Model save
Browse files- README.md +93 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1151 -0
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Llama-31-8B_task-1_180-samples_config-4
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Llama-31-8B_task-1_180-samples_config-4
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.4508
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 16
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 2.0972 | 0.9412 | 8 | 2.0718 |
|
| 57 |
+
| 2.0234 | 2.0 | 17 | 2.0545 |
|
| 58 |
+
| 2.0324 | 2.9412 | 25 | 2.0288 |
|
| 59 |
+
| 2.0064 | 4.0 | 34 | 1.9798 |
|
| 60 |
+
| 1.9611 | 4.9412 | 42 | 1.9139 |
|
| 61 |
+
| 1.8283 | 6.0 | 51 | 1.8090 |
|
| 62 |
+
| 1.6817 | 6.9412 | 59 | 1.7011 |
|
| 63 |
+
| 1.5762 | 8.0 | 68 | 1.6085 |
|
| 64 |
+
| 1.5529 | 8.9412 | 76 | 1.5659 |
|
| 65 |
+
| 1.4817 | 10.0 | 85 | 1.5206 |
|
| 66 |
+
| 1.5125 | 10.9412 | 93 | 1.4816 |
|
| 67 |
+
| 1.3226 | 12.0 | 102 | 1.4352 |
|
| 68 |
+
| 1.3823 | 12.9412 | 110 | 1.3951 |
|
| 69 |
+
| 1.2564 | 14.0 | 119 | 1.3580 |
|
| 70 |
+
| 1.1936 | 14.9412 | 127 | 1.3305 |
|
| 71 |
+
| 1.2322 | 16.0 | 136 | 1.3061 |
|
| 72 |
+
| 1.1389 | 16.9412 | 144 | 1.2910 |
|
| 73 |
+
| 1.2119 | 18.0 | 153 | 1.2775 |
|
| 74 |
+
| 1.0796 | 18.9412 | 161 | 1.2672 |
|
| 75 |
+
| 1.088 | 20.0 | 170 | 1.2627 |
|
| 76 |
+
| 1.0344 | 20.9412 | 178 | 1.2631 |
|
| 77 |
+
| 1.0175 | 22.0 | 187 | 1.2589 |
|
| 78 |
+
| 0.9509 | 22.9412 | 195 | 1.2707 |
|
| 79 |
+
| 0.8574 | 24.0 | 204 | 1.2784 |
|
| 80 |
+
| 0.8673 | 24.9412 | 212 | 1.2985 |
|
| 81 |
+
| 0.8657 | 26.0 | 221 | 1.3300 |
|
| 82 |
+
| 0.7453 | 26.9412 | 229 | 1.3725 |
|
| 83 |
+
| 0.7771 | 28.0 | 238 | 1.3823 |
|
| 84 |
+
| 0.6941 | 28.9412 | 246 | 1.4508 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- PEFT 0.12.0
|
| 90 |
+
- Transformers 4.44.0
|
| 91 |
+
- Pytorch 2.1.2+cu121
|
| 92 |
+
- Datasets 2.20.0
|
| 93 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9a85f33c3642d6e82adf7c78a24a2c28729b9ce155f10049683599ccef07afa
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.941176470588236,
|
| 3 |
+
"total_flos": 6.277931324145664e+16,
|
| 4 |
+
"train_loss": 1.3461502527560645,
|
| 5 |
+
"train_runtime": 4652.7461,
|
| 6 |
+
"train_samples": 136,
|
| 7 |
+
"train_samples_per_second": 4.385,
|
| 8 |
+
"train_steps_per_second": 0.258
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.941176470588236,
|
| 3 |
+
"total_flos": 6.277931324145664e+16,
|
| 4 |
+
"train_loss": 1.3461502527560645,
|
| 5 |
+
"train_runtime": 4652.7461,
|
| 6 |
+
"train_samples": 136,
|
| 7 |
+
"train_samples_per_second": 4.385,
|
| 8 |
+
"train_steps_per_second": 0.258
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.258855938911438,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_180-samples_config-4/checkpoint-187",
|
| 4 |
+
"epoch": 28.941176470588236,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 246,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11764705882352941,
|
| 13 |
+
"grad_norm": 1.5944128036499023,
|
| 14 |
+
"learning_rate": 8.333333333333334e-08,
|
| 15 |
+
"loss": 2.0252,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.23529411764705882,
|
| 20 |
+
"grad_norm": 1.674605369567871,
|
| 21 |
+
"learning_rate": 1.6666666666666668e-07,
|
| 22 |
+
"loss": 2.0106,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.47058823529411764,
|
| 27 |
+
"grad_norm": 1.6583189964294434,
|
| 28 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 29 |
+
"loss": 2.0484,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7058823529411765,
|
| 34 |
+
"grad_norm": 1.7035460472106934,
|
| 35 |
+
"learning_rate": 5.000000000000001e-07,
|
| 36 |
+
"loss": 2.1137,
|
| 37 |
+
"step": 6
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9411764705882353,
|
| 41 |
+
"grad_norm": 1.8433172702789307,
|
| 42 |
+
"learning_rate": 6.666666666666667e-07,
|
| 43 |
+
"loss": 2.0972,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9411764705882353,
|
| 48 |
+
"eval_loss": 2.0717952251434326,
|
| 49 |
+
"eval_runtime": 14.5106,
|
| 50 |
+
"eval_samples_per_second": 2.481,
|
| 51 |
+
"eval_steps_per_second": 2.481,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.1764705882352942,
|
| 56 |
+
"grad_norm": 1.5908912420272827,
|
| 57 |
+
"learning_rate": 8.333333333333333e-07,
|
| 58 |
+
"loss": 2.0639,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.4117647058823528,
|
| 63 |
+
"grad_norm": 1.6493914127349854,
|
| 64 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 65 |
+
"loss": 2.1013,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.6470588235294117,
|
| 70 |
+
"grad_norm": 1.6529414653778076,
|
| 71 |
+
"learning_rate": 1.1666666666666668e-06,
|
| 72 |
+
"loss": 2.1046,
|
| 73 |
+
"step": 14
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.8823529411764706,
|
| 77 |
+
"grad_norm": 1.7618305683135986,
|
| 78 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 79 |
+
"loss": 2.0234,
|
| 80 |
+
"step": 16
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.0,
|
| 84 |
+
"eval_loss": 2.054532766342163,
|
| 85 |
+
"eval_runtime": 14.511,
|
| 86 |
+
"eval_samples_per_second": 2.481,
|
| 87 |
+
"eval_steps_per_second": 2.481,
|
| 88 |
+
"step": 17
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.1176470588235294,
|
| 92 |
+
"grad_norm": 1.626803994178772,
|
| 93 |
+
"learning_rate": 1.5e-06,
|
| 94 |
+
"loss": 1.994,
|
| 95 |
+
"step": 18
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.3529411764705883,
|
| 99 |
+
"grad_norm": 1.7270427942276,
|
| 100 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 101 |
+
"loss": 2.0662,
|
| 102 |
+
"step": 20
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.588235294117647,
|
| 106 |
+
"grad_norm": 1.6685792207717896,
|
| 107 |
+
"learning_rate": 1.8333333333333333e-06,
|
| 108 |
+
"loss": 2.1119,
|
| 109 |
+
"step": 22
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.8235294117647056,
|
| 113 |
+
"grad_norm": 1.6774814128875732,
|
| 114 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 115 |
+
"loss": 2.0324,
|
| 116 |
+
"step": 24
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.9411764705882355,
|
| 120 |
+
"eval_loss": 2.0288267135620117,
|
| 121 |
+
"eval_runtime": 14.5108,
|
| 122 |
+
"eval_samples_per_second": 2.481,
|
| 123 |
+
"eval_steps_per_second": 2.481,
|
| 124 |
+
"step": 25
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.0588235294117645,
|
| 128 |
+
"grad_norm": 1.728971242904663,
|
| 129 |
+
"learning_rate": 2.166666666666667e-06,
|
| 130 |
+
"loss": 2.0096,
|
| 131 |
+
"step": 26
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.2941176470588234,
|
| 135 |
+
"grad_norm": 1.5353363752365112,
|
| 136 |
+
"learning_rate": 2.3333333333333336e-06,
|
| 137 |
+
"loss": 2.0035,
|
| 138 |
+
"step": 28
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.5294117647058822,
|
| 142 |
+
"grad_norm": 1.7659140825271606,
|
| 143 |
+
"learning_rate": 2.5e-06,
|
| 144 |
+
"loss": 2.0145,
|
| 145 |
+
"step": 30
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.764705882352941,
|
| 149 |
+
"grad_norm": 1.7244279384613037,
|
| 150 |
+
"learning_rate": 2.666666666666667e-06,
|
| 151 |
+
"loss": 1.9661,
|
| 152 |
+
"step": 32
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.0,
|
| 156 |
+
"grad_norm": 1.814552664756775,
|
| 157 |
+
"learning_rate": 2.8333333333333335e-06,
|
| 158 |
+
"loss": 2.0064,
|
| 159 |
+
"step": 34
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"eval_loss": 1.9798120260238647,
|
| 164 |
+
"eval_runtime": 14.4915,
|
| 165 |
+
"eval_samples_per_second": 2.484,
|
| 166 |
+
"eval_steps_per_second": 2.484,
|
| 167 |
+
"step": 34
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 4.235294117647059,
|
| 171 |
+
"grad_norm": 1.6728545427322388,
|
| 172 |
+
"learning_rate": 3e-06,
|
| 173 |
+
"loss": 1.9509,
|
| 174 |
+
"step": 36
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.470588235294118,
|
| 178 |
+
"grad_norm": 1.800223469734192,
|
| 179 |
+
"learning_rate": 3.1666666666666667e-06,
|
| 180 |
+
"loss": 1.9526,
|
| 181 |
+
"step": 38
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 4.705882352941177,
|
| 185 |
+
"grad_norm": 1.652232050895691,
|
| 186 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 187 |
+
"loss": 1.922,
|
| 188 |
+
"step": 40
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.9411764705882355,
|
| 192 |
+
"grad_norm": 1.769357681274414,
|
| 193 |
+
"learning_rate": 3.5e-06,
|
| 194 |
+
"loss": 1.9611,
|
| 195 |
+
"step": 42
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.9411764705882355,
|
| 199 |
+
"eval_loss": 1.9139456748962402,
|
| 200 |
+
"eval_runtime": 14.5046,
|
| 201 |
+
"eval_samples_per_second": 2.482,
|
| 202 |
+
"eval_steps_per_second": 2.482,
|
| 203 |
+
"step": 42
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.176470588235294,
|
| 207 |
+
"grad_norm": 1.7674305438995361,
|
| 208 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 209 |
+
"loss": 1.8548,
|
| 210 |
+
"step": 44
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 5.411764705882353,
|
| 214 |
+
"grad_norm": 1.7830374240875244,
|
| 215 |
+
"learning_rate": 3.833333333333334e-06,
|
| 216 |
+
"loss": 1.8919,
|
| 217 |
+
"step": 46
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.647058823529412,
|
| 221 |
+
"grad_norm": 2.0368635654449463,
|
| 222 |
+
"learning_rate": 4.000000000000001e-06,
|
| 223 |
+
"loss": 1.8827,
|
| 224 |
+
"step": 48
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.882352941176471,
|
| 228 |
+
"grad_norm": 1.5133813619613647,
|
| 229 |
+
"learning_rate": 4.166666666666667e-06,
|
| 230 |
+
"loss": 1.8283,
|
| 231 |
+
"step": 50
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.0,
|
| 235 |
+
"eval_loss": 1.8090087175369263,
|
| 236 |
+
"eval_runtime": 14.4945,
|
| 237 |
+
"eval_samples_per_second": 2.484,
|
| 238 |
+
"eval_steps_per_second": 2.484,
|
| 239 |
+
"step": 51
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.117647058823529,
|
| 243 |
+
"grad_norm": 1.5872511863708496,
|
| 244 |
+
"learning_rate": 4.333333333333334e-06,
|
| 245 |
+
"loss": 1.8319,
|
| 246 |
+
"step": 52
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 6.352941176470588,
|
| 250 |
+
"grad_norm": 1.550522804260254,
|
| 251 |
+
"learning_rate": 4.5e-06,
|
| 252 |
+
"loss": 1.7823,
|
| 253 |
+
"step": 54
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 6.588235294117647,
|
| 257 |
+
"grad_norm": 1.5826510190963745,
|
| 258 |
+
"learning_rate": 4.666666666666667e-06,
|
| 259 |
+
"loss": 1.7759,
|
| 260 |
+
"step": 56
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.823529411764706,
|
| 264 |
+
"grad_norm": 1.338010549545288,
|
| 265 |
+
"learning_rate": 4.833333333333333e-06,
|
| 266 |
+
"loss": 1.6817,
|
| 267 |
+
"step": 58
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.9411764705882355,
|
| 271 |
+
"eval_loss": 1.7011380195617676,
|
| 272 |
+
"eval_runtime": 14.5144,
|
| 273 |
+
"eval_samples_per_second": 2.48,
|
| 274 |
+
"eval_steps_per_second": 2.48,
|
| 275 |
+
"step": 59
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.0588235294117645,
|
| 279 |
+
"grad_norm": 1.1569616794586182,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 1.6941,
|
| 282 |
+
"step": 60
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.294117647058823,
|
| 286 |
+
"grad_norm": 1.2016438245773315,
|
| 287 |
+
"learning_rate": 5.1666666666666675e-06,
|
| 288 |
+
"loss": 1.7058,
|
| 289 |
+
"step": 62
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.529411764705882,
|
| 293 |
+
"grad_norm": 1.1135125160217285,
|
| 294 |
+
"learning_rate": 5.333333333333334e-06,
|
| 295 |
+
"loss": 1.6247,
|
| 296 |
+
"step": 64
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.764705882352941,
|
| 300 |
+
"grad_norm": 0.8475298285484314,
|
| 301 |
+
"learning_rate": 5.500000000000001e-06,
|
| 302 |
+
"loss": 1.5891,
|
| 303 |
+
"step": 66
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.0,
|
| 307 |
+
"grad_norm": 0.755041778087616,
|
| 308 |
+
"learning_rate": 5.666666666666667e-06,
|
| 309 |
+
"loss": 1.5762,
|
| 310 |
+
"step": 68
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.0,
|
| 314 |
+
"eval_loss": 1.6084668636322021,
|
| 315 |
+
"eval_runtime": 14.5036,
|
| 316 |
+
"eval_samples_per_second": 2.482,
|
| 317 |
+
"eval_steps_per_second": 2.482,
|
| 318 |
+
"step": 68
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 8.235294117647058,
|
| 322 |
+
"grad_norm": 0.7044244408607483,
|
| 323 |
+
"learning_rate": 5.833333333333334e-06,
|
| 324 |
+
"loss": 1.5742,
|
| 325 |
+
"step": 70
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 8.470588235294118,
|
| 329 |
+
"grad_norm": 0.6197890043258667,
|
| 330 |
+
"learning_rate": 6e-06,
|
| 331 |
+
"loss": 1.5981,
|
| 332 |
+
"step": 72
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.705882352941176,
|
| 336 |
+
"grad_norm": 0.6438341736793518,
|
| 337 |
+
"learning_rate": 6.166666666666667e-06,
|
| 338 |
+
"loss": 1.5194,
|
| 339 |
+
"step": 74
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.941176470588236,
|
| 343 |
+
"grad_norm": 0.627289891242981,
|
| 344 |
+
"learning_rate": 6.333333333333333e-06,
|
| 345 |
+
"loss": 1.5529,
|
| 346 |
+
"step": 76
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 8.941176470588236,
|
| 350 |
+
"eval_loss": 1.5658942461013794,
|
| 351 |
+
"eval_runtime": 14.5082,
|
| 352 |
+
"eval_samples_per_second": 2.481,
|
| 353 |
+
"eval_steps_per_second": 2.481,
|
| 354 |
+
"step": 76
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.176470588235293,
|
| 358 |
+
"grad_norm": 0.6046221852302551,
|
| 359 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 360 |
+
"loss": 1.5489,
|
| 361 |
+
"step": 78
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 9.411764705882353,
|
| 365 |
+
"grad_norm": 0.5346683263778687,
|
| 366 |
+
"learning_rate": 6.666666666666667e-06,
|
| 367 |
+
"loss": 1.5338,
|
| 368 |
+
"step": 80
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 9.647058823529411,
|
| 372 |
+
"grad_norm": 0.5408790111541748,
|
| 373 |
+
"learning_rate": 6.833333333333334e-06,
|
| 374 |
+
"loss": 1.48,
|
| 375 |
+
"step": 82
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 9.882352941176471,
|
| 379 |
+
"grad_norm": 0.5899155735969543,
|
| 380 |
+
"learning_rate": 7e-06,
|
| 381 |
+
"loss": 1.4817,
|
| 382 |
+
"step": 84
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 10.0,
|
| 386 |
+
"eval_loss": 1.5206388235092163,
|
| 387 |
+
"eval_runtime": 14.5107,
|
| 388 |
+
"eval_samples_per_second": 2.481,
|
| 389 |
+
"eval_steps_per_second": 2.481,
|
| 390 |
+
"step": 85
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 10.117647058823529,
|
| 394 |
+
"grad_norm": 0.5904850363731384,
|
| 395 |
+
"learning_rate": 7.166666666666667e-06,
|
| 396 |
+
"loss": 1.4943,
|
| 397 |
+
"step": 86
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 10.352941176470589,
|
| 401 |
+
"grad_norm": 0.5600600838661194,
|
| 402 |
+
"learning_rate": 7.333333333333333e-06,
|
| 403 |
+
"loss": 1.4419,
|
| 404 |
+
"step": 88
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 10.588235294117647,
|
| 408 |
+
"grad_norm": 0.4918341636657715,
|
| 409 |
+
"learning_rate": 7.500000000000001e-06,
|
| 410 |
+
"loss": 1.3978,
|
| 411 |
+
"step": 90
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 10.823529411764707,
|
| 415 |
+
"grad_norm": 0.5680522322654724,
|
| 416 |
+
"learning_rate": 7.666666666666667e-06,
|
| 417 |
+
"loss": 1.5125,
|
| 418 |
+
"step": 92
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 10.941176470588236,
|
| 422 |
+
"eval_loss": 1.4815658330917358,
|
| 423 |
+
"eval_runtime": 14.5146,
|
| 424 |
+
"eval_samples_per_second": 2.48,
|
| 425 |
+
"eval_steps_per_second": 2.48,
|
| 426 |
+
"step": 93
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 11.058823529411764,
|
| 430 |
+
"grad_norm": 0.4833405911922455,
|
| 431 |
+
"learning_rate": 7.833333333333333e-06,
|
| 432 |
+
"loss": 1.5109,
|
| 433 |
+
"step": 94
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 11.294117647058824,
|
| 437 |
+
"grad_norm": 0.5413841605186462,
|
| 438 |
+
"learning_rate": 8.000000000000001e-06,
|
| 439 |
+
"loss": 1.4351,
|
| 440 |
+
"step": 96
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 11.529411764705882,
|
| 444 |
+
"grad_norm": 0.5074775218963623,
|
| 445 |
+
"learning_rate": 8.166666666666668e-06,
|
| 446 |
+
"loss": 1.4643,
|
| 447 |
+
"step": 98
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 11.764705882352942,
|
| 451 |
+
"grad_norm": 0.5865756869316101,
|
| 452 |
+
"learning_rate": 8.333333333333334e-06,
|
| 453 |
+
"loss": 1.3969,
|
| 454 |
+
"step": 100
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 12.0,
|
| 458 |
+
"grad_norm": 0.5256586074829102,
|
| 459 |
+
"learning_rate": 8.5e-06,
|
| 460 |
+
"loss": 1.3226,
|
| 461 |
+
"step": 102
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 12.0,
|
| 465 |
+
"eval_loss": 1.4351813793182373,
|
| 466 |
+
"eval_runtime": 14.5096,
|
| 467 |
+
"eval_samples_per_second": 2.481,
|
| 468 |
+
"eval_steps_per_second": 2.481,
|
| 469 |
+
"step": 102
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 12.235294117647058,
|
| 473 |
+
"grad_norm": 0.5593088269233704,
|
| 474 |
+
"learning_rate": 8.666666666666668e-06,
|
| 475 |
+
"loss": 1.4301,
|
| 476 |
+
"step": 104
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 12.470588235294118,
|
| 480 |
+
"grad_norm": 0.5165168642997742,
|
| 481 |
+
"learning_rate": 8.833333333333334e-06,
|
| 482 |
+
"loss": 1.2965,
|
| 483 |
+
"step": 106
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 12.705882352941176,
|
| 487 |
+
"grad_norm": 0.5415379405021667,
|
| 488 |
+
"learning_rate": 9e-06,
|
| 489 |
+
"loss": 1.3613,
|
| 490 |
+
"step": 108
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 12.941176470588236,
|
| 494 |
+
"grad_norm": 0.5435191988945007,
|
| 495 |
+
"learning_rate": 9.166666666666666e-06,
|
| 496 |
+
"loss": 1.3823,
|
| 497 |
+
"step": 110
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 12.941176470588236,
|
| 501 |
+
"eval_loss": 1.3951374292373657,
|
| 502 |
+
"eval_runtime": 14.5488,
|
| 503 |
+
"eval_samples_per_second": 2.474,
|
| 504 |
+
"eval_steps_per_second": 2.474,
|
| 505 |
+
"step": 110
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 13.176470588235293,
|
| 509 |
+
"grad_norm": 0.5483547449111938,
|
| 510 |
+
"learning_rate": 9.333333333333334e-06,
|
| 511 |
+
"loss": 1.3189,
|
| 512 |
+
"step": 112
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 13.411764705882353,
|
| 516 |
+
"grad_norm": 0.6265339851379395,
|
| 517 |
+
"learning_rate": 9.5e-06,
|
| 518 |
+
"loss": 1.3235,
|
| 519 |
+
"step": 114
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 13.647058823529411,
|
| 523 |
+
"grad_norm": 0.5347606539726257,
|
| 524 |
+
"learning_rate": 9.666666666666667e-06,
|
| 525 |
+
"loss": 1.3265,
|
| 526 |
+
"step": 116
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 13.882352941176471,
|
| 530 |
+
"grad_norm": 0.5550796389579773,
|
| 531 |
+
"learning_rate": 9.833333333333333e-06,
|
| 532 |
+
"loss": 1.2564,
|
| 533 |
+
"step": 118
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 14.0,
|
| 537 |
+
"eval_loss": 1.358044981956482,
|
| 538 |
+
"eval_runtime": 14.5168,
|
| 539 |
+
"eval_samples_per_second": 2.48,
|
| 540 |
+
"eval_steps_per_second": 2.48,
|
| 541 |
+
"step": 119
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 14.117647058823529,
|
| 545 |
+
"grad_norm": 0.5553519129753113,
|
| 546 |
+
"learning_rate": 1e-05,
|
| 547 |
+
"loss": 1.3011,
|
| 548 |
+
"step": 120
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 14.352941176470589,
|
| 552 |
+
"grad_norm": 0.5510237812995911,
|
| 553 |
+
"learning_rate": 9.999915384288723e-06,
|
| 554 |
+
"loss": 1.2783,
|
| 555 |
+
"step": 122
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 14.588235294117647,
|
| 559 |
+
"grad_norm": 0.5882507562637329,
|
| 560 |
+
"learning_rate": 9.999661540018812e-06,
|
| 561 |
+
"loss": 1.3425,
|
| 562 |
+
"step": 124
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 14.823529411764707,
|
| 566 |
+
"grad_norm": 0.5551594495773315,
|
| 567 |
+
"learning_rate": 9.999238475781957e-06,
|
| 568 |
+
"loss": 1.1936,
|
| 569 |
+
"step": 126
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 14.941176470588236,
|
| 573 |
+
"eval_loss": 1.330453872680664,
|
| 574 |
+
"eval_runtime": 14.5004,
|
| 575 |
+
"eval_samples_per_second": 2.483,
|
| 576 |
+
"eval_steps_per_second": 2.483,
|
| 577 |
+
"step": 127
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 15.058823529411764,
|
| 581 |
+
"grad_norm": 0.6728988885879517,
|
| 582 |
+
"learning_rate": 9.99864620589731e-06,
|
| 583 |
+
"loss": 1.2968,
|
| 584 |
+
"step": 128
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 15.294117647058824,
|
| 588 |
+
"grad_norm": 0.6072357892990112,
|
| 589 |
+
"learning_rate": 9.997884750411004e-06,
|
| 590 |
+
"loss": 1.2174,
|
| 591 |
+
"step": 130
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 15.529411764705882,
|
| 595 |
+
"grad_norm": 0.6069150567054749,
|
| 596 |
+
"learning_rate": 9.99695413509548e-06,
|
| 597 |
+
"loss": 1.2296,
|
| 598 |
+
"step": 132
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 15.764705882352942,
|
| 602 |
+
"grad_norm": 0.567636251449585,
|
| 603 |
+
"learning_rate": 9.995854391448607e-06,
|
| 604 |
+
"loss": 1.2153,
|
| 605 |
+
"step": 134
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 16.0,
|
| 609 |
+
"grad_norm": 0.6102450489997864,
|
| 610 |
+
"learning_rate": 9.994585556692624e-06,
|
| 611 |
+
"loss": 1.2322,
|
| 612 |
+
"step": 136
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 16.0,
|
| 616 |
+
"eval_loss": 1.306054949760437,
|
| 617 |
+
"eval_runtime": 14.4899,
|
| 618 |
+
"eval_samples_per_second": 2.484,
|
| 619 |
+
"eval_steps_per_second": 2.484,
|
| 620 |
+
"step": 136
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 16.235294117647058,
|
| 624 |
+
"grad_norm": 0.6264614462852478,
|
| 625 |
+
"learning_rate": 9.993147673772869e-06,
|
| 626 |
+
"loss": 1.1767,
|
| 627 |
+
"step": 138
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 16.470588235294116,
|
| 631 |
+
"grad_norm": 0.5897552967071533,
|
| 632 |
+
"learning_rate": 9.991540791356342e-06,
|
| 633 |
+
"loss": 1.2402,
|
| 634 |
+
"step": 140
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 16.705882352941178,
|
| 638 |
+
"grad_norm": 0.5707640647888184,
|
| 639 |
+
"learning_rate": 9.989764963830038e-06,
|
| 640 |
+
"loss": 1.1951,
|
| 641 |
+
"step": 142
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 16.941176470588236,
|
| 645 |
+
"grad_norm": 0.5615460276603699,
|
| 646 |
+
"learning_rate": 9.987820251299121e-06,
|
| 647 |
+
"loss": 1.1389,
|
| 648 |
+
"step": 144
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 16.941176470588236,
|
| 652 |
+
"eval_loss": 1.291010856628418,
|
| 653 |
+
"eval_runtime": 14.4995,
|
| 654 |
+
"eval_samples_per_second": 2.483,
|
| 655 |
+
"eval_steps_per_second": 2.483,
|
| 656 |
+
"step": 144
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 17.176470588235293,
|
| 660 |
+
"grad_norm": 0.6482234597206116,
|
| 661 |
+
"learning_rate": 9.985706719584888e-06,
|
| 662 |
+
"loss": 1.1827,
|
| 663 |
+
"step": 146
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 17.41176470588235,
|
| 667 |
+
"grad_norm": 0.7177907824516296,
|
| 668 |
+
"learning_rate": 9.98342444022253e-06,
|
| 669 |
+
"loss": 1.1384,
|
| 670 |
+
"step": 148
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 17.647058823529413,
|
| 674 |
+
"grad_norm": 0.6740428805351257,
|
| 675 |
+
"learning_rate": 9.980973490458728e-06,
|
| 676 |
+
"loss": 1.1597,
|
| 677 |
+
"step": 150
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 17.88235294117647,
|
| 681 |
+
"grad_norm": 0.6563602089881897,
|
| 682 |
+
"learning_rate": 9.978353953249023e-06,
|
| 683 |
+
"loss": 1.2119,
|
| 684 |
+
"step": 152
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 18.0,
|
| 688 |
+
"eval_loss": 1.2774587869644165,
|
| 689 |
+
"eval_runtime": 14.492,
|
| 690 |
+
"eval_samples_per_second": 2.484,
|
| 691 |
+
"eval_steps_per_second": 2.484,
|
| 692 |
+
"step": 153
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 18.11764705882353,
|
| 696 |
+
"grad_norm": 0.697040319442749,
|
| 697 |
+
"learning_rate": 9.975565917255017e-06,
|
| 698 |
+
"loss": 1.1046,
|
| 699 |
+
"step": 154
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 18.352941176470587,
|
| 703 |
+
"grad_norm": 0.6884188652038574,
|
| 704 |
+
"learning_rate": 9.972609476841368e-06,
|
| 705 |
+
"loss": 1.175,
|
| 706 |
+
"step": 156
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 18.58823529411765,
|
| 710 |
+
"grad_norm": 0.6756815910339355,
|
| 711 |
+
"learning_rate": 9.9694847320726e-06,
|
| 712 |
+
"loss": 1.1308,
|
| 713 |
+
"step": 158
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 18.823529411764707,
|
| 717 |
+
"grad_norm": 0.7454915046691895,
|
| 718 |
+
"learning_rate": 9.966191788709716e-06,
|
| 719 |
+
"loss": 1.0796,
|
| 720 |
+
"step": 160
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 18.941176470588236,
|
| 724 |
+
"eval_loss": 1.2671666145324707,
|
| 725 |
+
"eval_runtime": 14.491,
|
| 726 |
+
"eval_samples_per_second": 2.484,
|
| 727 |
+
"eval_steps_per_second": 2.484,
|
| 728 |
+
"step": 161
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 19.058823529411764,
|
| 732 |
+
"grad_norm": 0.7441277503967285,
|
| 733 |
+
"learning_rate": 9.962730758206612e-06,
|
| 734 |
+
"loss": 1.085,
|
| 735 |
+
"step": 162
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 19.294117647058822,
|
| 739 |
+
"grad_norm": 0.7544702887535095,
|
| 740 |
+
"learning_rate": 9.959101757706308e-06,
|
| 741 |
+
"loss": 1.1764,
|
| 742 |
+
"step": 164
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 19.529411764705884,
|
| 746 |
+
"grad_norm": 0.7890501022338867,
|
| 747 |
+
"learning_rate": 9.955304910036993e-06,
|
| 748 |
+
"loss": 1.0506,
|
| 749 |
+
"step": 166
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 19.764705882352942,
|
| 753 |
+
"grad_norm": 0.7971728444099426,
|
| 754 |
+
"learning_rate": 9.951340343707852e-06,
|
| 755 |
+
"loss": 1.058,
|
| 756 |
+
"step": 168
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 20.0,
|
| 760 |
+
"grad_norm": 0.7496370077133179,
|
| 761 |
+
"learning_rate": 9.947208192904722e-06,
|
| 762 |
+
"loss": 1.088,
|
| 763 |
+
"step": 170
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 20.0,
|
| 767 |
+
"eval_loss": 1.2627261877059937,
|
| 768 |
+
"eval_runtime": 14.4935,
|
| 769 |
+
"eval_samples_per_second": 2.484,
|
| 770 |
+
"eval_steps_per_second": 2.484,
|
| 771 |
+
"step": 170
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 20.235294117647058,
|
| 775 |
+
"grad_norm": 0.8145542740821838,
|
| 776 |
+
"learning_rate": 9.942908597485558e-06,
|
| 777 |
+
"loss": 1.0338,
|
| 778 |
+
"step": 172
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 20.470588235294116,
|
| 782 |
+
"grad_norm": 0.7999013662338257,
|
| 783 |
+
"learning_rate": 9.938441702975689e-06,
|
| 784 |
+
"loss": 1.1188,
|
| 785 |
+
"step": 174
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 20.705882352941178,
|
| 789 |
+
"grad_norm": 0.8285914659500122,
|
| 790 |
+
"learning_rate": 9.933807660562898e-06,
|
| 791 |
+
"loss": 1.0152,
|
| 792 |
+
"step": 176
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 20.941176470588236,
|
| 796 |
+
"grad_norm": 0.8708339333534241,
|
| 797 |
+
"learning_rate": 9.929006627092298e-06,
|
| 798 |
+
"loss": 1.0344,
|
| 799 |
+
"step": 178
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 20.941176470588236,
|
| 803 |
+
"eval_loss": 1.2630927562713623,
|
| 804 |
+
"eval_runtime": 14.4971,
|
| 805 |
+
"eval_samples_per_second": 2.483,
|
| 806 |
+
"eval_steps_per_second": 2.483,
|
| 807 |
+
"step": 178
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 21.176470588235293,
|
| 811 |
+
"grad_norm": 0.7319707274436951,
|
| 812 |
+
"learning_rate": 9.924038765061042e-06,
|
| 813 |
+
"loss": 1.0431,
|
| 814 |
+
"step": 180
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 21.41176470588235,
|
| 818 |
+
"grad_norm": 0.9208843111991882,
|
| 819 |
+
"learning_rate": 9.918904242612794e-06,
|
| 820 |
+
"loss": 1.0477,
|
| 821 |
+
"step": 182
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 21.647058823529413,
|
| 825 |
+
"grad_norm": 0.9072057604789734,
|
| 826 |
+
"learning_rate": 9.913603233532067e-06,
|
| 827 |
+
"loss": 1.0263,
|
| 828 |
+
"step": 184
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 21.88235294117647,
|
| 832 |
+
"grad_norm": 0.873211145401001,
|
| 833 |
+
"learning_rate": 9.908135917238321e-06,
|
| 834 |
+
"loss": 1.0175,
|
| 835 |
+
"step": 186
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 22.0,
|
| 839 |
+
"eval_loss": 1.258855938911438,
|
| 840 |
+
"eval_runtime": 14.489,
|
| 841 |
+
"eval_samples_per_second": 2.485,
|
| 842 |
+
"eval_steps_per_second": 2.485,
|
| 843 |
+
"step": 187
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 22.11764705882353,
|
| 847 |
+
"grad_norm": 0.9776601791381836,
|
| 848 |
+
"learning_rate": 9.902502478779897e-06,
|
| 849 |
+
"loss": 0.9928,
|
| 850 |
+
"step": 188
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 22.352941176470587,
|
| 854 |
+
"grad_norm": 0.9805429577827454,
|
| 855 |
+
"learning_rate": 9.896703108827758e-06,
|
| 856 |
+
"loss": 0.9626,
|
| 857 |
+
"step": 190
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 22.58823529411765,
|
| 861 |
+
"grad_norm": 0.8789134621620178,
|
| 862 |
+
"learning_rate": 9.890738003669029e-06,
|
| 863 |
+
"loss": 0.9428,
|
| 864 |
+
"step": 192
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 22.823529411764707,
|
| 868 |
+
"grad_norm": 1.0301721096038818,
|
| 869 |
+
"learning_rate": 9.884607365200355e-06,
|
| 870 |
+
"loss": 0.9509,
|
| 871 |
+
"step": 194
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 22.941176470588236,
|
| 875 |
+
"eval_loss": 1.2707229852676392,
|
| 876 |
+
"eval_runtime": 14.5009,
|
| 877 |
+
"eval_samples_per_second": 2.483,
|
| 878 |
+
"eval_steps_per_second": 2.483,
|
| 879 |
+
"step": 195
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 23.058823529411764,
|
| 883 |
+
"grad_norm": 1.148660659790039,
|
| 884 |
+
"learning_rate": 9.878311400921072e-06,
|
| 885 |
+
"loss": 0.994,
|
| 886 |
+
"step": 196
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 23.294117647058822,
|
| 890 |
+
"grad_norm": 1.0924886465072632,
|
| 891 |
+
"learning_rate": 9.871850323926178e-06,
|
| 892 |
+
"loss": 1.04,
|
| 893 |
+
"step": 198
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 23.529411764705884,
|
| 897 |
+
"grad_norm": 1.0336880683898926,
|
| 898 |
+
"learning_rate": 9.86522435289912e-06,
|
| 899 |
+
"loss": 0.897,
|
| 900 |
+
"step": 200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 23.764705882352942,
|
| 904 |
+
"grad_norm": 1.0547744035720825,
|
| 905 |
+
"learning_rate": 9.858433712104403e-06,
|
| 906 |
+
"loss": 0.9449,
|
| 907 |
+
"step": 202
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 24.0,
|
| 911 |
+
"grad_norm": 1.0507797002792358,
|
| 912 |
+
"learning_rate": 9.851478631379982e-06,
|
| 913 |
+
"loss": 0.8574,
|
| 914 |
+
"step": 204
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 24.0,
|
| 918 |
+
"eval_loss": 1.2783534526824951,
|
| 919 |
+
"eval_runtime": 14.4915,
|
| 920 |
+
"eval_samples_per_second": 2.484,
|
| 921 |
+
"eval_steps_per_second": 2.484,
|
| 922 |
+
"step": 204
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 24.235294117647058,
|
| 926 |
+
"grad_norm": 1.1866151094436646,
|
| 927 |
+
"learning_rate": 9.844359346129504e-06,
|
| 928 |
+
"loss": 0.9402,
|
| 929 |
+
"step": 206
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 24.470588235294116,
|
| 933 |
+
"grad_norm": 1.207543134689331,
|
| 934 |
+
"learning_rate": 9.83707609731432e-06,
|
| 935 |
+
"loss": 0.8642,
|
| 936 |
+
"step": 208
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 24.705882352941178,
|
| 940 |
+
"grad_norm": 1.3277732133865356,
|
| 941 |
+
"learning_rate": 9.829629131445342e-06,
|
| 942 |
+
"loss": 0.8979,
|
| 943 |
+
"step": 210
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 24.941176470588236,
|
| 947 |
+
"grad_norm": 1.2087572813034058,
|
| 948 |
+
"learning_rate": 9.822018700574696e-06,
|
| 949 |
+
"loss": 0.8673,
|
| 950 |
+
"step": 212
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 24.941176470588236,
|
| 954 |
+
"eval_loss": 1.2985085248947144,
|
| 955 |
+
"eval_runtime": 14.5378,
|
| 956 |
+
"eval_samples_per_second": 2.476,
|
| 957 |
+
"eval_steps_per_second": 2.476,
|
| 958 |
+
"step": 212
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 25.176470588235293,
|
| 962 |
+
"grad_norm": 1.185181975364685,
|
| 963 |
+
"learning_rate": 9.81424506228719e-06,
|
| 964 |
+
"loss": 0.839,
|
| 965 |
+
"step": 214
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 25.41176470588235,
|
| 969 |
+
"grad_norm": 1.223609209060669,
|
| 970 |
+
"learning_rate": 9.806308479691595e-06,
|
| 971 |
+
"loss": 0.8175,
|
| 972 |
+
"step": 216
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 25.647058823529413,
|
| 976 |
+
"grad_norm": 1.1787949800491333,
|
| 977 |
+
"learning_rate": 9.798209221411748e-06,
|
| 978 |
+
"loss": 0.8512,
|
| 979 |
+
"step": 218
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 25.88235294117647,
|
| 983 |
+
"grad_norm": 1.4942697286605835,
|
| 984 |
+
"learning_rate": 9.789947561577445e-06,
|
| 985 |
+
"loss": 0.8657,
|
| 986 |
+
"step": 220
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 26.0,
|
| 990 |
+
"eval_loss": 1.32999849319458,
|
| 991 |
+
"eval_runtime": 14.4921,
|
| 992 |
+
"eval_samples_per_second": 2.484,
|
| 993 |
+
"eval_steps_per_second": 2.484,
|
| 994 |
+
"step": 221
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 26.11764705882353,
|
| 998 |
+
"grad_norm": 1.2106794118881226,
|
| 999 |
+
"learning_rate": 9.781523779815178e-06,
|
| 1000 |
+
"loss": 0.8279,
|
| 1001 |
+
"step": 222
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 26.352941176470587,
|
| 1005 |
+
"grad_norm": 1.2683756351470947,
|
| 1006 |
+
"learning_rate": 9.77293816123866e-06,
|
| 1007 |
+
"loss": 0.8012,
|
| 1008 |
+
"step": 224
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 26.58823529411765,
|
| 1012 |
+
"grad_norm": 1.3693079948425293,
|
| 1013 |
+
"learning_rate": 9.764190996439181e-06,
|
| 1014 |
+
"loss": 0.7962,
|
| 1015 |
+
"step": 226
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 26.823529411764707,
|
| 1019 |
+
"grad_norm": 1.341029405593872,
|
| 1020 |
+
"learning_rate": 9.755282581475769e-06,
|
| 1021 |
+
"loss": 0.7453,
|
| 1022 |
+
"step": 228
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 26.941176470588236,
|
| 1026 |
+
"eval_loss": 1.3724702596664429,
|
| 1027 |
+
"eval_runtime": 14.5144,
|
| 1028 |
+
"eval_samples_per_second": 2.48,
|
| 1029 |
+
"eval_steps_per_second": 2.48,
|
| 1030 |
+
"step": 229
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 27.058823529411764,
|
| 1034 |
+
"grad_norm": 1.5795172452926636,
|
| 1035 |
+
"learning_rate": 9.74621321786517e-06,
|
| 1036 |
+
"loss": 0.7852,
|
| 1037 |
+
"step": 230
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 27.294117647058822,
|
| 1041 |
+
"grad_norm": 1.4557024240493774,
|
| 1042 |
+
"learning_rate": 9.736983212571646e-06,
|
| 1043 |
+
"loss": 0.7336,
|
| 1044 |
+
"step": 232
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 27.529411764705884,
|
| 1048 |
+
"grad_norm": 1.538028597831726,
|
| 1049 |
+
"learning_rate": 9.727592877996585e-06,
|
| 1050 |
+
"loss": 0.7007,
|
| 1051 |
+
"step": 234
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 27.764705882352942,
|
| 1055 |
+
"grad_norm": 1.7676023244857788,
|
| 1056 |
+
"learning_rate": 9.718042531967918e-06,
|
| 1057 |
+
"loss": 0.7119,
|
| 1058 |
+
"step": 236
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 28.0,
|
| 1062 |
+
"grad_norm": 1.5406033992767334,
|
| 1063 |
+
"learning_rate": 9.708332497729378e-06,
|
| 1064 |
+
"loss": 0.7771,
|
| 1065 |
+
"step": 238
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 28.0,
|
| 1069 |
+
"eval_loss": 1.382300853729248,
|
| 1070 |
+
"eval_runtime": 14.493,
|
| 1071 |
+
"eval_samples_per_second": 2.484,
|
| 1072 |
+
"eval_steps_per_second": 2.484,
|
| 1073 |
+
"step": 238
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 28.235294117647058,
|
| 1077 |
+
"grad_norm": 1.6042836904525757,
|
| 1078 |
+
"learning_rate": 9.698463103929542e-06,
|
| 1079 |
+
"loss": 0.6619,
|
| 1080 |
+
"step": 240
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 28.470588235294116,
|
| 1084 |
+
"grad_norm": 1.640479326248169,
|
| 1085 |
+
"learning_rate": 9.688434684610725e-06,
|
| 1086 |
+
"loss": 0.7059,
|
| 1087 |
+
"step": 242
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 28.705882352941178,
|
| 1091 |
+
"grad_norm": 1.919432282447815,
|
| 1092 |
+
"learning_rate": 9.678247579197658e-06,
|
| 1093 |
+
"loss": 0.6835,
|
| 1094 |
+
"step": 244
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 28.941176470588236,
|
| 1098 |
+
"grad_norm": 2.0142574310302734,
|
| 1099 |
+
"learning_rate": 9.667902132486009e-06,
|
| 1100 |
+
"loss": 0.6941,
|
| 1101 |
+
"step": 246
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 28.941176470588236,
|
| 1105 |
+
"eval_loss": 1.450831651687622,
|
| 1106 |
+
"eval_runtime": 14.51,
|
| 1107 |
+
"eval_samples_per_second": 2.481,
|
| 1108 |
+
"eval_steps_per_second": 2.481,
|
| 1109 |
+
"step": 246
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 28.941176470588236,
|
| 1113 |
+
"step": 246,
|
| 1114 |
+
"total_flos": 6.277931324145664e+16,
|
| 1115 |
+
"train_loss": 1.3461502527560645,
|
| 1116 |
+
"train_runtime": 4652.7461,
|
| 1117 |
+
"train_samples_per_second": 4.385,
|
| 1118 |
+
"train_steps_per_second": 0.258
|
| 1119 |
+
}
|
| 1120 |
+
],
|
| 1121 |
+
"logging_steps": 2,
|
| 1122 |
+
"max_steps": 1200,
|
| 1123 |
+
"num_input_tokens_seen": 0,
|
| 1124 |
+
"num_train_epochs": 150,
|
| 1125 |
+
"save_steps": 25,
|
| 1126 |
+
"stateful_callbacks": {
|
| 1127 |
+
"EarlyStoppingCallback": {
|
| 1128 |
+
"args": {
|
| 1129 |
+
"early_stopping_patience": 7,
|
| 1130 |
+
"early_stopping_threshold": 0.0
|
| 1131 |
+
},
|
| 1132 |
+
"attributes": {
|
| 1133 |
+
"early_stopping_patience_counter": 0
|
| 1134 |
+
}
|
| 1135 |
+
},
|
| 1136 |
+
"TrainerControl": {
|
| 1137 |
+
"args": {
|
| 1138 |
+
"should_epoch_stop": false,
|
| 1139 |
+
"should_evaluate": false,
|
| 1140 |
+
"should_log": false,
|
| 1141 |
+
"should_save": true,
|
| 1142 |
+
"should_training_stop": true
|
| 1143 |
+
},
|
| 1144 |
+
"attributes": {}
|
| 1145 |
+
}
|
| 1146 |
+
},
|
| 1147 |
+
"total_flos": 6.277931324145664e+16,
|
| 1148 |
+
"train_batch_size": 1,
|
| 1149 |
+
"trial_name": null,
|
| 1150 |
+
"trial_params": null
|
| 1151 |
+
}
|