Model save
Browse files- README.md +67 -0
- all_results.json +8 -0
- generation_config.json +6 -0
- train_results.json +8 -0
- trainer_state.json +1417 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
model_name: Qwen2.5-3B-GRPO-Natural-Reasoning-stage-2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
- trl
|
| 7 |
+
- grpo
|
| 8 |
+
licence: license
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Qwen2.5-3B-GRPO-Natural-Reasoning-stage-2
|
| 12 |
+
|
| 13 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 14 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
+
|
| 16 |
+
## Quick start
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import pipeline
|
| 20 |
+
|
| 21 |
+
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?"
|
| 22 |
+
generator = pipeline("text-generation", model="qingyangzhang/Qwen2.5-3B-GRPO-Natural-Reasoning-stage-2", device="cuda")
|
| 23 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 24 |
+
print(output["generated_text"])
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
## Training procedure
|
| 28 |
+
|
| 29 |
+
[<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/zqyoung1127-tianjin-university/huggingface/runs/7xqfcts4)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
| 33 |
+
|
| 34 |
+
### Framework versions
|
| 35 |
+
|
| 36 |
+
- TRL: 0.14.0
|
| 37 |
+
- Transformers: 4.48.3
|
| 38 |
+
- Pytorch: 2.5.1
|
| 39 |
+
- Datasets: 3.1.0
|
| 40 |
+
- Tokenizers: 0.21.0
|
| 41 |
+
|
| 42 |
+
## Citations
|
| 43 |
+
|
| 44 |
+
Cite GRPO as:
|
| 45 |
+
|
| 46 |
+
```bibtex
|
| 47 |
+
@article{zhihong2024deepseekmath,
|
| 48 |
+
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
| 49 |
+
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
| 50 |
+
year = 2024,
|
| 51 |
+
eprint = {arXiv:2402.03300},
|
| 52 |
+
}
|
| 53 |
+
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
Cite TRL as:
|
| 57 |
+
|
| 58 |
+
```bibtex
|
| 59 |
+
@misc{vonwerra2022trl,
|
| 60 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 61 |
+
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},
|
| 62 |
+
year = 2020,
|
| 63 |
+
journal = {GitHub repository},
|
| 64 |
+
publisher = {GitHub},
|
| 65 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 66 |
+
}
|
| 67 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 1.7134473857538523e-08,
|
| 4 |
+
"train_runtime": 32762.3532,
|
| 5 |
+
"train_samples": 12058,
|
| 6 |
+
"train_samples_per_second": 0.368,
|
| 7 |
+
"train_steps_per_second": 0.004
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.48.3"
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 1.7134473857538523e-08,
|
| 4 |
+
"train_runtime": 32762.3532,
|
| 5 |
+
"train_samples": 12058,
|
| 6 |
+
"train_samples_per_second": 0.368,
|
| 7 |
+
"train_steps_per_second": 0.004
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9950248756218906,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 125,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"completion_length": 503.19444847106934,
|
| 13 |
+
"epoch": 0.007960199004975124,
|
| 14 |
+
"grad_norm": 0.0063313147984445095,
|
| 15 |
+
"learning_rate": 1e-06,
|
| 16 |
+
"loss": 0.0,
|
| 17 |
+
"reward": 0.4730902863666415,
|
| 18 |
+
"reward_std": 0.19683137070387602,
|
| 19 |
+
"rewards/accuracy_reward": 0.4730902863666415,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"completion_length": 484.8585090637207,
|
| 24 |
+
"epoch": 0.015920398009950248,
|
| 25 |
+
"grad_norm": 0.007317787501960993,
|
| 26 |
+
"learning_rate": 1e-06,
|
| 27 |
+
"loss": 0.0,
|
| 28 |
+
"reward": 0.4809027840383351,
|
| 29 |
+
"reward_std": 0.18855627719312906,
|
| 30 |
+
"rewards/accuracy_reward": 0.4809027840383351,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"completion_length": 491.93663787841797,
|
| 35 |
+
"epoch": 0.023880597014925373,
|
| 36 |
+
"grad_norm": 0.010451268404722214,
|
| 37 |
+
"learning_rate": 1e-06,
|
| 38 |
+
"loss": 0.0,
|
| 39 |
+
"reward": 0.4279513950459659,
|
| 40 |
+
"reward_std": 0.21083470317535102,
|
| 41 |
+
"rewards/accuracy_reward": 0.4279513950459659,
|
| 42 |
+
"step": 3
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"completion_length": 463.2604236602783,
|
| 46 |
+
"epoch": 0.031840796019900496,
|
| 47 |
+
"grad_norm": 0.005912041291594505,
|
| 48 |
+
"learning_rate": 1e-06,
|
| 49 |
+
"loss": 0.0,
|
| 50 |
+
"reward": 0.4904513908550143,
|
| 51 |
+
"reward_std": 0.18155438522808254,
|
| 52 |
+
"rewards/accuracy_reward": 0.4904513908550143,
|
| 53 |
+
"step": 4
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"completion_length": 464.4531307220459,
|
| 57 |
+
"epoch": 0.03980099502487562,
|
| 58 |
+
"grad_norm": 0.006213425658643246,
|
| 59 |
+
"learning_rate": 1e-06,
|
| 60 |
+
"loss": 0.0,
|
| 61 |
+
"reward": 0.508680566214025,
|
| 62 |
+
"reward_std": 0.19439041009172797,
|
| 63 |
+
"rewards/accuracy_reward": 0.508680566214025,
|
| 64 |
+
"step": 5
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"completion_length": 444.0486183166504,
|
| 68 |
+
"epoch": 0.04776119402985075,
|
| 69 |
+
"grad_norm": 0.00726802833378315,
|
| 70 |
+
"learning_rate": 1e-06,
|
| 71 |
+
"loss": 0.0,
|
| 72 |
+
"reward": 0.5290798731148243,
|
| 73 |
+
"reward_std": 0.16257907613180578,
|
| 74 |
+
"rewards/accuracy_reward": 0.5290798731148243,
|
| 75 |
+
"step": 6
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"completion_length": 486.56163215637207,
|
| 79 |
+
"epoch": 0.05572139303482587,
|
| 80 |
+
"grad_norm": 0.00643517728894949,
|
| 81 |
+
"learning_rate": 1e-06,
|
| 82 |
+
"loss": 0.0,
|
| 83 |
+
"reward": 0.49262153543531895,
|
| 84 |
+
"reward_std": 0.21985508035868406,
|
| 85 |
+
"rewards/accuracy_reward": 0.49262153543531895,
|
| 86 |
+
"step": 7
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"completion_length": 499.3489570617676,
|
| 90 |
+
"epoch": 0.06368159203980099,
|
| 91 |
+
"grad_norm": 0.006929068360477686,
|
| 92 |
+
"learning_rate": 1e-06,
|
| 93 |
+
"loss": 0.0,
|
| 94 |
+
"reward": 0.48090278450399637,
|
| 95 |
+
"reward_std": 0.2359681366942823,
|
| 96 |
+
"rewards/accuracy_reward": 0.48090278450399637,
|
| 97 |
+
"step": 8
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"completion_length": 460.5434055328369,
|
| 101 |
+
"epoch": 0.07164179104477612,
|
| 102 |
+
"grad_norm": 0.006942449603229761,
|
| 103 |
+
"learning_rate": 1e-06,
|
| 104 |
+
"loss": 0.0,
|
| 105 |
+
"reward": 0.5460069458931684,
|
| 106 |
+
"reward_std": 0.20838687336072326,
|
| 107 |
+
"rewards/accuracy_reward": 0.5460069458931684,
|
| 108 |
+
"step": 9
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"completion_length": 482.6258773803711,
|
| 112 |
+
"epoch": 0.07960199004975124,
|
| 113 |
+
"grad_norm": 0.006102504674345255,
|
| 114 |
+
"learning_rate": 1e-06,
|
| 115 |
+
"loss": 0.0,
|
| 116 |
+
"reward": 0.5121527821756899,
|
| 117 |
+
"reward_std": 0.21228309627622366,
|
| 118 |
+
"rewards/accuracy_reward": 0.5121527821756899,
|
| 119 |
+
"step": 10
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"completion_length": 472.4791660308838,
|
| 123 |
+
"epoch": 0.08756218905472637,
|
| 124 |
+
"grad_norm": 0.006756069138646126,
|
| 125 |
+
"learning_rate": 1e-06,
|
| 126 |
+
"loss": 0.0,
|
| 127 |
+
"reward": 0.5095486273057759,
|
| 128 |
+
"reward_std": 0.19290994992479682,
|
| 129 |
+
"rewards/accuracy_reward": 0.5095486273057759,
|
| 130 |
+
"step": 11
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"completion_length": 458.9878520965576,
|
| 134 |
+
"epoch": 0.0955223880597015,
|
| 135 |
+
"grad_norm": 0.00719108572229743,
|
| 136 |
+
"learning_rate": 1e-06,
|
| 137 |
+
"loss": 0.0,
|
| 138 |
+
"reward": 0.4908854253590107,
|
| 139 |
+
"reward_std": 0.2253248537890613,
|
| 140 |
+
"rewards/accuracy_reward": 0.4908854253590107,
|
| 141 |
+
"step": 12
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"completion_length": 492.2612934112549,
|
| 145 |
+
"epoch": 0.10348258706467661,
|
| 146 |
+
"grad_norm": 0.01182724628597498,
|
| 147 |
+
"learning_rate": 1e-06,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
+
"reward": 0.5069444486871362,
|
| 150 |
+
"reward_std": 0.1993837202899158,
|
| 151 |
+
"rewards/accuracy_reward": 0.5069444486871362,
|
| 152 |
+
"step": 13
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"completion_length": 480.2699718475342,
|
| 156 |
+
"epoch": 0.11144278606965174,
|
| 157 |
+
"grad_norm": 0.013605108484625816,
|
| 158 |
+
"learning_rate": 1e-06,
|
| 159 |
+
"loss": 0.0,
|
| 160 |
+
"reward": 0.4383680592291057,
|
| 161 |
+
"reward_std": 0.19313253066502512,
|
| 162 |
+
"rewards/accuracy_reward": 0.4383680592291057,
|
| 163 |
+
"step": 14
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"completion_length": 474.3836898803711,
|
| 167 |
+
"epoch": 0.11940298507462686,
|
| 168 |
+
"grad_norm": 0.005726557224988937,
|
| 169 |
+
"learning_rate": 1e-06,
|
| 170 |
+
"loss": 0.0,
|
| 171 |
+
"reward": 0.5199652798473835,
|
| 172 |
+
"reward_std": 0.17557879141531885,
|
| 173 |
+
"rewards/accuracy_reward": 0.5199652798473835,
|
| 174 |
+
"step": 15
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"completion_length": 479.70920753479004,
|
| 178 |
+
"epoch": 0.12736318407960198,
|
| 179 |
+
"grad_norm": 0.0056375423446297646,
|
| 180 |
+
"learning_rate": 1e-06,
|
| 181 |
+
"loss": 0.0,
|
| 182 |
+
"reward": 0.5078125055879354,
|
| 183 |
+
"reward_std": 0.1571849612519145,
|
| 184 |
+
"rewards/accuracy_reward": 0.5078125055879354,
|
| 185 |
+
"step": 16
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"completion_length": 482.3836860656738,
|
| 189 |
+
"epoch": 0.13532338308457711,
|
| 190 |
+
"grad_norm": 0.006233118008822203,
|
| 191 |
+
"learning_rate": 1e-06,
|
| 192 |
+
"loss": 0.0,
|
| 193 |
+
"reward": 0.4396701483055949,
|
| 194 |
+
"reward_std": 0.169666429865174,
|
| 195 |
+
"rewards/accuracy_reward": 0.4396701483055949,
|
| 196 |
+
"step": 17
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"completion_length": 461.2335090637207,
|
| 200 |
+
"epoch": 0.14328358208955225,
|
| 201 |
+
"grad_norm": 0.0069457427598536015,
|
| 202 |
+
"learning_rate": 1e-06,
|
| 203 |
+
"loss": 0.0,
|
| 204 |
+
"reward": 0.5221354234963655,
|
| 205 |
+
"reward_std": 0.1818335736170411,
|
| 206 |
+
"rewards/accuracy_reward": 0.5221354234963655,
|
| 207 |
+
"step": 18
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"completion_length": 497.4105911254883,
|
| 211 |
+
"epoch": 0.15124378109452735,
|
| 212 |
+
"grad_norm": 0.005326431710273027,
|
| 213 |
+
"learning_rate": 1e-06,
|
| 214 |
+
"loss": 0.0,
|
| 215 |
+
"reward": 0.48437500186264515,
|
| 216 |
+
"reward_std": 0.1591769636142999,
|
| 217 |
+
"rewards/accuracy_reward": 0.48437500186264515,
|
| 218 |
+
"step": 19
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"completion_length": 465.51562881469727,
|
| 222 |
+
"epoch": 0.15920398009950248,
|
| 223 |
+
"grad_norm": 0.006370695307850838,
|
| 224 |
+
"learning_rate": 1e-06,
|
| 225 |
+
"loss": 0.0,
|
| 226 |
+
"reward": 0.5729166744276881,
|
| 227 |
+
"reward_std": 0.1838494308758527,
|
| 228 |
+
"rewards/accuracy_reward": 0.5729166744276881,
|
| 229 |
+
"step": 20
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"completion_length": 456.2621555328369,
|
| 233 |
+
"epoch": 0.16716417910447762,
|
| 234 |
+
"grad_norm": 0.006426139269024134,
|
| 235 |
+
"learning_rate": 1e-06,
|
| 236 |
+
"loss": 0.0,
|
| 237 |
+
"reward": 0.5256076417863369,
|
| 238 |
+
"reward_std": 0.17757255700416863,
|
| 239 |
+
"rewards/accuracy_reward": 0.5256076417863369,
|
| 240 |
+
"step": 21
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"completion_length": 463.6510467529297,
|
| 244 |
+
"epoch": 0.17512437810945275,
|
| 245 |
+
"grad_norm": 0.006063092965632677,
|
| 246 |
+
"learning_rate": 1e-06,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"reward": 0.46831597946584225,
|
| 249 |
+
"reward_std": 0.17084068548865616,
|
| 250 |
+
"rewards/accuracy_reward": 0.46831597946584225,
|
| 251 |
+
"step": 22
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"completion_length": 494.66666412353516,
|
| 255 |
+
"epoch": 0.18308457711442785,
|
| 256 |
+
"grad_norm": 0.0067391162738204,
|
| 257 |
+
"learning_rate": 1e-06,
|
| 258 |
+
"loss": 0.0,
|
| 259 |
+
"reward": 0.4826388955116272,
|
| 260 |
+
"reward_std": 0.23759194742888212,
|
| 261 |
+
"rewards/accuracy_reward": 0.4826388955116272,
|
| 262 |
+
"step": 23
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"completion_length": 450.75694847106934,
|
| 266 |
+
"epoch": 0.191044776119403,
|
| 267 |
+
"grad_norm": 0.0065076653845608234,
|
| 268 |
+
"learning_rate": 1e-06,
|
| 269 |
+
"loss": 0.0,
|
| 270 |
+
"reward": 0.5755208358168602,
|
| 271 |
+
"reward_std": 0.20574828935787082,
|
| 272 |
+
"rewards/accuracy_reward": 0.5755208358168602,
|
| 273 |
+
"step": 24
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"completion_length": 481.1545238494873,
|
| 277 |
+
"epoch": 0.19900497512437812,
|
| 278 |
+
"grad_norm": 0.05355783551931381,
|
| 279 |
+
"learning_rate": 1e-06,
|
| 280 |
+
"loss": 0.0,
|
| 281 |
+
"reward": 0.544704869389534,
|
| 282 |
+
"reward_std": 0.20792170939967036,
|
| 283 |
+
"rewards/accuracy_reward": 0.544704869389534,
|
| 284 |
+
"step": 25
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"completion_length": 493.2404556274414,
|
| 288 |
+
"epoch": 0.20696517412935322,
|
| 289 |
+
"grad_norm": 0.005157908424735069,
|
| 290 |
+
"learning_rate": 1e-06,
|
| 291 |
+
"loss": 0.0,
|
| 292 |
+
"reward": 0.4583333386108279,
|
| 293 |
+
"reward_std": 0.1656919487286359,
|
| 294 |
+
"rewards/accuracy_reward": 0.4583333386108279,
|
| 295 |
+
"step": 26
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"completion_length": 462.6414966583252,
|
| 299 |
+
"epoch": 0.21492537313432836,
|
| 300 |
+
"grad_norm": 0.006888694129884243,
|
| 301 |
+
"learning_rate": 1e-06,
|
| 302 |
+
"loss": 0.0,
|
| 303 |
+
"reward": 0.5611979179084301,
|
| 304 |
+
"reward_std": 0.1818527397699654,
|
| 305 |
+
"rewards/accuracy_reward": 0.5611979179084301,
|
| 306 |
+
"step": 27
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"completion_length": 465.3498344421387,
|
| 310 |
+
"epoch": 0.2228855721393035,
|
| 311 |
+
"grad_norm": 0.006233619060367346,
|
| 312 |
+
"learning_rate": 1e-06,
|
| 313 |
+
"loss": 0.0,
|
| 314 |
+
"reward": 0.5138888899236917,
|
| 315 |
+
"reward_std": 0.18008951703086495,
|
| 316 |
+
"rewards/accuracy_reward": 0.5138888899236917,
|
| 317 |
+
"step": 28
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"completion_length": 491.0295162200928,
|
| 321 |
+
"epoch": 0.2308457711442786,
|
| 322 |
+
"grad_norm": 0.006753553636372089,
|
| 323 |
+
"learning_rate": 1e-06,
|
| 324 |
+
"loss": 0.0,
|
| 325 |
+
"reward": 0.4531250037252903,
|
| 326 |
+
"reward_std": 0.1917171513196081,
|
| 327 |
+
"rewards/accuracy_reward": 0.4531250037252903,
|
| 328 |
+
"step": 29
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"completion_length": 500.3993110656738,
|
| 332 |
+
"epoch": 0.23880597014925373,
|
| 333 |
+
"grad_norm": 0.007253080140799284,
|
| 334 |
+
"learning_rate": 1e-06,
|
| 335 |
+
"loss": 0.0,
|
| 336 |
+
"reward": 0.4483507014811039,
|
| 337 |
+
"reward_std": 0.2557898717932403,
|
| 338 |
+
"rewards/accuracy_reward": 0.4483507014811039,
|
| 339 |
+
"step": 30
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"completion_length": 470.89931297302246,
|
| 343 |
+
"epoch": 0.24676616915422886,
|
| 344 |
+
"grad_norm": 0.006938918959349394,
|
| 345 |
+
"learning_rate": 1e-06,
|
| 346 |
+
"loss": 0.0,
|
| 347 |
+
"reward": 0.5329861100763083,
|
| 348 |
+
"reward_std": 0.20399011299014091,
|
| 349 |
+
"rewards/accuracy_reward": 0.5329861100763083,
|
| 350 |
+
"step": 31
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"completion_length": 509.3090305328369,
|
| 354 |
+
"epoch": 0.25472636815920396,
|
| 355 |
+
"grad_norm": 0.006779938004910946,
|
| 356 |
+
"learning_rate": 1e-06,
|
| 357 |
+
"loss": 0.0,
|
| 358 |
+
"reward": 0.5164930569007993,
|
| 359 |
+
"reward_std": 0.20839094324037433,
|
| 360 |
+
"rewards/accuracy_reward": 0.5164930569007993,
|
| 361 |
+
"step": 32
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"completion_length": 474.19010734558105,
|
| 365 |
+
"epoch": 0.2626865671641791,
|
| 366 |
+
"grad_norm": 0.018072878941893578,
|
| 367 |
+
"learning_rate": 1e-06,
|
| 368 |
+
"loss": 0.0,
|
| 369 |
+
"reward": 0.5529513955116272,
|
| 370 |
+
"reward_std": 0.23518243874423206,
|
| 371 |
+
"rewards/accuracy_reward": 0.5529513955116272,
|
| 372 |
+
"step": 33
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"completion_length": 467.2725715637207,
|
| 376 |
+
"epoch": 0.27064676616915423,
|
| 377 |
+
"grad_norm": 0.006513183005154133,
|
| 378 |
+
"learning_rate": 1e-06,
|
| 379 |
+
"loss": 0.0,
|
| 380 |
+
"reward": 0.5225694482214749,
|
| 381 |
+
"reward_std": 0.17238700040616095,
|
| 382 |
+
"rewards/accuracy_reward": 0.5225694482214749,
|
| 383 |
+
"step": 34
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"completion_length": 464.1111145019531,
|
| 387 |
+
"epoch": 0.27860696517412936,
|
| 388 |
+
"grad_norm": 0.006131773814558983,
|
| 389 |
+
"learning_rate": 1e-06,
|
| 390 |
+
"loss": 0.0,
|
| 391 |
+
"reward": 0.475260422565043,
|
| 392 |
+
"reward_std": 0.17684485344216228,
|
| 393 |
+
"rewards/accuracy_reward": 0.475260422565043,
|
| 394 |
+
"step": 35
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"completion_length": 479.2005214691162,
|
| 398 |
+
"epoch": 0.2865671641791045,
|
| 399 |
+
"grad_norm": 0.006053759716451168,
|
| 400 |
+
"learning_rate": 1e-06,
|
| 401 |
+
"loss": 0.0,
|
| 402 |
+
"reward": 0.5112847229465842,
|
| 403 |
+
"reward_std": 0.16745366132818162,
|
| 404 |
+
"rewards/accuracy_reward": 0.5112847229465842,
|
| 405 |
+
"step": 36
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"completion_length": 474.2795162200928,
|
| 409 |
+
"epoch": 0.2945273631840796,
|
| 410 |
+
"grad_norm": 0.006722339428961277,
|
| 411 |
+
"learning_rate": 1e-06,
|
| 412 |
+
"loss": 0.0,
|
| 413 |
+
"reward": 0.5043402817100286,
|
| 414 |
+
"reward_std": 0.1968160946853459,
|
| 415 |
+
"rewards/accuracy_reward": 0.5043402817100286,
|
| 416 |
+
"step": 37
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"completion_length": 494.92275047302246,
|
| 420 |
+
"epoch": 0.3024875621890547,
|
| 421 |
+
"grad_norm": 0.006237765308469534,
|
| 422 |
+
"learning_rate": 1e-06,
|
| 423 |
+
"loss": 0.0,
|
| 424 |
+
"reward": 0.4839409776031971,
|
| 425 |
+
"reward_std": 0.196247041458264,
|
| 426 |
+
"rewards/accuracy_reward": 0.4839409776031971,
|
| 427 |
+
"step": 38
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"completion_length": 467.1024341583252,
|
| 431 |
+
"epoch": 0.31044776119402984,
|
| 432 |
+
"grad_norm": 0.005437185522168875,
|
| 433 |
+
"learning_rate": 1e-06,
|
| 434 |
+
"loss": 0.0,
|
| 435 |
+
"reward": 0.4986979286186397,
|
| 436 |
+
"reward_std": 0.14949205331504345,
|
| 437 |
+
"rewards/accuracy_reward": 0.4986979286186397,
|
| 438 |
+
"step": 39
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"completion_length": 500.1310806274414,
|
| 442 |
+
"epoch": 0.31840796019900497,
|
| 443 |
+
"grad_norm": 0.006678381934762001,
|
| 444 |
+
"learning_rate": 1e-06,
|
| 445 |
+
"loss": 0.0,
|
| 446 |
+
"reward": 0.5742187593132257,
|
| 447 |
+
"reward_std": 0.2146851746365428,
|
| 448 |
+
"rewards/accuracy_reward": 0.5742187593132257,
|
| 449 |
+
"step": 40
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"completion_length": 501.9566059112549,
|
| 453 |
+
"epoch": 0.3263681592039801,
|
| 454 |
+
"grad_norm": 0.006126942578703165,
|
| 455 |
+
"learning_rate": 1e-06,
|
| 456 |
+
"loss": 0.0,
|
| 457 |
+
"reward": 0.47439236333593726,
|
| 458 |
+
"reward_std": 0.185034736758098,
|
| 459 |
+
"rewards/accuracy_reward": 0.47439236333593726,
|
| 460 |
+
"step": 41
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"completion_length": 442.15538787841797,
|
| 464 |
+
"epoch": 0.33432835820895523,
|
| 465 |
+
"grad_norm": 0.006063259672373533,
|
| 466 |
+
"learning_rate": 1e-06,
|
| 467 |
+
"loss": 0.0,
|
| 468 |
+
"reward": 0.5737847294658422,
|
| 469 |
+
"reward_std": 0.16276894812472165,
|
| 470 |
+
"rewards/accuracy_reward": 0.5737847294658422,
|
| 471 |
+
"step": 42
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"completion_length": 480.30816078186035,
|
| 475 |
+
"epoch": 0.34228855721393037,
|
| 476 |
+
"grad_norm": 0.035705793648958206,
|
| 477 |
+
"learning_rate": 1e-06,
|
| 478 |
+
"loss": 0.0,
|
| 479 |
+
"reward": 0.5386284776031971,
|
| 480 |
+
"reward_std": 0.2133699539117515,
|
| 481 |
+
"rewards/accuracy_reward": 0.5386284776031971,
|
| 482 |
+
"step": 43
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"completion_length": 477.8211860656738,
|
| 486 |
+
"epoch": 0.3502487562189055,
|
| 487 |
+
"grad_norm": 0.007010245230048895,
|
| 488 |
+
"learning_rate": 1e-06,
|
| 489 |
+
"loss": 0.0,
|
| 490 |
+
"reward": 0.4769965298473835,
|
| 491 |
+
"reward_std": 0.17710949736647308,
|
| 492 |
+
"rewards/accuracy_reward": 0.4769965298473835,
|
| 493 |
+
"step": 44
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"completion_length": 462.7925453186035,
|
| 497 |
+
"epoch": 0.3582089552238806,
|
| 498 |
+
"grad_norm": 0.007418088149279356,
|
| 499 |
+
"learning_rate": 1e-06,
|
| 500 |
+
"loss": 0.0,
|
| 501 |
+
"reward": 0.5724826455116272,
|
| 502 |
+
"reward_std": 0.2099497839808464,
|
| 503 |
+
"rewards/accuracy_reward": 0.5724826455116272,
|
| 504 |
+
"step": 45
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"completion_length": 470.4783020019531,
|
| 508 |
+
"epoch": 0.3661691542288557,
|
| 509 |
+
"grad_norm": 0.007191660813987255,
|
| 510 |
+
"learning_rate": 1e-06,
|
| 511 |
+
"loss": 0.0,
|
| 512 |
+
"reward": 0.5125868069007993,
|
| 513 |
+
"reward_std": 0.19454265222884715,
|
| 514 |
+
"rewards/accuracy_reward": 0.5125868069007993,
|
| 515 |
+
"step": 46
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"completion_length": 470.67709159851074,
|
| 519 |
+
"epoch": 0.37412935323383084,
|
| 520 |
+
"grad_norm": 0.006237688474357128,
|
| 521 |
+
"learning_rate": 1e-06,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"reward": 0.5516493115574121,
|
| 524 |
+
"reward_std": 0.1919041178189218,
|
| 525 |
+
"rewards/accuracy_reward": 0.5516493115574121,
|
| 526 |
+
"step": 47
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"completion_length": 467.4557342529297,
|
| 530 |
+
"epoch": 0.382089552238806,
|
| 531 |
+
"grad_norm": 0.005811754148453474,
|
| 532 |
+
"learning_rate": 1e-06,
|
| 533 |
+
"loss": 0.0,
|
| 534 |
+
"reward": 0.4904513917863369,
|
| 535 |
+
"reward_std": 0.1371547463349998,
|
| 536 |
+
"rewards/accuracy_reward": 0.4904513917863369,
|
| 537 |
+
"step": 48
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"completion_length": 465.5026092529297,
|
| 541 |
+
"epoch": 0.3900497512437811,
|
| 542 |
+
"grad_norm": 0.02730730175971985,
|
| 543 |
+
"learning_rate": 1e-06,
|
| 544 |
+
"loss": 0.0,
|
| 545 |
+
"reward": 0.47222222574055195,
|
| 546 |
+
"reward_std": 0.17791698593646288,
|
| 547 |
+
"rewards/accuracy_reward": 0.47222222574055195,
|
| 548 |
+
"step": 49
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"completion_length": 478.4783020019531,
|
| 552 |
+
"epoch": 0.39800995024875624,
|
| 553 |
+
"grad_norm": 0.0069628264755010605,
|
| 554 |
+
"learning_rate": 1e-06,
|
| 555 |
+
"loss": 0.0,
|
| 556 |
+
"reward": 0.46788195008412004,
|
| 557 |
+
"reward_std": 0.1892542012501508,
|
| 558 |
+
"rewards/accuracy_reward": 0.46788195008412004,
|
| 559 |
+
"step": 50
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"completion_length": 468.75087547302246,
|
| 563 |
+
"epoch": 0.4059701492537313,
|
| 564 |
+
"grad_norm": 0.008021087385714054,
|
| 565 |
+
"learning_rate": 1e-06,
|
| 566 |
+
"loss": 0.0,
|
| 567 |
+
"reward": 0.4926215335726738,
|
| 568 |
+
"reward_std": 0.22644896060228348,
|
| 569 |
+
"rewards/accuracy_reward": 0.4926215335726738,
|
| 570 |
+
"step": 51
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"completion_length": 498.5251808166504,
|
| 574 |
+
"epoch": 0.41393034825870645,
|
| 575 |
+
"grad_norm": 0.0064814710058271885,
|
| 576 |
+
"learning_rate": 1e-06,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"reward": 0.49218750232830644,
|
| 579 |
+
"reward_std": 0.17422490078024566,
|
| 580 |
+
"rewards/accuracy_reward": 0.49218750232830644,
|
| 581 |
+
"step": 52
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"completion_length": 482.2578182220459,
|
| 585 |
+
"epoch": 0.4218905472636816,
|
| 586 |
+
"grad_norm": 0.005841956939548254,
|
| 587 |
+
"learning_rate": 1e-06,
|
| 588 |
+
"loss": 0.0,
|
| 589 |
+
"reward": 0.4978298582136631,
|
| 590 |
+
"reward_std": 0.1794568970799446,
|
| 591 |
+
"rewards/accuracy_reward": 0.4978298582136631,
|
| 592 |
+
"step": 53
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"completion_length": 470.75,
|
| 596 |
+
"epoch": 0.4298507462686567,
|
| 597 |
+
"grad_norm": 0.006833434570580721,
|
| 598 |
+
"learning_rate": 1e-06,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"reward": 0.5460069440305233,
|
| 601 |
+
"reward_std": 0.17903496301732957,
|
| 602 |
+
"rewards/accuracy_reward": 0.5460069440305233,
|
| 603 |
+
"step": 54
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"completion_length": 468.85677337646484,
|
| 607 |
+
"epoch": 0.43781094527363185,
|
| 608 |
+
"grad_norm": 0.05871806666254997,
|
| 609 |
+
"learning_rate": 1e-06,
|
| 610 |
+
"loss": 0.0,
|
| 611 |
+
"reward": 0.5507812574505806,
|
| 612 |
+
"reward_std": 0.17186261457391083,
|
| 613 |
+
"rewards/accuracy_reward": 0.5507812574505806,
|
| 614 |
+
"step": 55
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"completion_length": 446.83854484558105,
|
| 618 |
+
"epoch": 0.445771144278607,
|
| 619 |
+
"grad_norm": 0.006716958247125149,
|
| 620 |
+
"learning_rate": 1e-06,
|
| 621 |
+
"loss": 0.0,
|
| 622 |
+
"reward": 0.5321180680766702,
|
| 623 |
+
"reward_std": 0.1578453336842358,
|
| 624 |
+
"rewards/accuracy_reward": 0.5321180680766702,
|
| 625 |
+
"step": 56
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"completion_length": 449.37153244018555,
|
| 629 |
+
"epoch": 0.4537313432835821,
|
| 630 |
+
"grad_norm": 0.006345037836581469,
|
| 631 |
+
"learning_rate": 1e-06,
|
| 632 |
+
"loss": 0.0,
|
| 633 |
+
"reward": 0.547309035435319,
|
| 634 |
+
"reward_std": 0.1532673817127943,
|
| 635 |
+
"rewards/accuracy_reward": 0.547309035435319,
|
| 636 |
+
"step": 57
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"completion_length": 466.7022590637207,
|
| 640 |
+
"epoch": 0.4616915422885572,
|
| 641 |
+
"grad_norm": 0.010852845385670662,
|
| 642 |
+
"learning_rate": 1e-06,
|
| 643 |
+
"loss": 0.0,
|
| 644 |
+
"reward": 0.5611979253590107,
|
| 645 |
+
"reward_std": 0.1392110399901867,
|
| 646 |
+
"rewards/accuracy_reward": 0.5611979253590107,
|
| 647 |
+
"step": 58
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"completion_length": 474.2534770965576,
|
| 651 |
+
"epoch": 0.4696517412935323,
|
| 652 |
+
"grad_norm": 0.006359429098665714,
|
| 653 |
+
"learning_rate": 1e-06,
|
| 654 |
+
"loss": 0.0,
|
| 655 |
+
"reward": 0.476562503259629,
|
| 656 |
+
"reward_std": 0.17301563546061516,
|
| 657 |
+
"rewards/accuracy_reward": 0.476562503259629,
|
| 658 |
+
"step": 59
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"completion_length": 451.5312557220459,
|
| 662 |
+
"epoch": 0.47761194029850745,
|
| 663 |
+
"grad_norm": 0.007138302084058523,
|
| 664 |
+
"learning_rate": 1e-06,
|
| 665 |
+
"loss": 0.0,
|
| 666 |
+
"reward": 0.45269097946584225,
|
| 667 |
+
"reward_std": 0.19592578150331974,
|
| 668 |
+
"rewards/accuracy_reward": 0.45269097946584225,
|
| 669 |
+
"step": 60
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"completion_length": 474.8932342529297,
|
| 673 |
+
"epoch": 0.4855721393034826,
|
| 674 |
+
"grad_norm": 0.006120054051280022,
|
| 675 |
+
"learning_rate": 1e-06,
|
| 676 |
+
"loss": 0.0,
|
| 677 |
+
"reward": 0.4661458348855376,
|
| 678 |
+
"reward_std": 0.1684757302282378,
|
| 679 |
+
"rewards/accuracy_reward": 0.4661458348855376,
|
| 680 |
+
"step": 61
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"completion_length": 469.56510734558105,
|
| 684 |
+
"epoch": 0.4935323383084577,
|
| 685 |
+
"grad_norm": 0.006903901230543852,
|
| 686 |
+
"learning_rate": 1e-06,
|
| 687 |
+
"loss": 0.0,
|
| 688 |
+
"reward": 0.5125868087634444,
|
| 689 |
+
"reward_std": 0.20010435581207275,
|
| 690 |
+
"rewards/accuracy_reward": 0.5125868087634444,
|
| 691 |
+
"step": 62
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"completion_length": 453.6145877838135,
|
| 695 |
+
"epoch": 0.5014925373134328,
|
| 696 |
+
"grad_norm": 0.0065674264915287495,
|
| 697 |
+
"learning_rate": 1e-06,
|
| 698 |
+
"loss": 0.0,
|
| 699 |
+
"reward": 0.5347222294658422,
|
| 700 |
+
"reward_std": 0.14352841977961361,
|
| 701 |
+
"rewards/accuracy_reward": 0.5347222294658422,
|
| 702 |
+
"step": 63
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"completion_length": 452.13455390930176,
|
| 706 |
+
"epoch": 0.5094527363184079,
|
| 707 |
+
"grad_norm": 0.006244272459298372,
|
| 708 |
+
"learning_rate": 1e-06,
|
| 709 |
+
"loss": 0.0,
|
| 710 |
+
"reward": 0.5711805606260896,
|
| 711 |
+
"reward_std": 0.18628281145356596,
|
| 712 |
+
"rewards/accuracy_reward": 0.5711805606260896,
|
| 713 |
+
"step": 64
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"completion_length": 453.6111125946045,
|
| 717 |
+
"epoch": 0.5174129353233831,
|
| 718 |
+
"grad_norm": 0.005630127154290676,
|
| 719 |
+
"learning_rate": 1e-06,
|
| 720 |
+
"loss": 0.0,
|
| 721 |
+
"reward": 0.5633680566679686,
|
| 722 |
+
"reward_std": 0.13176781288348138,
|
| 723 |
+
"rewards/accuracy_reward": 0.5633680566679686,
|
| 724 |
+
"step": 65
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"completion_length": 454.0685787200928,
|
| 728 |
+
"epoch": 0.5253731343283582,
|
| 729 |
+
"grad_norm": 0.006047699134796858,
|
| 730 |
+
"learning_rate": 1e-06,
|
| 731 |
+
"loss": 0.0,
|
| 732 |
+
"reward": 0.5169270820915699,
|
| 733 |
+
"reward_std": 0.17424573958851397,
|
| 734 |
+
"rewards/accuracy_reward": 0.5169270820915699,
|
| 735 |
+
"step": 66
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"completion_length": 467.2552089691162,
|
| 739 |
+
"epoch": 0.5333333333333333,
|
| 740 |
+
"grad_norm": 0.005964316893368959,
|
| 741 |
+
"learning_rate": 1e-06,
|
| 742 |
+
"loss": 0.0,
|
| 743 |
+
"reward": 0.5078125037252903,
|
| 744 |
+
"reward_std": 0.1600186654832214,
|
| 745 |
+
"rewards/accuracy_reward": 0.5078125037252903,
|
| 746 |
+
"step": 67
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"completion_length": 475.27604484558105,
|
| 750 |
+
"epoch": 0.5412935323383085,
|
| 751 |
+
"grad_norm": 0.007332879584282637,
|
| 752 |
+
"learning_rate": 1e-06,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"reward": 0.5798611175268888,
|
| 755 |
+
"reward_std": 0.21456625079736114,
|
| 756 |
+
"rewards/accuracy_reward": 0.5798611175268888,
|
| 757 |
+
"step": 68
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"completion_length": 457.26041984558105,
|
| 761 |
+
"epoch": 0.5492537313432836,
|
| 762 |
+
"grad_norm": 0.006759831681847572,
|
| 763 |
+
"learning_rate": 1e-06,
|
| 764 |
+
"loss": 0.0,
|
| 765 |
+
"reward": 0.48784722620621324,
|
| 766 |
+
"reward_std": 0.17781772650778294,
|
| 767 |
+
"rewards/accuracy_reward": 0.48784722620621324,
|
| 768 |
+
"step": 69
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"completion_length": 449.7126770019531,
|
| 772 |
+
"epoch": 0.5572139303482587,
|
| 773 |
+
"grad_norm": 0.006766649428755045,
|
| 774 |
+
"learning_rate": 1e-06,
|
| 775 |
+
"loss": 0.0,
|
| 776 |
+
"reward": 0.4978298647329211,
|
| 777 |
+
"reward_std": 0.1652932451106608,
|
| 778 |
+
"rewards/accuracy_reward": 0.4978298647329211,
|
| 779 |
+
"step": 70
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"completion_length": 487.57726097106934,
|
| 783 |
+
"epoch": 0.5651741293532339,
|
| 784 |
+
"grad_norm": 0.007064457051455975,
|
| 785 |
+
"learning_rate": 1e-06,
|
| 786 |
+
"loss": 0.0,
|
| 787 |
+
"reward": 0.4340277826413512,
|
| 788 |
+
"reward_std": 0.15119286242406815,
|
| 789 |
+
"rewards/accuracy_reward": 0.4340277826413512,
|
| 790 |
+
"step": 71
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"completion_length": 425.9496593475342,
|
| 794 |
+
"epoch": 0.573134328358209,
|
| 795 |
+
"grad_norm": 0.007826046086847782,
|
| 796 |
+
"learning_rate": 1e-06,
|
| 797 |
+
"loss": 0.0,
|
| 798 |
+
"reward": 0.5941840391606092,
|
| 799 |
+
"reward_std": 0.1813936980906874,
|
| 800 |
+
"rewards/accuracy_reward": 0.5941840391606092,
|
| 801 |
+
"step": 72
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"completion_length": 469.32900047302246,
|
| 805 |
+
"epoch": 0.5810945273631841,
|
| 806 |
+
"grad_norm": 0.0057061235420405865,
|
| 807 |
+
"learning_rate": 1e-06,
|
| 808 |
+
"loss": 0.0,
|
| 809 |
+
"reward": 0.5503472303971648,
|
| 810 |
+
"reward_std": 0.1599263979587704,
|
| 811 |
+
"rewards/accuracy_reward": 0.5503472303971648,
|
| 812 |
+
"step": 73
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"completion_length": 420.5616340637207,
|
| 816 |
+
"epoch": 0.5890547263681593,
|
| 817 |
+
"grad_norm": 0.0060322158969938755,
|
| 818 |
+
"learning_rate": 1e-06,
|
| 819 |
+
"loss": 0.0,
|
| 820 |
+
"reward": 0.6349826510995626,
|
| 821 |
+
"reward_std": 0.14059699326753616,
|
| 822 |
+
"rewards/accuracy_reward": 0.6349826510995626,
|
| 823 |
+
"step": 74
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"completion_length": 433.3845520019531,
|
| 827 |
+
"epoch": 0.5970149253731343,
|
| 828 |
+
"grad_norm": 0.00608411431312561,
|
| 829 |
+
"learning_rate": 1e-06,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"reward": 0.5863715335726738,
|
| 832 |
+
"reward_std": 0.1365173237863928,
|
| 833 |
+
"rewards/accuracy_reward": 0.5863715335726738,
|
| 834 |
+
"step": 75
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"completion_length": 438.9913215637207,
|
| 838 |
+
"epoch": 0.6049751243781094,
|
| 839 |
+
"grad_norm": 0.010838707908987999,
|
| 840 |
+
"learning_rate": 1e-06,
|
| 841 |
+
"loss": 0.0,
|
| 842 |
+
"reward": 0.4947916679084301,
|
| 843 |
+
"reward_std": 0.16913633281365037,
|
| 844 |
+
"rewards/accuracy_reward": 0.4947916679084301,
|
| 845 |
+
"step": 76
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"completion_length": 436.12413787841797,
|
| 849 |
+
"epoch": 0.6129353233830845,
|
| 850 |
+
"grad_norm": 0.0062843686901032925,
|
| 851 |
+
"learning_rate": 1e-06,
|
| 852 |
+
"loss": 0.0,
|
| 853 |
+
"reward": 0.5416666697710752,
|
| 854 |
+
"reward_std": 0.13451572181656957,
|
| 855 |
+
"rewards/accuracy_reward": 0.5416666697710752,
|
| 856 |
+
"step": 77
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"completion_length": 434.7196216583252,
|
| 860 |
+
"epoch": 0.6208955223880597,
|
| 861 |
+
"grad_norm": 0.007163195870816708,
|
| 862 |
+
"learning_rate": 1e-06,
|
| 863 |
+
"loss": 0.0,
|
| 864 |
+
"reward": 0.5685763917863369,
|
| 865 |
+
"reward_std": 0.16896466561593115,
|
| 866 |
+
"rewards/accuracy_reward": 0.5685763917863369,
|
| 867 |
+
"step": 78
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"completion_length": 425.51388931274414,
|
| 871 |
+
"epoch": 0.6288557213930348,
|
| 872 |
+
"grad_norm": 0.007178325206041336,
|
| 873 |
+
"learning_rate": 1e-06,
|
| 874 |
+
"loss": 0.0,
|
| 875 |
+
"reward": 0.5069444458931684,
|
| 876 |
+
"reward_std": 0.17618598695844412,
|
| 877 |
+
"rewards/accuracy_reward": 0.5069444458931684,
|
| 878 |
+
"step": 79
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"completion_length": 447.2517433166504,
|
| 882 |
+
"epoch": 0.6368159203980099,
|
| 883 |
+
"grad_norm": 0.00694573950022459,
|
| 884 |
+
"learning_rate": 1e-06,
|
| 885 |
+
"loss": 0.0,
|
| 886 |
+
"reward": 0.5230034776031971,
|
| 887 |
+
"reward_std": 0.1816186774522066,
|
| 888 |
+
"rewards/accuracy_reward": 0.5230034776031971,
|
| 889 |
+
"step": 80
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"completion_length": 440.2196235656738,
|
| 893 |
+
"epoch": 0.6447761194029851,
|
| 894 |
+
"grad_norm": 0.0065235113725066185,
|
| 895 |
+
"learning_rate": 1e-06,
|
| 896 |
+
"loss": 0.0,
|
| 897 |
+
"reward": 0.596354179084301,
|
| 898 |
+
"reward_std": 0.1535110066179186,
|
| 899 |
+
"rewards/accuracy_reward": 0.596354179084301,
|
| 900 |
+
"step": 81
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"completion_length": 444.88368797302246,
|
| 904 |
+
"epoch": 0.6527363184079602,
|
| 905 |
+
"grad_norm": 0.006391232833266258,
|
| 906 |
+
"learning_rate": 1e-06,
|
| 907 |
+
"loss": 0.0,
|
| 908 |
+
"reward": 0.5659722285345197,
|
| 909 |
+
"reward_std": 0.15076033398509026,
|
| 910 |
+
"rewards/accuracy_reward": 0.5659722285345197,
|
| 911 |
+
"step": 82
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"completion_length": 455.1119842529297,
|
| 915 |
+
"epoch": 0.6606965174129353,
|
| 916 |
+
"grad_norm": 0.005797598976641893,
|
| 917 |
+
"learning_rate": 1e-06,
|
| 918 |
+
"loss": 0.0,
|
| 919 |
+
"reward": 0.5381944524124265,
|
| 920 |
+
"reward_std": 0.14913518843241036,
|
| 921 |
+
"rewards/accuracy_reward": 0.5381944524124265,
|
| 922 |
+
"step": 83
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"completion_length": 454.94879150390625,
|
| 926 |
+
"epoch": 0.6686567164179105,
|
| 927 |
+
"grad_norm": 0.006953164003789425,
|
| 928 |
+
"learning_rate": 1e-06,
|
| 929 |
+
"loss": 0.0,
|
| 930 |
+
"reward": 0.5164930578321218,
|
| 931 |
+
"reward_std": 0.16644407669082284,
|
| 932 |
+
"rewards/accuracy_reward": 0.5164930578321218,
|
| 933 |
+
"step": 84
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"completion_length": 454.31945037841797,
|
| 937 |
+
"epoch": 0.6766169154228856,
|
| 938 |
+
"grad_norm": 0.006526515819132328,
|
| 939 |
+
"learning_rate": 1e-06,
|
| 940 |
+
"loss": 0.0,
|
| 941 |
+
"reward": 0.5381944517139345,
|
| 942 |
+
"reward_std": 0.17874250491149724,
|
| 943 |
+
"rewards/accuracy_reward": 0.5381944517139345,
|
| 944 |
+
"step": 85
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"completion_length": 413.63195037841797,
|
| 948 |
+
"epoch": 0.6845771144278607,
|
| 949 |
+
"grad_norm": 0.006882105953991413,
|
| 950 |
+
"learning_rate": 1e-06,
|
| 951 |
+
"loss": 0.0,
|
| 952 |
+
"reward": 0.4709201497025788,
|
| 953 |
+
"reward_std": 0.15343356225639582,
|
| 954 |
+
"rewards/accuracy_reward": 0.4709201497025788,
|
| 955 |
+
"step": 86
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"completion_length": 477.28386306762695,
|
| 959 |
+
"epoch": 0.6925373134328359,
|
| 960 |
+
"grad_norm": 0.007171040400862694,
|
| 961 |
+
"learning_rate": 1e-06,
|
| 962 |
+
"loss": 0.0,
|
| 963 |
+
"reward": 0.4626736184582114,
|
| 964 |
+
"reward_std": 0.17724345158785582,
|
| 965 |
+
"rewards/accuracy_reward": 0.4626736184582114,
|
| 966 |
+
"step": 87
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"completion_length": 440.93230056762695,
|
| 970 |
+
"epoch": 0.700497512437811,
|
| 971 |
+
"grad_norm": 0.012264563702046871,
|
| 972 |
+
"learning_rate": 1e-06,
|
| 973 |
+
"loss": 0.0,
|
| 974 |
+
"reward": 0.539930559694767,
|
| 975 |
+
"reward_std": 0.2249910207465291,
|
| 976 |
+
"rewards/accuracy_reward": 0.539930559694767,
|
| 977 |
+
"step": 88
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"completion_length": 446.6111183166504,
|
| 981 |
+
"epoch": 0.708457711442786,
|
| 982 |
+
"grad_norm": 0.007123625837266445,
|
| 983 |
+
"learning_rate": 1e-06,
|
| 984 |
+
"loss": 0.0,
|
| 985 |
+
"reward": 0.5677083414047956,
|
| 986 |
+
"reward_std": 0.14550525438971817,
|
| 987 |
+
"rewards/accuracy_reward": 0.5677083414047956,
|
| 988 |
+
"step": 89
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"completion_length": 443.06945419311523,
|
| 992 |
+
"epoch": 0.7164179104477612,
|
| 993 |
+
"grad_norm": 0.006765348371118307,
|
| 994 |
+
"learning_rate": 1e-06,
|
| 995 |
+
"loss": 0.0,
|
| 996 |
+
"reward": 0.5434027817100286,
|
| 997 |
+
"reward_std": 0.14721272652968764,
|
| 998 |
+
"rewards/accuracy_reward": 0.5434027817100286,
|
| 999 |
+
"step": 90
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"completion_length": 438.7204875946045,
|
| 1003 |
+
"epoch": 0.7243781094527363,
|
| 1004 |
+
"grad_norm": 0.007179305423051119,
|
| 1005 |
+
"learning_rate": 1e-06,
|
| 1006 |
+
"loss": 0.0,
|
| 1007 |
+
"reward": 0.5785590391606092,
|
| 1008 |
+
"reward_std": 0.1922429515980184,
|
| 1009 |
+
"rewards/accuracy_reward": 0.5785590391606092,
|
| 1010 |
+
"step": 91
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"completion_length": 435.45659828186035,
|
| 1014 |
+
"epoch": 0.7323383084577114,
|
| 1015 |
+
"grad_norm": 0.03627901151776314,
|
| 1016 |
+
"learning_rate": 1e-06,
|
| 1017 |
+
"loss": 0.0,
|
| 1018 |
+
"reward": 0.5690104262903333,
|
| 1019 |
+
"reward_std": 0.20257419790141284,
|
| 1020 |
+
"rewards/accuracy_reward": 0.5690104262903333,
|
| 1021 |
+
"step": 92
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"completion_length": 450.00347328186035,
|
| 1025 |
+
"epoch": 0.7402985074626866,
|
| 1026 |
+
"grad_norm": 0.0072410209104418755,
|
| 1027 |
+
"learning_rate": 1e-06,
|
| 1028 |
+
"loss": 0.0,
|
| 1029 |
+
"reward": 0.45876736706122756,
|
| 1030 |
+
"reward_std": 0.1358756278641522,
|
| 1031 |
+
"rewards/accuracy_reward": 0.45876736706122756,
|
| 1032 |
+
"step": 93
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"completion_length": 445.3550338745117,
|
| 1036 |
+
"epoch": 0.7482587064676617,
|
| 1037 |
+
"grad_norm": 0.006944851018488407,
|
| 1038 |
+
"learning_rate": 1e-06,
|
| 1039 |
+
"loss": 0.0,
|
| 1040 |
+
"reward": 0.5486111212521791,
|
| 1041 |
+
"reward_std": 0.14192489348351955,
|
| 1042 |
+
"rewards/accuracy_reward": 0.5486111212521791,
|
| 1043 |
+
"step": 94
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"completion_length": 411.4861125946045,
|
| 1047 |
+
"epoch": 0.7562189054726368,
|
| 1048 |
+
"grad_norm": 0.007500652689486742,
|
| 1049 |
+
"learning_rate": 1e-06,
|
| 1050 |
+
"loss": 0.0,
|
| 1051 |
+
"reward": 0.5546875,
|
| 1052 |
+
"reward_std": 0.16345718037337065,
|
| 1053 |
+
"rewards/accuracy_reward": 0.5546875,
|
| 1054 |
+
"step": 95
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"completion_length": 434.6458377838135,
|
| 1058 |
+
"epoch": 0.764179104477612,
|
| 1059 |
+
"grad_norm": 0.008221461437642574,
|
| 1060 |
+
"learning_rate": 1e-06,
|
| 1061 |
+
"loss": 0.0,
|
| 1062 |
+
"reward": 0.5169270858168602,
|
| 1063 |
+
"reward_std": 0.157486256910488,
|
| 1064 |
+
"rewards/accuracy_reward": 0.5169270858168602,
|
| 1065 |
+
"step": 96
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"completion_length": 459.9088592529297,
|
| 1069 |
+
"epoch": 0.7721393034825871,
|
| 1070 |
+
"grad_norm": 0.008421896025538445,
|
| 1071 |
+
"learning_rate": 1e-06,
|
| 1072 |
+
"loss": 0.0,
|
| 1073 |
+
"reward": 0.4192708367481828,
|
| 1074 |
+
"reward_std": 0.16910302848555148,
|
| 1075 |
+
"rewards/accuracy_reward": 0.4192708367481828,
|
| 1076 |
+
"step": 97
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"completion_length": 441.1692752838135,
|
| 1080 |
+
"epoch": 0.7800995024875622,
|
| 1081 |
+
"grad_norm": 0.00576035724952817,
|
| 1082 |
+
"learning_rate": 1e-06,
|
| 1083 |
+
"loss": 0.0,
|
| 1084 |
+
"reward": 0.5894097305135801,
|
| 1085 |
+
"reward_std": 0.09535378613509238,
|
| 1086 |
+
"rewards/accuracy_reward": 0.5894097305135801,
|
| 1087 |
+
"step": 98
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"completion_length": 423.37239837646484,
|
| 1091 |
+
"epoch": 0.7880597014925373,
|
| 1092 |
+
"grad_norm": 0.007169231306761503,
|
| 1093 |
+
"learning_rate": 1e-06,
|
| 1094 |
+
"loss": 0.0,
|
| 1095 |
+
"reward": 0.5520833367481828,
|
| 1096 |
+
"reward_std": 0.17009410122409463,
|
| 1097 |
+
"rewards/accuracy_reward": 0.5520833367481828,
|
| 1098 |
+
"step": 99
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"completion_length": 447.38107681274414,
|
| 1102 |
+
"epoch": 0.7960199004975125,
|
| 1103 |
+
"grad_norm": 0.006430391687899828,
|
| 1104 |
+
"learning_rate": 1e-06,
|
| 1105 |
+
"loss": 0.0,
|
| 1106 |
+
"reward": 0.478298619389534,
|
| 1107 |
+
"reward_std": 0.1553269592113793,
|
| 1108 |
+
"rewards/accuracy_reward": 0.478298619389534,
|
| 1109 |
+
"step": 100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"completion_length": 434.5590305328369,
|
| 1113 |
+
"epoch": 0.8039800995024876,
|
| 1114 |
+
"grad_norm": 0.006948183756321669,
|
| 1115 |
+
"learning_rate": 1e-06,
|
| 1116 |
+
"loss": 0.0,
|
| 1117 |
+
"reward": 0.6111111119389534,
|
| 1118 |
+
"reward_std": 0.16623280476778746,
|
| 1119 |
+
"rewards/accuracy_reward": 0.6111111119389534,
|
| 1120 |
+
"step": 101
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"completion_length": 438.5807304382324,
|
| 1124 |
+
"epoch": 0.8119402985074626,
|
| 1125 |
+
"grad_norm": 0.00873401015996933,
|
| 1126 |
+
"learning_rate": 1e-06,
|
| 1127 |
+
"loss": 0.0,
|
| 1128 |
+
"reward": 0.554253475740552,
|
| 1129 |
+
"reward_std": 0.12938219658099115,
|
| 1130 |
+
"rewards/accuracy_reward": 0.554253475740552,
|
| 1131 |
+
"step": 102
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"completion_length": 440.63368225097656,
|
| 1135 |
+
"epoch": 0.8199004975124378,
|
| 1136 |
+
"grad_norm": 0.008209417574107647,
|
| 1137 |
+
"learning_rate": 1e-06,
|
| 1138 |
+
"loss": 0.0,
|
| 1139 |
+
"reward": 0.5355902817100286,
|
| 1140 |
+
"reward_std": 0.15484802844002843,
|
| 1141 |
+
"rewards/accuracy_reward": 0.5355902817100286,
|
| 1142 |
+
"step": 103
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"completion_length": 430.292537689209,
|
| 1146 |
+
"epoch": 0.8278606965174129,
|
| 1147 |
+
"grad_norm": 0.006974893156439066,
|
| 1148 |
+
"learning_rate": 1e-06,
|
| 1149 |
+
"loss": 0.0,
|
| 1150 |
+
"reward": 0.5351562616415322,
|
| 1151 |
+
"reward_std": 0.15955675020813942,
|
| 1152 |
+
"rewards/accuracy_reward": 0.5351562616415322,
|
| 1153 |
+
"step": 104
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"completion_length": 437.16406631469727,
|
| 1157 |
+
"epoch": 0.835820895522388,
|
| 1158 |
+
"grad_norm": 0.006820361595600843,
|
| 1159 |
+
"learning_rate": 1e-06,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"reward": 0.5325520914047956,
|
| 1162 |
+
"reward_std": 0.13739590148907155,
|
| 1163 |
+
"rewards/accuracy_reward": 0.5325520914047956,
|
| 1164 |
+
"step": 105
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"completion_length": 440.88281440734863,
|
| 1168 |
+
"epoch": 0.8437810945273632,
|
| 1169 |
+
"grad_norm": 0.007815063931047916,
|
| 1170 |
+
"learning_rate": 1e-06,
|
| 1171 |
+
"loss": 0.0,
|
| 1172 |
+
"reward": 0.5546875055879354,
|
| 1173 |
+
"reward_std": 0.16753076948225498,
|
| 1174 |
+
"rewards/accuracy_reward": 0.5546875055879354,
|
| 1175 |
+
"step": 106
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"completion_length": 440.1380310058594,
|
| 1179 |
+
"epoch": 0.8517412935323383,
|
| 1180 |
+
"grad_norm": 0.006534726824611425,
|
| 1181 |
+
"learning_rate": 1e-06,
|
| 1182 |
+
"loss": 0.0,
|
| 1183 |
+
"reward": 0.5225694496184587,
|
| 1184 |
+
"reward_std": 0.14320432161912322,
|
| 1185 |
+
"rewards/accuracy_reward": 0.5225694496184587,
|
| 1186 |
+
"step": 107
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"completion_length": 438.36284828186035,
|
| 1190 |
+
"epoch": 0.8597014925373134,
|
| 1191 |
+
"grad_norm": 0.008502320386469364,
|
| 1192 |
+
"learning_rate": 1e-06,
|
| 1193 |
+
"loss": 0.0,
|
| 1194 |
+
"reward": 0.5377604169771075,
|
| 1195 |
+
"reward_std": 0.16942514828406274,
|
| 1196 |
+
"rewards/accuracy_reward": 0.5377604169771075,
|
| 1197 |
+
"step": 108
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"completion_length": 433.4192771911621,
|
| 1201 |
+
"epoch": 0.8676616915422886,
|
| 1202 |
+
"grad_norm": 0.007831891067326069,
|
| 1203 |
+
"learning_rate": 1e-06,
|
| 1204 |
+
"loss": 0.0,
|
| 1205 |
+
"reward": 0.5112847285345197,
|
| 1206 |
+
"reward_std": 0.1527788401581347,
|
| 1207 |
+
"rewards/accuracy_reward": 0.5112847285345197,
|
| 1208 |
+
"step": 109
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"completion_length": 432.8906307220459,
|
| 1212 |
+
"epoch": 0.8756218905472637,
|
| 1213 |
+
"grad_norm": 0.007177690044045448,
|
| 1214 |
+
"learning_rate": 1e-06,
|
| 1215 |
+
"loss": 0.0,
|
| 1216 |
+
"reward": 0.5451388992369175,
|
| 1217 |
+
"reward_std": 0.1557791151572019,
|
| 1218 |
+
"rewards/accuracy_reward": 0.5451388992369175,
|
| 1219 |
+
"step": 110
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"completion_length": 444.034725189209,
|
| 1223 |
+
"epoch": 0.8835820895522388,
|
| 1224 |
+
"grad_norm": 0.007437328342348337,
|
| 1225 |
+
"learning_rate": 1e-06,
|
| 1226 |
+
"loss": 0.0,
|
| 1227 |
+
"reward": 0.5230034766718745,
|
| 1228 |
+
"reward_std": 0.16494862362742424,
|
| 1229 |
+
"rewards/accuracy_reward": 0.5230034766718745,
|
| 1230 |
+
"step": 111
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"completion_length": 431.6883716583252,
|
| 1234 |
+
"epoch": 0.891542288557214,
|
| 1235 |
+
"grad_norm": 0.007314461283385754,
|
| 1236 |
+
"learning_rate": 1e-06,
|
| 1237 |
+
"loss": 0.0,
|
| 1238 |
+
"reward": 0.5512152872979641,
|
| 1239 |
+
"reward_std": 0.15400438173674047,
|
| 1240 |
+
"rewards/accuracy_reward": 0.5512152872979641,
|
| 1241 |
+
"step": 112
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"completion_length": 417.52257347106934,
|
| 1245 |
+
"epoch": 0.8995024875621891,
|
| 1246 |
+
"grad_norm": 0.006493464577943087,
|
| 1247 |
+
"learning_rate": 1e-06,
|
| 1248 |
+
"loss": 0.0,
|
| 1249 |
+
"reward": 0.5915798712521791,
|
| 1250 |
+
"reward_std": 0.10944067395757884,
|
| 1251 |
+
"rewards/accuracy_reward": 0.5915798712521791,
|
| 1252 |
+
"step": 113
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"completion_length": 428.136287689209,
|
| 1256 |
+
"epoch": 0.9074626865671642,
|
| 1257 |
+
"grad_norm": 0.00739770894870162,
|
| 1258 |
+
"learning_rate": 1e-06,
|
| 1259 |
+
"loss": 0.0,
|
| 1260 |
+
"reward": 0.5920138908550143,
|
| 1261 |
+
"reward_std": 0.14007845730520785,
|
| 1262 |
+
"rewards/accuracy_reward": 0.5920138908550143,
|
| 1263 |
+
"step": 114
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"completion_length": 411.75086975097656,
|
| 1267 |
+
"epoch": 0.9154228855721394,
|
| 1268 |
+
"grad_norm": 0.012020394206047058,
|
| 1269 |
+
"learning_rate": 1e-06,
|
| 1270 |
+
"loss": 0.0,
|
| 1271 |
+
"reward": 0.5802951483055949,
|
| 1272 |
+
"reward_std": 0.1439069788902998,
|
| 1273 |
+
"rewards/accuracy_reward": 0.5802951483055949,
|
| 1274 |
+
"step": 115
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"completion_length": 440.9071216583252,
|
| 1278 |
+
"epoch": 0.9233830845771144,
|
| 1279 |
+
"grad_norm": 0.008760242722928524,
|
| 1280 |
+
"learning_rate": 1e-06,
|
| 1281 |
+
"loss": 0.0,
|
| 1282 |
+
"reward": 0.5147569524124265,
|
| 1283 |
+
"reward_std": 0.18262152979150414,
|
| 1284 |
+
"rewards/accuracy_reward": 0.5147569524124265,
|
| 1285 |
+
"step": 116
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"completion_length": 426.1597270965576,
|
| 1289 |
+
"epoch": 0.9313432835820895,
|
| 1290 |
+
"grad_norm": 0.008847164921462536,
|
| 1291 |
+
"learning_rate": 1e-06,
|
| 1292 |
+
"loss": 0.0,
|
| 1293 |
+
"reward": 0.5130208432674408,
|
| 1294 |
+
"reward_std": 0.14971066592261195,
|
| 1295 |
+
"rewards/accuracy_reward": 0.5130208432674408,
|
| 1296 |
+
"step": 117
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"completion_length": 403.698787689209,
|
| 1300 |
+
"epoch": 0.9393034825870646,
|
| 1301 |
+
"grad_norm": 0.00826039258390665,
|
| 1302 |
+
"learning_rate": 1e-06,
|
| 1303 |
+
"loss": 0.0,
|
| 1304 |
+
"reward": 0.5503472248092294,
|
| 1305 |
+
"reward_std": 0.13589490437880158,
|
| 1306 |
+
"rewards/accuracy_reward": 0.5503472248092294,
|
| 1307 |
+
"step": 118
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"completion_length": 430.99479484558105,
|
| 1311 |
+
"epoch": 0.9472636815920398,
|
| 1312 |
+
"grad_norm": 0.0083442572504282,
|
| 1313 |
+
"learning_rate": 1e-06,
|
| 1314 |
+
"loss": 0.0,
|
| 1315 |
+
"reward": 0.4691840326413512,
|
| 1316 |
+
"reward_std": 0.12581401481293142,
|
| 1317 |
+
"rewards/accuracy_reward": 0.4691840326413512,
|
| 1318 |
+
"step": 119
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"completion_length": 428.2230930328369,
|
| 1322 |
+
"epoch": 0.9552238805970149,
|
| 1323 |
+
"grad_norm": 0.00736872386187315,
|
| 1324 |
+
"learning_rate": 1e-06,
|
| 1325 |
+
"loss": 0.0,
|
| 1326 |
+
"reward": 0.5703124995925464,
|
| 1327 |
+
"reward_std": 0.13862833217717707,
|
| 1328 |
+
"rewards/accuracy_reward": 0.5703124995925464,
|
| 1329 |
+
"step": 120
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"completion_length": 456.17274475097656,
|
| 1333 |
+
"epoch": 0.96318407960199,
|
| 1334 |
+
"grad_norm": 0.007083515170961618,
|
| 1335 |
+
"learning_rate": 1e-06,
|
| 1336 |
+
"loss": 0.0,
|
| 1337 |
+
"reward": 0.5169270895421505,
|
| 1338 |
+
"reward_std": 0.1359748471295461,
|
| 1339 |
+
"rewards/accuracy_reward": 0.5169270895421505,
|
| 1340 |
+
"step": 121
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"completion_length": 437.1475715637207,
|
| 1344 |
+
"epoch": 0.9711442786069652,
|
| 1345 |
+
"grad_norm": 0.012382179498672485,
|
| 1346 |
+
"learning_rate": 1e-06,
|
| 1347 |
+
"loss": 0.0,
|
| 1348 |
+
"reward": 0.5082465298473835,
|
| 1349 |
+
"reward_std": 0.14862926630303264,
|
| 1350 |
+
"rewards/accuracy_reward": 0.5082465298473835,
|
| 1351 |
+
"step": 122
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"completion_length": 423.105037689209,
|
| 1355 |
+
"epoch": 0.9791044776119403,
|
| 1356 |
+
"grad_norm": 0.0077844285406172276,
|
| 1357 |
+
"learning_rate": 1e-06,
|
| 1358 |
+
"loss": 0.0,
|
| 1359 |
+
"reward": 0.514322922565043,
|
| 1360 |
+
"reward_std": 0.14436206291429698,
|
| 1361 |
+
"rewards/accuracy_reward": 0.514322922565043,
|
| 1362 |
+
"step": 123
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"completion_length": 408.1849002838135,
|
| 1366 |
+
"epoch": 0.9870646766169154,
|
| 1367 |
+
"grad_norm": 0.008202475495636463,
|
| 1368 |
+
"learning_rate": 1e-06,
|
| 1369 |
+
"loss": 0.0,
|
| 1370 |
+
"reward": 0.5703125111758709,
|
| 1371 |
+
"reward_std": 0.12822659336961806,
|
| 1372 |
+
"rewards/accuracy_reward": 0.5703125111758709,
|
| 1373 |
+
"step": 124
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"completion_length": 402.60243797302246,
|
| 1377 |
+
"epoch": 0.9950248756218906,
|
| 1378 |
+
"grad_norm": 0.007635696791112423,
|
| 1379 |
+
"learning_rate": 1e-06,
|
| 1380 |
+
"loss": 0.0,
|
| 1381 |
+
"reward": 0.6449652845039964,
|
| 1382 |
+
"reward_std": 0.14181664236821234,
|
| 1383 |
+
"rewards/accuracy_reward": 0.6449652845039964,
|
| 1384 |
+
"step": 125
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.9950248756218906,
|
| 1388 |
+
"step": 125,
|
| 1389 |
+
"total_flos": 0.0,
|
| 1390 |
+
"train_loss": 1.7134473857538523e-08,
|
| 1391 |
+
"train_runtime": 32762.3532,
|
| 1392 |
+
"train_samples_per_second": 0.368,
|
| 1393 |
+
"train_steps_per_second": 0.004
|
| 1394 |
+
}
|
| 1395 |
+
],
|
| 1396 |
+
"logging_steps": 1,
|
| 1397 |
+
"max_steps": 125,
|
| 1398 |
+
"num_input_tokens_seen": 0,
|
| 1399 |
+
"num_train_epochs": 1,
|
| 1400 |
+
"save_steps": 10,
|
| 1401 |
+
"stateful_callbacks": {
|
| 1402 |
+
"TrainerControl": {
|
| 1403 |
+
"args": {
|
| 1404 |
+
"should_epoch_stop": false,
|
| 1405 |
+
"should_evaluate": false,
|
| 1406 |
+
"should_log": false,
|
| 1407 |
+
"should_save": true,
|
| 1408 |
+
"should_training_stop": true
|
| 1409 |
+
},
|
| 1410 |
+
"attributes": {}
|
| 1411 |
+
}
|
| 1412 |
+
},
|
| 1413 |
+
"total_flos": 0.0,
|
| 1414 |
+
"train_batch_size": 1,
|
| 1415 |
+
"trial_name": null,
|
| 1416 |
+
"trial_params": null
|
| 1417 |
+
}
|