Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +1533 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: InfiniAILab/DeepSeek-R1-7B
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: DeepSeek-R1-7B-tuned
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for DeepSeek-R1-7B-tuned
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [InfiniAILab/DeepSeek-R1-7B](https://huggingface.co/InfiniAILab/DeepSeek-R1-7B).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="ZMC2019/DeepSeek-R1-7B-tuned", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenzhuoming911/huggingface/runs/ot263dx6)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.4.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 9.145616827248804e+17,
|
| 3 |
+
"train_loss": 0.3807801652267185,
|
| 4 |
+
"train_runtime": 28315.9454,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.604,
|
| 7 |
+
"train_steps_per_second": 0.038
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.49.0"
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 9.145616827248804e+17,
|
| 3 |
+
"train_loss": 0.3807801652267185,
|
| 4 |
+
"train_runtime": 28315.9454,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.604,
|
| 7 |
+
"train_steps_per_second": 0.038
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995320542817033,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1068,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004679457182966776,
|
| 13 |
+
"grad_norm": 2.2908554548637006,
|
| 14 |
+
"learning_rate": 9.345794392523365e-07,
|
| 15 |
+
"loss": 0.4939,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009358914365933552,
|
| 20 |
+
"grad_norm": 2.016859310665491,
|
| 21 |
+
"learning_rate": 1.869158878504673e-06,
|
| 22 |
+
"loss": 0.4723,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.014038371548900327,
|
| 27 |
+
"grad_norm": 1.5221155414770415,
|
| 28 |
+
"learning_rate": 2.8037383177570094e-06,
|
| 29 |
+
"loss": 0.4618,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018717828731867104,
|
| 34 |
+
"grad_norm": 0.5002414337717975,
|
| 35 |
+
"learning_rate": 3.738317757009346e-06,
|
| 36 |
+
"loss": 0.4567,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02339728591483388,
|
| 41 |
+
"grad_norm": 0.9841161532928453,
|
| 42 |
+
"learning_rate": 4.6728971962616825e-06,
|
| 43 |
+
"loss": 0.4435,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.028076743097800654,
|
| 48 |
+
"grad_norm": 0.6160542794694137,
|
| 49 |
+
"learning_rate": 5.607476635514019e-06,
|
| 50 |
+
"loss": 0.4308,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03275620028076743,
|
| 55 |
+
"grad_norm": 0.4169222842040913,
|
| 56 |
+
"learning_rate": 6.542056074766355e-06,
|
| 57 |
+
"loss": 0.4254,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03743565746373421,
|
| 62 |
+
"grad_norm": 0.43151336467869167,
|
| 63 |
+
"learning_rate": 7.476635514018692e-06,
|
| 64 |
+
"loss": 0.4131,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04211511464670098,
|
| 69 |
+
"grad_norm": 0.27790836608550784,
|
| 70 |
+
"learning_rate": 8.411214953271028e-06,
|
| 71 |
+
"loss": 0.4151,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04679457182966776,
|
| 76 |
+
"grad_norm": 0.3490921524994091,
|
| 77 |
+
"learning_rate": 9.345794392523365e-06,
|
| 78 |
+
"loss": 0.3969,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05147402901263454,
|
| 83 |
+
"grad_norm": 0.2784386545031061,
|
| 84 |
+
"learning_rate": 1.02803738317757e-05,
|
| 85 |
+
"loss": 0.3985,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05615348619560131,
|
| 90 |
+
"grad_norm": 0.2805705696670822,
|
| 91 |
+
"learning_rate": 1.1214953271028037e-05,
|
| 92 |
+
"loss": 0.4125,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06083294337856809,
|
| 97 |
+
"grad_norm": 0.2525496578964846,
|
| 98 |
+
"learning_rate": 1.2149532710280374e-05,
|
| 99 |
+
"loss": 0.3947,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06551240056153486,
|
| 104 |
+
"grad_norm": 0.23045102014975796,
|
| 105 |
+
"learning_rate": 1.308411214953271e-05,
|
| 106 |
+
"loss": 0.3955,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07019185774450164,
|
| 111 |
+
"grad_norm": 0.22022938803676545,
|
| 112 |
+
"learning_rate": 1.4018691588785047e-05,
|
| 113 |
+
"loss": 0.3967,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07487131492746842,
|
| 118 |
+
"grad_norm": 0.23347833396023018,
|
| 119 |
+
"learning_rate": 1.4953271028037384e-05,
|
| 120 |
+
"loss": 0.3909,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0795507721104352,
|
| 125 |
+
"grad_norm": 0.228913019838675,
|
| 126 |
+
"learning_rate": 1.588785046728972e-05,
|
| 127 |
+
"loss": 0.3945,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08423022929340196,
|
| 132 |
+
"grad_norm": 0.2633815411021567,
|
| 133 |
+
"learning_rate": 1.6822429906542056e-05,
|
| 134 |
+
"loss": 0.3824,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08890968647636874,
|
| 139 |
+
"grad_norm": 0.23342700291557855,
|
| 140 |
+
"learning_rate": 1.7757009345794395e-05,
|
| 141 |
+
"loss": 0.3862,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09358914365933552,
|
| 146 |
+
"grad_norm": 0.23300433901186635,
|
| 147 |
+
"learning_rate": 1.869158878504673e-05,
|
| 148 |
+
"loss": 0.3919,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.0982686008423023,
|
| 153 |
+
"grad_norm": 0.27373389148512267,
|
| 154 |
+
"learning_rate": 1.9626168224299065e-05,
|
| 155 |
+
"loss": 0.3779,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10294805802526907,
|
| 160 |
+
"grad_norm": 0.228261846212288,
|
| 161 |
+
"learning_rate": 1.9937565036420395e-05,
|
| 162 |
+
"loss": 0.3936,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10762751520823584,
|
| 167 |
+
"grad_norm": 0.23489411050580397,
|
| 168 |
+
"learning_rate": 1.9833506763787724e-05,
|
| 169 |
+
"loss": 0.3843,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11230697239120262,
|
| 174 |
+
"grad_norm": 0.27702591802476917,
|
| 175 |
+
"learning_rate": 1.972944849115505e-05,
|
| 176 |
+
"loss": 0.382,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1169864295741694,
|
| 181 |
+
"grad_norm": 0.225569280525892,
|
| 182 |
+
"learning_rate": 1.9625390218522374e-05,
|
| 183 |
+
"loss": 0.3819,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12166588675713617,
|
| 188 |
+
"grad_norm": 0.24311963459537528,
|
| 189 |
+
"learning_rate": 1.95213319458897e-05,
|
| 190 |
+
"loss": 0.3893,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12634534394010294,
|
| 195 |
+
"grad_norm": 0.260175889528399,
|
| 196 |
+
"learning_rate": 1.9417273673257027e-05,
|
| 197 |
+
"loss": 0.394,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.13102480112306972,
|
| 202 |
+
"grad_norm": 0.2556543935052257,
|
| 203 |
+
"learning_rate": 1.9313215400624352e-05,
|
| 204 |
+
"loss": 0.3872,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1357042583060365,
|
| 209 |
+
"grad_norm": 0.25822395228887385,
|
| 210 |
+
"learning_rate": 1.9209157127991677e-05,
|
| 211 |
+
"loss": 0.3904,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14038371548900327,
|
| 216 |
+
"grad_norm": 0.2289827168893927,
|
| 217 |
+
"learning_rate": 1.9105098855359002e-05,
|
| 218 |
+
"loss": 0.3881,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14506317267197005,
|
| 223 |
+
"grad_norm": 0.2782914404861313,
|
| 224 |
+
"learning_rate": 1.9001040582726327e-05,
|
| 225 |
+
"loss": 0.389,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14974262985493683,
|
| 230 |
+
"grad_norm": 0.2691987795720794,
|
| 231 |
+
"learning_rate": 1.8896982310093656e-05,
|
| 232 |
+
"loss": 0.3799,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1544220870379036,
|
| 237 |
+
"grad_norm": 0.22215928015704764,
|
| 238 |
+
"learning_rate": 1.879292403746098e-05,
|
| 239 |
+
"loss": 0.3798,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1591015442208704,
|
| 244 |
+
"grad_norm": 0.2503740618645921,
|
| 245 |
+
"learning_rate": 1.8688865764828306e-05,
|
| 246 |
+
"loss": 0.3977,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16378100140383717,
|
| 251 |
+
"grad_norm": 0.22564216914588497,
|
| 252 |
+
"learning_rate": 1.858480749219563e-05,
|
| 253 |
+
"loss": 0.3744,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16846045858680392,
|
| 258 |
+
"grad_norm": 0.25918009956565563,
|
| 259 |
+
"learning_rate": 1.8480749219562956e-05,
|
| 260 |
+
"loss": 0.3738,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1731399157697707,
|
| 265 |
+
"grad_norm": 0.2393508145158046,
|
| 266 |
+
"learning_rate": 1.837669094693028e-05,
|
| 267 |
+
"loss": 0.3857,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17781937295273748,
|
| 272 |
+
"grad_norm": 0.24654174660930164,
|
| 273 |
+
"learning_rate": 1.827263267429761e-05,
|
| 274 |
+
"loss": 0.3903,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18249883013570425,
|
| 279 |
+
"grad_norm": 0.28662121700475657,
|
| 280 |
+
"learning_rate": 1.8168574401664934e-05,
|
| 281 |
+
"loss": 0.3898,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18717828731867103,
|
| 286 |
+
"grad_norm": 0.23290473813531298,
|
| 287 |
+
"learning_rate": 1.806451612903226e-05,
|
| 288 |
+
"loss": 0.3768,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1918577445016378,
|
| 293 |
+
"grad_norm": 0.28192870043577783,
|
| 294 |
+
"learning_rate": 1.7960457856399584e-05,
|
| 295 |
+
"loss": 0.3879,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.1965372016846046,
|
| 300 |
+
"grad_norm": 0.27564026147091214,
|
| 301 |
+
"learning_rate": 1.785639958376691e-05,
|
| 302 |
+
"loss": 0.3865,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20121665886757137,
|
| 307 |
+
"grad_norm": 0.23229839176465608,
|
| 308 |
+
"learning_rate": 1.7752341311134234e-05,
|
| 309 |
+
"loss": 0.3841,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20589611605053815,
|
| 314 |
+
"grad_norm": 0.25015151051907036,
|
| 315 |
+
"learning_rate": 1.7648283038501563e-05,
|
| 316 |
+
"loss": 0.3915,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.21057557323350493,
|
| 321 |
+
"grad_norm": 0.24218523885962545,
|
| 322 |
+
"learning_rate": 1.7544224765868888e-05,
|
| 323 |
+
"loss": 0.3845,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21525503041647168,
|
| 328 |
+
"grad_norm": 0.21893648736945756,
|
| 329 |
+
"learning_rate": 1.7440166493236216e-05,
|
| 330 |
+
"loss": 0.3796,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21993448759943846,
|
| 335 |
+
"grad_norm": 0.24100134035505158,
|
| 336 |
+
"learning_rate": 1.733610822060354e-05,
|
| 337 |
+
"loss": 0.3809,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22461394478240523,
|
| 342 |
+
"grad_norm": 0.24831115571580942,
|
| 343 |
+
"learning_rate": 1.7232049947970866e-05,
|
| 344 |
+
"loss": 0.3942,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.229293401965372,
|
| 349 |
+
"grad_norm": 0.2270469313952638,
|
| 350 |
+
"learning_rate": 1.712799167533819e-05,
|
| 351 |
+
"loss": 0.3822,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2339728591483388,
|
| 356 |
+
"grad_norm": 0.21454127210032897,
|
| 357 |
+
"learning_rate": 1.7023933402705516e-05,
|
| 358 |
+
"loss": 0.3804,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23865231633130557,
|
| 363 |
+
"grad_norm": 0.2784358974791008,
|
| 364 |
+
"learning_rate": 1.691987513007284e-05,
|
| 365 |
+
"loss": 0.3891,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24333177351427235,
|
| 370 |
+
"grad_norm": 0.25560963065745107,
|
| 371 |
+
"learning_rate": 1.681581685744017e-05,
|
| 372 |
+
"loss": 0.3785,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24801123069723913,
|
| 377 |
+
"grad_norm": 0.29030559419788876,
|
| 378 |
+
"learning_rate": 1.6711758584807495e-05,
|
| 379 |
+
"loss": 0.3859,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2526906878802059,
|
| 384 |
+
"grad_norm": 0.23201558406292724,
|
| 385 |
+
"learning_rate": 1.660770031217482e-05,
|
| 386 |
+
"loss": 0.3905,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2573701450631727,
|
| 391 |
+
"grad_norm": 0.2230334421902013,
|
| 392 |
+
"learning_rate": 1.6503642039542145e-05,
|
| 393 |
+
"loss": 0.3826,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26204960224613943,
|
| 398 |
+
"grad_norm": 0.2888881421186973,
|
| 399 |
+
"learning_rate": 1.639958376690947e-05,
|
| 400 |
+
"loss": 0.3854,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.26672905942910624,
|
| 405 |
+
"grad_norm": 0.23960115819463665,
|
| 406 |
+
"learning_rate": 1.6295525494276795e-05,
|
| 407 |
+
"loss": 0.3812,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.271408516612073,
|
| 412 |
+
"grad_norm": 0.219894569143036,
|
| 413 |
+
"learning_rate": 1.6191467221644123e-05,
|
| 414 |
+
"loss": 0.3772,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.2760879737950398,
|
| 419 |
+
"grad_norm": 0.24801341276626648,
|
| 420 |
+
"learning_rate": 1.6087408949011448e-05,
|
| 421 |
+
"loss": 0.3809,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.28076743097800655,
|
| 426 |
+
"grad_norm": 0.2654106880151869,
|
| 427 |
+
"learning_rate": 1.5983350676378773e-05,
|
| 428 |
+
"loss": 0.3805,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2854468881609733,
|
| 433 |
+
"grad_norm": 0.22635581084433476,
|
| 434 |
+
"learning_rate": 1.5879292403746098e-05,
|
| 435 |
+
"loss": 0.3768,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2901263453439401,
|
| 440 |
+
"grad_norm": 0.21488693776906298,
|
| 441 |
+
"learning_rate": 1.5775234131113423e-05,
|
| 442 |
+
"loss": 0.3689,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.29480580252690686,
|
| 447 |
+
"grad_norm": 0.26183689025810514,
|
| 448 |
+
"learning_rate": 1.5671175858480748e-05,
|
| 449 |
+
"loss": 0.3735,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.29948525970987366,
|
| 454 |
+
"grad_norm": 0.2694040246267707,
|
| 455 |
+
"learning_rate": 1.5567117585848077e-05,
|
| 456 |
+
"loss": 0.3808,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3041647168928404,
|
| 461 |
+
"grad_norm": 0.24520431614646418,
|
| 462 |
+
"learning_rate": 1.54630593132154e-05,
|
| 463 |
+
"loss": 0.3854,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3088441740758072,
|
| 468 |
+
"grad_norm": 0.2564447473549132,
|
| 469 |
+
"learning_rate": 1.5359001040582727e-05,
|
| 470 |
+
"loss": 0.3862,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.31352363125877397,
|
| 475 |
+
"grad_norm": 0.23238465003590167,
|
| 476 |
+
"learning_rate": 1.5254942767950053e-05,
|
| 477 |
+
"loss": 0.3815,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3182030884417408,
|
| 482 |
+
"grad_norm": 0.2800169601088245,
|
| 483 |
+
"learning_rate": 1.515088449531738e-05,
|
| 484 |
+
"loss": 0.3814,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.32288254562470753,
|
| 489 |
+
"grad_norm": 0.22176804004915363,
|
| 490 |
+
"learning_rate": 1.5046826222684705e-05,
|
| 491 |
+
"loss": 0.3801,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.32756200280767434,
|
| 496 |
+
"grad_norm": 0.23327501996058547,
|
| 497 |
+
"learning_rate": 1.494276795005203e-05,
|
| 498 |
+
"loss": 0.3712,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3322414599906411,
|
| 503 |
+
"grad_norm": 0.23797943468099234,
|
| 504 |
+
"learning_rate": 1.4838709677419357e-05,
|
| 505 |
+
"loss": 0.3736,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.33692091717360784,
|
| 510 |
+
"grad_norm": 0.21540929537029724,
|
| 511 |
+
"learning_rate": 1.4734651404786682e-05,
|
| 512 |
+
"loss": 0.3785,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.34160037435657464,
|
| 517 |
+
"grad_norm": 0.2820377200347258,
|
| 518 |
+
"learning_rate": 1.4630593132154007e-05,
|
| 519 |
+
"loss": 0.3754,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3462798315395414,
|
| 524 |
+
"grad_norm": 0.2364483513673407,
|
| 525 |
+
"learning_rate": 1.4526534859521334e-05,
|
| 526 |
+
"loss": 0.3768,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3509592887225082,
|
| 531 |
+
"grad_norm": 0.23107190478630543,
|
| 532 |
+
"learning_rate": 1.4422476586888659e-05,
|
| 533 |
+
"loss": 0.384,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35563874590547495,
|
| 538 |
+
"grad_norm": 0.2544369764708807,
|
| 539 |
+
"learning_rate": 1.4318418314255984e-05,
|
| 540 |
+
"loss": 0.3821,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.36031820308844176,
|
| 545 |
+
"grad_norm": 0.2733772251893476,
|
| 546 |
+
"learning_rate": 1.421436004162331e-05,
|
| 547 |
+
"loss": 0.3863,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3649976602714085,
|
| 552 |
+
"grad_norm": 0.2328825486788227,
|
| 553 |
+
"learning_rate": 1.4110301768990635e-05,
|
| 554 |
+
"loss": 0.3794,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3696771174543753,
|
| 559 |
+
"grad_norm": 0.22430844792190455,
|
| 560 |
+
"learning_rate": 1.400624349635796e-05,
|
| 561 |
+
"loss": 0.3801,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.37435657463734207,
|
| 566 |
+
"grad_norm": 0.24928578537816098,
|
| 567 |
+
"learning_rate": 1.3902185223725287e-05,
|
| 568 |
+
"loss": 0.391,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.37903603182030887,
|
| 573 |
+
"grad_norm": 0.2314083212055415,
|
| 574 |
+
"learning_rate": 1.3798126951092612e-05,
|
| 575 |
+
"loss": 0.3767,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3837154890032756,
|
| 580 |
+
"grad_norm": 0.25193607656373374,
|
| 581 |
+
"learning_rate": 1.3694068678459939e-05,
|
| 582 |
+
"loss": 0.3742,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3883949461862424,
|
| 587 |
+
"grad_norm": 0.26856384975738834,
|
| 588 |
+
"learning_rate": 1.3590010405827266e-05,
|
| 589 |
+
"loss": 0.3893,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3930744033692092,
|
| 594 |
+
"grad_norm": 0.2410724044047713,
|
| 595 |
+
"learning_rate": 1.348595213319459e-05,
|
| 596 |
+
"loss": 0.3881,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39775386055217593,
|
| 601 |
+
"grad_norm": 0.22933262352367176,
|
| 602 |
+
"learning_rate": 1.3381893860561916e-05,
|
| 603 |
+
"loss": 0.389,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.40243331773514274,
|
| 608 |
+
"grad_norm": 0.2198762674864796,
|
| 609 |
+
"learning_rate": 1.3277835587929242e-05,
|
| 610 |
+
"loss": 0.3777,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4071127749181095,
|
| 615 |
+
"grad_norm": 0.2419080712284111,
|
| 616 |
+
"learning_rate": 1.3173777315296567e-05,
|
| 617 |
+
"loss": 0.3675,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4117922321010763,
|
| 622 |
+
"grad_norm": 0.22323453635381435,
|
| 623 |
+
"learning_rate": 1.3069719042663892e-05,
|
| 624 |
+
"loss": 0.3766,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.41647168928404305,
|
| 629 |
+
"grad_norm": 0.2439496427012552,
|
| 630 |
+
"learning_rate": 1.2965660770031219e-05,
|
| 631 |
+
"loss": 0.3737,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.42115114646700985,
|
| 636 |
+
"grad_norm": 0.21608448050711354,
|
| 637 |
+
"learning_rate": 1.2861602497398544e-05,
|
| 638 |
+
"loss": 0.3762,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4258306036499766,
|
| 643 |
+
"grad_norm": 0.23222753887880532,
|
| 644 |
+
"learning_rate": 1.2757544224765869e-05,
|
| 645 |
+
"loss": 0.3806,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.43051006083294335,
|
| 650 |
+
"grad_norm": 0.23089602293769354,
|
| 651 |
+
"learning_rate": 1.2653485952133196e-05,
|
| 652 |
+
"loss": 0.3866,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.43518951801591016,
|
| 657 |
+
"grad_norm": 0.22647211350083776,
|
| 658 |
+
"learning_rate": 1.2549427679500521e-05,
|
| 659 |
+
"loss": 0.376,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4398689751988769,
|
| 664 |
+
"grad_norm": 0.22578583335582927,
|
| 665 |
+
"learning_rate": 1.2445369406867846e-05,
|
| 666 |
+
"loss": 0.3755,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4445484323818437,
|
| 671 |
+
"grad_norm": 0.25240119086847307,
|
| 672 |
+
"learning_rate": 1.2341311134235173e-05,
|
| 673 |
+
"loss": 0.3705,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44922788956481047,
|
| 678 |
+
"grad_norm": 0.21696390759958575,
|
| 679 |
+
"learning_rate": 1.2237252861602498e-05,
|
| 680 |
+
"loss": 0.3791,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4539073467477773,
|
| 685 |
+
"grad_norm": 0.2259330179979768,
|
| 686 |
+
"learning_rate": 1.2133194588969823e-05,
|
| 687 |
+
"loss": 0.3647,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.458586803930744,
|
| 692 |
+
"grad_norm": 0.23734350889969866,
|
| 693 |
+
"learning_rate": 1.202913631633715e-05,
|
| 694 |
+
"loss": 0.3867,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.46326626111371083,
|
| 699 |
+
"grad_norm": 0.29490446479765287,
|
| 700 |
+
"learning_rate": 1.1925078043704474e-05,
|
| 701 |
+
"loss": 0.3802,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4679457182966776,
|
| 706 |
+
"grad_norm": 0.2539714715149494,
|
| 707 |
+
"learning_rate": 1.1821019771071803e-05,
|
| 708 |
+
"loss": 0.3769,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4726251754796444,
|
| 713 |
+
"grad_norm": 0.2653171806988273,
|
| 714 |
+
"learning_rate": 1.1716961498439128e-05,
|
| 715 |
+
"loss": 0.3774,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.47730463266261114,
|
| 720 |
+
"grad_norm": 0.22986118422933471,
|
| 721 |
+
"learning_rate": 1.1612903225806453e-05,
|
| 722 |
+
"loss": 0.3761,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4819840898455779,
|
| 727 |
+
"grad_norm": 0.264468288478972,
|
| 728 |
+
"learning_rate": 1.150884495317378e-05,
|
| 729 |
+
"loss": 0.3768,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4866635470285447,
|
| 734 |
+
"grad_norm": 0.2275931074116885,
|
| 735 |
+
"learning_rate": 1.1404786680541105e-05,
|
| 736 |
+
"loss": 0.3793,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.49134300421151145,
|
| 741 |
+
"grad_norm": 0.3117840889438511,
|
| 742 |
+
"learning_rate": 1.130072840790843e-05,
|
| 743 |
+
"loss": 0.3767,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.49602246139447825,
|
| 748 |
+
"grad_norm": 0.24416383968722374,
|
| 749 |
+
"learning_rate": 1.1196670135275756e-05,
|
| 750 |
+
"loss": 0.3767,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5007019185774451,
|
| 755 |
+
"grad_norm": 0.2500367823625742,
|
| 756 |
+
"learning_rate": 1.1092611862643081e-05,
|
| 757 |
+
"loss": 0.3773,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5053813757604118,
|
| 762 |
+
"grad_norm": 0.23404067505268092,
|
| 763 |
+
"learning_rate": 1.0988553590010406e-05,
|
| 764 |
+
"loss": 0.3789,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5100608329433786,
|
| 769 |
+
"grad_norm": 0.23836407315387556,
|
| 770 |
+
"learning_rate": 1.0884495317377733e-05,
|
| 771 |
+
"loss": 0.3807,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5147402901263454,
|
| 776 |
+
"grad_norm": 0.2272928154140146,
|
| 777 |
+
"learning_rate": 1.0780437044745058e-05,
|
| 778 |
+
"loss": 0.378,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5194197473093122,
|
| 783 |
+
"grad_norm": 0.21603973655035985,
|
| 784 |
+
"learning_rate": 1.0676378772112383e-05,
|
| 785 |
+
"loss": 0.3849,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5240992044922789,
|
| 790 |
+
"grad_norm": 0.26461820434483596,
|
| 791 |
+
"learning_rate": 1.057232049947971e-05,
|
| 792 |
+
"loss": 0.3807,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5287786616752457,
|
| 797 |
+
"grad_norm": 0.22573025113669873,
|
| 798 |
+
"learning_rate": 1.0468262226847035e-05,
|
| 799 |
+
"loss": 0.3713,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5334581188582125,
|
| 804 |
+
"grad_norm": 0.2398814988800669,
|
| 805 |
+
"learning_rate": 1.036420395421436e-05,
|
| 806 |
+
"loss": 0.3741,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5381375760411792,
|
| 811 |
+
"grad_norm": 0.33008700162835736,
|
| 812 |
+
"learning_rate": 1.0260145681581687e-05,
|
| 813 |
+
"loss": 0.3784,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.542817033224146,
|
| 818 |
+
"grad_norm": 0.2478593026168216,
|
| 819 |
+
"learning_rate": 1.0156087408949012e-05,
|
| 820 |
+
"loss": 0.3797,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5474964904071128,
|
| 825 |
+
"grad_norm": 0.22416882300252308,
|
| 826 |
+
"learning_rate": 1.0052029136316337e-05,
|
| 827 |
+
"loss": 0.3717,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5521759475900796,
|
| 832 |
+
"grad_norm": 0.24550032569746283,
|
| 833 |
+
"learning_rate": 9.947970863683663e-06,
|
| 834 |
+
"loss": 0.3716,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5568554047730463,
|
| 839 |
+
"grad_norm": 0.21152157772573982,
|
| 840 |
+
"learning_rate": 9.843912591050988e-06,
|
| 841 |
+
"loss": 0.3762,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5615348619560131,
|
| 846 |
+
"grad_norm": 0.26437115475677,
|
| 847 |
+
"learning_rate": 9.739854318418315e-06,
|
| 848 |
+
"loss": 0.3649,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5662143191389799,
|
| 853 |
+
"grad_norm": 0.24141737859739215,
|
| 854 |
+
"learning_rate": 9.63579604578564e-06,
|
| 855 |
+
"loss": 0.3721,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5708937763219466,
|
| 860 |
+
"grad_norm": 0.2158535958967608,
|
| 861 |
+
"learning_rate": 9.531737773152965e-06,
|
| 862 |
+
"loss": 0.3736,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5755732335049134,
|
| 867 |
+
"grad_norm": 0.25210607106723404,
|
| 868 |
+
"learning_rate": 9.427679500520292e-06,
|
| 869 |
+
"loss": 0.3779,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5802526906878802,
|
| 874 |
+
"grad_norm": 0.24941061104468912,
|
| 875 |
+
"learning_rate": 9.323621227887619e-06,
|
| 876 |
+
"loss": 0.3724,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.584932147870847,
|
| 881 |
+
"grad_norm": 0.23950130390892227,
|
| 882 |
+
"learning_rate": 9.219562955254944e-06,
|
| 883 |
+
"loss": 0.3718,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5896116050538137,
|
| 888 |
+
"grad_norm": 0.2413173383260915,
|
| 889 |
+
"learning_rate": 9.115504682622269e-06,
|
| 890 |
+
"loss": 0.3736,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5942910622367805,
|
| 895 |
+
"grad_norm": 0.23891221147926558,
|
| 896 |
+
"learning_rate": 9.011446409989595e-06,
|
| 897 |
+
"loss": 0.3722,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5989705194197473,
|
| 902 |
+
"grad_norm": 0.21323637844758167,
|
| 903 |
+
"learning_rate": 8.90738813735692e-06,
|
| 904 |
+
"loss": 0.3666,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6036499766027141,
|
| 909 |
+
"grad_norm": 0.23920099409630857,
|
| 910 |
+
"learning_rate": 8.803329864724245e-06,
|
| 911 |
+
"loss": 0.3833,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6083294337856808,
|
| 916 |
+
"grad_norm": 0.24543976835408943,
|
| 917 |
+
"learning_rate": 8.699271592091572e-06,
|
| 918 |
+
"loss": 0.3822,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6130088909686476,
|
| 923 |
+
"grad_norm": 0.23517185442217967,
|
| 924 |
+
"learning_rate": 8.595213319458897e-06,
|
| 925 |
+
"loss": 0.3825,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6176883481516144,
|
| 930 |
+
"grad_norm": 0.22209203218170853,
|
| 931 |
+
"learning_rate": 8.491155046826224e-06,
|
| 932 |
+
"loss": 0.3742,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6223678053345811,
|
| 937 |
+
"grad_norm": 0.2118379611031678,
|
| 938 |
+
"learning_rate": 8.387096774193549e-06,
|
| 939 |
+
"loss": 0.3705,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6270472625175479,
|
| 944 |
+
"grad_norm": 0.24116107131805098,
|
| 945 |
+
"learning_rate": 8.283038501560876e-06,
|
| 946 |
+
"loss": 0.3648,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6317267197005147,
|
| 951 |
+
"grad_norm": 0.24385133695583516,
|
| 952 |
+
"learning_rate": 8.1789802289282e-06,
|
| 953 |
+
"loss": 0.3846,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6364061768834816,
|
| 958 |
+
"grad_norm": 0.24780606354176135,
|
| 959 |
+
"learning_rate": 8.074921956295526e-06,
|
| 960 |
+
"loss": 0.3843,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6410856340664483,
|
| 965 |
+
"grad_norm": 0.267287826257429,
|
| 966 |
+
"learning_rate": 7.970863683662852e-06,
|
| 967 |
+
"loss": 0.3697,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6457650912494151,
|
| 972 |
+
"grad_norm": 0.2544017525039406,
|
| 973 |
+
"learning_rate": 7.866805411030177e-06,
|
| 974 |
+
"loss": 0.3709,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6504445484323819,
|
| 979 |
+
"grad_norm": 0.2455819067026457,
|
| 980 |
+
"learning_rate": 7.762747138397502e-06,
|
| 981 |
+
"loss": 0.3701,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6551240056153487,
|
| 986 |
+
"grad_norm": 0.259501849908747,
|
| 987 |
+
"learning_rate": 7.658688865764829e-06,
|
| 988 |
+
"loss": 0.3772,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6598034627983154,
|
| 993 |
+
"grad_norm": 0.20856381315062708,
|
| 994 |
+
"learning_rate": 7.554630593132155e-06,
|
| 995 |
+
"loss": 0.3707,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6644829199812822,
|
| 1000 |
+
"grad_norm": 0.2332621123767882,
|
| 1001 |
+
"learning_rate": 7.450572320499481e-06,
|
| 1002 |
+
"loss": 0.3894,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.669162377164249,
|
| 1007 |
+
"grad_norm": 0.20954093237017377,
|
| 1008 |
+
"learning_rate": 7.346514047866807e-06,
|
| 1009 |
+
"loss": 0.374,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6738418343472157,
|
| 1014 |
+
"grad_norm": 0.2010019285730511,
|
| 1015 |
+
"learning_rate": 7.242455775234132e-06,
|
| 1016 |
+
"loss": 0.3838,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6785212915301825,
|
| 1021 |
+
"grad_norm": 0.21248927092428815,
|
| 1022 |
+
"learning_rate": 7.1383975026014575e-06,
|
| 1023 |
+
"loss": 0.3612,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6832007487131493,
|
| 1028 |
+
"grad_norm": 0.1994556422452643,
|
| 1029 |
+
"learning_rate": 7.0343392299687825e-06,
|
| 1030 |
+
"loss": 0.3724,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6878802058961161,
|
| 1035 |
+
"grad_norm": 0.22422751080621398,
|
| 1036 |
+
"learning_rate": 6.930280957336108e-06,
|
| 1037 |
+
"loss": 0.3762,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6925596630790828,
|
| 1042 |
+
"grad_norm": 0.21331923051138799,
|
| 1043 |
+
"learning_rate": 6.826222684703434e-06,
|
| 1044 |
+
"loss": 0.368,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6972391202620496,
|
| 1049 |
+
"grad_norm": 0.2103235038933413,
|
| 1050 |
+
"learning_rate": 6.722164412070759e-06,
|
| 1051 |
+
"loss": 0.3703,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.7019185774450164,
|
| 1056 |
+
"grad_norm": 0.2156780953428616,
|
| 1057 |
+
"learning_rate": 6.618106139438086e-06,
|
| 1058 |
+
"loss": 0.3786,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7065980346279832,
|
| 1063 |
+
"grad_norm": 0.21490072085384168,
|
| 1064 |
+
"learning_rate": 6.514047866805412e-06,
|
| 1065 |
+
"loss": 0.3758,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7112774918109499,
|
| 1070 |
+
"grad_norm": 0.2247782023019425,
|
| 1071 |
+
"learning_rate": 6.409989594172738e-06,
|
| 1072 |
+
"loss": 0.3679,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7159569489939167,
|
| 1077 |
+
"grad_norm": 0.20942665269809468,
|
| 1078 |
+
"learning_rate": 6.305931321540063e-06,
|
| 1079 |
+
"loss": 0.3652,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7206364061768835,
|
| 1084 |
+
"grad_norm": 0.22300307299120317,
|
| 1085 |
+
"learning_rate": 6.201873048907389e-06,
|
| 1086 |
+
"loss": 0.3867,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7253158633598502,
|
| 1091 |
+
"grad_norm": 0.21731092424159765,
|
| 1092 |
+
"learning_rate": 6.0978147762747145e-06,
|
| 1093 |
+
"loss": 0.3699,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.729995320542817,
|
| 1098 |
+
"grad_norm": 0.2373583086701352,
|
| 1099 |
+
"learning_rate": 5.9937565036420395e-06,
|
| 1100 |
+
"loss": 0.3653,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7346747777257838,
|
| 1105 |
+
"grad_norm": 0.2066335501990478,
|
| 1106 |
+
"learning_rate": 5.889698231009365e-06,
|
| 1107 |
+
"loss": 0.3741,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7393542349087506,
|
| 1112 |
+
"grad_norm": 0.20910016326262895,
|
| 1113 |
+
"learning_rate": 5.785639958376691e-06,
|
| 1114 |
+
"loss": 0.3724,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7440336920917173,
|
| 1119 |
+
"grad_norm": 0.2235231360878696,
|
| 1120 |
+
"learning_rate": 5.681581685744018e-06,
|
| 1121 |
+
"loss": 0.3727,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7487131492746841,
|
| 1126 |
+
"grad_norm": 0.2046167285793584,
|
| 1127 |
+
"learning_rate": 5.577523413111343e-06,
|
| 1128 |
+
"loss": 0.3684,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7533926064576509,
|
| 1133 |
+
"grad_norm": 0.19515222922990866,
|
| 1134 |
+
"learning_rate": 5.473465140478669e-06,
|
| 1135 |
+
"loss": 0.3787,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7580720636406177,
|
| 1140 |
+
"grad_norm": 0.22525978812547012,
|
| 1141 |
+
"learning_rate": 5.369406867845994e-06,
|
| 1142 |
+
"loss": 0.3764,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7627515208235844,
|
| 1147 |
+
"grad_norm": 0.22394936960559922,
|
| 1148 |
+
"learning_rate": 5.26534859521332e-06,
|
| 1149 |
+
"loss": 0.3672,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7674309780065512,
|
| 1154 |
+
"grad_norm": 0.23343895861163633,
|
| 1155 |
+
"learning_rate": 5.161290322580646e-06,
|
| 1156 |
+
"loss": 0.3676,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.772110435189518,
|
| 1161 |
+
"grad_norm": 0.24463148457843642,
|
| 1162 |
+
"learning_rate": 5.057232049947971e-06,
|
| 1163 |
+
"loss": 0.3728,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7767898923724847,
|
| 1168 |
+
"grad_norm": 0.2187630043298853,
|
| 1169 |
+
"learning_rate": 4.953173777315297e-06,
|
| 1170 |
+
"loss": 0.3712,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7814693495554516,
|
| 1175 |
+
"grad_norm": 0.21300481471513596,
|
| 1176 |
+
"learning_rate": 4.849115504682622e-06,
|
| 1177 |
+
"loss": 0.381,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7861488067384184,
|
| 1182 |
+
"grad_norm": 0.20931843918006063,
|
| 1183 |
+
"learning_rate": 4.745057232049948e-06,
|
| 1184 |
+
"loss": 0.3747,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7908282639213852,
|
| 1189 |
+
"grad_norm": 0.21125591014093664,
|
| 1190 |
+
"learning_rate": 4.640998959417274e-06,
|
| 1191 |
+
"loss": 0.3735,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7955077211043519,
|
| 1196 |
+
"grad_norm": 0.2110487123545379,
|
| 1197 |
+
"learning_rate": 4.5369406867846e-06,
|
| 1198 |
+
"loss": 0.3735,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.8001871782873187,
|
| 1203 |
+
"grad_norm": 0.22392695446168392,
|
| 1204 |
+
"learning_rate": 4.432882414151926e-06,
|
| 1205 |
+
"loss": 0.3777,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8048666354702855,
|
| 1210 |
+
"grad_norm": 0.2117452208603545,
|
| 1211 |
+
"learning_rate": 4.328824141519251e-06,
|
| 1212 |
+
"loss": 0.3761,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8095460926532522,
|
| 1217 |
+
"grad_norm": 0.24234752709613971,
|
| 1218 |
+
"learning_rate": 4.224765868886577e-06,
|
| 1219 |
+
"loss": 0.3796,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.814225549836219,
|
| 1224 |
+
"grad_norm": 0.2025209483621438,
|
| 1225 |
+
"learning_rate": 4.120707596253903e-06,
|
| 1226 |
+
"loss": 0.3808,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8189050070191858,
|
| 1231 |
+
"grad_norm": 0.2226709019764019,
|
| 1232 |
+
"learning_rate": 4.0166493236212285e-06,
|
| 1233 |
+
"loss": 0.3752,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8235844642021526,
|
| 1238 |
+
"grad_norm": 0.2210571915933747,
|
| 1239 |
+
"learning_rate": 3.912591050988554e-06,
|
| 1240 |
+
"loss": 0.3704,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.8282639213851193,
|
| 1245 |
+
"grad_norm": 0.23618799628521495,
|
| 1246 |
+
"learning_rate": 3.8085327783558793e-06,
|
| 1247 |
+
"loss": 0.3737,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8329433785680861,
|
| 1252 |
+
"grad_norm": 0.20617597677407185,
|
| 1253 |
+
"learning_rate": 3.7044745057232052e-06,
|
| 1254 |
+
"loss": 0.3749,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8376228357510529,
|
| 1259 |
+
"grad_norm": 0.20798543863033134,
|
| 1260 |
+
"learning_rate": 3.600416233090531e-06,
|
| 1261 |
+
"loss": 0.3687,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8423022929340197,
|
| 1266 |
+
"grad_norm": 0.2089006102637797,
|
| 1267 |
+
"learning_rate": 3.496357960457857e-06,
|
| 1268 |
+
"loss": 0.3706,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8469817501169864,
|
| 1273 |
+
"grad_norm": 0.20477692589921484,
|
| 1274 |
+
"learning_rate": 3.3922996878251824e-06,
|
| 1275 |
+
"loss": 0.3702,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8516612072999532,
|
| 1280 |
+
"grad_norm": 0.21774749397741822,
|
| 1281 |
+
"learning_rate": 3.288241415192508e-06,
|
| 1282 |
+
"loss": 0.3657,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.85634066448292,
|
| 1287 |
+
"grad_norm": 0.24858244914099062,
|
| 1288 |
+
"learning_rate": 3.1841831425598337e-06,
|
| 1289 |
+
"loss": 0.3681,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8610201216658867,
|
| 1294 |
+
"grad_norm": 0.22753648396835552,
|
| 1295 |
+
"learning_rate": 3.0801248699271596e-06,
|
| 1296 |
+
"loss": 0.3703,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8656995788488535,
|
| 1301 |
+
"grad_norm": 0.2585954998067118,
|
| 1302 |
+
"learning_rate": 2.976066597294485e-06,
|
| 1303 |
+
"loss": 0.3748,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8703790360318203,
|
| 1308 |
+
"grad_norm": 0.23712893924962872,
|
| 1309 |
+
"learning_rate": 2.872008324661811e-06,
|
| 1310 |
+
"loss": 0.3724,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8750584932147871,
|
| 1315 |
+
"grad_norm": 0.21078832525011484,
|
| 1316 |
+
"learning_rate": 2.7679500520291363e-06,
|
| 1317 |
+
"loss": 0.3722,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8797379503977538,
|
| 1322 |
+
"grad_norm": 0.2005875423082211,
|
| 1323 |
+
"learning_rate": 2.6638917793964626e-06,
|
| 1324 |
+
"loss": 0.364,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.8844174075807206,
|
| 1329 |
+
"grad_norm": 0.21183567448111165,
|
| 1330 |
+
"learning_rate": 2.559833506763788e-06,
|
| 1331 |
+
"loss": 0.3646,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8890968647636874,
|
| 1336 |
+
"grad_norm": 0.23633491944791057,
|
| 1337 |
+
"learning_rate": 2.4557752341311135e-06,
|
| 1338 |
+
"loss": 0.369,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8937763219466542,
|
| 1343 |
+
"grad_norm": 0.20446185463761749,
|
| 1344 |
+
"learning_rate": 2.3517169614984394e-06,
|
| 1345 |
+
"loss": 0.3717,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8984557791296209,
|
| 1350 |
+
"grad_norm": 0.21120878547944943,
|
| 1351 |
+
"learning_rate": 2.2476586888657652e-06,
|
| 1352 |
+
"loss": 0.3691,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.9031352363125877,
|
| 1357 |
+
"grad_norm": 0.21926451373870526,
|
| 1358 |
+
"learning_rate": 2.1436004162330907e-06,
|
| 1359 |
+
"loss": 0.376,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9078146934955545,
|
| 1364 |
+
"grad_norm": 0.21234936601889798,
|
| 1365 |
+
"learning_rate": 2.0395421436004166e-06,
|
| 1366 |
+
"loss": 0.3721,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9124941506785212,
|
| 1371 |
+
"grad_norm": 0.22032807507001712,
|
| 1372 |
+
"learning_rate": 1.935483870967742e-06,
|
| 1373 |
+
"loss": 0.3796,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.917173607861488,
|
| 1378 |
+
"grad_norm": 0.20048012242437066,
|
| 1379 |
+
"learning_rate": 1.8314255983350679e-06,
|
| 1380 |
+
"loss": 0.3692,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9218530650444549,
|
| 1385 |
+
"grad_norm": 0.19197425552585032,
|
| 1386 |
+
"learning_rate": 1.7273673257023935e-06,
|
| 1387 |
+
"loss": 0.3602,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9265325222274217,
|
| 1392 |
+
"grad_norm": 0.19963248316970567,
|
| 1393 |
+
"learning_rate": 1.6233090530697194e-06,
|
| 1394 |
+
"loss": 0.3687,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9312119794103884,
|
| 1399 |
+
"grad_norm": 0.20252903061869637,
|
| 1400 |
+
"learning_rate": 1.5192507804370448e-06,
|
| 1401 |
+
"loss": 0.3693,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9358914365933552,
|
| 1406 |
+
"grad_norm": 0.22168638474832342,
|
| 1407 |
+
"learning_rate": 1.4151925078043705e-06,
|
| 1408 |
+
"loss": 0.3775,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.940570893776322,
|
| 1413 |
+
"grad_norm": 0.21135045250093049,
|
| 1414 |
+
"learning_rate": 1.3111342351716964e-06,
|
| 1415 |
+
"loss": 0.3707,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9452503509592888,
|
| 1420 |
+
"grad_norm": 0.20991603381075577,
|
| 1421 |
+
"learning_rate": 1.207075962539022e-06,
|
| 1422 |
+
"loss": 0.3801,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9499298081422555,
|
| 1427 |
+
"grad_norm": 0.19588787717171513,
|
| 1428 |
+
"learning_rate": 1.1030176899063477e-06,
|
| 1429 |
+
"loss": 0.3707,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9546092653252223,
|
| 1434 |
+
"grad_norm": 0.18850895260293038,
|
| 1435 |
+
"learning_rate": 9.989594172736733e-07,
|
| 1436 |
+
"loss": 0.3603,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9592887225081891,
|
| 1441 |
+
"grad_norm": 0.1924405623942021,
|
| 1442 |
+
"learning_rate": 8.94901144640999e-07,
|
| 1443 |
+
"loss": 0.3663,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9639681796911558,
|
| 1448 |
+
"grad_norm": 0.1934047488919004,
|
| 1449 |
+
"learning_rate": 7.908428720083247e-07,
|
| 1450 |
+
"loss": 0.3731,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9686476368741226,
|
| 1455 |
+
"grad_norm": 0.2027478493287533,
|
| 1456 |
+
"learning_rate": 6.867845993756504e-07,
|
| 1457 |
+
"loss": 0.3682,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9733270940570894,
|
| 1462 |
+
"grad_norm": 0.19171827074306003,
|
| 1463 |
+
"learning_rate": 5.827263267429762e-07,
|
| 1464 |
+
"loss": 0.3643,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9780065512400562,
|
| 1469 |
+
"grad_norm": 0.20102243551100357,
|
| 1470 |
+
"learning_rate": 4.786680541103018e-07,
|
| 1471 |
+
"loss": 0.3761,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9826860084230229,
|
| 1476 |
+
"grad_norm": 0.19333944542660678,
|
| 1477 |
+
"learning_rate": 3.7460978147762747e-07,
|
| 1478 |
+
"loss": 0.3782,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9873654656059897,
|
| 1483 |
+
"grad_norm": 0.2031908820930634,
|
| 1484 |
+
"learning_rate": 2.705515088449532e-07,
|
| 1485 |
+
"loss": 0.3766,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9920449227889565,
|
| 1490 |
+
"grad_norm": 0.1887326527462366,
|
| 1491 |
+
"learning_rate": 1.6649323621227891e-07,
|
| 1492 |
+
"loss": 0.376,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9967243799719232,
|
| 1497 |
+
"grad_norm": 0.195152345665213,
|
| 1498 |
+
"learning_rate": 6.243496357960458e-08,
|
| 1499 |
+
"loss": 0.3606,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9995320542817033,
|
| 1504 |
+
"step": 1068,
|
| 1505 |
+
"total_flos": 9.145616827248804e+17,
|
| 1506 |
+
"train_loss": 0.3807801652267185,
|
| 1507 |
+
"train_runtime": 28315.9454,
|
| 1508 |
+
"train_samples_per_second": 0.604,
|
| 1509 |
+
"train_steps_per_second": 0.038
|
| 1510 |
+
}
|
| 1511 |
+
],
|
| 1512 |
+
"logging_steps": 5,
|
| 1513 |
+
"max_steps": 1068,
|
| 1514 |
+
"num_input_tokens_seen": 0,
|
| 1515 |
+
"num_train_epochs": 1,
|
| 1516 |
+
"save_steps": 500,
|
| 1517 |
+
"stateful_callbacks": {
|
| 1518 |
+
"TrainerControl": {
|
| 1519 |
+
"args": {
|
| 1520 |
+
"should_epoch_stop": false,
|
| 1521 |
+
"should_evaluate": false,
|
| 1522 |
+
"should_log": false,
|
| 1523 |
+
"should_save": true,
|
| 1524 |
+
"should_training_stop": true
|
| 1525 |
+
},
|
| 1526 |
+
"attributes": {}
|
| 1527 |
+
}
|
| 1528 |
+
},
|
| 1529 |
+
"total_flos": 9.145616827248804e+17,
|
| 1530 |
+
"train_batch_size": 1,
|
| 1531 |
+
"trial_name": null,
|
| 1532 |
+
"trial_params": null
|
| 1533 |
+
}
|