate": 1.9731258169639846e-05,
1060
+ "loss": 0.3345,
1061
+ "step": 149
1062
+ },
1063
+ {
1064
+ "epoch": 0.32733224222585927,
1065
+ "grad_norm": 1.008543848991394,
1066
+ "learning_rate": 1.9725770992912893e-05,
1067
+ "loss": 0.3777,
1068
+ "step": 150
1069
+ },
1070
+ {
1071
+ "epoch": 0.32951445717403166,
1072
+ "grad_norm": 1.0348095893859863,
1073
+ "learning_rate": 1.972022914080411e-05,
1074
+ "loss": 0.4853,
1075
+ "step": 151
1076
+ },
1077
+ {
1078
+ "epoch": 0.33169667212220405,
1079
+ "grad_norm": 0.9160374999046326,
1080
+ "learning_rate": 1.9714632644468135e-05,
1081
+ "loss": 0.3965,
1082
+ "step": 152
1083
+ },
1084
+ {
1085
+ "epoch": 0.33387888707037644,
1086
+ "grad_norm": 1.0338672399520874,
1087
+ "learning_rate": 1.9708981535366797e-05,
1088
+ "loss": 0.3135,
1089
+ "step": 153
1090
+ },
1091
+ {
1092
+ "epoch": 0.33606110201854883,
1093
+ "grad_norm": 1.1491649150848389,
1094
+ "learning_rate": 1.970327584526895e-05,
1095
+ "loss": 0.4182,
1096
+ "step": 154
1097
+ },
1098
+ {
1099
+ "epoch": 0.3382433169667212,
1100
+ "grad_norm": 1.494714617729187,
1101
+ "learning_rate": 1.9697515606250276e-05,
1102
+ "loss": 0.4977,
1103
+ "step": 155
1104
+ },
1105
+ {
1106
+ "epoch": 0.3404255319148936,
1107
+ "grad_norm": 1.0470036268234253,
1108
+ "learning_rate": 1.9691700850693126e-05,
1109
+ "loss": 0.3763,
1110
+ "step": 156
1111
+ },
1112
+ {
1113
+ "epoch": 0.342607746863066,
1114
+ "grad_norm": 1.1883833408355713,
1115
+ "learning_rate": 1.9685831611286312e-05,
1116
+ "loss": 0.3776,
1117
+ "step": 157
1118
+ },
1119
+ {
1120
+ "epoch": 0.3447899618112384,
1121
+ "grad_norm": 1.0385247468948364,
1122
+ "learning_rate": 1.967990792102495e-05,
1123
+ "loss": 0.3593,
1124
+ "step": 158
1125
+ },
1126
+ {
1127
+ "epoch": 0.3469721767594108,
1128
+ "grad_norm": 0.9821687340736389,
1129
+ "learning_rate": 1.9673929813210265e-05,
1130
+ "loss": 0.447,
1131
+ "step": 159
1132
+ },
1133
+ {
1134
+ "epoch": 0.3491543917075832,
1135
+ "grad_norm": 1.0155584812164307,
1136
+ "learning_rate": 1.9667897321449387e-05,
1137
+ "loss": 0.3818,
1138
+ "step": 160
1139
+ },
1140
+ {
1141
+ "epoch": 0.3513366066557556,
1142
+ "grad_norm": 1.146998405456543,
1143
+ "learning_rate": 1.9661810479655184e-05,
1144
+ "loss": 0.4201,
1145
+ "step": 161
1146
+ },
1147
+ {
1148
+ "epoch": 0.353518821603928,
1149
+ "grad_norm": 1.3749990463256836,
1150
+ "learning_rate": 1.9655669322046068e-05,
1151
+ "loss": 0.3451,
1152
+ "step": 162
1153
+ },
1154
+ {
1155
+ "epoch": 0.3557010365521004,
1156
+ "grad_norm": 1.7536747455596924,
1157
+ "learning_rate": 1.9649473883145792e-05,
1158
+ "loss": 0.4524,
1159
+ "step": 163
1160
+ },
1161
+ {
1162
+ "epoch": 0.3578832515002728,
1163
+ "grad_norm": 1.5470932722091675,
1164
+ "learning_rate": 1.9643224197783265e-05,
1165
+ "loss": 0.5467,
1166
+ "step": 164
1167
+ },
1168
+ {
1169
+ "epoch": 0.36006546644844517,
1170
+ "grad_norm": 0.9227492213249207,
1171
+ "learning_rate": 1.9636920301092352e-05,
1172
+ "loss": 0.2745,
1173
+ "step": 165
1174
+ },
1175
+ {
1176
+ "epoch": 0.36224768139661756,
1177
+ "grad_norm": 1.2530218362808228,
1178
+ "learning_rate": 1.9630562228511682e-05,
1179
+ "loss": 0.5124,
1180
+ "step": 166
1181
+ },
1182
+ {
1183
+ "epoch": 0.36442989634478995,
1184
+ "grad_norm": 1.3264926671981812,
1185
+ "learning_rate": 1.962415001578444e-05,
1186
+ "loss": 0.4022,
1187
+ "step": 167
1188
+ },
1189
+ {
1190
+ "epoch": 0.36661211129296234,
1191
+ "grad_norm": 1.3500545024871826,
1192
+ "learning_rate": 1.9617683698958168e-05,
1193
+ "loss": 0.3885,
1194
+ "step": 168
1195
+ },
1196
+ {
1197
+ "epoch": 0.36879432624113473,
1198
+ "grad_norm": 1.1173303127288818,
1199
+ "learning_rate": 1.9611163314384574e-05,
1200
+ "loss": 0.3948,
1201
+ "step": 169
1202
+ },
1203
+ {
1204
+ "epoch": 0.3709765411893072,
1205
+ "grad_norm": 0.9746338725090027,
1206
+ "learning_rate": 1.9604588898719314e-05,
1207
+ "loss": 0.3872,
1208
+ "step": 170
1209
+ },
1210
+ {
1211
+ "epoch": 0.37315875613747956,
1212
+ "grad_norm": 0.9952365756034851,
1213
+ "learning_rate": 1.9597960488921785e-05,
1214
+ "loss": 0.2785,
1215
+ "step": 171
1216
+ },
1217
+ {
1218
+ "epoch": 0.37534097108565195,
1219
+ "grad_norm": 1.2752764225006104,
1220
+ "learning_rate": 1.9591278122254938e-05,
1221
+ "loss": 0.3341,
1222
+ "step": 172
1223
+ },
1224
+ {
1225
+ "epoch": 0.37752318603382434,
1226
+ "grad_norm": 1.0955722332000732,
1227
+ "learning_rate": 1.9584541836285035e-05,
1228
+ "loss": 0.3497,
1229
+ "step": 173
1230
+ },
1231
+ {
1232
+ "epoch": 0.37970540098199673,
1233
+ "grad_norm": 1.093616008758545,
1234
+ "learning_rate": 1.957775166888147e-05,
1235
+ "loss": 0.2703,
1236
+ "step": 174
1237
+ },
1238
+ {
1239
+ "epoch": 0.3818876159301691,
1240
+ "grad_norm": 1.205116629600525,
1241
+ "learning_rate": 1.957090765821654e-05,
1242
+ "loss": 0.3353,
1243
+ "step": 175
1244
+ },
1245
+ {
1246
+ "epoch": 0.3840698308783415,
1247
+ "grad_norm": 1.2280943393707275,
1248
+ "learning_rate": 1.9564009842765225e-05,
1249
+ "loss": 0.464,
1250
+ "step": 176
1251
+ },
1252
+ {
1253
+ "epoch": 0.3862520458265139,
1254
+ "grad_norm": 1.1583482027053833,
1255
+ "learning_rate": 1.955705826130499e-05,
1256
+ "loss": 0.1943,
1257
+ "step": 177
1258
+ },
1259
+ {
1260
+ "epoch": 0.3884342607746863,
1261
+ "grad_norm": 1.1244933605194092,
1262
+ "learning_rate": 1.9550052952915545e-05,
1263
+ "loss": 0.3303,
1264
+ "step": 178
1265
+ },
1266
+ {
1267
+ "epoch": 0.3906164757228587,
1268
+ "grad_norm": 1.328026533126831,
1269
+ "learning_rate": 1.9542993956978647e-05,
1270
+ "loss": 0.3624,
1271
+ "step": 179
1272
+ },
1273
+ {
1274
+ "epoch": 0.39279869067103107,
1275
+ "grad_norm": 1.142669916152954,
1276
+ "learning_rate": 1.9535881313177864e-05,
1277
+ "loss": 0.4521,
1278
+ "step": 180
1279
+ },
1280
+ {
1281
+ "epoch": 0.3949809056192035,
1282
+ "grad_norm": 1.34759521484375,
1283
+ "learning_rate": 1.9528715061498355e-05,
1284
+ "loss": 0.4105,
1285
+ "step": 181
1286
+ },
1287
+ {
1288
+ "epoch": 0.3971631205673759,
1289
+ "grad_norm": 0.8993829488754272,
1290
+ "learning_rate": 1.9521495242226648e-05,
1291
+ "loss": 0.365,
1292
+ "step": 182
1293
+ },
1294
+ {
1295
+ "epoch": 0.3993453355155483,
1296
+ "grad_norm": 1.045101284980774,
1297
+ "learning_rate": 1.9514221895950416e-05,
1298
+ "loss": 0.3752,
1299
+ "step": 183
1300
+ },
1301
+ {
1302
+ "epoch": 0.4015275504637207,
1303
+ "grad_norm": 1.0296684503555298,
1304
+ "learning_rate": 1.950689506355824e-05,
1305
+ "loss": 0.2618,
1306
+ "step": 184
1307
+ },
1308
+ {
1309
+ "epoch": 0.4037097654118931,
1310
+ "grad_norm": 1.1462877988815308,
1311
+ "learning_rate": 1.949951478623938e-05,
1312
+ "loss": 0.3225,
1313
+ "step": 185
1314
+ },
1315
+ {
1316
+ "epoch": 0.40589198036006546,
1317
+ "grad_norm": 1.2176220417022705,
1318
+ "learning_rate": 1.949208110548356e-05,
1319
+ "loss": 0.307,
1320
+ "step": 186
1321
+ },
1322
+ {
1323
+ "epoch": 0.40807419530823785,
1324
+ "grad_norm": 1.1352124214172363,
1325
+ "learning_rate": 1.948459406308071e-05,
1326
+ "loss": 0.3668,
1327
+ "step": 187
1328
+ },
1329
+ {
1330
+ "epoch": 0.41025641025641024,
1331
+ "grad_norm": 1.4213913679122925,
1332
+ "learning_rate": 1.9477053701120746e-05,
1333
+ "loss": 0.4662,
1334
+ "step": 188
1335
+ },
1336
+ {
1337
+ "epoch": 0.41243862520458263,
1338
+ "grad_norm": 1.2231138944625854,
1339
+ "learning_rate": 1.9469460061993336e-05,
1340
+ "loss": 0.3893,
1341
+ "step": 189
1342
+ },
1343
+ {
1344
+ "epoch": 0.414620840152755,
1345
+ "grad_norm": 1.3416531085968018,
1346
+ "learning_rate": 1.9461813188387652e-05,
1347
+ "loss": 0.4218,
1348
+ "step": 190
1349
+ },
1350
+ {
1351
+ "epoch": 0.41680305510092747,
1352
+ "grad_norm": 1.2881159782409668,
1353
+ "learning_rate": 1.9454113123292133e-05,
1354
+ "loss": 0.3376,
1355
+ "step": 191
1356
+ },
1357
+ {
1358
+ "epoch": 0.41898527004909986,
1359
+ "grad_norm": 1.5161348581314087,
1360
+ "learning_rate": 1.9446359909994253e-05,
1361
+ "loss": 0.3796,
1362
+ "step": 192
1363
+ },
1364
+ {
1365
+ "epoch": 0.42116748499727225,
1366
+ "grad_norm": 1.3906810283660889,
1367
+ "learning_rate": 1.9438553592080257e-05,
1368
+ "loss": 0.2375,
1369
+ "step": 193
1370
+ },
1371
+ {
1372
+ "epoch": 0.42334969994544464,
1373
+ "grad_norm": 1.2929737567901611,
1374
+ "learning_rate": 1.9430694213434936e-05,
1375
+ "loss": 0.3133,
1376
+ "step": 194
1377
+ },
1378
+ {
1379
+ "epoch": 0.425531914893617,
1380
+ "grad_norm": 1.113404631614685,
1381
+ "learning_rate": 1.942278181824137e-05,
1382
+ "loss": 0.1978,
1383
+ "step": 195
1384
+ },
1385
+ {
1386
+ "epoch": 0.4277141298417894,
1387
+ "grad_norm": 0.9426998496055603,
1388
+ "learning_rate": 1.9414816450980686e-05,
1389
+ "loss": 0.3381,
1390
+ "step": 196
1391
+ },
1392
+ {
1393
+ "epoch": 0.4298963447899618,
1394
+ "grad_norm": 1.4274523258209229,
1395
+ "learning_rate": 1.94067981564318e-05,
1396
+ "loss": 0.2779,
1397
+ "step": 197
1398
+ },
1399
+ {
1400
+ "epoch": 0.4320785597381342,
1401
+ "grad_norm": 1.493589162826538,
1402
+ "learning_rate": 1.9398726979671174e-05,
1403
+ "loss": 0.2695,
1404
+ "step": 198
1405
+ },
1406
+ {
1407
+ "epoch": 0.4342607746863066,
1408
+ "grad_norm": 1.3514424562454224,
1409
+ "learning_rate": 1.9390602966072548e-05,
1410
+ "loss": 0.3338,
1411
+ "step": 199
1412
+ },
1413
+ {
1414
+ "epoch": 0.436442989634479,
1415
+ "grad_norm": 1.7675963640213013,
1416
+ "learning_rate": 1.9382426161306712e-05,
1417
+ "loss": 0.3629,
1418
+ "step": 200
1419
+ },
1420
+ {
1421
+ "epoch": 0.4386252045826514,
1422
+ "grad_norm": 1.0754345655441284,
1423
+ "learning_rate": 1.9374196611341212e-05,
1424
+ "loss": 0.322,
1425
+ "step": 201
1426
+ },
1427
+ {
1428
+ "epoch": 0.4408074195308238,
1429
+ "grad_norm": 1.1144013404846191,
1430
+ "learning_rate": 1.9365914362440125e-05,
1431
+ "loss": 0.2,
1432
+ "step": 202
1433
+ },
1434
+ {
1435
+ "epoch": 0.4429896344789962,
1436
+ "grad_norm": 1.3349831104278564,
1437
+ "learning_rate": 1.9357579461163783e-05,
1438
+ "loss": 0.2963,
1439
+ "step": 203
1440
+ },
1441
+ {
1442
+ "epoch": 0.4451718494271686,
1443
+ "grad_norm": 1.3588327169418335,
1444
+ "learning_rate": 1.9349191954368515e-05,
1445
+ "loss": 0.3544,
1446
+ "step": 204
1447
+ },
1448
+ {
1449
+ "epoch": 0.447354064375341,
1450
+ "grad_norm": 1.5795652866363525,
1451
+ "learning_rate": 1.9340751889206378e-05,
1452
+ "loss": 0.3851,
1453
+ "step": 205
1454
+ },
1455
+ {
1456
+ "epoch": 0.44953627932351337,
1457
+ "grad_norm": 1.3659369945526123,
1458
+ "learning_rate": 1.93322593131249e-05,
1459
+ "loss": 0.2808,
1460
+ "step": 206
1461
+ },
1462
+ {
1463
+ "epoch": 0.45171849427168576,
1464
+ "grad_norm": 1.5584542751312256,
1465
+ "learning_rate": 1.932371427386681e-05,
1466
+ "loss": 0.2838,
1467
+ "step": 207
1468
+ },
1469
+ {
1470
+ "epoch": 0.45390070921985815,
1471
+ "grad_norm": 1.3657653331756592,
1472
+ "learning_rate": 1.931511681946977e-05,
1473
+ "loss": 0.3128,
1474
+ "step": 208
1475
+ },
1476
+ {
1477
+ "epoch": 0.45608292416803053,
1478
+ "grad_norm": 1.8486205339431763,
1479
+ "learning_rate": 1.9306466998266102e-05,
1480
+ "loss": 0.3635,
1481
+ "step": 209
1482
+ },
1483
+ {
1484
+ "epoch": 0.4582651391162029,
1485
+ "grad_norm": 1.8429385423660278,
1486
+ "learning_rate": 1.9297764858882516e-05,
1487
+ "loss": 0.3445,
1488
+ "step": 210
1489
+ },
1490
+ {
1491
+ "epoch": 0.4604473540643753,
1492
+ "grad_norm": 1.359290361404419,
1493
+ "learning_rate": 1.9289010450239843e-05,
1494
+ "loss": 0.2864,
1495
+ "step": 211
1496
+ },
1497
+ {
1498
+ "epoch": 0.46262956901254776,
1499
+ "grad_norm": 1.2047313451766968,
1500
+ "learning_rate": 1.928020382155276e-05,
1501
+ "loss": 0.3323,
1502
+ "step": 212
1503
+ },
1504
+ {
1505
+ "epoch": 0.46481178396072015,
1506
+ "grad_norm": 1.4549658298492432,
1507
+ "learning_rate": 1.9271345022329502e-05,
1508
+ "loss": 0.3763,
1509
+ "step": 213
1510
+ },
1511
+ {
1512
+ "epoch": 0.46699399890889254,
1513
+ "grad_norm": 1.3349789381027222,
1514
+ "learning_rate": 1.9262434102371596e-05,
1515
+ "loss": 0.405,
1516
+ "step": 214
1517
+ },
1518
+ {
1519
+ "epoch": 0.4691762138570649,
1520
+ "grad_norm": 1.9315582513809204,
1521
+ "learning_rate": 1.9253471111773572e-05,
1522
+ "loss": 0.2949,
1523
+ "step": 215
1524
+ },
1525
+ {
1526
+ "epoch": 0.4713584288052373,
1527
+ "grad_norm": 1.1657265424728394,
1528
+ "learning_rate": 1.924445610092269e-05,
1529
+ "loss": 0.253,
1530
+ "step": 216
1531
+ },
1532
+ {
1533
+ "epoch": 0.4735406437534097,
1534
+ "grad_norm": 1.4558275938034058,
1535
+ "learning_rate": 1.9235389120498645e-05,
1536
+ "loss": 0.3077,
1537
+ "step": 217
1538
+ },
1539
+ {
1540
+ "epoch": 0.4757228587015821,
1541
+ "grad_norm": 1.4263584613800049,
1542
+ "learning_rate": 1.9226270221473302e-05,
1543
+ "loss": 0.3251,
1544
+ "step": 218
1545
+ },
1546
+ {
1547
+ "epoch": 0.4779050736497545,
1548
+ "grad_norm": 1.7486201524734497,
1549
+ "learning_rate": 1.921709945511039e-05,
1550
+ "loss": 0.2536,
1551
+ "step": 219
1552
+ },
1553
+ {
1554
+ "epoch": 0.4800872885979269,
1555
+ "grad_norm": 1.5430760383605957,
1556
+ "learning_rate": 1.9207876872965217e-05,
1557
+ "loss": 0.331,
1558
+ "step": 220
1559
+ },
1560
+ {
1561
+ "epoch": 0.48226950354609927,
1562
+ "grad_norm": 1.64284348487854,
1563
+ "learning_rate": 1.9198602526884388e-05,
1564
+ "loss": 0.3541,
1565
+ "step": 221
1566
+ },
1567
+ {
1568
+ "epoch": 0.4844517184942717,
1569
+ "grad_norm": 1.3553285598754883,
1570
+ "learning_rate": 1.9189276469005508e-05,
1571
+ "loss": 0.3196,
1572
+ "step": 222
1573
+ },
1574
+ {
1575
+ "epoch": 0.4866339334424441,
1576
+ "grad_norm": 1.4145045280456543,
1577
+ "learning_rate": 1.917989875175689e-05,
1578
+ "loss": 0.2487,
1579
+ "step": 223
1580
+ },
1581
+ {
1582
+ "epoch": 0.4888161483906165,
1583
+ "grad_norm": 1.3680609464645386,
1584
+ "learning_rate": 1.9170469427857264e-05,
1585
+ "loss": 0.3235,
1586
+ "step": 224
1587
+ },
1588
+ {
1589
+ "epoch": 0.4909983633387889,
1590
+ "grad_norm": 1.6969547271728516,
1591
+ "learning_rate": 1.9160988550315475e-05,
1592
+ "loss": 0.2292,
1593
+ "step": 225
1594
+ },
1595
+ {
1596
+ "epoch": 0.49318057828696127,
1597
+ "grad_norm": 1.4224244356155396,
1598
+ "learning_rate": 1.9151456172430186e-05,
1599
+ "loss": 0.2442,
1600
+ "step": 226
1601
+ },
1602
+ {
1603
+ "epoch": 0.49536279323513366,
1604
+ "grad_norm": 1.21607506275177,
1605
+ "learning_rate": 1.914187234778958e-05,
1606
+ "loss": 0.3315,
1607
+ "step": 227
1608
+ },
1609
+ {
1610
+ "epoch": 0.49754500818330605,
1611
+ "grad_norm": 1.3110462427139282,
1612
+ "learning_rate": 1.913223713027106e-05,
1613
+ "loss": 0.409,
1614
+ "step": 228
1615
+ },
1616
+ {
1617
+ "epoch": 0.49972722313147844,
1618
+ "grad_norm": 1.3133397102355957,
1619
+ "learning_rate": 1.9122550574040942e-05,
1620
+ "loss": 0.3491,
1621
+ "step": 229
1622
+ },
1623
+ {
1624
+ "epoch": 0.5019094380796508,
1625
+ "grad_norm": 1.2212580442428589,
1626
+ "learning_rate": 1.9112812733554155e-05,
1627
+ "loss": 0.2702,
1628
+ "step": 230
1629
+ },
1630
+ {
1631
+ "epoch": 0.5040916530278232,
1632
+ "grad_norm": 1.3722357749938965,
1633
+ "learning_rate": 1.910302366355393e-05,
1634
+ "loss": 0.3729,
1635
+ "step": 231
1636
+ },
1637
+ {
1638
+ "epoch": 0.5062738679759956,
1639
+ "grad_norm": 1.6117819547653198,
1640
+ "learning_rate": 1.90931834190715e-05,
1641
+ "loss": 0.3857,
1642
+ "step": 232
1643
+ },
1644
+ {
1645
+ "epoch": 0.508456082924168,
1646
+ "grad_norm": 1.6422029733657837,
1647
+ "learning_rate": 1.9083292055425783e-05,
1648
+ "loss": 0.4329,
1649
+ "step": 233
1650
+ },
1651
+ {
1652
+ "epoch": 0.5106382978723404,
1653
+ "grad_norm": 1.2110570669174194,
1654
+ "learning_rate": 1.907334962822307e-05,
1655
+ "loss": 0.3052,
1656
+ "step": 234
1657
+ },
1658
+ {
1659
+ "epoch": 0.5128205128205128,
1660
+ "grad_norm": 1.0881627798080444,
1661
+ "learning_rate": 1.906335619335672e-05,
1662
+ "loss": 0.2195,
1663
+ "step": 235
1664
+ },
1665
+ {
1666
+ "epoch": 0.5150027277686852,
1667
+ "grad_norm": 1.6490594148635864,
1668
+ "learning_rate": 1.9053311807006845e-05,
1669
+ "loss": 0.2015,
1670
+ "step": 236
1671
+ },
1672
+ {
1673
+ "epoch": 0.5171849427168577,
1674
+ "grad_norm": 1.5541980266571045,
1675
+ "learning_rate": 1.904321652563998e-05,
1676
+ "loss": 0.3576,
1677
+ "step": 237
1678
+ },
1679
+ {
1680
+ "epoch": 0.51936715766503,
1681
+ "grad_norm": 2.599008321762085,
1682
+ "learning_rate": 1.903307040600879e-05,
1683
+ "loss": 0.3018,
1684
+ "step": 238
1685
+ },
1686
+ {
1687
+ "epoch": 0.5215493726132024,
1688
+ "grad_norm": 1.2262473106384277,
1689
+ "learning_rate": 1.902287350515173e-05,
1690
+ "loss": 0.3705,
1691
+ "step": 239
1692
+ },
1693
+ {
1694
+ "epoch": 0.5237315875613748,
1695
+ "grad_norm": 1.2602461576461792,
1696
+ "learning_rate": 1.9012625880392733e-05,
1697
+ "loss": 0.2783,
1698
+ "step": 240
1699
+ },
1700
+ {
1701
+ "epoch": 0.5259138025095472,
1702
+ "grad_norm": 1.8364081382751465,
1703
+ "learning_rate": 1.900232758934089e-05,
1704
+ "loss": 0.3277,
1705
+ "step": 241
1706
+ },
1707
+ {
1708
+ "epoch": 0.5280960174577196,
1709
+ "grad_norm": 1.2885158061981201,
1710
+ "learning_rate": 1.899197868989011e-05,
1711
+ "loss": 0.3201,
1712
+ "step": 242
1713
+ },
1714
+ {
1715
+ "epoch": 0.530278232405892,
1716
+ "grad_norm": 1.391256332397461,
1717
+ "learning_rate": 1.898157924021883e-05,
1718
+ "loss": 0.3269,
1719
+ "step": 243
1720
+ },
1721
+ {
1722
+ "epoch": 0.5324604473540644,
1723
+ "grad_norm": 1.265567660331726,
1724
+ "learning_rate": 1.8971129298789644e-05,
1725
+ "loss": 0.2002,
1726
+ "step": 244
1727
+ },
1728
+ {
1729
+ "epoch": 0.5346426623022368,
1730
+ "grad_norm": 1.565754771232605,
1731
+ "learning_rate": 1.8960628924349006e-05,
1732
+ "loss": 0.3627,
1733
+ "step": 245
1734
+ },
1735
+ {
1736
+ "epoch": 0.5368248772504092,
1737
+ "grad_norm": 1.4450806379318237,
1738
+ "learning_rate": 1.8950078175926886e-05,
1739
+ "loss": 0.2806,
1740
+ "step": 246
1741
+ },
1742
+ {
1743
+ "epoch": 0.5390070921985816,
1744
+ "grad_norm": 1.5299197435379028,
1745
+ "learning_rate": 1.8939477112836445e-05,
1746
+ "loss": 0.3822,
1747
+ "step": 247
1748
+ },
1749
+ {
1750
+ "epoch": 0.541189307146754,
1751
+ "grad_norm": 2.0761196613311768,
1752
+ "learning_rate": 1.892882579467369e-05,
1753
+ "loss": 0.3204,
1754
+ "step": 248
1755
+ },
1756
+ {
1757
+ "epoch": 0.5433715220949263,
1758
+ "grad_norm": 1.6398018598556519,
1759
+ "learning_rate": 1.8918124281317162e-05,
1760
+ "loss": 0.2604,
1761
+ "step": 249
1762
+ },
1763
+ {
1764
+ "epoch": 0.5455537370430987,
1765
+ "grad_norm": 1.4368712902069092,
1766
+ "learning_rate": 1.8907372632927573e-05,
1767
+ "loss": 0.2421,
1768
+ "step": 250
1769
+ },
1770
+ {
1771
+ "epoch": 0.5477359519912711,
1772
+ "grad_norm": 1.2730286121368408,
1773
+ "learning_rate": 1.8896570909947477e-05,
1774
+ "loss": 0.2659,
1775
+ "step": 251
1776
+ },
1777
+ {
1778
+ "epoch": 0.5499181669394435,
1779
+ "grad_norm": 1.9445446729660034,
1780
+ "learning_rate": 1.8885719173100937e-05,
1781
+ "loss": 0.3552,
1782
+ "step": 252
1783
+ },
1784
+ {
1785
+ "epoch": 0.5521003818876159,
1786
+ "grad_norm": 1.2720203399658203,
1787
+ "learning_rate": 1.887481748339318e-05,
1788
+ "loss": 0.1519,
1789
+ "step": 253
1790
+ },
1791
+ {
1792
+ "epoch": 0.5542825968357883,
1793
+ "grad_norm": 1.6237303018569946,
1794
+ "learning_rate": 1.8863865902110253e-05,
1795
+ "loss": 0.3111,
1796
+ "step": 254
1797
+ },
1798
+ {
1799
+ "epoch": 0.5564648117839607,
1800
+ "grad_norm": 2.242192029953003,
1801
+ "learning_rate": 1.8852864490818678e-05,
1802
+ "loss": 0.2879,
1803
+ "step": 255
1804
+ },
1805
+ {
1806
+ "epoch": 0.5586470267321331,
1807
+ "grad_norm": 3.0388717651367188,
1808
+ "learning_rate": 1.8841813311365105e-05,
1809
+ "loss": 0.4525,
1810
+ "step": 256
1811
+ },
1812
+ {
1813
+ "epoch": 0.5608292416803055,
1814
+ "grad_norm": 1.7905107736587524,
1815
+ "learning_rate": 1.8830712425875964e-05,
1816
+ "loss": 0.3407,
1817
+ "step": 257
1818
+ },
1819
+ {
1820
+ "epoch": 0.563011456628478,
1821
+ "grad_norm": 2.1850087642669678,
1822
+ "learning_rate": 1.8819561896757124e-05,
1823
+ "loss": 0.3232,
1824
+ "step": 258
1825
+ },
1826
+ {
1827
+ "epoch": 0.5651936715766503,
1828
+ "grad_norm": 2.0054867267608643,
1829
+ "learning_rate": 1.8808361786693533e-05,
1830
+ "loss": 0.3558,
1831
+ "step": 259
1832
+ },
1833
+ {
1834
+ "epoch": 0.5673758865248227,
1835
+ "grad_norm": 2.004746675491333,
1836
+ "learning_rate": 1.879711215864886e-05,
1837
+ "loss": 0.2397,
1838
+ "step": 260
1839
+ },
1840
+ {
1841
+ "epoch": 0.5695581014729951,
1842
+ "grad_norm": 2.072324752807617,
1843
+ "learning_rate": 1.8785813075865164e-05,
1844
+ "loss": 0.1571,
1845
+ "step": 261
1846
+ },
1847
+ {
1848
+ "epoch": 0.5717403164211675,
1849
+ "grad_norm": 1.6970444917678833,
1850
+ "learning_rate": 1.877446460186251e-05,
1851
+ "loss": 0.2875,
1852
+ "step": 262
1853
+ },
1854
+ {
1855
+ "epoch": 0.5739225313693399,
1856
+ "grad_norm": 1.8173935413360596,
1857
+ "learning_rate": 1.8763066800438638e-05,
1858
+ "loss": 0.3473,
1859
+ "step": 263
1860
+ },
1861
+ {
1862
+ "epoch": 0.5761047463175123,
1863
+ "grad_norm": 1.4054244756698608,
1864
+ "learning_rate": 1.875161973566858e-05,
1865
+ "loss": 0.2878,
1866
+ "step": 264
1867
+ },
1868
+ {
1869
+ "epoch": 0.5782869612656847,
1870
+ "grad_norm": 1.1835930347442627,
1871
+ "learning_rate": 1.874012347190432e-05,
1872
+ "loss": 0.2728,
1873
+ "step": 265
1874
+ },
1875
+ {
1876
+ "epoch": 0.5804691762138571,
1877
+ "grad_norm": 1.64986252784729,
1878
+ "learning_rate": 1.8728578073774427e-05,
1879
+ "loss": 0.2887,
1880
+ "step": 266
1881
+ },
1882
+ {
1883
+ "epoch": 0.5826513911620295,
1884
+ "grad_norm": 1.8838175535202026,
1885
+ "learning_rate": 1.8716983606183673e-05,
1886
+ "loss": 0.3546,
1887
+ "step": 267
1888
+ },
1889
+ {
1890
+ "epoch": 0.5848336061102019,
1891
+ "grad_norm": 1.3140724897384644,
1892
+ "learning_rate": 1.87053401343127e-05,
1893
+ "loss": 0.2229,
1894
+ "step": 268
1895
+ },
1896
+ {
1897
+ "epoch": 0.5870158210583742,
1898
+ "grad_norm": 1.9315850734710693,
1899
+ "learning_rate": 1.8693647723617637e-05,
1900
+ "loss": 0.276,
1901
+ "step": 269
1902
+ },
1903
+ {
1904
+ "epoch": 0.5891980360065466,
1905
+ "grad_norm": 1.7035211324691772,
1906
+ "learning_rate": 1.8681906439829716e-05,
1907
+ "loss": 0.2677,
1908
+ "step": 270
1909
+ },
1910
+ {
1911
+ "epoch": 0.591380250954719,
1912
+ "grad_norm": 2.1659624576568604,
1913
+ "learning_rate": 1.8670116348954945e-05,
1914
+ "loss": 0.1785,
1915
+ "step": 271
1916
+ },
1917
+ {
1918
+ "epoch": 0.5935624659028914,
1919
+ "grad_norm": 1.514590859413147,
1920
+ "learning_rate": 1.865827751727368e-05,
1921
+ "loss": 0.2866,
1922
+ "step": 272
1923
+ },
1924
+ {
1925
+ "epoch": 0.5957446808510638,
1926
+ "grad_norm": 1.163939356803894,
1927
+ "learning_rate": 1.864639001134031e-05,
1928
+ "loss": 0.1527,
1929
+ "step": 273
1930
+ },
1931
+ {
1932
+ "epoch": 0.5979268957992362,
1933
+ "grad_norm": 1.9229791164398193,
1934
+ "learning_rate": 1.863445389798284e-05,
1935
+ "loss": 0.2854,
1936
+ "step": 274
1937
+ },
1938
+ {
1939
+ "epoch": 0.6001091107474086,
1940
+ "grad_norm": 1.6761242151260376,
1941
+ "learning_rate": 1.8622469244302542e-05,
1942
+ "loss": 0.3369,
1943
+ "step": 275
1944
+ },
1945
+ {
1946
+ "epoch": 0.602291325695581,
1947
+ "grad_norm": 1.756821632385254,
1948
+ "learning_rate": 1.8610436117673557e-05,
1949
+ "loss": 0.2876,
1950
+ "step": 276
1951
+ },
1952
+ {
1953
+ "epoch": 0.6044735406437534,
1954
+ "grad_norm": 1.683331847190857,
1955
+ "learning_rate": 1.8598354585742537e-05,
1956
+ "loss": 0.2549,
1957
+ "step": 277
1958
+ },
1959
+ {
1960
+ "epoch": 0.6066557555919257,
1961
+ "grad_norm": 1.3528157472610474,
1962
+ "learning_rate": 1.858622471642824e-05,
1963
+ "loss": 0.1952,
1964
+ "step": 278
1965
+ },
1966
+ {
1967
+ "epoch": 0.6088379705400983,
1968
+ "grad_norm": 1.5143969058990479,
1969
+ "learning_rate": 1.8574046577921182e-05,
1970
+ "loss": 0.2271,
1971
+ "step": 279
1972
+ },
1973
+ {
1974
+ "epoch": 0.6110201854882706,
1975
+ "grad_norm": 1.311161994934082,
1976
+ "learning_rate": 1.8561820238683216e-05,
1977
+ "loss": 0.2717,
1978
+ "step": 280
1979
+ },
1980
+ {
1981
+ "epoch": 0.613202400436443,
1982
+ "grad_norm": 1.728922724723816,
1983
+ "learning_rate": 1.8549545767447174e-05,
1984
+ "loss": 0.2746,
1985
+ "step": 281
1986
+ },
1987
+ {
1988
+ "epoch": 0.6153846153846154,
1989
+ "grad_norm": 2.3760488033294678,
1990
+ "learning_rate": 1.853722323321647e-05,
1991
+ "loss": 0.368,
1992
+ "step": 282
1993
+ },
1994
+ {
1995
+ "epoch": 0.6175668303327878,
1996
+ "grad_norm": 1.243605375289917,
1997
+ "learning_rate": 1.8524852705264716e-05,
1998
+ "loss": 0.313,
1999
+ "step": 283
2000
+ },
2001
+ {
2002
+ "epoch": 0.6197490452809602,
2003
+ "grad_norm": 1.5179970264434814,
2004
+ "learning_rate": 1.8512434253135324e-05,
2005
+ "loss": 0.3288,
2006
+ "step": 284
2007
+ },
2008
+ {
2009
+ "epoch": 0.6219312602291326,
2010
+ "grad_norm": 1.7583152055740356,
2011
+ "learning_rate": 1.8499967946641127e-05,
2012
+ "loss": 0.2581,
2013
+ "step": 285
2014
+ },
2015
+ {
2016
+ "epoch": 0.624113475177305,
2017
+ "grad_norm": 1.474806308746338,
2018
+ "learning_rate": 1.848745385586398e-05,
2019
+ "loss": 0.2277,
2020
+ "step": 286
2021
+ },
2022
+ {
2023
+ "epoch": 0.6262956901254774,
2024
+ "grad_norm": 2.0060956478118896,
2025
+ "learning_rate": 1.8474892051154366e-05,
2026
+ "loss": 0.2442,
2027
+ "step": 287
2028
+ },
2029
+ {
2030
+ "epoch": 0.6284779050736498,
2031
+ "grad_norm": 1.372650146484375,
2032
+ "learning_rate": 1.8462282603131005e-05,
2033
+ "loss": 0.238,
2034
+ "step": 288
2035
+ },
2036
+ {
2037
+ "epoch": 0.6306601200218221,
2038
+ "grad_norm": 1.8136199712753296,
2039
+ "learning_rate": 1.8449625582680445e-05,
2040
+ "loss": 0.3289,
2041
+ "step": 289
2042
+ },
2043
+ {
2044
+ "epoch": 0.6328423349699945,
2045
+ "grad_norm": 1.6018167734146118,
2046
+ "learning_rate": 1.843692106095668e-05,
2047
+ "loss": 0.2418,
2048
+ "step": 290
2049
+ },
2050
+ {
2051
+ "epoch": 0.6350245499181669,
2052
+ "grad_norm": 1.5912113189697266,
2053
+ "learning_rate": 1.842416910938074e-05,
2054
+ "loss": 0.2491,
2055
+ "step": 291
2056
+ },
2057
+ {
2058
+ "epoch": 0.6372067648663393,
2059
+ "grad_norm": 1.552306056022644,
2060
+ "learning_rate": 1.841136979964029e-05,
2061
+ "loss": 0.229,
2062
+ "step": 292
2063
+ },
2064
+ {
2065
+ "epoch": 0.6393889798145117,
2066
+ "grad_norm": 1.960476040840149,
2067
+ "learning_rate": 1.8398523203689235e-05,
2068
+ "loss": 0.3936,
2069
+ "step": 293
2070
+ },
2071
+ {
2072
+ "epoch": 0.6415711947626841,
2073
+ "grad_norm": 1.6437554359436035,
2074
+ "learning_rate": 1.8385629393747292e-05,
2075
+ "loss": 0.2372,
2076
+ "step": 294
2077
+ },
2078
+ {
2079
+ "epoch": 0.6437534097108565,
2080
+ "grad_norm": 1.9688218832015991,
2081
+ "learning_rate": 1.837268844229962e-05,
2082
+ "loss": 0.2557,
2083
+ "step": 295
2084
+ },
2085
+ {
2086
+ "epoch": 0.6459356246590289,
2087
+ "grad_norm": 1.8227428197860718,
2088
+ "learning_rate": 1.8359700422096385e-05,
2089
+ "loss": 0.3069,
2090
+ "step": 296
2091
+ },
2092
+ {
2093
+ "epoch": 0.6481178396072013,
2094
+ "grad_norm": 1.7406502962112427,
2095
+ "learning_rate": 1.8346665406152362e-05,
2096
+ "loss": 0.3527,
2097
+ "step": 297
2098
+ },
2099
+ {
2100
+ "epoch": 0.6503000545553737,
2101
+ "grad_norm": 1.6546075344085693,
2102
+ "learning_rate": 1.8333583467746515e-05,
2103
+ "loss": 0.2991,
2104
+ "step": 298
2105
+ },
2106
+ {
2107
+ "epoch": 0.6524822695035462,
2108
+ "grad_norm": 1.7377084493637085,
2109
+ "learning_rate": 1.83204546804216e-05,
2110
+ "loss": 0.2752,
2111
+ "step": 299
2112
+ },
2113
+ {
2114
+ "epoch": 0.6546644844517185,
2115
+ "grad_norm": 1.8209704160690308,
2116
+ "learning_rate": 1.8307279117983744e-05,
2117
+ "loss": 0.3455,
2118
+ "step": 300
2119
+ },
2120
+ {
2121
+ "epoch": 0.6568466993998909,
2122
+ "grad_norm": 1.4391992092132568,
2123
+ "learning_rate": 1.829405685450202e-05,
2124
+ "loss": 0.2037,
2125
+ "step": 301
2126
+ },
2127
+ {
2128
+ "epoch": 0.6590289143480633,
2129
+ "grad_norm": 1.7136852741241455,
2130
+ "learning_rate": 1.828078796430805e-05,
2131
+ "loss": 0.2731,
2132
+ "step": 302
2133
+ },
2134
+ {
2135
+ "epoch": 0.6612111292962357,
2136
+ "grad_norm": 1.6503560543060303,
2137
+ "learning_rate": 1.826747252199558e-05,
2138
+ "loss": 0.2998,
2139
+ "step": 303
2140
+ },
2141
+ {
2142
+ "epoch": 0.6633933442444081,
2143
+ "grad_norm": 1.778838872909546,
2144
+ "learning_rate": 1.8254110602420047e-05,
2145
+ "loss": 0.2556,
2146
+ "step": 304
2147
+ },
2148
+ {
2149
+ "epoch": 0.6655755591925805,
2150
+ "grad_norm": 1.5218554735183716,
2151
+ "learning_rate": 1.8240702280698176e-05,
2152
+ "loss": 0.2465,
2153
+ "step": 305
2154
+ },
2155
+ {
2156
+ "epoch": 0.6677577741407529,
2157
+ "grad_norm": 1.326884150505066,
2158
+ "learning_rate": 1.822724763220755e-05,
2159
+ "loss": 0.214,
2160
+ "step": 306
2161
+ },
2162
+ {
2163
+ "epoch": 0.6699399890889253,
2164
+ "grad_norm": 1.969869613647461,
2165
+ "learning_rate": 1.8213746732586186e-05,
2166
+ "loss": 0.2511,
2167
+ "step": 307
2168
+ },
2169
+ {
2170
+ "epoch": 0.6721222040370977,
2171
+ "grad_norm": 1.5750274658203125,
2172
+ "learning_rate": 1.8200199657732115e-05,
2173
+ "loss": 0.2821,
2174
+ "step": 308
2175
+ },
2176
+ {
2177
+ "epoch": 0.67430441898527,
2178
+ "grad_norm": 1.5090693235397339,
2179
+ "learning_rate": 1.8186606483802945e-05,
2180
+ "loss": 0.1838,
2181
+ "step": 309
2182
+ },
2183
+ {
2184
+ "epoch": 0.6764866339334424,
2185
+ "grad_norm": 1.4013510942459106,
2186
+ "learning_rate": 1.817296728721545e-05,
2187
+ "loss": 0.2353,
2188
+ "step": 310
2189
+ },
2190
+ {
2191
+ "epoch": 0.6786688488816148,
2192
+ "grad_norm": 1.4008636474609375,
2193
+ "learning_rate": 1.815928214464511e-05,
2194
+ "loss": 0.2296,
2195
+ "step": 311
2196
+ },
2197
+ {
2198
+ "epoch": 0.6808510638297872,
2199
+ "grad_norm": 2.5458900928497314,
2200
+ "learning_rate": 1.814555113302573e-05,
2201
+ "loss": 0.3881,
2202
+ "step": 312
2203
+ },
2204
+ {
2205
+ "epoch": 0.6830332787779596,
2206
+ "grad_norm": 1.3896178007125854,
2207
+ "learning_rate": 1.813177432954894e-05,
2208
+ "loss": 0.2354,
2209
+ "step": 313
2210
+ },
2211
+ {
2212
+ "epoch": 0.685215493726132,
2213
+ "grad_norm": 1.6341583728790283,
2214
+ "learning_rate": 1.811795181166383e-05,
2215
+ "loss": 0.268,
2216
+ "step": 314
2217
+ },
2218
+ {
2219
+ "epoch": 0.6873977086743044,
2220
+ "grad_norm": 1.7440088987350464,
2221
+ "learning_rate": 1.8104083657076466e-05,
2222
+ "loss": 0.2788,
2223
+ "step": 315
2224
+ },
2225
+ {
2226
+ "epoch": 0.6895799236224768,
2227
+ "grad_norm": 2.507354497909546,
2228
+ "learning_rate": 1.8090169943749477e-05,
2229
+ "loss": 0.3692,
2230
+ "step": 316
2231
+ },
2232
+ {
2233
+ "epoch": 0.6917621385706492,
2234
+ "grad_norm": 1.8427482843399048,
2235
+ "learning_rate": 1.80762107499016e-05,
2236
+ "loss": 0.213,
2237
+ "step": 317
2238
+ },
2239
+ {
2240
+ "epoch": 0.6939443535188216,
2241
+ "grad_norm": 1.5794975757598877,
2242
+ "learning_rate": 1.8062206154007267e-05,
2243
+ "loss": 0.2771,
2244
+ "step": 318
2245
+ },
2246
+ {
2247
+ "epoch": 0.696126568466994,
2248
+ "grad_norm": 2.8045501708984375,
2249
+ "learning_rate": 1.8048156234796124e-05,
2250
+ "loss": 0.1448,
2251
+ "step": 319
2252
+ },
2253
+ {
2254
+ "epoch": 0.6983087834151664,
2255
+ "grad_norm": 3.0969858169555664,
2256
+ "learning_rate": 1.8034061071252632e-05,
2257
+ "loss": 0.312,
2258
+ "step": 320
2259
+ },
2260
+ {
2261
+ "epoch": 0.7004909983633388,
2262
+ "grad_norm": 2.205915689468384,
2263
+ "learning_rate": 1.8019920742615596e-05,
2264
+ "loss": 0.3327,
2265
+ "step": 321
2266
+ },
2267
+ {
2268
+ "epoch": 0.7026732133115112,
2269
+ "grad_norm": 1.9107706546783447,
2270
+ "learning_rate": 1.8005735328377718e-05,
2271
+ "loss": 0.2814,
2272
+ "step": 322
2273
+ },
2274
+ {
2275
+ "epoch": 0.7048554282596836,
2276
+ "grad_norm": 1.5513135194778442,
2277
+ "learning_rate": 1.7991504908285162e-05,
2278
+ "loss": 0.2538,
2279
+ "step": 323
2280
+ },
2281
+ {
2282
+ "epoch": 0.707037643207856,
2283
+ "grad_norm": 2.1072094440460205,
2284
+ "learning_rate": 1.7977229562337104e-05,
2285
+ "loss": 0.296,
2286
+ "step": 324
2287
+ },
2288
+ {
2289
+ "epoch": 0.7092198581560284,
2290
+ "grad_norm": 1.547297716140747,
2291
+ "learning_rate": 1.7962909370785283e-05,
2292
+ "loss": 0.2716,
2293
+ "step": 325
2294
+ },
2295
+ {
2296
+ "epoch": 0.7114020731042008,
2297
+ "grad_norm": 1.8487380743026733,
2298
+ "learning_rate": 1.7948544414133534e-05,
2299
+ "loss": 0.2548,
2300
+ "step": 326
2301
+ },
2302
+ {
2303
+ "epoch": 0.7135842880523732,
2304
+ "grad_norm": 1.794865608215332,
2305
+ "learning_rate": 1.7934134773137364e-05,
2306
+ "loss": 0.2193,
2307
+ "step": 327
2308
+ },
2309
+ {
2310
+ "epoch": 0.7157665030005456,
2311
+ "grad_norm": 1.4590160846710205,
2312
+ "learning_rate": 1.7919680528803468e-05,
2313
+ "loss": 0.1581,
2314
+ "step": 328
2315
+ },
2316
+ {
2317
+ "epoch": 0.717948717948718,
2318
+ "grad_norm": 2.010289192199707,
2319
+ "learning_rate": 1.7905181762389298e-05,
2320
+ "loss": 0.3312,
2321
+ "step": 329
2322
+ },
2323
+ {
2324
+ "epoch": 0.7201309328968903,
2325
+ "grad_norm": 1.8437626361846924,
2326
+ "learning_rate": 1.7890638555402585e-05,
2327
+ "loss": 0.338,
2328
+ "step": 330
2329
+ },
2330
+ {
2331
+ "epoch": 0.7223131478450627,
2332
+ "grad_norm": 1.8818646669387817,
2333
+ "learning_rate": 1.7876050989600908e-05,
2334
+ "loss": 0.2822,
2335
+ "step": 331
2336
+ },
2337
+ {
2338
+ "epoch": 0.7244953627932351,
2339
+ "grad_norm": 1.4414920806884766,
2340
+ "learning_rate": 1.7861419146991204e-05,
2341
+ "loss": 0.1611,
2342
+ "step": 332
2343
+ },
2344
+ {
2345
+ "epoch": 0.7266775777414075,
2346
+ "grad_norm": 1.7592997550964355,
2347
+ "learning_rate": 1.7846743109829318e-05,
2348
+ "loss": 0.1889,
2349
+ "step": 333
2350
+ },
2351
+ {
2352
+ "epoch": 0.7288597926895799,
2353
+ "grad_norm": 1.8910146951675415,
2354
+ "learning_rate": 1.7832022960619562e-05,
2355
+ "loss": 0.2466,
2356
+ "step": 334
2357
+ },
2358
+ {
2359
+ "epoch": 0.7310420076377523,
2360
+ "grad_norm": 1.9606562852859497,
2361
+ "learning_rate": 1.7817258782114216e-05,
2362
+ "loss": 0.3082,
2363
+ "step": 335
2364
+ },
2365
+ {
2366
+ "epoch": 0.7332242225859247,
2367
+ "grad_norm": 1.5216842889785767,
2368
+ "learning_rate": 1.7802450657313086e-05,
2369
+ "loss": 0.2702,
2370
+ "step": 336
2371
+ },
2372
+ {
2373
+ "epoch": 0.7354064375340971,
2374
+ "grad_norm": 2.0545153617858887,
2375
+ "learning_rate": 1.7787598669463027e-05,
2376
+ "loss": 0.2168,
2377
+ "step": 337
2378
+ },
2379
+ {
2380
+ "epoch": 0.7375886524822695,
2381
+ "grad_norm": 2.3853023052215576,
2382
+ "learning_rate": 1.777270290205749e-05,
2383
+ "loss": 0.2697,
2384
+ "step": 338
2385
+ },
2386
+ {
2387
+ "epoch": 0.7397708674304418,
2388
+ "grad_norm": 1.5850306749343872,
2389
+ "learning_rate": 1.7757763438836027e-05,
2390
+ "loss": 0.2776,
2391
+ "step": 339
2392
+ },
2393
+ {
2394
+ "epoch": 0.7419530823786143,
2395
+ "grad_norm": 1.8929774761199951,
2396
+ "learning_rate": 1.7742780363783843e-05,
2397
+ "loss": 0.2768,
2398
+ "step": 340
2399
+ },
2400
+ {
2401
+ "epoch": 0.7441352973267867,
2402
+ "grad_norm": 2.5149059295654297,
2403
+ "learning_rate": 1.7727753761131312e-05,
2404
+ "loss": 0.2035,
2405
+ "step": 341
2406
+ },
2407
+ {
2408
+ "epoch": 0.7463175122749591,
2409
+ "grad_norm": 2.0072574615478516,
2410
+ "learning_rate": 1.7712683715353514e-05,
2411
+ "loss": 0.2996,
2412
+ "step": 342
2413
+ },
2414
+ {
2415
+ "epoch": 0.7484997272231315,
2416
+ "grad_norm": 1.8985759019851685,
2417
+ "learning_rate": 1.7697570311169746e-05,
2418
+ "loss": 0.2971,
2419
+ "step": 343
2420
+ },
2421
+ {
2422
+ "epoch": 0.7506819421713039,
2423
+ "grad_norm": 1.7933598756790161,
2424
+ "learning_rate": 1.7682413633543057e-05,
2425
+ "loss": 0.1999,
2426
+ "step": 344
2427
+ },
2428
+ {
2429
+ "epoch": 0.7528641571194763,
2430
+ "grad_norm": 2.1801459789276123,
2431
+ "learning_rate": 1.766721376767976e-05,
2432
+ "loss": 0.2834,
2433
+ "step": 345
2434
+ },
2435
+ {
2436
+ "epoch": 0.7550463720676487,
2437
+ "grad_norm": 2.213613271713257,
2438
+ "learning_rate": 1.7651970799028976e-05,
2439
+ "loss": 0.3526,
2440
+ "step": 346
2441
+ },
2442
+ {
2443
+ "epoch": 0.7572285870158211,
2444
+ "grad_norm": 2.226930856704712,
2445
+ "learning_rate": 1.7636684813282113e-05,
2446
+ "loss": 0.221,
2447
+ "step": 347
2448
+ },
2449
+ {
2450
+ "epoch": 0.7594108019639935,
2451
+ "grad_norm": 2.073094606399536,
2452
+ "learning_rate": 1.7621355896372424e-05,
2453
+ "loss": 0.1289,
2454
+ "step": 348
2455
+ },
2456
+ {
2457
+ "epoch": 0.7615930169121659,
2458
+ "grad_norm": 1.817728042602539,
2459
+ "learning_rate": 1.760598413447451e-05,
2460
+ "loss": 0.2903,
2461
+ "step": 349
2462
+ },
2463
+ {
2464
+ "epoch": 0.7637752318603382,
2465
+ "grad_norm": 1.7736403942108154,
2466
+ "learning_rate": 1.7590569614003825e-05,
2467
+ "loss": 0.3416,
2468
+ "step": 350
2469
+ },
2470
+ {
2471
+ "epoch": 0.7659574468085106,
2472
+ "grad_norm": 1.8209755420684814,
2473
+ "learning_rate": 1.7575112421616203e-05,
2474
+ "loss": 0.209,
2475
+ "step": 351
2476
+ },
2477
+ {
2478
+ "epoch": 0.768139661756683,
2479
+ "grad_norm": 2.1143956184387207,
2480
+ "learning_rate": 1.7559612644207364e-05,
2481
+ "loss": 0.248,
2482
+ "step": 352
2483
+ },
2484
+ {
2485
+ "epoch": 0.7703218767048554,
2486
+ "grad_norm": 2.564955234527588,
2487
+ "learning_rate": 1.7544070368912435e-05,
2488
+ "loss": 0.2898,
2489
+ "step": 353
2490
+ },
2491
+ {
2492
+ "epoch": 0.7725040916530278,
2493
+ "grad_norm": 1.8118090629577637,
2494
+ "learning_rate": 1.7528485683105444e-05,
2495
+ "loss": 0.2374,
2496
+ "step": 354
2497
+ },
2498
+ {
2499
+ "epoch": 0.7746863066012002,
2500
+ "grad_norm": 2.656928777694702,
2501
+ "learning_rate": 1.751285867439885e-05,
2502
+ "loss": 0.3049,
2503
+ "step": 355
2504
+ },
2505
+ {
2506
+ "epoch": 0.7768685215493726,
2507
+ "grad_norm": 3.4277329444885254,
2508
+ "learning_rate": 1.7497189430643025e-05,
2509
+ "loss": 0.3216,
2510
+ "step": 356
2511
+ },
2512
+ {
2513
+ "epoch": 0.779050736497545,
2514
+ "grad_norm": 2.2048025131225586,
2515
+ "learning_rate": 1.7481478039925784e-05,
2516
+ "loss": 0.2718,
2517
+ "step": 357
2518
+ },
2519
+ {
2520
+ "epoch": 0.7812329514457174,
2521
+ "grad_norm": 1.7105648517608643,
2522
+ "learning_rate": 1.746572459057188e-05,
2523
+ "loss": 0.2421,
2524
+ "step": 358
2525
+ },
2526
+ {
2527
+ "epoch": 0.7834151663938898,
2528
+ "grad_norm": 1.4163354635238647,
2529
+ "learning_rate": 1.7449929171142495e-05,
2530
+ "loss": 0.2668,
2531
+ "step": 359
2532
+ },
2533
+ {
2534
+ "epoch": 0.7855973813420621,
2535
+ "grad_norm": 2.316988468170166,
2536
+ "learning_rate": 1.7434091870434772e-05,
2537
+ "loss": 0.1913,
2538
+ "step": 360
2539
+ },
2540
+ {
2541
+ "epoch": 0.7877795962902346,
2542
+ "grad_norm": 1.7749286890029907,
2543
+ "learning_rate": 1.741821277748128e-05,
2544
+ "loss": 0.1675,
2545
+ "step": 361
2546
+ },
2547
+ {
2548
+ "epoch": 0.789961811238407,
2549
+ "grad_norm": 1.6692242622375488,
2550
+ "learning_rate": 1.740229198154955e-05,
2551
+ "loss": 0.1973,
2552
+ "step": 362
2553
+ },
2554
+ {
2555
+ "epoch": 0.7921440261865794,
2556
+ "grad_norm": 1.7292042970657349,
2557
+ "learning_rate": 1.738632957214154e-05,
2558
+ "loss": 0.285,
2559
+ "step": 363
2560
+ },
2561
+ {
2562
+ "epoch": 0.7943262411347518,
2563
+ "grad_norm": 1.389611840248108,
2564
+ "learning_rate": 1.737032563899315e-05,
2565
+ "loss": 0.2458,
2566
+ "step": 364
2567
+ },
2568
+ {
2569
+ "epoch": 0.7965084560829242,
2570
+ "grad_norm": 2.399740695953369,
2571
+ "learning_rate": 1.7354280272073718e-05,
2572
+ "loss": 0.2779,
2573
+ "step": 365
2574
+ },
2575
+ {
2576
+ "epoch": 0.7986906710310966,
2577
+ "grad_norm": 1.7526628971099854,
2578
+ "learning_rate": 1.7338193561585507e-05,
2579
+ "loss": 0.1781,
2580
+ "step": 366
2581
+ },
2582
+ {
2583
+ "epoch": 0.800872885979269,
2584
+ "grad_norm": 1.1837629079818726,
2585
+ "learning_rate": 1.7322065597963206e-05,
2586
+ "loss": 0.1506,
2587
+ "step": 367
2588
+ },
2589
+ {
2590
+ "epoch": 0.8030551009274414,
2591
+ "grad_norm": 2.0996508598327637,
2592
+ "learning_rate": 1.730589647187341e-05,
2593
+ "loss": 0.2591,
2594
+ "step": 368
2595
+ },
2596
+ {
2597
+ "epoch": 0.8052373158756138,
2598
+ "grad_norm": 1.83616042137146,
2599
+ "learning_rate": 1.7289686274214116e-05,
2600
+ "loss": 0.2328,
2601
+ "step": 369
2602
+ },
2603
+ {
2604
+ "epoch": 0.8074195308237861,
2605
+ "grad_norm": 1.7485703229904175,
2606
+ "learning_rate": 1.7273435096114223e-05,
2607
+ "loss": 0.1933,
2608
+ "step": 370
2609
+ },
2610
+ {
2611
+ "epoch": 0.8096017457719585,
2612
+ "grad_norm": 1.69053316116333,
2613
+ "learning_rate": 1.7257143028933004e-05,
2614
+ "loss": 0.1454,
2615
+ "step": 371
2616
+ },
2617
+ {
2618
+ "epoch": 0.8117839607201309,
2619
+ "grad_norm": 2.0164339542388916,
2620
+ "learning_rate": 1.7240810164259597e-05,
2621
+ "loss": 0.2374,
2622
+ "step": 372
2623
+ },
2624
+ {
2625
+ "epoch": 0.8139661756683033,
2626
+ "grad_norm": 1.9152922630310059,
2627
+ "learning_rate": 1.722443659391249e-05,
2628
+ "loss": 0.2679,
2629
+ "step": 373
2630
+ },
2631
+ {
2632
+ "epoch": 0.8161483906164757,
2633
+ "grad_norm": 1.842621922492981,
2634
+ "learning_rate": 1.7208022409939012e-05,
2635
+ "loss": 0.2535,
2636
+ "step": 374
2637
+ },
2638
+ {
2639
+ "epoch": 0.8183306055646481,
2640
+ "grad_norm": 1.975754976272583,
2641
+ "learning_rate": 1.7191567704614806e-05,
2642
+ "loss": 0.2771,
2643
+ "step": 375
2644
+ },
2645
+ {
2646
+ "epoch": 0.8205128205128205,
2647
+ "grad_norm": 2.002427577972412,
2648
+ "learning_rate": 1.717507257044331e-05,
2649
+ "loss": 0.2521,
2650
+ "step": 376
2651
+ },
2652
+ {
2653
+ "epoch": 0.8226950354609929,
2654
+ "grad_norm": 1.8171672821044922,
2655
+ "learning_rate": 1.7158537100155256e-05,
2656
+ "loss": 0.1732,
2657
+ "step": 377
2658
+ },
2659
+ {
2660
+ "epoch": 0.8248772504091653,
2661
+ "grad_norm": 2.4099912643432617,
2662
+ "learning_rate": 1.714196138670811e-05,
2663
+ "loss": 0.1903,
2664
+ "step": 378
2665
+ },
2666
+ {
2667
+ "epoch": 0.8270594653573377,
2668
+ "grad_norm": 2.192172050476074,
2669
+ "learning_rate": 1.7125345523285598e-05,
2670
+ "loss": 0.1533,
2671
+ "step": 379
2672
+ },
2673
+ {
2674
+ "epoch": 0.82924168030551,
2675
+ "grad_norm": 1.4280940294265747,
2676
+ "learning_rate": 1.7108689603297134e-05,
2677
+ "loss": 0.1654,
2678
+ "step": 380
2679
+ },
2680
+ {
2681
+ "epoch": 0.8314238952536824,
2682
+ "grad_norm": 2.107060194015503,
2683
+ "learning_rate": 1.7091993720377336e-05,
2684
+ "loss": 0.2626,
2685
+ "step": 381
2686
+ },
2687
+ {
2688
+ "epoch": 0.8336061102018549,
2689
+ "grad_norm": 2.0047659873962402,
2690
+ "learning_rate": 1.7075257968385472e-05,
2691
+ "loss": 0.3092,
2692
+ "step": 382
2693
+ },
2694
+ {
2695
+ "epoch": 0.8357883251500273,
2696
+ "grad_norm": 1.796487808227539,
2697
+ "learning_rate": 1.7058482441404946e-05,
2698
+ "loss": 0.3114,
2699
+ "step": 383
2700
+ },
2701
+ {
2702
+ "epoch": 0.8379705400981997,
2703
+ "grad_norm": 1.7347898483276367,
2704
+ "learning_rate": 1.7041667233742763e-05,
2705
+ "loss": 0.2335,
2706
+ "step": 384
2707
+ },
2708
+ {
2709
+ "epoch": 0.8401527550463721,
2710
+ "grad_norm": 4.162664890289307,
2711
+ "learning_rate": 1.7024812439929004e-05,
2712
+ "loss": 0.3763,
2713
+ "step": 385
2714
+ },
2715
+ {
2716
+ "epoch": 0.8423349699945445,
2717
+ "grad_norm": 2.301137685775757,
2718
+ "learning_rate": 1.7007918154716286e-05,
2719
+ "loss": 0.2288,
2720
+ "step": 386
2721
+ },
2722
+ {
2723
+ "epoch": 0.8445171849427169,
2724
+ "grad_norm": 2.1186411380767822,
2725
+ "learning_rate": 1.6990984473079245e-05,
2726
+ "loss": 0.2563,
2727
+ "step": 387
2728
+ },
2729
+ {
2730
+ "epoch": 0.8466993998908893,
2731
+ "grad_norm": 2.251436948776245,
2732
+ "learning_rate": 1.6974011490213976e-05,
2733
+ "loss": 0.2387,
2734
+ "step": 388
2735
+ },
2736
+ {
2737
+ "epoch": 0.8488816148390617,
2738
+ "grad_norm": 2.201972246170044,
2739
+ "learning_rate": 1.6956999301537533e-05,
2740
+ "loss": 0.2157,
2741
+ "step": 389
2742
+ },
2743
+ {
2744
+ "epoch": 0.851063829787234,
2745
+ "grad_norm": 1.8352923393249512,
2746
+ "learning_rate": 1.6939948002687352e-05,
2747
+ "loss": 0.2014,
2748
+ "step": 390
2749
+ },
2750
+ {
2751
+ "epoch": 0.8532460447354064,
2752
+ "grad_norm": 1.7831623554229736,
2753
+ "learning_rate": 1.692285768952076e-05,
2754
+ "loss": 0.2098,
2755
+ "step": 391
2756
+ },
2757
+ {
2758
+ "epoch": 0.8554282596835788,
2759
+ "grad_norm": 2.747898578643799,
2760
+ "learning_rate": 1.6905728458114384e-05,
2761
+ "loss": 0.358,
2762
+ "step": 392
2763
+ },
2764
+ {
2765
+ "epoch": 0.8576104746317512,
2766
+ "grad_norm": 2.2360734939575195,
2767
+ "learning_rate": 1.6888560404763656e-05,
2768
+ "loss": 0.3157,
2769
+ "step": 393
2770
+ },
2771
+ {
2772
+ "epoch": 0.8597926895799236,
2773
+ "grad_norm": 2.639230728149414,
2774
+ "learning_rate": 1.687135362598225e-05,
2775
+ "loss": 0.2,
2776
+ "step": 394
2777
+ },
2778
+ {
2779
+ "epoch": 0.861974904528096,
2780
+ "grad_norm": 2.2100465297698975,
2781
+ "learning_rate": 1.6854108218501534e-05,
2782
+ "loss": 0.2923,
2783
+ "step": 395
2784
+ },
2785
+ {
2786
+ "epoch": 0.8641571194762684,
2787
+ "grad_norm": 1.9703783988952637,
2788
+ "learning_rate": 1.6836824279270053e-05,
2789
+ "loss": 0.1823,
2790
+ "step": 396
2791
+ },
2792
+ {
2793
+ "epoch": 0.8663393344244408,
2794
+ "grad_norm": 1.6612106561660767,
2795
+ "learning_rate": 1.6819501905452945e-05,
2796
+ "loss": 0.2014,
2797
+ "step": 397
2798
+ },
2799
+ {
2800
+ "epoch": 0.8685215493726132,
2801
+ "grad_norm": 1.8585114479064941,
2802
+ "learning_rate": 1.680214119443143e-05,
2803
+ "loss": 0.2264,
2804
+ "step": 398
2805
+ },
2806
+ {
2807
+ "epoch": 0.8707037643207856,
2808
+ "grad_norm": 1.6524639129638672,
2809
+ "learning_rate": 1.6784742243802242e-05,
2810
+ "loss": 0.2493,
2811
+ "step": 399
2812
+ },
2813
+ {
2814
+ "epoch": 0.872885979268958,
2815
+ "grad_norm": 1.7347056865692139,
2816
+ "learning_rate": 1.676730515137709e-05,
2817
+ "loss": 0.1117,
2818
+ "step": 400
2819
+ },
2820
+ {
2821
+ "epoch": 0.8750681942171303,
2822
+ "grad_norm": 4.263298034667969,
2823
+ "learning_rate": 1.6749830015182106e-05,
2824
+ "loss": 0.4225,
2825
+ "step": 401
2826
+ },
2827
+ {
2828
+ "epoch": 0.8772504091653028,
2829
+ "grad_norm": 1.9091832637786865,
2830
+ "learning_rate": 1.673231693345729e-05,
2831
+ "loss": 0.212,
2832
+ "step": 402
2833
+ },
2834
+ {
2835
+ "epoch": 0.8794326241134752,
2836
+ "grad_norm": 2.1852641105651855,
2837
+ "learning_rate": 1.6714766004655952e-05,
2838
+ "loss": 0.2277,
2839
+ "step": 403
2840
+ },
2841
+ {
2842
+ "epoch": 0.8816148390616476,
2843
+ "grad_norm": 2.200873851776123,
2844
+ "learning_rate": 1.6697177327444185e-05,
2845
+ "loss": 0.3014,
2846
+ "step": 404
2847
+ },
2848
+ {
2849
+ "epoch": 0.88379705400982,
2850
+ "grad_norm": 1.8276499509811401,
2851
+ "learning_rate": 1.6679551000700277e-05,
2852
+ "loss": 0.1585,
2853
+ "step": 405
2854
+ },
2855
+ {
2856
+ "epoch": 0.8859792689579924,
2857
+ "grad_norm": 2.2364282608032227,
2858
+ "learning_rate": 1.6661887123514183e-05,
2859
+ "loss": 0.1494,
2860
+ "step": 406
2861
+ },
2862
+ {
2863
+ "epoch": 0.8881614839061648,
2864
+ "grad_norm": 2.0222830772399902,
2865
+ "learning_rate": 1.6644185795186946e-05,
2866
+ "loss": 0.2673,
2867
+ "step": 407
2868
+ },
2869
+ {
2870
+ "epoch": 0.8903436988543372,
2871
+ "grad_norm": 2.9449918270111084,
2872
+ "learning_rate": 1.662644711523014e-05,
2873
+ "loss": 0.3708,
2874
+ "step": 408
2875
+ },
2876
+ {
2877
+ "epoch": 0.8925259138025096,
2878
+ "grad_norm": 1.4988254308700562,
2879
+ "learning_rate": 1.660867118336535e-05,
2880
+ "loss": 0.1401,
2881
+ "step": 409
2882
+ },
2883
+ {
2884
+ "epoch": 0.894708128750682,
2885
+ "grad_norm": 2.212355375289917,
2886
+ "learning_rate": 1.6590858099523545e-05,
2887
+ "loss": 0.2032,
2888
+ "step": 410
2889
+ },
2890
+ {
2891
+ "epoch": 0.8968903436988543,
2892
+ "grad_norm": 2.242018699645996,
2893
+ "learning_rate": 1.657300796384457e-05,
2894
+ "loss": 0.2475,
2895
+ "step": 411
2896
+ },
2897
+ {
2898
+ "epoch": 0.8990725586470267,
2899
+ "grad_norm": 2.596482276916504,
2900
+ "learning_rate": 1.6555120876676557e-05,
2901
+ "loss": 0.3207,
2902
+ "step": 412
2903
+ },
2904
+ {
2905
+ "epoch": 0.9012547735951991,
2906
+ "grad_norm": 2.6144678592681885,
2907
+ "learning_rate": 1.6537196938575376e-05,
2908
+ "loss": 0.2693,
2909
+ "step": 413
2910
+ },
2911
+ {
2912
+ "epoch": 0.9034369885433715,
2913
+ "grad_norm": 2.0551865100860596,
2914
+ "learning_rate": 1.6519236250304058e-05,
2915
+ "loss": 0.1352,
2916
+ "step": 414
2917
+ },
2918
+ {
2919
+ "epoch": 0.9056192034915439,
2920
+ "grad_norm": 1.8955483436584473,
2921
+ "learning_rate": 1.6501238912832226e-05,
2922
+ "loss": 0.2083,
2923
+ "step": 415
2924
+ },
2925
+ {
2926
+ "epoch": 0.9078014184397163,
2927
+ "grad_norm": 2.737642526626587,
2928
+ "learning_rate": 1.648320502733555e-05,
2929
+ "loss": 0.3512,
2930
+ "step": 416
2931
+ },
2932
+ {
2933
+ "epoch": 0.9099836333878887,
2934
+ "grad_norm": 1.874455451965332,
2935
+ "learning_rate": 1.646513469519514e-05,
2936
+ "loss": 0.245,
2937
+ "step": 417
2938
+ },
2939
+ {
2940
+ "epoch": 0.9121658483360611,
2941
+ "grad_norm": 1.4540960788726807,
2942
+ "learning_rate": 1.644702801799702e-05,
2943
+ "loss": 0.1915,
2944
+ "step": 418
2945
+ },
2946
+ {
2947
+ "epoch": 0.9143480632842335,
2948
+ "grad_norm": 2.55229115486145,
2949
+ "learning_rate": 1.6428885097531524e-05,
2950
+ "loss": 0.2691,
2951
+ "step": 419
2952
+ },
2953
+ {
2954
+ "epoch": 0.9165302782324058,
2955
+ "grad_norm": 2.6212050914764404,
2956
+ "learning_rate": 1.641070603579273e-05,
2957
+ "loss": 0.3018,
2958
+ "step": 420
2959
+ },
2960
+ {
2961
+ "epoch": 0.9187124931805782,
2962
+ "grad_norm": 2.048126220703125,
2963
+ "learning_rate": 1.63924909349779e-05,
2964
+ "loss": 0.16,
2965
+ "step": 421
2966
+ },
2967
+ {
2968
+ "epoch": 0.9208947081287506,
2969
+ "grad_norm": 1.604466199874878,
2970
+ "learning_rate": 1.63742398974869e-05,
2971
+ "loss": 0.16,
2972
+ "step": 422
2973
+ },
2974
+ {
2975
+ "epoch": 0.9230769230769231,
2976
+ "grad_norm": 2.0032010078430176,
2977
+ "learning_rate": 1.6355953025921606e-05,
2978
+ "loss": 0.2789,
2979
+ "step": 423
2980
+ },
2981
+ {
2982
+ "epoch": 0.9252591380250955,
2983
+ "grad_norm": 2.1669390201568604,
2984
+ "learning_rate": 1.633763042308536e-05,
2985
+ "loss": 0.2223,
2986
+ "step": 424
2987
+ },
2988
+ {
2989
+ "epoch": 0.9274413529732679,
2990
+ "grad_norm": 2.4847841262817383,
2991
+ "learning_rate": 1.6319272191982364e-05,
2992
+ "loss": 0.2193,
2993
+ "step": 425
2994
+ },
2995
+ {
2996
+ "epoch": 0.9296235679214403,
2997
+ "grad_norm": 2.116520404815674,
2998
+ "learning_rate": 1.6300878435817115e-05,
2999
+ "loss": 0.2634,
3000
+ "step": 426
3001
+ },
3002
+ {
3003
+ "epoch": 0.9318057828696127,
3004
+ "grad_norm": 2.1085104942321777,
3005
+ "learning_rate": 1.6282449257993814e-05,
3006
+ "loss": 0.2019,
3007
+ "step": 427
3008
+ },
3009
+ {
3010
+ "epoch": 0.9339879978177851,
3011
+ "grad_norm": 1.8518610000610352,
3012
+ "learning_rate": 1.626398476211581e-05,
3013
+ "loss": 0.281,
3014
+ "step": 428
3015
+ },
3016
+ {
3017
+ "epoch": 0.9361702127659575,
3018
+ "grad_norm": 2.573018789291382,
3019
+ "learning_rate": 1.624548505198498e-05,
3020
+ "loss": 0.1693,
3021
+ "step": 429
3022
+ },
3023
+ {
3024
+ "epoch": 0.9383524277141299,
3025
+ "grad_norm": 1.71120285987854,
3026
+ "learning_rate": 1.622695023160117e-05,
3027
+ "loss": 0.1845,
3028
+ "step": 430
3029
+ },
3030
+ {
3031
+ "epoch": 0.9405346426623022,
3032
+ "grad_norm": 2.493091583251953,
3033
+ "learning_rate": 1.6208380405161623e-05,
3034
+ "loss": 0.2344,
3035
+ "step": 431
3036
+ },
3037
+ {
3038
+ "epoch": 0.9427168576104746,
3039
+ "grad_norm": 2.0557820796966553,
3040
+ "learning_rate": 1.6189775677060347e-05,
3041
+ "loss": 0.2579,
3042
+ "step": 432
3043
+ },
3044
+ {
3045
+ "epoch": 0.944899072558647,
3046
+ "grad_norm": 2.64087176322937,
3047
+ "learning_rate": 1.6171136151887577e-05,
3048
+ "loss": 0.1322,
3049
+ "step": 433
3050
+ },
3051
+ {
3052
+ "epoch": 0.9470812875068194,
3053
+ "grad_norm": 1.8148539066314697,
3054
+ "learning_rate": 1.6152461934429154e-05,
3055
+ "loss": 0.206,
3056
+ "step": 434
3057
+ },
3058
+ {
3059
+ "epoch": 0.9492635024549918,
3060
+ "grad_norm": 2.2910168170928955,
3061
+ "learning_rate": 1.6133753129665968e-05,
3062
+ "loss": 0.2088,
3063
+ "step": 435
3064
+ },
3065
+ {
3066
+ "epoch": 0.9514457174031642,
3067
+ "grad_norm": 2.097425937652588,
3068
+ "learning_rate": 1.6115009842773322e-05,
3069
+ "loss": 0.1765,
3070
+ "step": 436
3071
+ },
3072
+ {
3073
+ "epoch": 0.9536279323513366,
3074
+ "grad_norm": 1.9903476238250732,
3075
+ "learning_rate": 1.6096232179120388e-05,
3076
+ "loss": 0.3164,
3077
+ "step": 437
3078
+ },
3079
+ {
3080
+ "epoch": 0.955810147299509,
3081
+ "grad_norm": 2.1688966751098633,
3082
+ "learning_rate": 1.6077420244269585e-05,
3083
+ "loss": 0.2361,
3084
+ "step": 438
3085
+ },
3086
+ {
3087
+ "epoch": 0.9579923622476814,
3088
+ "grad_norm": 2.8505375385284424,
3089
+ "learning_rate": 1.6058574143975995e-05,
3090
+ "loss": 0.2636,
3091
+ "step": 439
3092
+ },
3093
+ {
3094
+ "epoch": 0.9601745771958538,
3095
+ "grad_norm": 3.311235189437866,
3096
+ "learning_rate": 1.603969398418677e-05,
3097
+ "loss": 0.3795,
3098
+ "step": 440
3099
+ },
3100
+ {
3101
+ "epoch": 0.9623567921440261,
3102
+ "grad_norm": 1.8277406692504883,
3103
+ "learning_rate": 1.6020779871040538e-05,
3104
+ "loss": 0.1737,
3105
+ "step": 441
3106
+ },
3107
+ {
3108
+ "epoch": 0.9645390070921985,
3109
+ "grad_norm": 2.1164958477020264,
3110
+ "learning_rate": 1.6001831910866795e-05,
3111
+ "loss": 0.1468,
3112
+ "step": 442
3113
+ },
3114
+ {
3115
+ "epoch": 0.966721222040371,
3116
+ "grad_norm": 2.103459358215332,
3117
+ "learning_rate": 1.5982850210185313e-05,
3118
+ "loss": 0.1544,
3119
+ "step": 443
3120
+ },
3121
+ {
3122
+ "epoch": 0.9689034369885434,
3123
+ "grad_norm": 1.900844693183899,
3124
+ "learning_rate": 1.5963834875705556e-05,
3125
+ "loss": 0.2253,
3126
+ "step": 444
3127
+ },
3128
+ {
3129
+ "epoch": 0.9710856519367158,
3130
+ "grad_norm": 3.1280438899993896,
3131
+ "learning_rate": 1.5944786014326053e-05,
3132
+ "loss": 0.3032,
3133
+ "step": 445
3134
+ },
3135
+ {
3136
+ "epoch": 0.9732678668848882,
3137
+ "grad_norm": 1.8489347696304321,
3138
+ "learning_rate": 1.5925703733133823e-05,
3139
+ "loss": 0.1499,
3140
+ "step": 446
3141
+ },
3142
+ {
3143
+ "epoch": 0.9754500818330606,
3144
+ "grad_norm": 2.221360683441162,
3145
+ "learning_rate": 1.5906588139403752e-05,
3146
+ "loss": 0.2354,
3147
+ "step": 447
3148
+ },
3149
+ {
3150
+ "epoch": 0.977632296781233,
3151
+ "grad_norm": 2.9962828159332275,
3152
+ "learning_rate": 1.5887439340598002e-05,
3153
+ "loss": 0.2583,
3154
+ "step": 448
3155
+ },
3156
+ {
3157
+ "epoch": 0.9798145117294054,
3158
+ "grad_norm": 1.688433051109314,
3159
+ "learning_rate": 1.5868257444365408e-05,
3160
+ "loss": 0.2026,
3161
+ "step": 449
3162
+ },
3163
+ {
3164
+ "epoch": 0.9819967266775778,
3165
+ "grad_norm": 1.9176521301269531,
3166
+ "learning_rate": 1.5849042558540863e-05,
3167
+ "loss": 0.2106,
3168
+ "step": 450
3169
+ },
3170
+ {
3171
+ "epoch": 0.9841789416257501,
3172
+ "grad_norm": 1.9299747943878174,
3173
+ "learning_rate": 1.5829794791144723e-05,
3174
+ "loss": 0.1221,
3175
+ "step": 451
3176
+ },
3177
+ {
3178
+ "epoch": 0.9863611565739225,
3179
+ "grad_norm": 2.396916389465332,
3180
+ "learning_rate": 1.581051425038219e-05,
3181
+ "loss": 0.2966,
3182
+ "step": 452
3183
+ },
3184
+ {
3185
+ "epoch": 0.9885433715220949,
3186
+ "grad_norm": 2.132479667663574,
3187
+ "learning_rate": 1.5791201044642707e-05,
3188
+ "loss": 0.2392,
3189
+ "step": 453
3190
+ },
3191
+ {
3192
+ "epoch": 0.9907255864702673,
3193
+ "grad_norm": 1.897214651107788,
3194
+ "learning_rate": 1.577185528249936e-05,
3195
+ "loss": 0.1549,
3196
+ "step": 454
3197
+ },
3198
+ {
3199
+ "epoch": 0.9929078014184397,
3200
+ "grad_norm": 2.2790167331695557,
3201
+ "learning_rate": 1.5752477072708247e-05,
3202
+ "loss": 0.3243,
3203
+ "step": 455
3204
+ },
3205
+ {
3206
+ "epoch": 0.9950900163666121,
3207
+ "grad_norm": 2.3962960243225098,
3208
+ "learning_rate": 1.5733066524207875e-05,
3209
+ "loss": 0.2082,
3210
+ "step": 456
3211
+ },
3212
+ {
3213
+ "epoch": 0.9972722313147845,
3214
+ "grad_norm": 1.7336385250091553,
3215
+ "learning_rate": 1.5713623746118558e-05,
3216
+ "loss": 0.157,
3217
+ "step": 457
3218
+ },
3219
+ {
3220
+ "epoch": 0.9994544462629569,
3221
+ "grad_norm": 1.8935623168945312,
3222
+ "learning_rate": 1.5694148847741793e-05,
3223
+ "loss": 0.2305,
3224
+ "step": 458
3225
+ },
3226
+ {
3227
+ "epoch": 1.0,
3228
+ "grad_norm": 5.8416337966918945,
3229
+ "learning_rate": 1.5674641938559644e-05,
3230
+ "loss": 0.3029,
3231
+ "step": 459
3232
+ },
3233
+ {
3234
+ "epoch": 1.0,
3235
+ "eval_loss": 0.1403220295906067,
3236
+ "eval_runtime": 19.9242,
3237
+ "eval_samples_per_second": 7.478,
3238
+ "eval_steps_per_second": 1.907,
3239
+ "step": 459
3240
+ }
3241
+ ],
3242
+ "logging_steps": 1,
3243
+ "max_steps": 1375,
3244
+ "num_input_tokens_seen": 0,
3245
+ "num_train_epochs": 4,
3246
+ "save_steps": 459,
3247
+ "stateful_callbacks": {
3248
+ "TrainerControl": {
3249
+ "args": {
3250
+ "should_epoch_stop": false,
3251
+ "should_evaluate": false,
3252
+ "should_log": false,
3253
+ "should_save": true,
3254
+ "should_training_stop": false
3255
+ },
3256
+ "attributes": {}
3257
+ }
3258
+ },
3259
+ "total_flos": 5.006541592933171e+17,
3260
+ "train_batch_size": 2,
3261
+ "trial_name": null,
3262
+ "trial_params": null
3263
+ }
checkpoint-459/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9782f3189b2775d8981fd1818051f75ea4e7ed0ea5d50644d78a1e3bfb534506
3
+ size 9144
checkpoint-459/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-918/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-coder-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-918/adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-coder-3B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 32,
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": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "w1",
28
+ "v_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "o_proj",
32
+ "w2",
33
+ "c_proj",
34
+ "c_attn"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
checkpoint-918/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c55649ff5f49e9bb51fce48d3cb5307cd002da45b833d9ef56c1a03a62956a7
3
+ size 14783648
checkpoint-918/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-918/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-918/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c6d134c1d2eed9ea4db66bc5eedf05c6f21b3ac50cf83507d5dd23fa0c50b7
3
+ size 8663940
checkpoint-918/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc822572ddc1090888e89e169c6237a4320749a8a4df7c309137f32ec93b344c
3
+ size 14512
checkpoint-918/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038f487efdd3bb7fe2a132f95e1d1eb7902548e98c45b248f8cfce66e7879067
3
+ size 14512
checkpoint-918/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46013ea05292bb5196c4a8bc6924c527f4b8e6e1c106364b5149f56bf5f1a74e
3
+ size 988
checkpoint-918/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2471572c57ddc974001314485e8374cac09c574228213424eb7975fa30be70f8
3
+ size 1064
checkpoint-918/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-918/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896