Model save
Browse files- README.md +78 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1992 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: 01-ai/Yi-6B
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Yi-6B-ruozhiba-1e-5-50
|
| 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 |
+
# Yi-6B-ruozhiba-1e-5-50
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.9875
|
| 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: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 20
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 1.8114 | 4.0 | 220 | 1.8505 |
|
| 54 |
+
| 1.6723 | 5.0 | 275 | 1.8372 |
|
| 55 |
+
| 1.6532 | 6.0 | 330 | 1.8296 |
|
| 56 |
+
| 1.7187 | 7.0 | 385 | 1.8273 |
|
| 57 |
+
| 1.6945 | 8.0 | 440 | 1.8345 |
|
| 58 |
+
| 1.5494 | 9.0 | 495 | 1.8452 |
|
| 59 |
+
| 1.5329 | 10.0 | 550 | 1.8665 |
|
| 60 |
+
| 1.4105 | 11.0 | 605 | 1.8877 |
|
| 61 |
+
| 1.3862 | 12.0 | 660 | 1.9066 |
|
| 62 |
+
| 1.4126 | 13.0 | 715 | 1.9303 |
|
| 63 |
+
| 1.388 | 14.0 | 770 | 1.9449 |
|
| 64 |
+
| 1.3653 | 15.0 | 825 | 1.9637 |
|
| 65 |
+
| 1.361 | 16.0 | 880 | 1.9738 |
|
| 66 |
+
| 1.2944 | 17.0 | 935 | 1.9819 |
|
| 67 |
+
| 1.3433 | 18.0 | 990 | 1.9856 |
|
| 68 |
+
| 1.2058 | 19.0 | 1045 | 1.9871 |
|
| 69 |
+
| 1.2904 | 20.0 | 1100 | 1.9875 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.7.1
|
| 75 |
+
- Transformers 4.36.2
|
| 76 |
+
- Pytorch 2.2.2+cu118
|
| 77 |
+
- Datasets 2.14.6
|
| 78 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 1.987522840499878,
|
| 4 |
+
"eval_runtime": 4.9168,
|
| 5 |
+
"eval_samples": 23,
|
| 6 |
+
"eval_samples_per_second": 4.678,
|
| 7 |
+
"eval_steps_per_second": 1.22,
|
| 8 |
+
"train_loss": 1.2573659207604149,
|
| 9 |
+
"train_runtime": 10567.2291,
|
| 10 |
+
"train_samples": 217,
|
| 11 |
+
"train_samples_per_second": 0.411,
|
| 12 |
+
"train_steps_per_second": 0.104
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 1.987522840499878,
|
| 4 |
+
"eval_runtime": 4.9168,
|
| 5 |
+
"eval_samples": 23,
|
| 6 |
+
"eval_samples_per_second": 4.678,
|
| 7 |
+
"eval_steps_per_second": 1.22
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 1.2573659207604149,
|
| 4 |
+
"train_runtime": 10567.2291,
|
| 5 |
+
"train_samples": 217,
|
| 6 |
+
"train_samples_per_second": 0.411,
|
| 7 |
+
"train_steps_per_second": 0.104
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1992 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 9.090909090909091e-08,
|
| 14 |
+
"loss": 2.3833,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 20 |
+
"loss": 2.4789,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 7.272727272727273e-07,
|
| 26 |
+
"loss": 2.3195,
|
| 27 |
+
"step": 8
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.22,
|
| 31 |
+
"learning_rate": 1.090909090909091e-06,
|
| 32 |
+
"loss": 2.3366,
|
| 33 |
+
"step": 12
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.29,
|
| 37 |
+
"learning_rate": 1.4545454545454546e-06,
|
| 38 |
+
"loss": 2.3221,
|
| 39 |
+
"step": 16
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.36,
|
| 43 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 44 |
+
"loss": 2.4036,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.44,
|
| 49 |
+
"learning_rate": 2.181818181818182e-06,
|
| 50 |
+
"loss": 2.4224,
|
| 51 |
+
"step": 24
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.51,
|
| 55 |
+
"learning_rate": 2.5454545454545456e-06,
|
| 56 |
+
"loss": 2.6085,
|
| 57 |
+
"step": 28
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.58,
|
| 61 |
+
"learning_rate": 2.9090909090909093e-06,
|
| 62 |
+
"loss": 2.5477,
|
| 63 |
+
"step": 32
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.65,
|
| 67 |
+
"learning_rate": 3.272727272727273e-06,
|
| 68 |
+
"loss": 2.4446,
|
| 69 |
+
"step": 36
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.73,
|
| 73 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 74 |
+
"loss": 2.3109,
|
| 75 |
+
"step": 40
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.8,
|
| 79 |
+
"learning_rate": 4.000000000000001e-06,
|
| 80 |
+
"loss": 2.4149,
|
| 81 |
+
"step": 44
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.87,
|
| 85 |
+
"learning_rate": 4.363636363636364e-06,
|
| 86 |
+
"loss": 2.5514,
|
| 87 |
+
"step": 48
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.95,
|
| 91 |
+
"learning_rate": 4.727272727272728e-06,
|
| 92 |
+
"loss": 2.3816,
|
| 93 |
+
"step": 52
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.02,
|
| 97 |
+
"learning_rate": 5.090909090909091e-06,
|
| 98 |
+
"loss": 2.6293,
|
| 99 |
+
"step": 56
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.09,
|
| 103 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 104 |
+
"loss": 2.2422,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.16,
|
| 109 |
+
"learning_rate": 5.8181818181818185e-06,
|
| 110 |
+
"loss": 2.4031,
|
| 111 |
+
"step": 64
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.24,
|
| 115 |
+
"learning_rate": 6.181818181818182e-06,
|
| 116 |
+
"loss": 2.2303,
|
| 117 |
+
"step": 68
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.31,
|
| 121 |
+
"learning_rate": 6.545454545454546e-06,
|
| 122 |
+
"loss": 2.2847,
|
| 123 |
+
"step": 72
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.38,
|
| 127 |
+
"learning_rate": 6.90909090909091e-06,
|
| 128 |
+
"loss": 2.1578,
|
| 129 |
+
"step": 76
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.45,
|
| 133 |
+
"learning_rate": 7.272727272727273e-06,
|
| 134 |
+
"loss": 2.1774,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.53,
|
| 139 |
+
"learning_rate": 7.636363636363638e-06,
|
| 140 |
+
"loss": 2.197,
|
| 141 |
+
"step": 84
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.6,
|
| 145 |
+
"learning_rate": 8.000000000000001e-06,
|
| 146 |
+
"loss": 2.2093,
|
| 147 |
+
"step": 88
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.67,
|
| 151 |
+
"learning_rate": 8.363636363636365e-06,
|
| 152 |
+
"loss": 2.1004,
|
| 153 |
+
"step": 92
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.75,
|
| 157 |
+
"learning_rate": 8.727272727272728e-06,
|
| 158 |
+
"loss": 2.0526,
|
| 159 |
+
"step": 96
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.82,
|
| 163 |
+
"learning_rate": 9.090909090909091e-06,
|
| 164 |
+
"loss": 2.0771,
|
| 165 |
+
"step": 100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.89,
|
| 169 |
+
"learning_rate": 9.454545454545456e-06,
|
| 170 |
+
"loss": 2.0219,
|
| 171 |
+
"step": 104
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.96,
|
| 175 |
+
"learning_rate": 9.81818181818182e-06,
|
| 176 |
+
"loss": 1.9439,
|
| 177 |
+
"step": 108
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.04,
|
| 181 |
+
"learning_rate": 9.999899300364534e-06,
|
| 182 |
+
"loss": 1.9175,
|
| 183 |
+
"step": 112
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.11,
|
| 187 |
+
"learning_rate": 9.99909372761763e-06,
|
| 188 |
+
"loss": 1.8281,
|
| 189 |
+
"step": 116
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.18,
|
| 193 |
+
"learning_rate": 9.997482711915926e-06,
|
| 194 |
+
"loss": 1.9423,
|
| 195 |
+
"step": 120
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.25,
|
| 199 |
+
"learning_rate": 9.99506651282272e-06,
|
| 200 |
+
"loss": 1.9385,
|
| 201 |
+
"step": 124
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.33,
|
| 205 |
+
"learning_rate": 9.991845519630679e-06,
|
| 206 |
+
"loss": 2.0381,
|
| 207 |
+
"step": 128
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.4,
|
| 211 |
+
"learning_rate": 9.987820251299121e-06,
|
| 212 |
+
"loss": 2.0296,
|
| 213 |
+
"step": 132
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.47,
|
| 217 |
+
"learning_rate": 9.982991356370404e-06,
|
| 218 |
+
"loss": 1.9167,
|
| 219 |
+
"step": 136
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.55,
|
| 223 |
+
"learning_rate": 9.977359612865424e-06,
|
| 224 |
+
"loss": 1.9132,
|
| 225 |
+
"step": 140
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.62,
|
| 229 |
+
"learning_rate": 9.970925928158275e-06,
|
| 230 |
+
"loss": 1.8455,
|
| 231 |
+
"step": 144
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.69,
|
| 235 |
+
"learning_rate": 9.963691338830045e-06,
|
| 236 |
+
"loss": 1.8692,
|
| 237 |
+
"step": 148
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.76,
|
| 241 |
+
"learning_rate": 9.955657010501807e-06,
|
| 242 |
+
"loss": 1.8812,
|
| 243 |
+
"step": 152
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.84,
|
| 247 |
+
"learning_rate": 9.946824237646823e-06,
|
| 248 |
+
"loss": 1.9785,
|
| 249 |
+
"step": 156
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.91,
|
| 253 |
+
"learning_rate": 9.937194443381972e-06,
|
| 254 |
+
"loss": 1.9511,
|
| 255 |
+
"step": 160
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.98,
|
| 259 |
+
"learning_rate": 9.926769179238467e-06,
|
| 260 |
+
"loss": 1.8505,
|
| 261 |
+
"step": 164
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.05,
|
| 265 |
+
"learning_rate": 9.915550124911866e-06,
|
| 266 |
+
"loss": 1.9195,
|
| 267 |
+
"step": 168
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.13,
|
| 271 |
+
"learning_rate": 9.903539087991462e-06,
|
| 272 |
+
"loss": 1.8527,
|
| 273 |
+
"step": 172
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.2,
|
| 277 |
+
"learning_rate": 9.890738003669029e-06,
|
| 278 |
+
"loss": 1.7579,
|
| 279 |
+
"step": 176
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.27,
|
| 283 |
+
"learning_rate": 9.877148934427037e-06,
|
| 284 |
+
"loss": 1.9244,
|
| 285 |
+
"step": 180
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.35,
|
| 289 |
+
"learning_rate": 9.862774069706346e-06,
|
| 290 |
+
"loss": 1.8144,
|
| 291 |
+
"step": 184
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.42,
|
| 295 |
+
"learning_rate": 9.847615725553457e-06,
|
| 296 |
+
"loss": 1.8462,
|
| 297 |
+
"step": 188
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.49,
|
| 301 |
+
"learning_rate": 9.831676344247343e-06,
|
| 302 |
+
"loss": 1.7888,
|
| 303 |
+
"step": 192
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.56,
|
| 307 |
+
"learning_rate": 9.814958493905962e-06,
|
| 308 |
+
"loss": 1.9216,
|
| 309 |
+
"step": 196
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.64,
|
| 313 |
+
"learning_rate": 9.797464868072489e-06,
|
| 314 |
+
"loss": 1.7411,
|
| 315 |
+
"step": 200
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.71,
|
| 319 |
+
"learning_rate": 9.779198285281326e-06,
|
| 320 |
+
"loss": 1.7989,
|
| 321 |
+
"step": 204
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.78,
|
| 325 |
+
"learning_rate": 9.760161688604008e-06,
|
| 326 |
+
"loss": 1.8476,
|
| 327 |
+
"step": 208
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.85,
|
| 331 |
+
"learning_rate": 9.740358145174999e-06,
|
| 332 |
+
"loss": 1.7767,
|
| 333 |
+
"step": 212
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.93,
|
| 337 |
+
"learning_rate": 9.719790845697534e-06,
|
| 338 |
+
"loss": 1.7036,
|
| 339 |
+
"step": 216
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.0,
|
| 343 |
+
"learning_rate": 9.698463103929542e-06,
|
| 344 |
+
"loss": 1.8114,
|
| 345 |
+
"step": 220
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.0,
|
| 349 |
+
"gpt4_scores": 0.65,
|
| 350 |
+
"step": 220
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.0,
|
| 354 |
+
"std": 0.11335784048754634,
|
| 355 |
+
"step": 220
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 4.0,
|
| 359 |
+
"eval_loss": 1.8505451679229736,
|
| 360 |
+
"eval_runtime": 4.9659,
|
| 361 |
+
"eval_samples_per_second": 4.632,
|
| 362 |
+
"eval_steps_per_second": 1.208,
|
| 363 |
+
"step": 220
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.07,
|
| 367 |
+
"learning_rate": 9.676378356149733e-06,
|
| 368 |
+
"loss": 1.7635,
|
| 369 |
+
"step": 224
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.15,
|
| 373 |
+
"learning_rate": 9.653540160603956e-06,
|
| 374 |
+
"loss": 1.5819,
|
| 375 |
+
"step": 228
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.22,
|
| 379 |
+
"learning_rate": 9.629952196931902e-06,
|
| 380 |
+
"loss": 1.8023,
|
| 381 |
+
"step": 232
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.29,
|
| 385 |
+
"learning_rate": 9.60561826557425e-06,
|
| 386 |
+
"loss": 1.7447,
|
| 387 |
+
"step": 236
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.36,
|
| 391 |
+
"learning_rate": 9.580542287160348e-06,
|
| 392 |
+
"loss": 1.7547,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.44,
|
| 397 |
+
"learning_rate": 9.554728301876525e-06,
|
| 398 |
+
"loss": 1.8657,
|
| 399 |
+
"step": 244
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.51,
|
| 403 |
+
"learning_rate": 9.528180468815155e-06,
|
| 404 |
+
"loss": 1.7641,
|
| 405 |
+
"step": 248
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.58,
|
| 409 |
+
"learning_rate": 9.50090306530454e-06,
|
| 410 |
+
"loss": 1.7088,
|
| 411 |
+
"step": 252
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.65,
|
| 415 |
+
"learning_rate": 9.47290048621977e-06,
|
| 416 |
+
"loss": 1.8404,
|
| 417 |
+
"step": 256
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.73,
|
| 421 |
+
"learning_rate": 9.444177243274619e-06,
|
| 422 |
+
"loss": 1.7781,
|
| 423 |
+
"step": 260
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.8,
|
| 427 |
+
"learning_rate": 9.414737964294636e-06,
|
| 428 |
+
"loss": 1.804,
|
| 429 |
+
"step": 264
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.87,
|
| 433 |
+
"learning_rate": 9.384587392471516e-06,
|
| 434 |
+
"loss": 1.8061,
|
| 435 |
+
"step": 268
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.95,
|
| 439 |
+
"learning_rate": 9.353730385598887e-06,
|
| 440 |
+
"loss": 1.6723,
|
| 441 |
+
"step": 272
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 5.0,
|
| 445 |
+
"gpt4_scores": 0.73,
|
| 446 |
+
"step": 275
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.0,
|
| 450 |
+
"std": 0.10959014554237986,
|
| 451 |
+
"step": 275
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 5.0,
|
| 455 |
+
"eval_loss": 1.8371697664260864,
|
| 456 |
+
"eval_runtime": 4.9576,
|
| 457 |
+
"eval_samples_per_second": 4.639,
|
| 458 |
+
"eval_steps_per_second": 1.21,
|
| 459 |
+
"step": 275
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 5.02,
|
| 463 |
+
"learning_rate": 9.322171915289635e-06,
|
| 464 |
+
"loss": 1.7486,
|
| 465 |
+
"step": 276
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 5.09,
|
| 469 |
+
"learning_rate": 9.289917066174887e-06,
|
| 470 |
+
"loss": 1.7675,
|
| 471 |
+
"step": 280
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 5.16,
|
| 475 |
+
"learning_rate": 9.256971035084786e-06,
|
| 476 |
+
"loss": 1.7188,
|
| 477 |
+
"step": 284
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 5.24,
|
| 481 |
+
"learning_rate": 9.223339130211194e-06,
|
| 482 |
+
"loss": 1.7628,
|
| 483 |
+
"step": 288
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.31,
|
| 487 |
+
"learning_rate": 9.189026770252437e-06,
|
| 488 |
+
"loss": 1.6931,
|
| 489 |
+
"step": 292
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.38,
|
| 493 |
+
"learning_rate": 9.154039483540273e-06,
|
| 494 |
+
"loss": 1.5731,
|
| 495 |
+
"step": 296
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.45,
|
| 499 |
+
"learning_rate": 9.118382907149164e-06,
|
| 500 |
+
"loss": 1.7763,
|
| 501 |
+
"step": 300
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.53,
|
| 505 |
+
"learning_rate": 9.08206278598805e-06,
|
| 506 |
+
"loss": 1.7601,
|
| 507 |
+
"step": 304
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 5.6,
|
| 511 |
+
"learning_rate": 9.045084971874738e-06,
|
| 512 |
+
"loss": 1.6893,
|
| 513 |
+
"step": 308
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.67,
|
| 517 |
+
"learning_rate": 9.007455422593077e-06,
|
| 518 |
+
"loss": 1.7848,
|
| 519 |
+
"step": 312
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.75,
|
| 523 |
+
"learning_rate": 8.969180200933048e-06,
|
| 524 |
+
"loss": 1.7517,
|
| 525 |
+
"step": 316
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.82,
|
| 529 |
+
"learning_rate": 8.930265473713939e-06,
|
| 530 |
+
"loss": 1.6602,
|
| 531 |
+
"step": 320
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 5.89,
|
| 535 |
+
"learning_rate": 8.890717510790763e-06,
|
| 536 |
+
"loss": 1.6003,
|
| 537 |
+
"step": 324
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 5.96,
|
| 541 |
+
"learning_rate": 8.850542684044078e-06,
|
| 542 |
+
"loss": 1.6532,
|
| 543 |
+
"step": 328
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 6.0,
|
| 547 |
+
"gpt4_scores": 0.65,
|
| 548 |
+
"step": 330
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.0,
|
| 552 |
+
"std": 0.1298075498574717,
|
| 553 |
+
"step": 330
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.0,
|
| 557 |
+
"eval_loss": 1.8295962810516357,
|
| 558 |
+
"eval_runtime": 4.9535,
|
| 559 |
+
"eval_samples_per_second": 4.643,
|
| 560 |
+
"eval_steps_per_second": 1.211,
|
| 561 |
+
"step": 330
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 6.04,
|
| 565 |
+
"learning_rate": 8.809747466353356e-06,
|
| 566 |
+
"loss": 1.597,
|
| 567 |
+
"step": 332
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.11,
|
| 571 |
+
"learning_rate": 8.768338430554083e-06,
|
| 572 |
+
"loss": 1.7247,
|
| 573 |
+
"step": 336
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 6.18,
|
| 577 |
+
"learning_rate": 8.726322248378775e-06,
|
| 578 |
+
"loss": 1.7433,
|
| 579 |
+
"step": 340
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 6.25,
|
| 583 |
+
"learning_rate": 8.683705689382025e-06,
|
| 584 |
+
"loss": 1.6082,
|
| 585 |
+
"step": 344
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 6.33,
|
| 589 |
+
"learning_rate": 8.640495619849821e-06,
|
| 590 |
+
"loss": 1.6855,
|
| 591 |
+
"step": 348
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 6.4,
|
| 595 |
+
"learning_rate": 8.596699001693257e-06,
|
| 596 |
+
"loss": 1.5826,
|
| 597 |
+
"step": 352
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.47,
|
| 601 |
+
"learning_rate": 8.552322891326846e-06,
|
| 602 |
+
"loss": 1.6749,
|
| 603 |
+
"step": 356
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 6.55,
|
| 607 |
+
"learning_rate": 8.507374438531606e-06,
|
| 608 |
+
"loss": 1.649,
|
| 609 |
+
"step": 360
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 6.62,
|
| 613 |
+
"learning_rate": 8.461860885303116e-06,
|
| 614 |
+
"loss": 1.6959,
|
| 615 |
+
"step": 364
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 6.69,
|
| 619 |
+
"learning_rate": 8.415789564684673e-06,
|
| 620 |
+
"loss": 1.6805,
|
| 621 |
+
"step": 368
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 6.76,
|
| 625 |
+
"learning_rate": 8.36916789958584e-06,
|
| 626 |
+
"loss": 1.67,
|
| 627 |
+
"step": 372
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 6.84,
|
| 631 |
+
"learning_rate": 8.322003401586463e-06,
|
| 632 |
+
"loss": 1.6226,
|
| 633 |
+
"step": 376
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 6.91,
|
| 637 |
+
"learning_rate": 8.274303669726427e-06,
|
| 638 |
+
"loss": 1.6525,
|
| 639 |
+
"step": 380
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.98,
|
| 643 |
+
"learning_rate": 8.226076389281316e-06,
|
| 644 |
+
"loss": 1.7187,
|
| 645 |
+
"step": 384
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 7.0,
|
| 649 |
+
"gpt4_scores": 0.74,
|
| 650 |
+
"step": 385
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.0,
|
| 654 |
+
"std": 0.11153474794878948,
|
| 655 |
+
"step": 385
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 7.0,
|
| 659 |
+
"eval_loss": 1.8273346424102783,
|
| 660 |
+
"eval_runtime": 4.923,
|
| 661 |
+
"eval_samples_per_second": 4.672,
|
| 662 |
+
"eval_steps_per_second": 1.219,
|
| 663 |
+
"step": 385
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 7.05,
|
| 667 |
+
"learning_rate": 8.177329330524182e-06,
|
| 668 |
+
"loss": 1.6103,
|
| 669 |
+
"step": 388
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 7.13,
|
| 673 |
+
"learning_rate": 8.128070347473609e-06,
|
| 674 |
+
"loss": 1.546,
|
| 675 |
+
"step": 392
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 7.2,
|
| 679 |
+
"learning_rate": 8.078307376628292e-06,
|
| 680 |
+
"loss": 1.551,
|
| 681 |
+
"step": 396
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 7.27,
|
| 685 |
+
"learning_rate": 8.028048435688333e-06,
|
| 686 |
+
"loss": 1.6379,
|
| 687 |
+
"step": 400
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 7.35,
|
| 691 |
+
"learning_rate": 7.97730162226344e-06,
|
| 692 |
+
"loss": 1.61,
|
| 693 |
+
"step": 404
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 7.42,
|
| 697 |
+
"learning_rate": 7.92607511256826e-06,
|
| 698 |
+
"loss": 1.6151,
|
| 699 |
+
"step": 408
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 7.49,
|
| 703 |
+
"learning_rate": 7.874377160105037e-06,
|
| 704 |
+
"loss": 1.6989,
|
| 705 |
+
"step": 412
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 7.56,
|
| 709 |
+
"learning_rate": 7.822216094333847e-06,
|
| 710 |
+
"loss": 1.6711,
|
| 711 |
+
"step": 416
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 7.64,
|
| 715 |
+
"learning_rate": 7.769600319330553e-06,
|
| 716 |
+
"loss": 1.6344,
|
| 717 |
+
"step": 420
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 7.71,
|
| 721 |
+
"learning_rate": 7.716538312432767e-06,
|
| 722 |
+
"loss": 1.6,
|
| 723 |
+
"step": 424
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 7.78,
|
| 727 |
+
"learning_rate": 7.663038622873999e-06,
|
| 728 |
+
"loss": 1.6563,
|
| 729 |
+
"step": 428
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 7.85,
|
| 733 |
+
"learning_rate": 7.60910987040623e-06,
|
| 734 |
+
"loss": 1.5933,
|
| 735 |
+
"step": 432
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 7.93,
|
| 739 |
+
"learning_rate": 7.554760743911104e-06,
|
| 740 |
+
"loss": 1.6445,
|
| 741 |
+
"step": 436
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 8.0,
|
| 745 |
+
"learning_rate": 7.500000000000001e-06,
|
| 746 |
+
"loss": 1.6945,
|
| 747 |
+
"step": 440
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 8.0,
|
| 751 |
+
"gpt4_scores": 0.71,
|
| 752 |
+
"step": 440
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.0,
|
| 756 |
+
"std": 0.10904127658827183,
|
| 757 |
+
"step": 440
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 8.0,
|
| 761 |
+
"eval_loss": 1.8345035314559937,
|
| 762 |
+
"eval_runtime": 4.9576,
|
| 763 |
+
"eval_samples_per_second": 4.639,
|
| 764 |
+
"eval_steps_per_second": 1.21,
|
| 765 |
+
"step": 440
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 8.07,
|
| 769 |
+
"learning_rate": 7.444836461603195e-06,
|
| 770 |
+
"loss": 1.6089,
|
| 771 |
+
"step": 444
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 8.15,
|
| 775 |
+
"learning_rate": 7.3892790165483164e-06,
|
| 776 |
+
"loss": 1.6294,
|
| 777 |
+
"step": 448
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 8.22,
|
| 781 |
+
"learning_rate": 7.333336616128369e-06,
|
| 782 |
+
"loss": 1.6516,
|
| 783 |
+
"step": 452
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 8.29,
|
| 787 |
+
"learning_rate": 7.2770182736595164e-06,
|
| 788 |
+
"loss": 1.4944,
|
| 789 |
+
"step": 456
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 8.36,
|
| 793 |
+
"learning_rate": 7.2203330630288714e-06,
|
| 794 |
+
"loss": 1.5007,
|
| 795 |
+
"step": 460
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 8.44,
|
| 799 |
+
"learning_rate": 7.163290117232542e-06,
|
| 800 |
+
"loss": 1.5207,
|
| 801 |
+
"step": 464
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 8.51,
|
| 805 |
+
"learning_rate": 7.105898626904134e-06,
|
| 806 |
+
"loss": 1.6485,
|
| 807 |
+
"step": 468
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 8.58,
|
| 811 |
+
"learning_rate": 7.048167838833977e-06,
|
| 812 |
+
"loss": 1.554,
|
| 813 |
+
"step": 472
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 8.65,
|
| 817 |
+
"learning_rate": 6.990107054479313e-06,
|
| 818 |
+
"loss": 1.5661,
|
| 819 |
+
"step": 476
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 8.73,
|
| 823 |
+
"learning_rate": 6.931725628465643e-06,
|
| 824 |
+
"loss": 1.496,
|
| 825 |
+
"step": 480
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 8.8,
|
| 829 |
+
"learning_rate": 6.873032967079562e-06,
|
| 830 |
+
"loss": 1.554,
|
| 831 |
+
"step": 484
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 8.87,
|
| 835 |
+
"learning_rate": 6.814038526753205e-06,
|
| 836 |
+
"loss": 1.574,
|
| 837 |
+
"step": 488
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.95,
|
| 841 |
+
"learning_rate": 6.75475181254068e-06,
|
| 842 |
+
"loss": 1.5494,
|
| 843 |
+
"step": 492
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 9.0,
|
| 847 |
+
"gpt4_scores": 0.5700000000000001,
|
| 848 |
+
"step": 495
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.0,
|
| 852 |
+
"std": 0.13787675656179324,
|
| 853 |
+
"step": 495
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 9.0,
|
| 857 |
+
"eval_loss": 1.8451542854309082,
|
| 858 |
+
"eval_runtime": 4.9243,
|
| 859 |
+
"eval_samples_per_second": 4.671,
|
| 860 |
+
"eval_steps_per_second": 1.218,
|
| 861 |
+
"step": 495
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 9.02,
|
| 865 |
+
"learning_rate": 6.695182376586603e-06,
|
| 866 |
+
"loss": 1.6572,
|
| 867 |
+
"step": 496
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 9.09,
|
| 871 |
+
"learning_rate": 6.635339816587109e-06,
|
| 872 |
+
"loss": 1.5122,
|
| 873 |
+
"step": 500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 9.16,
|
| 877 |
+
"learning_rate": 6.5752337742434644e-06,
|
| 878 |
+
"loss": 1.4632,
|
| 879 |
+
"step": 504
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 9.24,
|
| 883 |
+
"learning_rate": 6.514873933708637e-06,
|
| 884 |
+
"loss": 1.4757,
|
| 885 |
+
"step": 508
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 9.31,
|
| 889 |
+
"learning_rate": 6.454270020026996e-06,
|
| 890 |
+
"loss": 1.5465,
|
| 891 |
+
"step": 512
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 9.38,
|
| 895 |
+
"learning_rate": 6.39343179756744e-06,
|
| 896 |
+
"loss": 1.5713,
|
| 897 |
+
"step": 516
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 9.45,
|
| 901 |
+
"learning_rate": 6.332369068450175e-06,
|
| 902 |
+
"loss": 1.5246,
|
| 903 |
+
"step": 520
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 9.53,
|
| 907 |
+
"learning_rate": 6.271091670967437e-06,
|
| 908 |
+
"loss": 1.478,
|
| 909 |
+
"step": 524
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 9.6,
|
| 913 |
+
"learning_rate": 6.209609477998339e-06,
|
| 914 |
+
"loss": 1.5593,
|
| 915 |
+
"step": 528
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 9.67,
|
| 919 |
+
"learning_rate": 6.1479323954182055e-06,
|
| 920 |
+
"loss": 1.5553,
|
| 921 |
+
"step": 532
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 9.75,
|
| 925 |
+
"learning_rate": 6.08607036050254e-06,
|
| 926 |
+
"loss": 1.5434,
|
| 927 |
+
"step": 536
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 9.82,
|
| 931 |
+
"learning_rate": 6.024033340325954e-06,
|
| 932 |
+
"loss": 1.4686,
|
| 933 |
+
"step": 540
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 9.89,
|
| 937 |
+
"learning_rate": 5.961831330156306e-06,
|
| 938 |
+
"loss": 1.4344,
|
| 939 |
+
"step": 544
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 9.96,
|
| 943 |
+
"learning_rate": 5.89947435184427e-06,
|
| 944 |
+
"loss": 1.5329,
|
| 945 |
+
"step": 548
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 10.0,
|
| 949 |
+
"gpt4_scores": 0.6,
|
| 950 |
+
"step": 550
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 10.0,
|
| 954 |
+
"std": 0.14352700094407322,
|
| 955 |
+
"step": 550
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 10.0,
|
| 959 |
+
"eval_loss": 1.8664953708648682,
|
| 960 |
+
"eval_runtime": 4.9654,
|
| 961 |
+
"eval_samples_per_second": 4.632,
|
| 962 |
+
"eval_steps_per_second": 1.208,
|
| 963 |
+
"step": 550
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 10.04,
|
| 967 |
+
"learning_rate": 5.8369724522086545e-06,
|
| 968 |
+
"loss": 1.5753,
|
| 969 |
+
"step": 552
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 10.11,
|
| 973 |
+
"learning_rate": 5.774335701417662e-06,
|
| 974 |
+
"loss": 1.4623,
|
| 975 |
+
"step": 556
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 10.18,
|
| 979 |
+
"learning_rate": 5.711574191366427e-06,
|
| 980 |
+
"loss": 1.4908,
|
| 981 |
+
"step": 560
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 10.25,
|
| 985 |
+
"learning_rate": 5.648698034051009e-06,
|
| 986 |
+
"loss": 1.4846,
|
| 987 |
+
"step": 564
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 10.33,
|
| 991 |
+
"learning_rate": 5.585717359939192e-06,
|
| 992 |
+
"loss": 1.4591,
|
| 993 |
+
"step": 568
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 10.4,
|
| 997 |
+
"learning_rate": 5.522642316338268e-06,
|
| 998 |
+
"loss": 1.4508,
|
| 999 |
+
"step": 572
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 10.47,
|
| 1003 |
+
"learning_rate": 5.459483065760138e-06,
|
| 1004 |
+
"loss": 1.4282,
|
| 1005 |
+
"step": 576
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 10.55,
|
| 1009 |
+
"learning_rate": 5.396249784283943e-06,
|
| 1010 |
+
"loss": 1.4565,
|
| 1011 |
+
"step": 580
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 10.62,
|
| 1015 |
+
"learning_rate": 5.33295265991652e-06,
|
| 1016 |
+
"loss": 1.5174,
|
| 1017 |
+
"step": 584
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 10.69,
|
| 1021 |
+
"learning_rate": 5.26960189095093e-06,
|
| 1022 |
+
"loss": 1.4063,
|
| 1023 |
+
"step": 588
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 10.76,
|
| 1027 |
+
"learning_rate": 5.206207684323337e-06,
|
| 1028 |
+
"loss": 1.4412,
|
| 1029 |
+
"step": 592
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 10.84,
|
| 1033 |
+
"learning_rate": 5.142780253968481e-06,
|
| 1034 |
+
"loss": 1.5706,
|
| 1035 |
+
"step": 596
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 10.91,
|
| 1039 |
+
"learning_rate": 5.07932981917404e-06,
|
| 1040 |
+
"loss": 1.4704,
|
| 1041 |
+
"step": 600
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 10.98,
|
| 1045 |
+
"learning_rate": 5.015866602934112e-06,
|
| 1046 |
+
"loss": 1.4105,
|
| 1047 |
+
"step": 604
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 11.0,
|
| 1051 |
+
"gpt4_scores": 0.5700000000000001,
|
| 1052 |
+
"step": 605
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 11.0,
|
| 1056 |
+
"std": 0.12653062870309306,
|
| 1057 |
+
"step": 605
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 11.0,
|
| 1061 |
+
"eval_loss": 1.8876867294311523,
|
| 1062 |
+
"eval_runtime": 4.9571,
|
| 1063 |
+
"eval_samples_per_second": 4.64,
|
| 1064 |
+
"eval_steps_per_second": 1.21,
|
| 1065 |
+
"step": 605
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 11.05,
|
| 1069 |
+
"learning_rate": 4.952400830302117e-06,
|
| 1070 |
+
"loss": 1.3259,
|
| 1071 |
+
"step": 608
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 11.13,
|
| 1075 |
+
"learning_rate": 4.888942726743353e-06,
|
| 1076 |
+
"loss": 1.371,
|
| 1077 |
+
"step": 612
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 11.2,
|
| 1081 |
+
"learning_rate": 4.825502516487497e-06,
|
| 1082 |
+
"loss": 1.4825,
|
| 1083 |
+
"step": 616
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 11.27,
|
| 1087 |
+
"learning_rate": 4.762090420881289e-06,
|
| 1088 |
+
"loss": 1.3511,
|
| 1089 |
+
"step": 620
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 11.35,
|
| 1093 |
+
"learning_rate": 4.6987166567417085e-06,
|
| 1094 |
+
"loss": 1.4314,
|
| 1095 |
+
"step": 624
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 11.42,
|
| 1099 |
+
"learning_rate": 4.635391434709847e-06,
|
| 1100 |
+
"loss": 1.4736,
|
| 1101 |
+
"step": 628
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 11.49,
|
| 1105 |
+
"learning_rate": 4.572124957605803e-06,
|
| 1106 |
+
"loss": 1.4653,
|
| 1107 |
+
"step": 632
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 11.56,
|
| 1111 |
+
"learning_rate": 4.5089274187848144e-06,
|
| 1112 |
+
"loss": 1.4053,
|
| 1113 |
+
"step": 636
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 11.64,
|
| 1117 |
+
"learning_rate": 4.445809000494945e-06,
|
| 1118 |
+
"loss": 1.4959,
|
| 1119 |
+
"step": 640
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 11.71,
|
| 1123 |
+
"learning_rate": 4.382779872236527e-06,
|
| 1124 |
+
"loss": 1.4142,
|
| 1125 |
+
"step": 644
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 11.78,
|
| 1129 |
+
"learning_rate": 4.319850189123681e-06,
|
| 1130 |
+
"loss": 1.3764,
|
| 1131 |
+
"step": 648
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 11.85,
|
| 1135 |
+
"learning_rate": 4.257030090248142e-06,
|
| 1136 |
+
"loss": 1.5262,
|
| 1137 |
+
"step": 652
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 11.93,
|
| 1141 |
+
"learning_rate": 4.194329697045681e-06,
|
| 1142 |
+
"loss": 1.4114,
|
| 1143 |
+
"step": 656
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 12.0,
|
| 1147 |
+
"learning_rate": 4.131759111665349e-06,
|
| 1148 |
+
"loss": 1.3862,
|
| 1149 |
+
"step": 660
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 12.0,
|
| 1153 |
+
"gpt4_scores": 0.64,
|
| 1154 |
+
"step": 660
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 12.0,
|
| 1158 |
+
"std": 0.13505554412907303,
|
| 1159 |
+
"step": 660
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 12.0,
|
| 1163 |
+
"eval_loss": 1.9065581560134888,
|
| 1164 |
+
"eval_runtime": 4.9613,
|
| 1165 |
+
"eval_samples_per_second": 4.636,
|
| 1166 |
+
"eval_steps_per_second": 1.209,
|
| 1167 |
+
"step": 660
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 12.07,
|
| 1171 |
+
"learning_rate": 4.06932841534185e-06,
|
| 1172 |
+
"loss": 1.4282,
|
| 1173 |
+
"step": 664
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 12.15,
|
| 1177 |
+
"learning_rate": 4.007047666771274e-06,
|
| 1178 |
+
"loss": 1.3369,
|
| 1179 |
+
"step": 668
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 12.22,
|
| 1183 |
+
"learning_rate": 3.944926900490452e-06,
|
| 1184 |
+
"loss": 1.4198,
|
| 1185 |
+
"step": 672
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 12.29,
|
| 1189 |
+
"learning_rate": 3.882976125260229e-06,
|
| 1190 |
+
"loss": 1.3799,
|
| 1191 |
+
"step": 676
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 12.36,
|
| 1195 |
+
"learning_rate": 3.821205322452863e-06,
|
| 1196 |
+
"loss": 1.4461,
|
| 1197 |
+
"step": 680
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 12.44,
|
| 1201 |
+
"learning_rate": 3.7596244444438577e-06,
|
| 1202 |
+
"loss": 1.4154,
|
| 1203 |
+
"step": 684
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 12.51,
|
| 1207 |
+
"learning_rate": 3.69824341300844e-06,
|
| 1208 |
+
"loss": 1.3719,
|
| 1209 |
+
"step": 688
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 12.58,
|
| 1213 |
+
"learning_rate": 3.637072117723012e-06,
|
| 1214 |
+
"loss": 1.3079,
|
| 1215 |
+
"step": 692
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 12.65,
|
| 1219 |
+
"learning_rate": 3.5761204143717387e-06,
|
| 1220 |
+
"loss": 1.3786,
|
| 1221 |
+
"step": 696
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 12.73,
|
| 1225 |
+
"learning_rate": 3.5153981233586277e-06,
|
| 1226 |
+
"loss": 1.3406,
|
| 1227 |
+
"step": 700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 12.8,
|
| 1231 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 1232 |
+
"loss": 1.3967,
|
| 1233 |
+
"step": 704
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 12.87,
|
| 1237 |
+
"learning_rate": 3.394680873574546e-06,
|
| 1238 |
+
"loss": 1.4914,
|
| 1239 |
+
"step": 708
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 12.95,
|
| 1243 |
+
"learning_rate": 3.3347053645005965e-06,
|
| 1244 |
+
"loss": 1.4126,
|
| 1245 |
+
"step": 712
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 13.0,
|
| 1249 |
+
"gpt4_scores": 0.53,
|
| 1250 |
+
"step": 715
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 13.0,
|
| 1254 |
+
"std": 0.14356183336806477,
|
| 1255 |
+
"step": 715
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 13.0,
|
| 1259 |
+
"eval_loss": 1.9303113222122192,
|
| 1260 |
+
"eval_runtime": 4.9701,
|
| 1261 |
+
"eval_samples_per_second": 4.628,
|
| 1262 |
+
"eval_steps_per_second": 1.207,
|
| 1263 |
+
"step": 715
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 13.02,
|
| 1267 |
+
"learning_rate": 3.274998164025148e-06,
|
| 1268 |
+
"loss": 1.4012,
|
| 1269 |
+
"step": 716
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 13.09,
|
| 1273 |
+
"learning_rate": 3.2155688920406415e-06,
|
| 1274 |
+
"loss": 1.4258,
|
| 1275 |
+
"step": 720
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 13.16,
|
| 1279 |
+
"learning_rate": 3.156427123660297e-06,
|
| 1280 |
+
"loss": 1.3023,
|
| 1281 |
+
"step": 724
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 13.24,
|
| 1285 |
+
"learning_rate": 3.097582387675385e-06,
|
| 1286 |
+
"loss": 1.3797,
|
| 1287 |
+
"step": 728
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 13.31,
|
| 1291 |
+
"learning_rate": 3.0390441650199727e-06,
|
| 1292 |
+
"loss": 1.335,
|
| 1293 |
+
"step": 732
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 13.38,
|
| 1297 |
+
"learning_rate": 2.980821887243377e-06,
|
| 1298 |
+
"loss": 1.388,
|
| 1299 |
+
"step": 736
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 13.45,
|
| 1303 |
+
"learning_rate": 2.9229249349905686e-06,
|
| 1304 |
+
"loss": 1.2886,
|
| 1305 |
+
"step": 740
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 13.53,
|
| 1309 |
+
"learning_rate": 2.8653626364907918e-06,
|
| 1310 |
+
"loss": 1.3144,
|
| 1311 |
+
"step": 744
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 13.6,
|
| 1315 |
+
"learning_rate": 2.8081442660546126e-06,
|
| 1316 |
+
"loss": 1.3285,
|
| 1317 |
+
"step": 748
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 13.67,
|
| 1321 |
+
"learning_rate": 2.751279042579672e-06,
|
| 1322 |
+
"loss": 1.4061,
|
| 1323 |
+
"step": 752
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 13.75,
|
| 1327 |
+
"learning_rate": 2.694776128065345e-06,
|
| 1328 |
+
"loss": 1.3877,
|
| 1329 |
+
"step": 756
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 13.82,
|
| 1333 |
+
"learning_rate": 2.6386446261365874e-06,
|
| 1334 |
+
"loss": 1.2318,
|
| 1335 |
+
"step": 760
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 13.89,
|
| 1339 |
+
"learning_rate": 2.5828935805771804e-06,
|
| 1340 |
+
"loss": 1.3826,
|
| 1341 |
+
"step": 764
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 13.96,
|
| 1345 |
+
"learning_rate": 2.527531973872617e-06,
|
| 1346 |
+
"loss": 1.388,
|
| 1347 |
+
"step": 768
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 14.0,
|
| 1351 |
+
"gpt4_scores": 0.62,
|
| 1352 |
+
"step": 770
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 14.0,
|
| 1356 |
+
"std": 0.1362350909274112,
|
| 1357 |
+
"step": 770
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 14.0,
|
| 1361 |
+
"eval_loss": 1.9448539018630981,
|
| 1362 |
+
"eval_runtime": 4.9425,
|
| 1363 |
+
"eval_samples_per_second": 4.654,
|
| 1364 |
+
"eval_steps_per_second": 1.214,
|
| 1365 |
+
"step": 770
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 14.04,
|
| 1369 |
+
"learning_rate": 2.4725687257628533e-06,
|
| 1370 |
+
"loss": 1.524,
|
| 1371 |
+
"step": 772
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 14.11,
|
| 1375 |
+
"learning_rate": 2.418012691805191e-06,
|
| 1376 |
+
"loss": 1.3961,
|
| 1377 |
+
"step": 776
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 14.18,
|
| 1381 |
+
"learning_rate": 2.363872661947488e-06,
|
| 1382 |
+
"loss": 1.3303,
|
| 1383 |
+
"step": 780
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 14.25,
|
| 1387 |
+
"learning_rate": 2.310157359111938e-06,
|
| 1388 |
+
"loss": 1.3642,
|
| 1389 |
+
"step": 784
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 14.33,
|
| 1393 |
+
"learning_rate": 2.2568754377896516e-06,
|
| 1394 |
+
"loss": 1.3532,
|
| 1395 |
+
"step": 788
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 14.4,
|
| 1399 |
+
"learning_rate": 2.204035482646267e-06,
|
| 1400 |
+
"loss": 1.2528,
|
| 1401 |
+
"step": 792
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 14.47,
|
| 1405 |
+
"learning_rate": 2.1516460071388062e-06,
|
| 1406 |
+
"loss": 1.3888,
|
| 1407 |
+
"step": 796
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 14.55,
|
| 1411 |
+
"learning_rate": 2.09971545214401e-06,
|
| 1412 |
+
"loss": 1.269,
|
| 1413 |
+
"step": 800
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 14.62,
|
| 1417 |
+
"learning_rate": 2.0482521845983522e-06,
|
| 1418 |
+
"loss": 1.3103,
|
| 1419 |
+
"step": 804
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 14.69,
|
| 1423 |
+
"learning_rate": 1.9972644961499853e-06,
|
| 1424 |
+
"loss": 1.3151,
|
| 1425 |
+
"step": 808
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 14.76,
|
| 1429 |
+
"learning_rate": 1.946760601822809e-06,
|
| 1430 |
+
"loss": 1.3055,
|
| 1431 |
+
"step": 812
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 14.84,
|
| 1435 |
+
"learning_rate": 1.8967486386928819e-06,
|
| 1436 |
+
"loss": 1.3414,
|
| 1437 |
+
"step": 816
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 14.91,
|
| 1441 |
+
"learning_rate": 1.8472366645773892e-06,
|
| 1442 |
+
"loss": 1.3481,
|
| 1443 |
+
"step": 820
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 14.98,
|
| 1447 |
+
"learning_rate": 1.798232656736389e-06,
|
| 1448 |
+
"loss": 1.3653,
|
| 1449 |
+
"step": 824
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 15.0,
|
| 1453 |
+
"gpt4_scores": 0.605,
|
| 1454 |
+
"step": 825
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 15.0,
|
| 1458 |
+
"std": 0.13312588027877975,
|
| 1459 |
+
"step": 825
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 15.0,
|
| 1463 |
+
"eval_loss": 1.9636751413345337,
|
| 1464 |
+
"eval_runtime": 4.9484,
|
| 1465 |
+
"eval_samples_per_second": 4.648,
|
| 1466 |
+
"eval_steps_per_second": 1.213,
|
| 1467 |
+
"step": 825
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 15.05,
|
| 1471 |
+
"learning_rate": 1.7497445105875377e-06,
|
| 1472 |
+
"loss": 1.4389,
|
| 1473 |
+
"step": 828
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 15.13,
|
| 1477 |
+
"learning_rate": 1.7017800384339928e-06,
|
| 1478 |
+
"loss": 1.3568,
|
| 1479 |
+
"step": 832
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 15.2,
|
| 1483 |
+
"learning_rate": 1.6543469682057105e-06,
|
| 1484 |
+
"loss": 1.3535,
|
| 1485 |
+
"step": 836
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 15.27,
|
| 1489 |
+
"learning_rate": 1.6074529422143398e-06,
|
| 1490 |
+
"loss": 1.2696,
|
| 1491 |
+
"step": 840
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 15.35,
|
| 1495 |
+
"learning_rate": 1.561105515921915e-06,
|
| 1496 |
+
"loss": 1.2854,
|
| 1497 |
+
"step": 844
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 15.42,
|
| 1501 |
+
"learning_rate": 1.5153121567235334e-06,
|
| 1502 |
+
"loss": 1.2779,
|
| 1503 |
+
"step": 848
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 15.49,
|
| 1507 |
+
"learning_rate": 1.470080242744218e-06,
|
| 1508 |
+
"loss": 1.3024,
|
| 1509 |
+
"step": 852
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 15.56,
|
| 1513 |
+
"learning_rate": 1.4254170616501828e-06,
|
| 1514 |
+
"loss": 1.3081,
|
| 1515 |
+
"step": 856
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 15.64,
|
| 1519 |
+
"learning_rate": 1.3813298094746491e-06,
|
| 1520 |
+
"loss": 1.2898,
|
| 1521 |
+
"step": 860
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 15.71,
|
| 1525 |
+
"learning_rate": 1.3378255894584463e-06,
|
| 1526 |
+
"loss": 1.2944,
|
| 1527 |
+
"step": 864
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 15.78,
|
| 1531 |
+
"learning_rate": 1.2949114109055417e-06,
|
| 1532 |
+
"loss": 1.3638,
|
| 1533 |
+
"step": 868
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 15.85,
|
| 1537 |
+
"learning_rate": 1.2525941880537307e-06,
|
| 1538 |
+
"loss": 1.3272,
|
| 1539 |
+
"step": 872
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 15.93,
|
| 1543 |
+
"learning_rate": 1.210880738960616e-06,
|
| 1544 |
+
"loss": 1.2646,
|
| 1545 |
+
"step": 876
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 16.0,
|
| 1549 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 1550 |
+
"loss": 1.361,
|
| 1551 |
+
"step": 880
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 16.0,
|
| 1555 |
+
"gpt4_scores": 0.5999999999999999,
|
| 1556 |
+
"step": 880
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 16.0,
|
| 1560 |
+
"std": 0.1319090595827292,
|
| 1561 |
+
"step": 880
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 16.0,
|
| 1565 |
+
"eval_loss": 1.9738112688064575,
|
| 1566 |
+
"eval_runtime": 4.9552,
|
| 1567 |
+
"eval_samples_per_second": 4.642,
|
| 1568 |
+
"eval_steps_per_second": 1.211,
|
| 1569 |
+
"step": 880
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 16.07,
|
| 1573 |
+
"learning_rate": 1.1292919468045876e-06,
|
| 1574 |
+
"loss": 1.2656,
|
| 1575 |
+
"step": 884
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 16.15,
|
| 1579 |
+
"learning_rate": 1.0894297491479044e-06,
|
| 1580 |
+
"loss": 1.376,
|
| 1581 |
+
"step": 888
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 16.22,
|
| 1585 |
+
"learning_rate": 1.0501976139444191e-06,
|
| 1586 |
+
"loss": 1.2771,
|
| 1587 |
+
"step": 892
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 16.29,
|
| 1591 |
+
"learning_rate": 1.0116018621892237e-06,
|
| 1592 |
+
"loss": 1.2919,
|
| 1593 |
+
"step": 896
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 16.36,
|
| 1597 |
+
"learning_rate": 9.73648712344707e-07,
|
| 1598 |
+
"loss": 1.3542,
|
| 1599 |
+
"step": 900
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 16.44,
|
| 1603 |
+
"learning_rate": 9.363442793386606e-07,
|
| 1604 |
+
"loss": 1.275,
|
| 1605 |
+
"step": 904
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 16.51,
|
| 1609 |
+
"learning_rate": 8.996945735790447e-07,
|
| 1610 |
+
"loss": 1.3197,
|
| 1611 |
+
"step": 908
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 16.58,
|
| 1615 |
+
"learning_rate": 8.637054999856148e-07,
|
| 1616 |
+
"loss": 1.3272,
|
| 1617 |
+
"step": 912
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 16.65,
|
| 1621 |
+
"learning_rate": 8.283828570385239e-07,
|
| 1622 |
+
"loss": 1.2585,
|
| 1623 |
+
"step": 916
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 16.73,
|
| 1627 |
+
"learning_rate": 7.937323358440935e-07,
|
| 1628 |
+
"loss": 1.2851,
|
| 1629 |
+
"step": 920
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 16.8,
|
| 1633 |
+
"learning_rate": 7.597595192178702e-07,
|
| 1634 |
+
"loss": 1.2787,
|
| 1635 |
+
"step": 924
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 16.87,
|
| 1639 |
+
"learning_rate": 7.264698807851328e-07,
|
| 1640 |
+
"loss": 1.3594,
|
| 1641 |
+
"step": 928
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 16.95,
|
| 1645 |
+
"learning_rate": 6.938687840989972e-07,
|
| 1646 |
+
"loss": 1.2944,
|
| 1647 |
+
"step": 932
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 17.0,
|
| 1651 |
+
"gpt4_scores": 0.6100000000000001,
|
| 1652 |
+
"step": 935
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 17.0,
|
| 1656 |
+
"std": 0.1352405264704334,
|
| 1657 |
+
"step": 935
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 17.0,
|
| 1661 |
+
"eval_loss": 1.9819345474243164,
|
| 1662 |
+
"eval_runtime": 4.9634,
|
| 1663 |
+
"eval_samples_per_second": 4.634,
|
| 1664 |
+
"eval_steps_per_second": 1.209,
|
| 1665 |
+
"step": 935
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 17.02,
|
| 1669 |
+
"learning_rate": 6.619614817762537e-07,
|
| 1670 |
+
"loss": 1.3019,
|
| 1671 |
+
"step": 936
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 17.09,
|
| 1675 |
+
"learning_rate": 6.307531146510754e-07,
|
| 1676 |
+
"loss": 1.2263,
|
| 1677 |
+
"step": 940
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 17.16,
|
| 1681 |
+
"learning_rate": 6.002487109467347e-07,
|
| 1682 |
+
"loss": 1.2774,
|
| 1683 |
+
"step": 944
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 17.24,
|
| 1687 |
+
"learning_rate": 5.704531854654721e-07,
|
| 1688 |
+
"loss": 1.3117,
|
| 1689 |
+
"step": 948
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 17.31,
|
| 1693 |
+
"learning_rate": 5.413713387966329e-07,
|
| 1694 |
+
"loss": 1.3669,
|
| 1695 |
+
"step": 952
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 17.38,
|
| 1699 |
+
"learning_rate": 5.130078565432089e-07,
|
| 1700 |
+
"loss": 1.3741,
|
| 1701 |
+
"step": 956
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 17.45,
|
| 1705 |
+
"learning_rate": 4.853673085668947e-07,
|
| 1706 |
+
"loss": 1.259,
|
| 1707 |
+
"step": 960
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 17.53,
|
| 1711 |
+
"learning_rate": 4.58454148251814e-07,
|
| 1712 |
+
"loss": 1.2952,
|
| 1713 |
+
"step": 964
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 17.6,
|
| 1717 |
+
"learning_rate": 4.322727117869951e-07,
|
| 1718 |
+
"loss": 1.2957,
|
| 1719 |
+
"step": 968
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 17.67,
|
| 1723 |
+
"learning_rate": 4.0682721746773346e-07,
|
| 1724 |
+
"loss": 1.2796,
|
| 1725 |
+
"step": 972
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 17.75,
|
| 1729 |
+
"learning_rate": 3.821217650159453e-07,
|
| 1730 |
+
"loss": 1.3251,
|
| 1731 |
+
"step": 976
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 17.82,
|
| 1735 |
+
"learning_rate": 3.581603349196372e-07,
|
| 1736 |
+
"loss": 1.2795,
|
| 1737 |
+
"step": 980
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 17.89,
|
| 1741 |
+
"learning_rate": 3.3494678779157464e-07,
|
| 1742 |
+
"loss": 1.2337,
|
| 1743 |
+
"step": 984
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 17.96,
|
| 1747 |
+
"learning_rate": 3.1248486374726884e-07,
|
| 1748 |
+
"loss": 1.3433,
|
| 1749 |
+
"step": 988
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 18.0,
|
| 1753 |
+
"gpt4_scores": 0.5599999999999999,
|
| 1754 |
+
"step": 990
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 18.0,
|
| 1758 |
+
"std": 0.14573949361789343,
|
| 1759 |
+
"step": 990
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 18.0,
|
| 1763 |
+
"eval_loss": 1.9856066703796387,
|
| 1764 |
+
"eval_runtime": 4.9567,
|
| 1765 |
+
"eval_samples_per_second": 4.64,
|
| 1766 |
+
"eval_steps_per_second": 1.21,
|
| 1767 |
+
"step": 990
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 18.04,
|
| 1771 |
+
"learning_rate": 2.9077818180237693e-07,
|
| 1772 |
+
"loss": 1.2889,
|
| 1773 |
+
"step": 992
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 18.11,
|
| 1777 |
+
"learning_rate": 2.6983023928961406e-07,
|
| 1778 |
+
"loss": 1.3571,
|
| 1779 |
+
"step": 996
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 18.18,
|
| 1783 |
+
"learning_rate": 2.4964441129527337e-07,
|
| 1784 |
+
"loss": 1.2855,
|
| 1785 |
+
"step": 1000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 18.25,
|
| 1789 |
+
"learning_rate": 2.3022395011543687e-07,
|
| 1790 |
+
"loss": 1.2844,
|
| 1791 |
+
"step": 1004
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 18.33,
|
| 1795 |
+
"learning_rate": 2.1157198473197417e-07,
|
| 1796 |
+
"loss": 1.3131,
|
| 1797 |
+
"step": 1008
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 18.4,
|
| 1801 |
+
"learning_rate": 1.9369152030840553e-07,
|
| 1802 |
+
"loss": 1.2825,
|
| 1803 |
+
"step": 1012
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 18.47,
|
| 1807 |
+
"learning_rate": 1.765854377057219e-07,
|
| 1808 |
+
"loss": 1.2378,
|
| 1809 |
+
"step": 1016
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 18.55,
|
| 1813 |
+
"learning_rate": 1.6025649301821877e-07,
|
| 1814 |
+
"loss": 1.3067,
|
| 1815 |
+
"step": 1020
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 18.62,
|
| 1819 |
+
"learning_rate": 1.4470731712944885e-07,
|
| 1820 |
+
"loss": 1.367,
|
| 1821 |
+
"step": 1024
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 18.69,
|
| 1825 |
+
"learning_rate": 1.2994041528833267e-07,
|
| 1826 |
+
"loss": 1.2553,
|
| 1827 |
+
"step": 1028
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 18.76,
|
| 1831 |
+
"learning_rate": 1.1595816670552429e-07,
|
| 1832 |
+
"loss": 1.392,
|
| 1833 |
+
"step": 1032
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 18.84,
|
| 1837 |
+
"learning_rate": 1.0276282417007399e-07,
|
| 1838 |
+
"loss": 1.2524,
|
| 1839 |
+
"step": 1036
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 18.91,
|
| 1843 |
+
"learning_rate": 9.035651368646647e-08,
|
| 1844 |
+
"loss": 1.2067,
|
| 1845 |
+
"step": 1040
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 18.98,
|
| 1849 |
+
"learning_rate": 7.874123413208145e-08,
|
| 1850 |
+
"loss": 1.2058,
|
| 1851 |
+
"step": 1044
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 19.0,
|
| 1855 |
+
"gpt4_scores": 0.5399999999999999,
|
| 1856 |
+
"step": 1045
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 19.0,
|
| 1860 |
+
"std": 0.1422673539502299,
|
| 1861 |
+
"step": 1045
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 19.0,
|
| 1865 |
+
"eval_loss": 1.9871299266815186,
|
| 1866 |
+
"eval_runtime": 4.9631,
|
| 1867 |
+
"eval_samples_per_second": 4.634,
|
| 1868 |
+
"eval_steps_per_second": 1.209,
|
| 1869 |
+
"step": 1045
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 19.05,
|
| 1873 |
+
"learning_rate": 6.791885693514134e-08,
|
| 1874 |
+
"loss": 1.2248,
|
| 1875 |
+
"step": 1048
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 19.13,
|
| 1879 |
+
"learning_rate": 5.7891125773187896e-08,
|
| 1880 |
+
"loss": 1.3235,
|
| 1881 |
+
"step": 1052
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 19.2,
|
| 1885 |
+
"learning_rate": 4.865965629214819e-08,
|
| 1886 |
+
"loss": 1.337,
|
| 1887 |
+
"step": 1056
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 19.27,
|
| 1891 |
+
"learning_rate": 4.02259358460233e-08,
|
| 1892 |
+
"loss": 1.2373,
|
| 1893 |
+
"step": 1060
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 19.35,
|
| 1897 |
+
"learning_rate": 3.25913232572489e-08,
|
| 1898 |
+
"loss": 1.2713,
|
| 1899 |
+
"step": 1064
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 19.42,
|
| 1903 |
+
"learning_rate": 2.57570485977654e-08,
|
| 1904 |
+
"loss": 1.2856,
|
| 1905 |
+
"step": 1068
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 19.49,
|
| 1909 |
+
"learning_rate": 1.9724212990830938e-08,
|
| 1910 |
+
"loss": 1.3416,
|
| 1911 |
+
"step": 1072
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 19.56,
|
| 1915 |
+
"learning_rate": 1.449378843361271e-08,
|
| 1916 |
+
"loss": 1.2418,
|
| 1917 |
+
"step": 1076
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 19.64,
|
| 1921 |
+
"learning_rate": 1.006661764057837e-08,
|
| 1922 |
+
"loss": 1.2665,
|
| 1923 |
+
"step": 1080
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 19.71,
|
| 1927 |
+
"learning_rate": 6.4434139077201865e-09,
|
| 1928 |
+
"loss": 1.2837,
|
| 1929 |
+
"step": 1084
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 19.78,
|
| 1933 |
+
"learning_rate": 3.6247609976319818e-09,
|
| 1934 |
+
"loss": 1.2405,
|
| 1935 |
+
"step": 1088
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 19.85,
|
| 1939 |
+
"learning_rate": 1.61111304545436e-09,
|
| 1940 |
+
"loss": 1.3201,
|
| 1941 |
+
"step": 1092
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 19.93,
|
| 1945 |
+
"learning_rate": 4.027944857032395e-10,
|
| 1946 |
+
"loss": 1.37,
|
| 1947 |
+
"step": 1096
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 20.0,
|
| 1951 |
+
"learning_rate": 0.0,
|
| 1952 |
+
"loss": 1.2904,
|
| 1953 |
+
"step": 1100
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 20.0,
|
| 1957 |
+
"gpt4_scores": 0.59,
|
| 1958 |
+
"step": 1100
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 20.0,
|
| 1962 |
+
"std": 0.130728726758888,
|
| 1963 |
+
"step": 1100
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 20.0,
|
| 1967 |
+
"eval_loss": 1.987522840499878,
|
| 1968 |
+
"eval_runtime": 4.9557,
|
| 1969 |
+
"eval_samples_per_second": 4.641,
|
| 1970 |
+
"eval_steps_per_second": 1.211,
|
| 1971 |
+
"step": 1100
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 20.0,
|
| 1975 |
+
"step": 1100,
|
| 1976 |
+
"total_flos": 3.792475205866291e+16,
|
| 1977 |
+
"train_loss": 1.2573659207604149,
|
| 1978 |
+
"train_runtime": 10567.2291,
|
| 1979 |
+
"train_samples_per_second": 0.411,
|
| 1980 |
+
"train_steps_per_second": 0.104
|
| 1981 |
+
}
|
| 1982 |
+
],
|
| 1983 |
+
"logging_steps": 4,
|
| 1984 |
+
"max_steps": 1100,
|
| 1985 |
+
"num_input_tokens_seen": 0,
|
| 1986 |
+
"num_train_epochs": 20,
|
| 1987 |
+
"save_steps": 55,
|
| 1988 |
+
"total_flos": 3.792475205866291e+16,
|
| 1989 |
+
"train_batch_size": 4,
|
| 1990 |
+
"trial_name": null,
|
| 1991 |
+
"trial_params": null
|
| 1992 |
+
}
|