Model save
Browse files- README.md +68 -0
- all_results.json +8 -0
- generation_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +2243 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Gaussian
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- grpo
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Gaussian
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
|
| 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="LLucass/Gaussian", 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/lavatorywang-nus/openr1/runs/wuysuu4f)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
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).
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.18.0
|
| 38 |
+
- Transformers: 4.50.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.6.0
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
Cite GRPO as:
|
| 46 |
+
|
| 47 |
+
```bibtex
|
| 48 |
+
@article{zhihong2024deepseekmath,
|
| 49 |
+
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
| 50 |
+
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},
|
| 51 |
+
year = 2024,
|
| 52 |
+
eprint = {arXiv:2402.03300},
|
| 53 |
+
}
|
| 54 |
+
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
Cite TRL as:
|
| 58 |
+
|
| 59 |
+
```bibtex
|
| 60 |
+
@misc{vonwerra2022trl,
|
| 61 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 62 |
+
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},
|
| 63 |
+
year = 2020,
|
| 64 |
+
journal = {GitHub repository},
|
| 65 |
+
publisher = {GitHub},
|
| 66 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 67 |
+
}
|
| 68 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 0.0,
|
| 3 |
+
"train_loss": -0.004574703625403345,
|
| 4 |
+
"train_runtime": 8361.7209,
|
| 5 |
+
"train_samples": 7000,
|
| 6 |
+
"train_samples_per_second": 1.148,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 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": "4.50.0"
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 0.0,
|
| 3 |
+
"train_loss": -0.004574703625403345,
|
| 4 |
+
"train_runtime": 8361.7209,
|
| 5 |
+
"train_samples": 7000,
|
| 6 |
+
"train_samples_per_second": 1.148,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11428571428571428,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"completion_length": 2700.4271850585938,
|
| 14 |
+
"cov_mean": -6.0587970438064076e-05,
|
| 15 |
+
"cov_std": 0.35307812318205833,
|
| 16 |
+
"entropy": 0.3681640625,
|
| 17 |
+
"epoch": 0.001142857142857143,
|
| 18 |
+
"grad_norm": 0.45492634177207947,
|
| 19 |
+
"kl": 0.0,
|
| 20 |
+
"learning_rate": 1e-07,
|
| 21 |
+
"loss": -0.0382,
|
| 22 |
+
"reward": 0.7604166893288493,
|
| 23 |
+
"reward_std": 0.4268697127699852,
|
| 24 |
+
"rewards/accuracy_reward": 0.25000001303851604,
|
| 25 |
+
"rewards/format_reward": 0.5104166669771075,
|
| 26 |
+
"step": 1,
|
| 27 |
+
"w_high_ratio": 0.2200421690940857,
|
| 28 |
+
"w_low_ratio": 0.03663695091381669,
|
| 29 |
+
"w_max": 2.1593789756298065,
|
| 30 |
+
"w_mean": 1.4711343348026276,
|
| 31 |
+
"w_min": 6.525355682266089e-35,
|
| 32 |
+
"w_std": 0.2659660503268242
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"completion_length": 3127.3958435058594,
|
| 36 |
+
"cov_mean": -2.155053698515985e-05,
|
| 37 |
+
"cov_std": 0.310540571808815,
|
| 38 |
+
"entropy": 0.353515625,
|
| 39 |
+
"epoch": 0.002285714285714286,
|
| 40 |
+
"grad_norm": 0.5142282843589783,
|
| 41 |
+
"kl": 0.0,
|
| 42 |
+
"learning_rate": 2e-07,
|
| 43 |
+
"loss": 0.0049,
|
| 44 |
+
"reward": 0.6458333637565374,
|
| 45 |
+
"reward_std": 0.4249730706214905,
|
| 46 |
+
"rewards/accuracy_reward": 0.2812500102445483,
|
| 47 |
+
"rewards/format_reward": 0.3645833386108279,
|
| 48 |
+
"step": 2,
|
| 49 |
+
"w_high_ratio": 0.05183619633316994,
|
| 50 |
+
"w_low_ratio": 0.036958135198801756,
|
| 51 |
+
"w_max": 1.8325217366218567,
|
| 52 |
+
"w_mean": 1.2113382518291473,
|
| 53 |
+
"w_min": 0.0,
|
| 54 |
+
"w_std": 0.20957503467798233
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"completion_length": 3733.9583740234375,
|
| 58 |
+
"cov_mean": -2.010253456319333e-05,
|
| 59 |
+
"cov_std": 0.2787674851715565,
|
| 60 |
+
"entropy": 0.451171875,
|
| 61 |
+
"epoch": 0.0034285714285714284,
|
| 62 |
+
"grad_norm": 0.28526851534843445,
|
| 63 |
+
"kl": 4.315376281738281e-05,
|
| 64 |
+
"learning_rate": 3e-07,
|
| 65 |
+
"loss": 0.0391,
|
| 66 |
+
"reward": 0.16666667070239782,
|
| 67 |
+
"reward_std": 0.31075509265065193,
|
| 68 |
+
"rewards/accuracy_reward": 0.031250000931322575,
|
| 69 |
+
"rewards/format_reward": 0.13541666697710752,
|
| 70 |
+
"step": 3,
|
| 71 |
+
"w_high_ratio": 0.0,
|
| 72 |
+
"w_low_ratio": 0.03727753087878227,
|
| 73 |
+
"w_max": 1.426508367061615,
|
| 74 |
+
"w_mean": 1.069275826215744,
|
| 75 |
+
"w_min": 0.0,
|
| 76 |
+
"w_std": 0.17276715114712715
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"completion_length": 2456.5104370117188,
|
| 80 |
+
"cov_mean": 6.050579213479068e-05,
|
| 81 |
+
"cov_std": 0.4746721386909485,
|
| 82 |
+
"entropy": 0.404296875,
|
| 83 |
+
"epoch": 0.004571428571428572,
|
| 84 |
+
"grad_norm": 0.4348958432674408,
|
| 85 |
+
"kl": 3.764033317565918e-05,
|
| 86 |
+
"learning_rate": 4e-07,
|
| 87 |
+
"loss": -0.0128,
|
| 88 |
+
"reward": 0.8125000223517418,
|
| 89 |
+
"reward_std": 0.4816601872444153,
|
| 90 |
+
"rewards/accuracy_reward": 0.1354166679084301,
|
| 91 |
+
"rewards/format_reward": 0.677083358168602,
|
| 92 |
+
"step": 4,
|
| 93 |
+
"w_high_ratio": 0.09904679656028748,
|
| 94 |
+
"w_low_ratio": 0.03708651335909963,
|
| 95 |
+
"w_max": 2.0615443289279938,
|
| 96 |
+
"w_mean": 1.430301010608673,
|
| 97 |
+
"w_min": 2.2357144385761694e-24,
|
| 98 |
+
"w_std": 0.25941959768533707
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"completion_length": 3495.9584350585938,
|
| 102 |
+
"cov_mean": -0.00011635808687060489,
|
| 103 |
+
"cov_std": 0.43240153789520264,
|
| 104 |
+
"entropy": 0.4658203125,
|
| 105 |
+
"epoch": 0.005714285714285714,
|
| 106 |
+
"grad_norm": 0.44890686869621277,
|
| 107 |
+
"kl": 4.1797757148742676e-05,
|
| 108 |
+
"learning_rate": 5e-07,
|
| 109 |
+
"loss": -0.077,
|
| 110 |
+
"reward": 0.38541667722165585,
|
| 111 |
+
"reward_std": 0.41880372166633606,
|
| 112 |
+
"rewards/accuracy_reward": 0.0416666679084301,
|
| 113 |
+
"rewards/format_reward": 0.34375001303851604,
|
| 114 |
+
"step": 5,
|
| 115 |
+
"w_high_ratio": 0.057075776159763336,
|
| 116 |
+
"w_low_ratio": 0.04613090865314007,
|
| 117 |
+
"w_max": 1.8747033178806305,
|
| 118 |
+
"w_mean": 1.2025023698806763,
|
| 119 |
+
"w_min": 2.0185204017920427e-32,
|
| 120 |
+
"w_std": 0.24863697960972786
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"completion_length": 3429.7604370117188,
|
| 124 |
+
"cov_mean": 7.305060944418074e-05,
|
| 125 |
+
"cov_std": 0.3747733160853386,
|
| 126 |
+
"entropy": 0.4658203125,
|
| 127 |
+
"epoch": 0.006857142857142857,
|
| 128 |
+
"grad_norm": 0.323794424533844,
|
| 129 |
+
"kl": 4.607439041137695e-05,
|
| 130 |
+
"learning_rate": 6e-07,
|
| 131 |
+
"loss": 0.0289,
|
| 132 |
+
"reward": 0.4791666828095913,
|
| 133 |
+
"reward_std": 0.4919559434056282,
|
| 134 |
+
"rewards/accuracy_reward": 0.1666666716337204,
|
| 135 |
+
"rewards/format_reward": 0.3125000111758709,
|
| 136 |
+
"step": 6,
|
| 137 |
+
"w_high_ratio": 0.0,
|
| 138 |
+
"w_low_ratio": 0.045196511782705784,
|
| 139 |
+
"w_max": 1.4718832075595856,
|
| 140 |
+
"w_mean": 1.11675626039505,
|
| 141 |
+
"w_min": 0.25,
|
| 142 |
+
"w_std": 0.20970172435045242
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"completion_length": 3298.1875610351562,
|
| 146 |
+
"cov_mean": 1.544893893878907e-05,
|
| 147 |
+
"cov_std": 0.5214613378047943,
|
| 148 |
+
"entropy": 0.3837890625,
|
| 149 |
+
"epoch": 0.008,
|
| 150 |
+
"grad_norm": 0.3830799460411072,
|
| 151 |
+
"kl": 2.524256706237793e-05,
|
| 152 |
+
"learning_rate": 7e-07,
|
| 153 |
+
"loss": -0.0429,
|
| 154 |
+
"reward": 0.802083358168602,
|
| 155 |
+
"reward_std": 0.5995434895157814,
|
| 156 |
+
"rewards/accuracy_reward": 0.2083333432674408,
|
| 157 |
+
"rewards/format_reward": 0.5937500223517418,
|
| 158 |
+
"step": 7,
|
| 159 |
+
"w_high_ratio": 0.10538750886917114,
|
| 160 |
+
"w_low_ratio": 0.0529888030141592,
|
| 161 |
+
"w_max": 1.5837838649749756,
|
| 162 |
+
"w_mean": 1.266415923833847,
|
| 163 |
+
"w_min": 1.0439673559219887e-43,
|
| 164 |
+
"w_std": 0.28801921010017395
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"completion_length": 2903.697998046875,
|
| 168 |
+
"cov_mean": -8.183626050595194e-06,
|
| 169 |
+
"cov_std": 0.2509700208902359,
|
| 170 |
+
"entropy": 0.355712890625,
|
| 171 |
+
"epoch": 0.009142857142857144,
|
| 172 |
+
"grad_norm": 0.2550622820854187,
|
| 173 |
+
"kl": 1.93864107131958e-05,
|
| 174 |
+
"learning_rate": 8e-07,
|
| 175 |
+
"loss": -0.0211,
|
| 176 |
+
"reward": 0.7812500298023224,
|
| 177 |
+
"reward_std": 0.3037422299385071,
|
| 178 |
+
"rewards/accuracy_reward": 0.3333333432674408,
|
| 179 |
+
"rewards/format_reward": 0.4479166865348816,
|
| 180 |
+
"step": 8,
|
| 181 |
+
"w_high_ratio": 0.152647502720356,
|
| 182 |
+
"w_low_ratio": 0.020135570783168077,
|
| 183 |
+
"w_max": 1.6893351376056671,
|
| 184 |
+
"w_mean": 1.325122356414795,
|
| 185 |
+
"w_min": 0.5,
|
| 186 |
+
"w_std": 0.13287343829870224
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"completion_length": 3427.0001220703125,
|
| 190 |
+
"cov_mean": 2.1584107344096992e-05,
|
| 191 |
+
"cov_std": 0.41377831995487213,
|
| 192 |
+
"entropy": 0.4404296875,
|
| 193 |
+
"epoch": 0.010285714285714285,
|
| 194 |
+
"grad_norm": 0.36070960760116577,
|
| 195 |
+
"kl": 4.297494888305664e-05,
|
| 196 |
+
"learning_rate": 9e-07,
|
| 197 |
+
"loss": -0.0144,
|
| 198 |
+
"reward": 0.4375000149011612,
|
| 199 |
+
"reward_std": 0.5150812789797783,
|
| 200 |
+
"rewards/accuracy_reward": 0.11458333395421505,
|
| 201 |
+
"rewards/format_reward": 0.322916679084301,
|
| 202 |
+
"step": 9,
|
| 203 |
+
"w_high_ratio": 0.0,
|
| 204 |
+
"w_low_ratio": 0.053231239318847656,
|
| 205 |
+
"w_max": 1.665610283613205,
|
| 206 |
+
"w_mean": 1.168578028678894,
|
| 207 |
+
"w_min": 0.0,
|
| 208 |
+
"w_std": 0.2691279575228691
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"completion_length": 2921.260498046875,
|
| 212 |
+
"cov_mean": -0.00011126142680950579,
|
| 213 |
+
"cov_std": 0.37009984999895096,
|
| 214 |
+
"entropy": 0.34130859375,
|
| 215 |
+
"epoch": 0.011428571428571429,
|
| 216 |
+
"grad_norm": 0.463008314371109,
|
| 217 |
+
"kl": 2.7805566787719727e-05,
|
| 218 |
+
"learning_rate": 1e-06,
|
| 219 |
+
"loss": -0.0304,
|
| 220 |
+
"reward": 0.604166679084301,
|
| 221 |
+
"reward_std": 0.49994633346796036,
|
| 222 |
+
"rewards/accuracy_reward": 0.19791667349636555,
|
| 223 |
+
"rewards/format_reward": 0.4062500111758709,
|
| 224 |
+
"step": 10,
|
| 225 |
+
"w_high_ratio": 0.10105682164430618,
|
| 226 |
+
"w_low_ratio": 0.039817056618630886,
|
| 227 |
+
"w_max": 2.203812062740326,
|
| 228 |
+
"w_mean": 1.3322690725326538,
|
| 229 |
+
"w_min": 0.0,
|
| 230 |
+
"w_std": 0.24996469356119633
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"completion_length": 3739.4583740234375,
|
| 234 |
+
"cov_mean": 1.6300052948281518e-05,
|
| 235 |
+
"cov_std": 0.22599393874406815,
|
| 236 |
+
"entropy": 0.3876953125,
|
| 237 |
+
"epoch": 0.012571428571428572,
|
| 238 |
+
"grad_norm": 0.2399490475654602,
|
| 239 |
+
"kl": 2.893805503845215e-05,
|
| 240 |
+
"learning_rate": 9.997258721585931e-07,
|
| 241 |
+
"loss": 0.0375,
|
| 242 |
+
"reward": 0.1979166716337204,
|
| 243 |
+
"reward_std": 0.3496348336338997,
|
| 244 |
+
"rewards/accuracy_reward": 0.07291666697710752,
|
| 245 |
+
"rewards/format_reward": 0.12500000558793545,
|
| 246 |
+
"step": 11,
|
| 247 |
+
"w_high_ratio": 0.0,
|
| 248 |
+
"w_low_ratio": 0.03310772683471441,
|
| 249 |
+
"w_max": 1.3216401040554047,
|
| 250 |
+
"w_mean": 1.05658358335495,
|
| 251 |
+
"w_min": 0.25,
|
| 252 |
+
"w_std": 0.13504411466419697
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"completion_length": 2672.3959045410156,
|
| 256 |
+
"cov_mean": -1.72590916918125e-05,
|
| 257 |
+
"cov_std": 0.4432706832885742,
|
| 258 |
+
"entropy": 0.38525390625,
|
| 259 |
+
"epoch": 0.013714285714285714,
|
| 260 |
+
"grad_norm": 0.5923348665237427,
|
| 261 |
+
"kl": 3.87728214263916e-05,
|
| 262 |
+
"learning_rate": 9.989038226169207e-07,
|
| 263 |
+
"loss": -0.0398,
|
| 264 |
+
"reward": 0.7916666865348816,
|
| 265 |
+
"reward_std": 0.44830071553587914,
|
| 266 |
+
"rewards/accuracy_reward": 0.15625,
|
| 267 |
+
"rewards/format_reward": 0.6354166865348816,
|
| 268 |
+
"step": 12,
|
| 269 |
+
"w_high_ratio": 0.18827838450670242,
|
| 270 |
+
"w_low_ratio": 0.039877891540527344,
|
| 271 |
+
"w_max": 2.278617113828659,
|
| 272 |
+
"w_mean": 1.533039778470993,
|
| 273 |
+
"w_min": 0.0,
|
| 274 |
+
"w_std": 0.30229373276233673
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"completion_length": 3129.9168090820312,
|
| 278 |
+
"cov_mean": 5.8586666455084924e-05,
|
| 279 |
+
"cov_std": 0.3728199526667595,
|
| 280 |
+
"entropy": 0.3896484375,
|
| 281 |
+
"epoch": 0.014857142857142857,
|
| 282 |
+
"grad_norm": 0.7794428467750549,
|
| 283 |
+
"kl": 2.4527311325073242e-05,
|
| 284 |
+
"learning_rate": 9.975348529157229e-07,
|
| 285 |
+
"loss": -0.0268,
|
| 286 |
+
"reward": 0.6145833507180214,
|
| 287 |
+
"reward_std": 0.3987155184149742,
|
| 288 |
+
"rewards/accuracy_reward": 0.1979166716337204,
|
| 289 |
+
"rewards/format_reward": 0.4166666716337204,
|
| 290 |
+
"step": 13,
|
| 291 |
+
"w_high_ratio": 0.1489243432879448,
|
| 292 |
+
"w_low_ratio": 0.03552113357000053,
|
| 293 |
+
"w_max": 1.913963943719864,
|
| 294 |
+
"w_mean": 1.3093808591365814,
|
| 295 |
+
"w_min": 0.0,
|
| 296 |
+
"w_std": 0.22065079398453236
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"completion_length": 2925.8750610351562,
|
| 300 |
+
"cov_mean": 7.129182449716609e-06,
|
| 301 |
+
"cov_std": 0.3760656714439392,
|
| 302 |
+
"entropy": 0.353515625,
|
| 303 |
+
"epoch": 0.016,
|
| 304 |
+
"grad_norm": 0.6446069478988647,
|
| 305 |
+
"kl": 2.3916363716125488e-05,
|
| 306 |
+
"learning_rate": 9.956206309337066e-07,
|
| 307 |
+
"loss": -0.0123,
|
| 308 |
+
"reward": 0.6562500298023224,
|
| 309 |
+
"reward_std": 0.41464143246412277,
|
| 310 |
+
"rewards/accuracy_reward": 0.17708334233611822,
|
| 311 |
+
"rewards/format_reward": 0.4791666716337204,
|
| 312 |
+
"step": 14,
|
| 313 |
+
"w_high_ratio": 0.04337232932448387,
|
| 314 |
+
"w_low_ratio": 0.04529819544404745,
|
| 315 |
+
"w_max": 1.892830729484558,
|
| 316 |
+
"w_mean": 1.2675927579402924,
|
| 317 |
+
"w_min": 7.264961823368798e-41,
|
| 318 |
+
"w_std": 0.26389942318201065
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"completion_length": 2977.6458740234375,
|
| 322 |
+
"cov_mean": 2.068816957034869e-05,
|
| 323 |
+
"cov_std": 0.2604588344693184,
|
| 324 |
+
"entropy": 0.3759765625,
|
| 325 |
+
"epoch": 0.017142857142857144,
|
| 326 |
+
"grad_norm": 0.4150949716567993,
|
| 327 |
+
"kl": 3.0860304832458496e-05,
|
| 328 |
+
"learning_rate": 9.931634888554935e-07,
|
| 329 |
+
"loss": -0.0032,
|
| 330 |
+
"reward": 0.6041666902601719,
|
| 331 |
+
"reward_std": 0.25453949719667435,
|
| 332 |
+
"rewards/accuracy_reward": 0.20833333861082792,
|
| 333 |
+
"rewards/format_reward": 0.3958333358168602,
|
| 334 |
+
"step": 15,
|
| 335 |
+
"w_high_ratio": 0.0,
|
| 336 |
+
"w_low_ratio": 0.027457581600174308,
|
| 337 |
+
"w_max": 1.3896198272705078,
|
| 338 |
+
"w_mean": 1.1120553016662598,
|
| 339 |
+
"w_min": 0.0,
|
| 340 |
+
"w_std": 0.1376371644437313
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"completion_length": 3860.1771850585938,
|
| 344 |
+
"cov_mean": 3.589540312987083e-05,
|
| 345 |
+
"cov_std": 0.1900031939148903,
|
| 346 |
+
"entropy": 0.45751953125,
|
| 347 |
+
"epoch": 0.018285714285714287,
|
| 348 |
+
"grad_norm": 0.25400859117507935,
|
| 349 |
+
"kl": 3.0994415283203125e-05,
|
| 350 |
+
"learning_rate": 9.901664203302124e-07,
|
| 351 |
+
"loss": 0.0468,
|
| 352 |
+
"reward": 0.1458333395421505,
|
| 353 |
+
"reward_std": 0.24955713748931885,
|
| 354 |
+
"rewards/accuracy_reward": 0.06250000279396772,
|
| 355 |
+
"rewards/format_reward": 0.08333333674818277,
|
| 356 |
+
"step": 16,
|
| 357 |
+
"w_high_ratio": 0.0,
|
| 358 |
+
"w_low_ratio": 0.028868926223367453,
|
| 359 |
+
"w_max": 1.2315952479839325,
|
| 360 |
+
"w_mean": 1.0204393565654755,
|
| 361 |
+
"w_min": 0.25,
|
| 362 |
+
"w_std": 0.10705284960567951
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"completion_length": 2540.4895935058594,
|
| 366 |
+
"cov_mean": -0.0001341435610129338,
|
| 367 |
+
"cov_std": 0.47027114033699036,
|
| 368 |
+
"entropy": 0.45166015625,
|
| 369 |
+
"epoch": 0.019428571428571427,
|
| 370 |
+
"grad_norm": 0.46505773067474365,
|
| 371 |
+
"kl": 5.486607551574707e-05,
|
| 372 |
+
"learning_rate": 9.866330768241983e-07,
|
| 373 |
+
"loss": -0.0001,
|
| 374 |
+
"reward": 0.812500037252903,
|
| 375 |
+
"reward_std": 0.49661170691251755,
|
| 376 |
+
"rewards/accuracy_reward": 0.2291666716337204,
|
| 377 |
+
"rewards/format_reward": 0.5833333507180214,
|
| 378 |
+
"step": 17,
|
| 379 |
+
"w_high_ratio": 0.15490177273750305,
|
| 380 |
+
"w_low_ratio": 0.04533949866890907,
|
| 381 |
+
"w_max": 2.4269833266735077,
|
| 382 |
+
"w_mean": 1.407887727022171,
|
| 383 |
+
"w_min": 6.344169701078957e-36,
|
| 384 |
+
"w_std": 0.2766948938369751
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"completion_length": 3100.604248046875,
|
| 388 |
+
"cov_mean": 9.316997420683037e-06,
|
| 389 |
+
"cov_std": 0.345074113458395,
|
| 390 |
+
"entropy": 0.36865234375,
|
| 391 |
+
"epoch": 0.02057142857142857,
|
| 392 |
+
"grad_norm": 0.26780965924263,
|
| 393 |
+
"kl": 3.306567668914795e-05,
|
| 394 |
+
"learning_rate": 9.825677631722435e-07,
|
| 395 |
+
"loss": 0.0093,
|
| 396 |
+
"reward": 0.5208333507180214,
|
| 397 |
+
"reward_std": 0.4629998616874218,
|
| 398 |
+
"rewards/accuracy_reward": 0.11458333861082792,
|
| 399 |
+
"rewards/format_reward": 0.4062500074505806,
|
| 400 |
+
"step": 18,
|
| 401 |
+
"w_high_ratio": 0.12114312499761581,
|
| 402 |
+
"w_low_ratio": 0.046439004596322775,
|
| 403 |
+
"w_max": 2.0130829215049744,
|
| 404 |
+
"w_mean": 1.2991048991680145,
|
| 405 |
+
"w_min": 0.0,
|
| 406 |
+
"w_std": 0.22966066375374794
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"completion_length": 3111.229248046875,
|
| 410 |
+
"cov_mean": -1.3287149158713873e-10,
|
| 411 |
+
"cov_std": 0.305859737098217,
|
| 412 |
+
"entropy": 0.37939453125,
|
| 413 |
+
"epoch": 0.021714285714285714,
|
| 414 |
+
"grad_norm": 0.2747480869293213,
|
| 415 |
+
"kl": 4.106760025024414e-05,
|
| 416 |
+
"learning_rate": 9.779754323328192e-07,
|
| 417 |
+
"loss": -0.0265,
|
| 418 |
+
"reward": 0.8437500251457095,
|
| 419 |
+
"reward_std": 0.44304458051919937,
|
| 420 |
+
"rewards/accuracy_reward": 0.3854166818782687,
|
| 421 |
+
"rewards/format_reward": 0.4583333535119891,
|
| 422 |
+
"step": 19,
|
| 423 |
+
"w_high_ratio": 0.007512019481509924,
|
| 424 |
+
"w_low_ratio": 0.03380460711196065,
|
| 425 |
+
"w_max": 1.7184137105941772,
|
| 426 |
+
"w_mean": 1.2587754130363464,
|
| 427 |
+
"w_min": 0.0,
|
| 428 |
+
"w_std": 0.17892248183488846
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"completion_length": 2602.0000610351562,
|
| 432 |
+
"cov_mean": -4.431823981576599e-06,
|
| 433 |
+
"cov_std": 0.3394951745867729,
|
| 434 |
+
"entropy": 0.334716796875,
|
| 435 |
+
"epoch": 0.022857142857142857,
|
| 436 |
+
"grad_norm": 0.2722320854663849,
|
| 437 |
+
"kl": 7.30752944946289e-05,
|
| 438 |
+
"learning_rate": 9.728616793536587e-07,
|
| 439 |
+
"loss": -0.016,
|
| 440 |
+
"reward": 0.989583358168602,
|
| 441 |
+
"reward_std": 0.41970477253198624,
|
| 442 |
+
"rewards/accuracy_reward": 0.2812500074505806,
|
| 443 |
+
"rewards/format_reward": 0.708333358168602,
|
| 444 |
+
"step": 20,
|
| 445 |
+
"w_high_ratio": 0.053037188947200775,
|
| 446 |
+
"w_low_ratio": 0.03638318553566933,
|
| 447 |
+
"w_max": 1.8807734847068787,
|
| 448 |
+
"w_mean": 1.3341735899448395,
|
| 449 |
+
"w_min": 0.28736552596092224,
|
| 450 |
+
"w_std": 0.21230074390769005
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"completion_length": 2938.9896240234375,
|
| 454 |
+
"cov_mean": 1.115940267482074e-05,
|
| 455 |
+
"cov_std": 0.3257220685482025,
|
| 456 |
+
"entropy": 0.42919921875,
|
| 457 |
+
"epoch": 0.024,
|
| 458 |
+
"grad_norm": 0.9565598964691162,
|
| 459 |
+
"kl": 0.00023573637008666992,
|
| 460 |
+
"learning_rate": 9.672327345550543e-07,
|
| 461 |
+
"loss": 0.0067,
|
| 462 |
+
"reward": 0.604166692122817,
|
| 463 |
+
"reward_std": 0.4190382584929466,
|
| 464 |
+
"rewards/accuracy_reward": 0.17708333674818277,
|
| 465 |
+
"rewards/format_reward": 0.4270833460614085,
|
| 466 |
+
"step": 21,
|
| 467 |
+
"w_high_ratio": 0.2210865318775177,
|
| 468 |
+
"w_low_ratio": 0.03242270671762526,
|
| 469 |
+
"w_max": 1.8820680975914001,
|
| 470 |
+
"w_mean": 1.4674345552921295,
|
| 471 |
+
"w_min": 2.9579121420725567e-37,
|
| 472 |
+
"w_std": 0.23061984032392502
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"completion_length": 1817.8125305175781,
|
| 476 |
+
"cov_mean": 3.471795207588002e-05,
|
| 477 |
+
"cov_std": 0.4554404318332672,
|
| 478 |
+
"entropy": 0.37548828125,
|
| 479 |
+
"epoch": 0.025142857142857144,
|
| 480 |
+
"grad_norm": 0.6403908729553223,
|
| 481 |
+
"kl": 0.0001913309097290039,
|
| 482 |
+
"learning_rate": 9.610954559391704e-07,
|
| 483 |
+
"loss": -0.0476,
|
| 484 |
+
"reward": 1.1041667014360428,
|
| 485 |
+
"reward_std": 0.36877378076314926,
|
| 486 |
+
"rewards/accuracy_reward": 0.28125000558793545,
|
| 487 |
+
"rewards/format_reward": 0.8229166716337204,
|
| 488 |
+
"step": 22,
|
| 489 |
+
"w_high_ratio": 0.3237294889986515,
|
| 490 |
+
"w_low_ratio": 0.03283138480037451,
|
| 491 |
+
"w_max": 3.265183061361313,
|
| 492 |
+
"w_mean": 1.977644294500351,
|
| 493 |
+
"w_min": 5.22007475166266e-30,
|
| 494 |
+
"w_std": 0.34112248569726944
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"completion_length": 2787.4896850585938,
|
| 498 |
+
"cov_mean": 3.710087821673369e-05,
|
| 499 |
+
"cov_std": 0.3974616304039955,
|
| 500 |
+
"entropy": 0.38525390625,
|
| 501 |
+
"epoch": 0.026285714285714287,
|
| 502 |
+
"grad_norm": 0.6307149529457092,
|
| 503 |
+
"kl": 0.00013697147369384766,
|
| 504 |
+
"learning_rate": 9.54457320834625e-07,
|
| 505 |
+
"loss": -0.0959,
|
| 506 |
+
"reward": 0.6041666716337204,
|
| 507 |
+
"reward_std": 0.4507869631052017,
|
| 508 |
+
"rewards/accuracy_reward": 0.14583333395421505,
|
| 509 |
+
"rewards/format_reward": 0.4583333358168602,
|
| 510 |
+
"step": 23,
|
| 511 |
+
"w_high_ratio": 0.18567950278520584,
|
| 512 |
+
"w_low_ratio": 0.042684963904321194,
|
| 513 |
+
"w_max": 2.490270048379898,
|
| 514 |
+
"w_mean": 1.4617709517478943,
|
| 515 |
+
"w_min": 1.9980297628321344e-34,
|
| 516 |
+
"w_std": 0.30704520270228386
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"completion_length": 3070.3125610351562,
|
| 520 |
+
"cov_mean": 5.4191557865124196e-05,
|
| 521 |
+
"cov_std": 0.5094943791627884,
|
| 522 |
+
"entropy": 0.367431640625,
|
| 523 |
+
"epoch": 0.027428571428571427,
|
| 524 |
+
"grad_norm": 0.5826663374900818,
|
| 525 |
+
"kl": 0.0001633763313293457,
|
| 526 |
+
"learning_rate": 9.473264167865171e-07,
|
| 527 |
+
"loss": -0.02,
|
| 528 |
+
"reward": 0.8229166939854622,
|
| 529 |
+
"reward_std": 0.5960981249809265,
|
| 530 |
+
"rewards/accuracy_reward": 0.2708333358168602,
|
| 531 |
+
"rewards/format_reward": 0.5520833507180214,
|
| 532 |
+
"step": 24,
|
| 533 |
+
"w_high_ratio": 0.16660767421126366,
|
| 534 |
+
"w_low_ratio": 0.05264063738286495,
|
| 535 |
+
"w_max": 2.2747649252414703,
|
| 536 |
+
"w_mean": 1.4129657745361328,
|
| 537 |
+
"w_min": 0.0,
|
| 538 |
+
"w_std": 0.3425128310918808
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"completion_length": 3037.8125,
|
| 542 |
+
"cov_mean": -3.0258611332101282e-05,
|
| 543 |
+
"cov_std": 0.2974156364798546,
|
| 544 |
+
"entropy": 0.4462890625,
|
| 545 |
+
"epoch": 0.02857142857142857,
|
| 546 |
+
"grad_norm": 0.33458662033081055,
|
| 547 |
+
"kl": 0.00022605061531066895,
|
| 548 |
+
"learning_rate": 9.397114317029974e-07,
|
| 549 |
+
"loss": 0.0202,
|
| 550 |
+
"reward": 0.6875000149011612,
|
| 551 |
+
"reward_std": 0.4009811282157898,
|
| 552 |
+
"rewards/accuracy_reward": 0.2395833432674408,
|
| 553 |
+
"rewards/format_reward": 0.4479166865348816,
|
| 554 |
+
"step": 25,
|
| 555 |
+
"w_high_ratio": 0.1122930608689785,
|
| 556 |
+
"w_low_ratio": 0.034513187827542424,
|
| 557 |
+
"w_max": 1.991903692483902,
|
| 558 |
+
"w_mean": 1.2860748171806335,
|
| 559 |
+
"w_min": 0.25,
|
| 560 |
+
"w_std": 0.2155727706849575
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"completion_length": 3117.4584350585938,
|
| 564 |
+
"cov_mean": -8.455652073280362e-05,
|
| 565 |
+
"cov_std": 0.23132415860891342,
|
| 566 |
+
"entropy": 0.42626953125,
|
| 567 |
+
"epoch": 0.029714285714285714,
|
| 568 |
+
"grad_norm": 0.41856279969215393,
|
| 569 |
+
"kl": 6.198883056640625e-05,
|
| 570 |
+
"learning_rate": 9.316216432703916e-07,
|
| 571 |
+
"loss": -0.053,
|
| 572 |
+
"reward": 0.6562500074505806,
|
| 573 |
+
"reward_std": 0.20796867460012436,
|
| 574 |
+
"rewards/accuracy_reward": 0.1979166716337204,
|
| 575 |
+
"rewards/format_reward": 0.4583333432674408,
|
| 576 |
+
"step": 26,
|
| 577 |
+
"w_high_ratio": 0.04478337988257408,
|
| 578 |
+
"w_low_ratio": 0.011211750796064734,
|
| 579 |
+
"w_max": 1.7470227479934692,
|
| 580 |
+
"w_mean": 1.224214792251587,
|
| 581 |
+
"w_min": 0.25,
|
| 582 |
+
"w_std": 0.10643218830227852
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"completion_length": 3314.1041870117188,
|
| 586 |
+
"cov_mean": 2.3687035081820795e-05,
|
| 587 |
+
"cov_std": 0.44449782371520996,
|
| 588 |
+
"entropy": 0.44921875,
|
| 589 |
+
"epoch": 0.030857142857142857,
|
| 590 |
+
"grad_norm": 0.3447716236114502,
|
| 591 |
+
"kl": 0.0005403757095336914,
|
| 592 |
+
"learning_rate": 9.230669076497687e-07,
|
| 593 |
+
"loss": -0.0255,
|
| 594 |
+
"reward": 0.6354166865348816,
|
| 595 |
+
"reward_std": 0.5543549209833145,
|
| 596 |
+
"rewards/accuracy_reward": 0.1875000037252903,
|
| 597 |
+
"rewards/format_reward": 0.447916679084301,
|
| 598 |
+
"step": 27,
|
| 599 |
+
"w_high_ratio": 0.04345417395234108,
|
| 600 |
+
"w_low_ratio": 0.047908838372677565,
|
| 601 |
+
"w_max": 1.680276095867157,
|
| 602 |
+
"w_mean": 1.1971288323402405,
|
| 603 |
+
"w_min": 0.0,
|
| 604 |
+
"w_std": 0.23072999715805054
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"completion_length": 3026.5626220703125,
|
| 608 |
+
"cov_mean": 4.19466396124335e-05,
|
| 609 |
+
"cov_std": 0.4268927723169327,
|
| 610 |
+
"entropy": 0.4091796875,
|
| 611 |
+
"epoch": 0.032,
|
| 612 |
+
"grad_norm": 0.4165506958961487,
|
| 613 |
+
"kl": 0.00021666288375854492,
|
| 614 |
+
"learning_rate": 9.140576474687263e-07,
|
| 615 |
+
"loss": -0.0277,
|
| 616 |
+
"reward": 0.8437500298023224,
|
| 617 |
+
"reward_std": 0.4840777963399887,
|
| 618 |
+
"rewards/accuracy_reward": 0.3750000149011612,
|
| 619 |
+
"rewards/format_reward": 0.4687500149011612,
|
| 620 |
+
"step": 28,
|
| 621 |
+
"w_high_ratio": 0.09859117493033409,
|
| 622 |
+
"w_low_ratio": 0.04558967752382159,
|
| 623 |
+
"w_max": 2.2461937069892883,
|
| 624 |
+
"w_mean": 1.3320654332637787,
|
| 625 |
+
"w_min": 0.0,
|
| 626 |
+
"w_std": 0.2779119908809662
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"completion_length": 3620.1563110351562,
|
| 630 |
+
"cov_mean": -3.5699086538443225e-05,
|
| 631 |
+
"cov_std": 0.34214310348033905,
|
| 632 |
+
"entropy": 0.43017578125,
|
| 633 |
+
"epoch": 0.03314285714285714,
|
| 634 |
+
"grad_norm": 0.3975992202758789,
|
| 635 |
+
"kl": 0.0004680156707763672,
|
| 636 |
+
"learning_rate": 9.046048391230247e-07,
|
| 637 |
+
"loss": 0.0814,
|
| 638 |
+
"reward": 0.2291666716337204,
|
| 639 |
+
"reward_std": 0.39027639478445053,
|
| 640 |
+
"rewards/accuracy_reward": 0.0625,
|
| 641 |
+
"rewards/format_reward": 0.1666666716337204,
|
| 642 |
+
"step": 29,
|
| 643 |
+
"w_high_ratio": 0.0,
|
| 644 |
+
"w_low_ratio": 0.04788992367684841,
|
| 645 |
+
"w_max": 1.3650976717472076,
|
| 646 |
+
"w_mean": 1.0994165241718292,
|
| 647 |
+
"w_min": 0.25,
|
| 648 |
+
"w_std": 0.22099098190665245
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"completion_length": 3238.17724609375,
|
| 652 |
+
"cov_mean": 5.147313459019642e-06,
|
| 653 |
+
"cov_std": 0.466504842042923,
|
| 654 |
+
"entropy": 0.38134765625,
|
| 655 |
+
"epoch": 0.03428571428571429,
|
| 656 |
+
"grad_norm": 0.3571697175502777,
|
| 657 |
+
"kl": 0.0008358955383300781,
|
| 658 |
+
"learning_rate": 8.9471999940354e-07,
|
| 659 |
+
"loss": 0.0066,
|
| 660 |
+
"reward": 0.7395833693444729,
|
| 661 |
+
"reward_std": 0.6347565650939941,
|
| 662 |
+
"rewards/accuracy_reward": 0.2708333423361182,
|
| 663 |
+
"rewards/format_reward": 0.4687500074505806,
|
| 664 |
+
"step": 30,
|
| 665 |
+
"w_high_ratio": 0.09309378266334534,
|
| 666 |
+
"w_low_ratio": 0.04863026458770037,
|
| 667 |
+
"w_max": 1.7810659110546112,
|
| 668 |
+
"w_mean": 1.2216298282146454,
|
| 669 |
+
"w_min": 0.0,
|
| 670 |
+
"w_std": 0.26985964179039
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"completion_length": 3252.6771240234375,
|
| 674 |
+
"cov_mean": -2.1283684873196762e-05,
|
| 675 |
+
"cov_std": 0.31266890093684196,
|
| 676 |
+
"entropy": 0.376953125,
|
| 677 |
+
"epoch": 0.03542857142857143,
|
| 678 |
+
"grad_norm": 0.28267669677734375,
|
| 679 |
+
"kl": 0.00033402442932128906,
|
| 680 |
+
"learning_rate": 8.844151714648274e-07,
|
| 681 |
+
"loss": 0.0136,
|
| 682 |
+
"reward": 0.53125,
|
| 683 |
+
"reward_std": 0.3965660147368908,
|
| 684 |
+
"rewards/accuracy_reward": 0.1979166679084301,
|
| 685 |
+
"rewards/format_reward": 0.3333333358168602,
|
| 686 |
+
"step": 31,
|
| 687 |
+
"w_high_ratio": 0.13101918064057827,
|
| 688 |
+
"w_low_ratio": 0.03200887469574809,
|
| 689 |
+
"w_max": 1.9720379710197449,
|
| 690 |
+
"w_mean": 1.2918123006820679,
|
| 691 |
+
"w_min": 0.25,
|
| 692 |
+
"w_std": 0.22479910403490067
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"completion_length": 3411.0208740234375,
|
| 696 |
+
"cov_mean": -2.1311116142896935e-06,
|
| 697 |
+
"cov_std": 0.37892643362283707,
|
| 698 |
+
"entropy": 0.439453125,
|
| 699 |
+
"epoch": 0.036571428571428574,
|
| 700 |
+
"grad_norm": 0.245382159948349,
|
| 701 |
+
"kl": 0.00054168701171875,
|
| 702 |
+
"learning_rate": 8.737029101523929e-07,
|
| 703 |
+
"loss": 0.0361,
|
| 704 |
+
"reward": 0.6666666716337204,
|
| 705 |
+
"reward_std": 0.5180360972881317,
|
| 706 |
+
"rewards/accuracy_reward": 0.2916666669771075,
|
| 707 |
+
"rewards/format_reward": 0.3750000037252903,
|
| 708 |
+
"step": 32,
|
| 709 |
+
"w_high_ratio": 0.0408792570233345,
|
| 710 |
+
"w_low_ratio": 0.0450265696272254,
|
| 711 |
+
"w_max": 1.5775762796401978,
|
| 712 |
+
"w_mean": 1.1778713762760162,
|
| 713 |
+
"w_min": 0.0,
|
| 714 |
+
"w_std": 0.22701822221279144
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"completion_length": 3525.760498046875,
|
| 718 |
+
"cov_mean": -4.6630036194983404e-05,
|
| 719 |
+
"cov_std": 0.3494578003883362,
|
| 720 |
+
"entropy": 0.37939453125,
|
| 721 |
+
"epoch": 0.037714285714285714,
|
| 722 |
+
"grad_norm": 0.2607223689556122,
|
| 723 |
+
"kl": 0.0014134645462036133,
|
| 724 |
+
"learning_rate": 8.625962667065487e-07,
|
| 725 |
+
"loss": 0.0251,
|
| 726 |
+
"reward": 0.47916669212281704,
|
| 727 |
+
"reward_std": 0.5007270351052284,
|
| 728 |
+
"rewards/accuracy_reward": 0.18750001024454832,
|
| 729 |
+
"rewards/format_reward": 0.2916666818782687,
|
| 730 |
+
"step": 33,
|
| 731 |
+
"w_high_ratio": 0.038857411593198776,
|
| 732 |
+
"w_low_ratio": 0.04762307275086641,
|
| 733 |
+
"w_max": 1.5454095602035522,
|
| 734 |
+
"w_mean": 1.1393149495124817,
|
| 735 |
+
"w_min": 0.0,
|
| 736 |
+
"w_std": 0.22297161258757114
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"completion_length": 2453.9791870117188,
|
| 740 |
+
"cov_mean": -9.226416841556784e-05,
|
| 741 |
+
"cov_std": 0.4420240595936775,
|
| 742 |
+
"entropy": 0.43701171875,
|
| 743 |
+
"epoch": 0.038857142857142854,
|
| 744 |
+
"grad_norm": 0.5145274996757507,
|
| 745 |
+
"kl": 0.0017969608306884766,
|
| 746 |
+
"learning_rate": 8.511087728614862e-07,
|
| 747 |
+
"loss": -0.018,
|
| 748 |
+
"reward": 0.9583333684131503,
|
| 749 |
+
"reward_std": 0.4463650956749916,
|
| 750 |
+
"rewards/accuracy_reward": 0.375000006519258,
|
| 751 |
+
"rewards/format_reward": 0.5833333432674408,
|
| 752 |
+
"step": 34,
|
| 753 |
+
"w_high_ratio": 0.13110801950097084,
|
| 754 |
+
"w_low_ratio": 0.052741190418601036,
|
| 755 |
+
"w_max": 2.1099403500556946,
|
| 756 |
+
"w_mean": 1.343121200799942,
|
| 757 |
+
"w_min": 0.0,
|
| 758 |
+
"w_std": 0.31580859050154686
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"completion_length": 3289.4376220703125,
|
| 762 |
+
"cov_mean": 5.6672024584258907e-05,
|
| 763 |
+
"cov_std": 0.3820243999361992,
|
| 764 |
+
"entropy": 0.42529296875,
|
| 765 |
+
"epoch": 0.04,
|
| 766 |
+
"grad_norm": 0.35655274987220764,
|
| 767 |
+
"kl": 0.0010710954666137695,
|
| 768 |
+
"learning_rate": 8.392544243589427e-07,
|
| 769 |
+
"loss": 0.0185,
|
| 770 |
+
"reward": 0.6458333432674408,
|
| 771 |
+
"reward_std": 0.5987429097294807,
|
| 772 |
+
"rewards/accuracy_reward": 0.2708333395421505,
|
| 773 |
+
"rewards/format_reward": 0.3750000037252903,
|
| 774 |
+
"step": 35,
|
| 775 |
+
"w_high_ratio": 0.0,
|
| 776 |
+
"w_low_ratio": 0.05319366045296192,
|
| 777 |
+
"w_max": 1.4592802226543427,
|
| 778 |
+
"w_mean": 1.0992730259895325,
|
| 779 |
+
"w_min": 3.853570776893247e-45,
|
| 780 |
+
"w_std": 0.22482672333717346
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"completion_length": 3621.78125,
|
| 784 |
+
"cov_mean": 7.363205986621324e-05,
|
| 785 |
+
"cov_std": 0.19353903084993362,
|
| 786 |
+
"entropy": 0.4765625,
|
| 787 |
+
"epoch": 0.04114285714285714,
|
| 788 |
+
"grad_norm": 0.30453404784202576,
|
| 789 |
+
"kl": 0.001312553882598877,
|
| 790 |
+
"learning_rate": 8.270476638965461e-07,
|
| 791 |
+
"loss": -0.0147,
|
| 792 |
+
"reward": 0.1666666716337204,
|
| 793 |
+
"reward_std": 0.17689276114106178,
|
| 794 |
+
"rewards/accuracy_reward": 0.010416666977107525,
|
| 795 |
+
"rewards/format_reward": 0.15625,
|
| 796 |
+
"step": 36,
|
| 797 |
+
"w_high_ratio": 0.006425275932997465,
|
| 798 |
+
"w_low_ratio": 0.022115232422947884,
|
| 799 |
+
"w_max": 1.4147455394268036,
|
| 800 |
+
"w_mean": 1.117747575044632,
|
| 801 |
+
"w_min": 0.5,
|
| 802 |
+
"w_std": 0.1310933344066143
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"completion_length": 3511.2813110351562,
|
| 806 |
+
"cov_mean": -8.677186542627169e-06,
|
| 807 |
+
"cov_std": 0.2782720513641834,
|
| 808 |
+
"entropy": 0.43408203125,
|
| 809 |
+
"epoch": 0.04228571428571429,
|
| 810 |
+
"grad_norm": 0.357716828584671,
|
| 811 |
+
"kl": 0.0007710456848144531,
|
| 812 |
+
"learning_rate": 8.145033635316128e-07,
|
| 813 |
+
"loss": -0.0037,
|
| 814 |
+
"reward": 0.21875000279396772,
|
| 815 |
+
"reward_std": 0.20087094232439995,
|
| 816 |
+
"rewards/accuracy_reward": 0.010416666977107525,
|
| 817 |
+
"rewards/format_reward": 0.20833333861082792,
|
| 818 |
+
"step": 37,
|
| 819 |
+
"w_high_ratio": 0.07502041757106781,
|
| 820 |
+
"w_low_ratio": 0.02649637684226036,
|
| 821 |
+
"w_max": 1.848203331232071,
|
| 822 |
+
"w_mean": 1.2203471958637238,
|
| 823 |
+
"w_min": 0.25,
|
| 824 |
+
"w_std": 0.18464426696300507
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"completion_length": 3627.8438110351562,
|
| 828 |
+
"cov_mean": -6.837155524408445e-05,
|
| 829 |
+
"cov_std": 0.14785446226596832,
|
| 830 |
+
"entropy": 0.44921875,
|
| 831 |
+
"epoch": 0.04342857142857143,
|
| 832 |
+
"grad_norm": 0.28619271516799927,
|
| 833 |
+
"kl": 0.0005115270614624023,
|
| 834 |
+
"learning_rate": 8.01636806561836e-07,
|
| 835 |
+
"loss": 0.0051,
|
| 836 |
+
"reward": 0.3645833358168602,
|
| 837 |
+
"reward_std": 0.25648824870586395,
|
| 838 |
+
"rewards/accuracy_reward": 0.1770833395421505,
|
| 839 |
+
"rewards/format_reward": 0.1875000111758709,
|
| 840 |
+
"step": 38,
|
| 841 |
+
"w_high_ratio": 0.051015257835388184,
|
| 842 |
+
"w_low_ratio": 0.01901705004274845,
|
| 843 |
+
"w_max": 1.441689670085907,
|
| 844 |
+
"w_mean": 1.1396986544132233,
|
| 845 |
+
"w_min": 0.5,
|
| 846 |
+
"w_std": 0.09881949052214622
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"completion_length": 3050.979248046875,
|
| 850 |
+
"cov_mean": 4.009085705547477e-05,
|
| 851 |
+
"cov_std": 0.20474716648459435,
|
| 852 |
+
"entropy": 0.366943359375,
|
| 853 |
+
"epoch": 0.044571428571428574,
|
| 854 |
+
"grad_norm": 0.2579488158226013,
|
| 855 |
+
"kl": 0.0016760826110839844,
|
| 856 |
+
"learning_rate": 7.884636689049422e-07,
|
| 857 |
+
"loss": -0.0486,
|
| 858 |
+
"reward": 0.7083333358168602,
|
| 859 |
+
"reward_std": 0.2621734067797661,
|
| 860 |
+
"rewards/accuracy_reward": 0.21875,
|
| 861 |
+
"rewards/format_reward": 0.4895833358168602,
|
| 862 |
+
"step": 39,
|
| 863 |
+
"w_high_ratio": 0.04251348227262497,
|
| 864 |
+
"w_low_ratio": 0.022377901477739215,
|
| 865 |
+
"w_max": 1.5512709319591522,
|
| 866 |
+
"w_mean": 1.1656133532524109,
|
| 867 |
+
"w_min": 0.25,
|
| 868 |
+
"w_std": 0.12140309438109398
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"completion_length": 2983.6876220703125,
|
| 872 |
+
"cov_mean": -2.4692089027666952e-05,
|
| 873 |
+
"cov_std": 0.3223262317478657,
|
| 874 |
+
"entropy": 0.39697265625,
|
| 875 |
+
"epoch": 0.045714285714285714,
|
| 876 |
+
"grad_norm": 0.3634110987186432,
|
| 877 |
+
"kl": 0.003978729248046875,
|
| 878 |
+
"learning_rate": 7.75e-07,
|
| 879 |
+
"loss": 0.0235,
|
| 880 |
+
"reward": 0.7083333507180214,
|
| 881 |
+
"reward_std": 0.39669927954673767,
|
| 882 |
+
"rewards/accuracy_reward": 0.20833334140479565,
|
| 883 |
+
"rewards/format_reward": 0.5000000149011612,
|
| 884 |
+
"step": 40,
|
| 885 |
+
"w_high_ratio": 0.023237863555550575,
|
| 886 |
+
"w_low_ratio": 0.03736424632370472,
|
| 887 |
+
"w_max": 1.7330412566661835,
|
| 888 |
+
"w_mean": 1.253759890794754,
|
| 889 |
+
"w_min": 0.0,
|
| 890 |
+
"w_std": 0.2265719212591648
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"completion_length": 3342.916748046875,
|
| 894 |
+
"cov_mean": 7.446667950716801e-06,
|
| 895 |
+
"cov_std": 0.36464616656303406,
|
| 896 |
+
"entropy": 0.38232421875,
|
| 897 |
+
"epoch": 0.046857142857142854,
|
| 898 |
+
"grad_norm": 0.3088231682777405,
|
| 899 |
+
"kl": 0.0006549358367919922,
|
| 900 |
+
"learning_rate": 7.612622032536507e-07,
|
| 901 |
+
"loss": 0.01,
|
| 902 |
+
"reward": 0.416666679084301,
|
| 903 |
+
"reward_std": 0.49482717365026474,
|
| 904 |
+
"rewards/accuracy_reward": 0.10416667070239782,
|
| 905 |
+
"rewards/format_reward": 0.3125000037252903,
|
| 906 |
+
"step": 41,
|
| 907 |
+
"w_high_ratio": 0.02740619331598282,
|
| 908 |
+
"w_low_ratio": 0.045960213989019394,
|
| 909 |
+
"w_max": 1.735625982284546,
|
| 910 |
+
"w_mean": 1.2091110348701477,
|
| 911 |
+
"w_min": 0.0,
|
| 912 |
+
"w_std": 0.24962139129638672
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"completion_length": 3026.229248046875,
|
| 916 |
+
"cov_mean": 2.7950623916694894e-05,
|
| 917 |
+
"cov_std": 0.22710799425840378,
|
| 918 |
+
"entropy": 0.46923828125,
|
| 919 |
+
"epoch": 0.048,
|
| 920 |
+
"grad_norm": 0.188913494348526,
|
| 921 |
+
"kl": 0.0005321502685546875,
|
| 922 |
+
"learning_rate": 7.472670160550848e-07,
|
| 923 |
+
"loss": 0.0293,
|
| 924 |
+
"reward": 0.36458334140479565,
|
| 925 |
+
"reward_std": 0.2087036520242691,
|
| 926 |
+
"rewards/accuracy_reward": 0.010416666977107525,
|
| 927 |
+
"rewards/format_reward": 0.3541666744276881,
|
| 928 |
+
"step": 42,
|
| 929 |
+
"w_high_ratio": 0.0,
|
| 930 |
+
"w_low_ratio": 0.03042191034182906,
|
| 931 |
+
"w_max": 1.318351686000824,
|
| 932 |
+
"w_mean": 1.0878586322069168,
|
| 933 |
+
"w_min": 0.25,
|
| 934 |
+
"w_std": 0.1288738138973713
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"completion_length": 3391.8333740234375,
|
| 938 |
+
"cov_mean": 1.0224231118627358e-05,
|
| 939 |
+
"cov_std": 0.3281352184712887,
|
| 940 |
+
"entropy": 0.421875,
|
| 941 |
+
"epoch": 0.04914285714285714,
|
| 942 |
+
"grad_norm": 0.3027113378047943,
|
| 943 |
+
"kl": 0.0014162063598632812,
|
| 944 |
+
"learning_rate": 7.330314893841101e-07,
|
| 945 |
+
"loss": 0.0293,
|
| 946 |
+
"reward": 0.4479166716337204,
|
| 947 |
+
"reward_std": 0.4176873341202736,
|
| 948 |
+
"rewards/accuracy_reward": 0.18750000558793545,
|
| 949 |
+
"rewards/format_reward": 0.2604166716337204,
|
| 950 |
+
"step": 43,
|
| 951 |
+
"w_high_ratio": 0.0,
|
| 952 |
+
"w_low_ratio": 0.0375382611528039,
|
| 953 |
+
"w_max": 1.406785786151886,
|
| 954 |
+
"w_mean": 1.0772785246372223,
|
| 955 |
+
"w_min": 0.0,
|
| 956 |
+
"w_std": 0.17778386548161507
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"completion_length": 2956.250030517578,
|
| 960 |
+
"cov_mean": -4.8457440243510064e-05,
|
| 961 |
+
"cov_std": 0.4899379573762417,
|
| 962 |
+
"entropy": 0.3984375,
|
| 963 |
+
"epoch": 0.05028571428571429,
|
| 964 |
+
"grad_norm": 0.4807187020778656,
|
| 965 |
+
"kl": 0.001889944076538086,
|
| 966 |
+
"learning_rate": 7.185729670371604e-07,
|
| 967 |
+
"loss": 0.0382,
|
| 968 |
+
"reward": 0.7395833684131503,
|
| 969 |
+
"reward_std": 0.4934317544102669,
|
| 970 |
+
"rewards/accuracy_reward": 0.2395833432674408,
|
| 971 |
+
"rewards/format_reward": 0.5000000176951289,
|
| 972 |
+
"step": 44,
|
| 973 |
+
"w_high_ratio": 0.09932601824402809,
|
| 974 |
+
"w_low_ratio": 0.052049466874450445,
|
| 975 |
+
"w_max": 2.26826411485672,
|
| 976 |
+
"w_mean": 1.3322851359844208,
|
| 977 |
+
"w_min": 0.0,
|
| 978 |
+
"w_std": 0.30705559998750687
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"completion_length": 3707.854248046875,
|
| 982 |
+
"cov_mean": -4.304830235923873e-05,
|
| 983 |
+
"cov_std": 0.290540874004364,
|
| 984 |
+
"entropy": 0.4033203125,
|
| 985 |
+
"epoch": 0.05142857142857143,
|
| 986 |
+
"grad_norm": 0.16171735525131226,
|
| 987 |
+
"kl": 0.002239227294921875,
|
| 988 |
+
"learning_rate": 7.039090644965509e-07,
|
| 989 |
+
"loss": 0.0065,
|
| 990 |
+
"reward": 0.5000000279396772,
|
| 991 |
+
"reward_std": 0.4716969132423401,
|
| 992 |
+
"rewards/accuracy_reward": 0.21875000279396772,
|
| 993 |
+
"rewards/format_reward": 0.2812500102445483,
|
| 994 |
+
"step": 45,
|
| 995 |
+
"w_high_ratio": 0.0,
|
| 996 |
+
"w_low_ratio": 0.03661782294511795,
|
| 997 |
+
"w_max": 1.3389239609241486,
|
| 998 |
+
"w_mean": 1.0591736733913422,
|
| 999 |
+
"w_min": 0.0,
|
| 1000 |
+
"w_std": 0.1518448255956173
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"completion_length": 3539.2188110351562,
|
| 1004 |
+
"cov_mean": 0.00013026446868025232,
|
| 1005 |
+
"cov_std": 0.34402996301651,
|
| 1006 |
+
"entropy": 0.5166015625,
|
| 1007 |
+
"epoch": 0.052571428571428575,
|
| 1008 |
+
"grad_norm": 0.28467056155204773,
|
| 1009 |
+
"kl": 0.0012564659118652344,
|
| 1010 |
+
"learning_rate": 6.890576474687263e-07,
|
| 1011 |
+
"loss": 0.0542,
|
| 1012 |
+
"reward": 0.2395833395421505,
|
| 1013 |
+
"reward_std": 0.31017982587218285,
|
| 1014 |
+
"rewards/accuracy_reward": 0.041666666977107525,
|
| 1015 |
+
"rewards/format_reward": 0.1979166716337204,
|
| 1016 |
+
"step": 46,
|
| 1017 |
+
"w_high_ratio": 0.038347791880369186,
|
| 1018 |
+
"w_low_ratio": 0.04659654130227864,
|
| 1019 |
+
"w_max": 1.562936246395111,
|
| 1020 |
+
"w_mean": 1.0923520624637604,
|
| 1021 |
+
"w_min": 6.825020352992891e-31,
|
| 1022 |
+
"w_std": 0.19784706830978394
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"completion_length": 3168.5313110351562,
|
| 1026 |
+
"cov_mean": -1.4116008060227614e-05,
|
| 1027 |
+
"cov_std": 0.3409600518643856,
|
| 1028 |
+
"entropy": 0.4072265625,
|
| 1029 |
+
"epoch": 0.053714285714285714,
|
| 1030 |
+
"grad_norm": 0.21553435921669006,
|
| 1031 |
+
"kl": 0.0014462471008300781,
|
| 1032 |
+
"learning_rate": 6.740368101176495e-07,
|
| 1033 |
+
"loss": 0.0063,
|
| 1034 |
+
"reward": 0.7083333432674408,
|
| 1035 |
+
"reward_std": 0.505032941699028,
|
| 1036 |
+
"rewards/accuracy_reward": 0.28125,
|
| 1037 |
+
"rewards/format_reward": 0.4270833358168602,
|
| 1038 |
+
"step": 47,
|
| 1039 |
+
"w_high_ratio": 0.1824447140097618,
|
| 1040 |
+
"w_low_ratio": 0.0349124651402235,
|
| 1041 |
+
"w_max": 1.8283918797969818,
|
| 1042 |
+
"w_mean": 1.3520298600196838,
|
| 1043 |
+
"w_min": 0.25,
|
| 1044 |
+
"w_std": 0.17590370774269104
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"completion_length": 3045.5209350585938,
|
| 1048 |
+
"cov_mean": 1.4324002222565468e-05,
|
| 1049 |
+
"cov_std": 0.41333913803100586,
|
| 1050 |
+
"entropy": 0.40966796875,
|
| 1051 |
+
"epoch": 0.054857142857142854,
|
| 1052 |
+
"grad_norm": 0.514603316783905,
|
| 1053 |
+
"kl": 0.0032389163970947266,
|
| 1054 |
+
"learning_rate": 6.588648530198504e-07,
|
| 1055 |
+
"loss": -0.0291,
|
| 1056 |
+
"reward": 0.5729166902601719,
|
| 1057 |
+
"reward_std": 0.4265441298484802,
|
| 1058 |
+
"rewards/accuracy_reward": 0.20833334419876337,
|
| 1059 |
+
"rewards/format_reward": 0.3645833460614085,
|
| 1060 |
+
"step": 48,
|
| 1061 |
+
"w_high_ratio": 0.14455852285027504,
|
| 1062 |
+
"w_low_ratio": 0.04336892580613494,
|
| 1063 |
+
"w_max": 2.106689363718033,
|
| 1064 |
+
"w_mean": 1.3398694097995758,
|
| 1065 |
+
"w_min": 0.0,
|
| 1066 |
+
"w_std": 0.29295507818460464
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"completion_length": 2561.3646850585938,
|
| 1070 |
+
"cov_mean": -5.681005814039963e-05,
|
| 1071 |
+
"cov_std": 0.3279518857598305,
|
| 1072 |
+
"entropy": 0.36865234375,
|
| 1073 |
+
"epoch": 0.056,
|
| 1074 |
+
"grad_norm": 0.25349730253219604,
|
| 1075 |
+
"kl": 0.0052852630615234375,
|
| 1076 |
+
"learning_rate": 6.435602608679916e-07,
|
| 1077 |
+
"loss": 0.0033,
|
| 1078 |
+
"reward": 0.833333358168602,
|
| 1079 |
+
"reward_std": 0.46440815925598145,
|
| 1080 |
+
"rewards/accuracy_reward": 0.21875001303851604,
|
| 1081 |
+
"rewards/format_reward": 0.6145833432674408,
|
| 1082 |
+
"step": 49,
|
| 1083 |
+
"w_high_ratio": 0.02398517169058323,
|
| 1084 |
+
"w_low_ratio": 0.04019799269735813,
|
| 1085 |
+
"w_max": 1.7071016132831573,
|
| 1086 |
+
"w_mean": 1.2629328966140747,
|
| 1087 |
+
"w_min": 0.25,
|
| 1088 |
+
"w_std": 0.19682494550943375
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"completion_length": 3245.2083740234375,
|
| 1092 |
+
"cov_mean": 4.621147024863603e-05,
|
| 1093 |
+
"cov_std": 0.35216138139367104,
|
| 1094 |
+
"entropy": 0.35205078125,
|
| 1095 |
+
"epoch": 0.05714285714285714,
|
| 1096 |
+
"grad_norm": 0.20161262154579163,
|
| 1097 |
+
"kl": 0.0010981559753417969,
|
| 1098 |
+
"learning_rate": 6.281416799501187e-07,
|
| 1099 |
+
"loss": 0.014,
|
| 1100 |
+
"reward": 0.6354166967794299,
|
| 1101 |
+
"reward_std": 0.420846089720726,
|
| 1102 |
+
"rewards/accuracy_reward": 0.2812500149011612,
|
| 1103 |
+
"rewards/format_reward": 0.3541666818782687,
|
| 1104 |
+
"step": 50,
|
| 1105 |
+
"w_high_ratio": 0.0,
|
| 1106 |
+
"w_low_ratio": 0.042036826722323895,
|
| 1107 |
+
"w_max": 1.5023921430110931,
|
| 1108 |
+
"w_mean": 1.146658033132553,
|
| 1109 |
+
"w_min": 0.0,
|
| 1110 |
+
"w_std": 0.206118730828166
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"completion_length": 2383.6980590820312,
|
| 1114 |
+
"cov_mean": -2.697939362406032e-05,
|
| 1115 |
+
"cov_std": 0.38119756057858467,
|
| 1116 |
+
"entropy": 0.42822265625,
|
| 1117 |
+
"epoch": 0.05828571428571429,
|
| 1118 |
+
"grad_norm": 0.4689660966396332,
|
| 1119 |
+
"kl": 0.0037221908569335938,
|
| 1120 |
+
"learning_rate": 6.126278954320294e-07,
|
| 1121 |
+
"loss": 0.011,
|
| 1122 |
+
"reward": 0.7604166865348816,
|
| 1123 |
+
"reward_std": 0.39414726570248604,
|
| 1124 |
+
"rewards/accuracy_reward": 0.20833333861082792,
|
| 1125 |
+
"rewards/format_reward": 0.5520833432674408,
|
| 1126 |
+
"step": 51,
|
| 1127 |
+
"w_high_ratio": 0.0406239777803421,
|
| 1128 |
+
"w_low_ratio": 0.04253132501617074,
|
| 1129 |
+
"w_max": 1.5954174101352692,
|
| 1130 |
+
"w_mean": 1.217557042837143,
|
| 1131 |
+
"w_min": 0.0,
|
| 1132 |
+
"w_std": 0.24302981421351433
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"completion_length": 3188.3021240234375,
|
| 1136 |
+
"cov_mean": -1.9340616745466832e-05,
|
| 1137 |
+
"cov_std": 0.42421338707208633,
|
| 1138 |
+
"entropy": 0.41259765625,
|
| 1139 |
+
"epoch": 0.05942857142857143,
|
| 1140 |
+
"grad_norm": 0.43333640694618225,
|
| 1141 |
+
"kl": 0.0021028518676757812,
|
| 1142 |
+
"learning_rate": 5.97037808470444e-07,
|
| 1143 |
+
"loss": -0.0265,
|
| 1144 |
+
"reward": 0.7500000298023224,
|
| 1145 |
+
"reward_std": 0.56574647128582,
|
| 1146 |
+
"rewards/accuracy_reward": 0.3229166716337204,
|
| 1147 |
+
"rewards/format_reward": 0.4270833507180214,
|
| 1148 |
+
"step": 52,
|
| 1149 |
+
"w_high_ratio": 0.0,
|
| 1150 |
+
"w_low_ratio": 0.04618662968277931,
|
| 1151 |
+
"w_max": 1.4080191552639008,
|
| 1152 |
+
"w_mean": 1.1331122517585754,
|
| 1153 |
+
"w_min": 0.25,
|
| 1154 |
+
"w_std": 0.21432508528232574
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"completion_length": 2943.291748046875,
|
| 1158 |
+
"cov_mean": 1.8985145061378716e-05,
|
| 1159 |
+
"cov_std": 0.42384568601846695,
|
| 1160 |
+
"entropy": 0.41259765625,
|
| 1161 |
+
"epoch": 0.060571428571428575,
|
| 1162 |
+
"grad_norm": 0.28105950355529785,
|
| 1163 |
+
"kl": 0.001844644546508789,
|
| 1164 |
+
"learning_rate": 5.813904131848564e-07,
|
| 1165 |
+
"loss": 0.0064,
|
| 1166 |
+
"reward": 0.895833358168602,
|
| 1167 |
+
"reward_std": 0.5318989902734756,
|
| 1168 |
+
"rewards/accuracy_reward": 0.30208334885537624,
|
| 1169 |
+
"rewards/format_reward": 0.5937500149011612,
|
| 1170 |
+
"step": 53,
|
| 1171 |
+
"w_high_ratio": 0.0625,
|
| 1172 |
+
"w_low_ratio": 0.04191893618553877,
|
| 1173 |
+
"w_max": 1.6293854713439941,
|
| 1174 |
+
"w_mean": 1.2208082973957062,
|
| 1175 |
+
"w_min": 0.25,
|
| 1176 |
+
"w_std": 0.20713179931044579
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"completion_length": 3035.8438110351562,
|
| 1180 |
+
"cov_mean": 6.566583215317223e-05,
|
| 1181 |
+
"cov_std": 0.39858507737517357,
|
| 1182 |
+
"entropy": 0.3798828125,
|
| 1183 |
+
"epoch": 0.061714285714285715,
|
| 1184 |
+
"grad_norm": 0.38175392150878906,
|
| 1185 |
+
"kl": 0.0011749267578125,
|
| 1186 |
+
"learning_rate": 5.657047735161255e-07,
|
| 1187 |
+
"loss": -0.0521,
|
| 1188 |
+
"reward": 0.9791667088866234,
|
| 1189 |
+
"reward_std": 0.5917666852474213,
|
| 1190 |
+
"rewards/accuracy_reward": 0.42708334885537624,
|
| 1191 |
+
"rewards/format_reward": 0.552083358168602,
|
| 1192 |
+
"step": 54,
|
| 1193 |
+
"w_high_ratio": 0.044216301292181015,
|
| 1194 |
+
"w_low_ratio": 0.03513730876147747,
|
| 1195 |
+
"w_max": 1.7533048391342163,
|
| 1196 |
+
"w_mean": 1.3249602317810059,
|
| 1197 |
+
"w_min": 0.0,
|
| 1198 |
+
"w_std": 0.22004129365086555
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"completion_length": 3354.666748046875,
|
| 1202 |
+
"cov_mean": -3.56279870175058e-05,
|
| 1203 |
+
"cov_std": 0.30405301228165627,
|
| 1204 |
+
"entropy": 0.419921875,
|
| 1205 |
+
"epoch": 0.06285714285714286,
|
| 1206 |
+
"grad_norm": 0.3018040060997009,
|
| 1207 |
+
"kl": 0.0012395381927490234,
|
| 1208 |
+
"learning_rate": 5.5e-07,
|
| 1209 |
+
"loss": -0.0185,
|
| 1210 |
+
"reward": 0.5208333469927311,
|
| 1211 |
+
"reward_std": 0.3702617585659027,
|
| 1212 |
+
"rewards/accuracy_reward": 0.1979166716337204,
|
| 1213 |
+
"rewards/format_reward": 0.3229166679084301,
|
| 1214 |
+
"step": 55,
|
| 1215 |
+
"w_high_ratio": 0.0,
|
| 1216 |
+
"w_low_ratio": 0.03356400621123612,
|
| 1217 |
+
"w_max": 1.4872715771198273,
|
| 1218 |
+
"w_mean": 1.1252524256706238,
|
| 1219 |
+
"w_min": 0.0,
|
| 1220 |
+
"w_std": 0.17813249677419662
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"completion_length": 3199.7188720703125,
|
| 1224 |
+
"cov_mean": -1.4941413155611372e-05,
|
| 1225 |
+
"cov_std": 0.25671473518013954,
|
| 1226 |
+
"entropy": 0.40185546875,
|
| 1227 |
+
"epoch": 0.064,
|
| 1228 |
+
"grad_norm": 0.21876569092273712,
|
| 1229 |
+
"kl": 0.0006089210510253906,
|
| 1230 |
+
"learning_rate": 5.342952264838747e-07,
|
| 1231 |
+
"loss": -0.0325,
|
| 1232 |
+
"reward": 0.6458333395421505,
|
| 1233 |
+
"reward_std": 0.27983931452035904,
|
| 1234 |
+
"rewards/accuracy_reward": 0.1979166716337204,
|
| 1235 |
+
"rewards/format_reward": 0.4479166828095913,
|
| 1236 |
+
"step": 56,
|
| 1237 |
+
"w_high_ratio": 0.0,
|
| 1238 |
+
"w_low_ratio": 0.028304541716352105,
|
| 1239 |
+
"w_max": 1.453190177679062,
|
| 1240 |
+
"w_mean": 1.1167612671852112,
|
| 1241 |
+
"w_min": 1.400437147815929e-36,
|
| 1242 |
+
"w_std": 0.14085076563060284
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"completion_length": 3545.4271850585938,
|
| 1246 |
+
"cov_mean": 1.6042108654801268e-05,
|
| 1247 |
+
"cov_std": 0.19959648326039314,
|
| 1248 |
+
"entropy": 0.31787109375,
|
| 1249 |
+
"epoch": 0.06514285714285714,
|
| 1250 |
+
"grad_norm": 0.15603993833065033,
|
| 1251 |
+
"kl": 0.0003676414489746094,
|
| 1252 |
+
"learning_rate": 5.186095868151436e-07,
|
| 1253 |
+
"loss": 0.0067,
|
| 1254 |
+
"reward": 0.4270833395421505,
|
| 1255 |
+
"reward_std": 0.26762784644961357,
|
| 1256 |
+
"rewards/accuracy_reward": 0.13541667256504297,
|
| 1257 |
+
"rewards/format_reward": 0.29166667722165585,
|
| 1258 |
+
"step": 57,
|
| 1259 |
+
"w_high_ratio": 0.0,
|
| 1260 |
+
"w_low_ratio": 0.028780631721019745,
|
| 1261 |
+
"w_max": 1.3290077447891235,
|
| 1262 |
+
"w_mean": 1.1172043681144714,
|
| 1263 |
+
"w_min": 0.25,
|
| 1264 |
+
"w_std": 0.12668126448988914
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"completion_length": 2554.1458740234375,
|
| 1268 |
+
"cov_mean": -8.6602381998091e-05,
|
| 1269 |
+
"cov_std": 0.4178408235311508,
|
| 1270 |
+
"entropy": 0.333740234375,
|
| 1271 |
+
"epoch": 0.06628571428571428,
|
| 1272 |
+
"grad_norm": 0.4292741119861603,
|
| 1273 |
+
"kl": 0.0062389373779296875,
|
| 1274 |
+
"learning_rate": 5.02962191529556e-07,
|
| 1275 |
+
"loss": -0.045,
|
| 1276 |
+
"reward": 0.9375000447034836,
|
| 1277 |
+
"reward_std": 0.5022420063614845,
|
| 1278 |
+
"rewards/accuracy_reward": 0.28125000558793545,
|
| 1279 |
+
"rewards/format_reward": 0.6562500223517418,
|
| 1280 |
+
"step": 58,
|
| 1281 |
+
"w_high_ratio": 0.08225274085998535,
|
| 1282 |
+
"w_low_ratio": 0.038829353637993336,
|
| 1283 |
+
"w_max": 1.8886817693710327,
|
| 1284 |
+
"w_mean": 1.3429239392280579,
|
| 1285 |
+
"w_min": 0.0,
|
| 1286 |
+
"w_std": 0.24752679839730263
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"completion_length": 3169.0625610351562,
|
| 1290 |
+
"cov_mean": 4.032192100567045e-05,
|
| 1291 |
+
"cov_std": 0.30262381583452225,
|
| 1292 |
+
"entropy": 0.34619140625,
|
| 1293 |
+
"epoch": 0.06742857142857143,
|
| 1294 |
+
"grad_norm": 0.38411930203437805,
|
| 1295 |
+
"kl": 0.0004928112030029297,
|
| 1296 |
+
"learning_rate": 4.873721045679706e-07,
|
| 1297 |
+
"loss": 0.0209,
|
| 1298 |
+
"reward": 0.5000000102445483,
|
| 1299 |
+
"reward_std": 0.27465011551976204,
|
| 1300 |
+
"rewards/accuracy_reward": 0.1770833358168602,
|
| 1301 |
+
"rewards/format_reward": 0.3229166669771075,
|
| 1302 |
+
"step": 59,
|
| 1303 |
+
"w_high_ratio": 0.15833117440342903,
|
| 1304 |
+
"w_low_ratio": 0.027412693481892347,
|
| 1305 |
+
"w_max": 2.2743676006793976,
|
| 1306 |
+
"w_mean": 1.3636261224746704,
|
| 1307 |
+
"w_min": 0.25,
|
| 1308 |
+
"w_std": 0.22530828416347504
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"completion_length": 3205.885498046875,
|
| 1312 |
+
"cov_mean": 5.204351282372954e-06,
|
| 1313 |
+
"cov_std": 0.21868624165654182,
|
| 1314 |
+
"entropy": 0.35986328125,
|
| 1315 |
+
"epoch": 0.06857142857142857,
|
| 1316 |
+
"grad_norm": 0.2159898579120636,
|
| 1317 |
+
"kl": 0.0013399124145507812,
|
| 1318 |
+
"learning_rate": 4.7185832004988133e-07,
|
| 1319 |
+
"loss": 0.0012,
|
| 1320 |
+
"reward": 0.552083358168602,
|
| 1321 |
+
"reward_std": 0.3438131511211395,
|
| 1322 |
+
"rewards/accuracy_reward": 0.13541667070239782,
|
| 1323 |
+
"rewards/format_reward": 0.416666679084301,
|
| 1324 |
+
"step": 60,
|
| 1325 |
+
"w_high_ratio": 0.0,
|
| 1326 |
+
"w_low_ratio": 0.0294471038505435,
|
| 1327 |
+
"w_max": 1.4707800149917603,
|
| 1328 |
+
"w_mean": 1.1660968363285065,
|
| 1329 |
+
"w_min": 0.25,
|
| 1330 |
+
"w_std": 0.13705550134181976
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"completion_length": 3322.7084350585938,
|
| 1334 |
+
"cov_mean": 3.926075260096695e-05,
|
| 1335 |
+
"cov_std": 0.3601963371038437,
|
| 1336 |
+
"entropy": 0.3564453125,
|
| 1337 |
+
"epoch": 0.06971428571428571,
|
| 1338 |
+
"grad_norm": 0.39628517627716064,
|
| 1339 |
+
"kl": 0.0009188652038574219,
|
| 1340 |
+
"learning_rate": 4.5643973913200837e-07,
|
| 1341 |
+
"loss": -0.0714,
|
| 1342 |
+
"reward": 0.5833333414047956,
|
| 1343 |
+
"reward_std": 0.515319935977459,
|
| 1344 |
+
"rewards/accuracy_reward": 0.1666666716337204,
|
| 1345 |
+
"rewards/format_reward": 0.41666666977107525,
|
| 1346 |
+
"step": 61,
|
| 1347 |
+
"w_high_ratio": 0.03236403688788414,
|
| 1348 |
+
"w_low_ratio": 0.03914234112016857,
|
| 1349 |
+
"w_max": 1.7150523364543915,
|
| 1350 |
+
"w_mean": 1.2098670601844788,
|
| 1351 |
+
"w_min": 0.0,
|
| 1352 |
+
"w_std": 0.2282575462013483
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"completion_length": 3006.885498046875,
|
| 1356 |
+
"cov_mean": 2.1906609163124813e-05,
|
| 1357 |
+
"cov_std": 0.46718820184469223,
|
| 1358 |
+
"entropy": 0.33935546875,
|
| 1359 |
+
"epoch": 0.07085714285714285,
|
| 1360 |
+
"grad_norm": 0.30309396982192993,
|
| 1361 |
+
"kl": 0.0017642974853515625,
|
| 1362 |
+
"learning_rate": 4.4113514698014953e-07,
|
| 1363 |
+
"loss": -0.035,
|
| 1364 |
+
"reward": 0.8229167014360428,
|
| 1365 |
+
"reward_std": 0.6976551413536072,
|
| 1366 |
+
"rewards/accuracy_reward": 0.27083334140479565,
|
| 1367 |
+
"rewards/format_reward": 0.5520833432674408,
|
| 1368 |
+
"step": 62,
|
| 1369 |
+
"w_high_ratio": 0.0,
|
| 1370 |
+
"w_low_ratio": 0.05965683329850435,
|
| 1371 |
+
"w_max": 1.593172937631607,
|
| 1372 |
+
"w_mean": 1.1934809386730194,
|
| 1373 |
+
"w_min": 1.0754965713692971e-43,
|
| 1374 |
+
"w_std": 0.28461313247680664
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"completion_length": 2580.229248046875,
|
| 1378 |
+
"cov_mean": 5.573407906922512e-05,
|
| 1379 |
+
"cov_std": 0.3945640027523041,
|
| 1380 |
+
"entropy": 0.39111328125,
|
| 1381 |
+
"epoch": 0.072,
|
| 1382 |
+
"grad_norm": 0.45718619227409363,
|
| 1383 |
+
"kl": 0.001735687255859375,
|
| 1384 |
+
"learning_rate": 4.2596318988235037e-07,
|
| 1385 |
+
"loss": -0.0807,
|
| 1386 |
+
"reward": 0.958333358168602,
|
| 1387 |
+
"reward_std": 0.5150914192199707,
|
| 1388 |
+
"rewards/accuracy_reward": 0.31250001303851604,
|
| 1389 |
+
"rewards/format_reward": 0.6458333432674408,
|
| 1390 |
+
"step": 63,
|
| 1391 |
+
"w_high_ratio": 0.08918174356222153,
|
| 1392 |
+
"w_low_ratio": 0.03547394182533026,
|
| 1393 |
+
"w_max": 2.0218554735183716,
|
| 1394 |
+
"w_mean": 1.3539214432239532,
|
| 1395 |
+
"w_min": 0.0,
|
| 1396 |
+
"w_std": 0.23917281255126
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"completion_length": 3340.0313110351562,
|
| 1400 |
+
"cov_mean": 7.548666690126993e-05,
|
| 1401 |
+
"cov_std": 0.31813300400972366,
|
| 1402 |
+
"entropy": 0.4248046875,
|
| 1403 |
+
"epoch": 0.07314285714285715,
|
| 1404 |
+
"grad_norm": 0.5389249920845032,
|
| 1405 |
+
"kl": 0.0018744468688964844,
|
| 1406 |
+
"learning_rate": 4.1094235253127374e-07,
|
| 1407 |
+
"loss": -0.0757,
|
| 1408 |
+
"reward": 0.5104166865348816,
|
| 1409 |
+
"reward_std": 0.4255366772413254,
|
| 1410 |
+
"rewards/accuracy_reward": 0.1979166753590107,
|
| 1411 |
+
"rewards/format_reward": 0.3125000074505806,
|
| 1412 |
+
"step": 64,
|
| 1413 |
+
"w_high_ratio": 0.15633241832256317,
|
| 1414 |
+
"w_low_ratio": 0.0320257218554616,
|
| 1415 |
+
"w_max": 1.8200311660766602,
|
| 1416 |
+
"w_mean": 1.3009037971496582,
|
| 1417 |
+
"w_min": 0.25,
|
| 1418 |
+
"w_std": 0.21954189240932465
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"completion_length": 2969.541748046875,
|
| 1422 |
+
"cov_mean": -2.4962878342194017e-05,
|
| 1423 |
+
"cov_std": 0.2727944627404213,
|
| 1424 |
+
"entropy": 0.353759765625,
|
| 1425 |
+
"epoch": 0.07428571428571429,
|
| 1426 |
+
"grad_norm": 0.2332458198070526,
|
| 1427 |
+
"kl": 0.0015840530395507812,
|
| 1428 |
+
"learning_rate": 3.9609093550344907e-07,
|
| 1429 |
+
"loss": 0.012,
|
| 1430 |
+
"reward": 0.666666679084301,
|
| 1431 |
+
"reward_std": 0.357291292399168,
|
| 1432 |
+
"rewards/accuracy_reward": 0.2083333358168602,
|
| 1433 |
+
"rewards/format_reward": 0.4583333432674408,
|
| 1434 |
+
"step": 65,
|
| 1435 |
+
"w_high_ratio": 0.0,
|
| 1436 |
+
"w_low_ratio": 0.03699250426143408,
|
| 1437 |
+
"w_max": 1.5260689854621887,
|
| 1438 |
+
"w_mean": 1.164745956659317,
|
| 1439 |
+
"w_min": 1.0748096548620851e-35,
|
| 1440 |
+
"w_std": 0.14831626787781715
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"completion_length": 2311.2709197998047,
|
| 1444 |
+
"cov_mean": 2.157548601644521e-05,
|
| 1445 |
+
"cov_std": 0.23550356552004814,
|
| 1446 |
+
"entropy": 0.31787109375,
|
| 1447 |
+
"epoch": 0.07542857142857143,
|
| 1448 |
+
"grad_norm": 0.5557933449745178,
|
| 1449 |
+
"kl": 0.0011758804321289062,
|
| 1450 |
+
"learning_rate": 3.8142703296283953e-07,
|
| 1451 |
+
"loss": -0.0116,
|
| 1452 |
+
"reward": 0.9062500260770321,
|
| 1453 |
+
"reward_std": 0.29818330332636833,
|
| 1454 |
+
"rewards/accuracy_reward": 0.38541667722165585,
|
| 1455 |
+
"rewards/format_reward": 0.520833333954215,
|
| 1456 |
+
"step": 66,
|
| 1457 |
+
"w_high_ratio": 0.10277381911873817,
|
| 1458 |
+
"w_low_ratio": 0.03059569653123617,
|
| 1459 |
+
"w_max": 1.97393798828125,
|
| 1460 |
+
"w_mean": 1.278551459312439,
|
| 1461 |
+
"w_min": 0.0,
|
| 1462 |
+
"w_std": 0.20061488449573517
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"completion_length": 3726.135498046875,
|
| 1466 |
+
"cov_mean": 8.957304089562967e-07,
|
| 1467 |
+
"cov_std": 0.12987565249204636,
|
| 1468 |
+
"entropy": 0.35205078125,
|
| 1469 |
+
"epoch": 0.07657142857142857,
|
| 1470 |
+
"grad_norm": 0.11042757332324982,
|
| 1471 |
+
"kl": 0.0013402700424194336,
|
| 1472 |
+
"learning_rate": 3.6696851061588994e-07,
|
| 1473 |
+
"loss": -0.0059,
|
| 1474 |
+
"reward": 0.1770833358168602,
|
| 1475 |
+
"reward_std": 0.15668470412492752,
|
| 1476 |
+
"rewards/accuracy_reward": 0.03125,
|
| 1477 |
+
"rewards/format_reward": 0.1458333358168602,
|
| 1478 |
+
"step": 67,
|
| 1479 |
+
"w_high_ratio": 0.0,
|
| 1480 |
+
"w_low_ratio": 0.01588357798755169,
|
| 1481 |
+
"w_max": 1.2971015870571136,
|
| 1482 |
+
"w_mean": 1.0769366472959518,
|
| 1483 |
+
"w_min": 0.5,
|
| 1484 |
+
"w_std": 0.08244858682155609
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"completion_length": 2420.979232788086,
|
| 1488 |
+
"cov_mean": 1.4521759112540167e-05,
|
| 1489 |
+
"cov_std": 0.2692869156599045,
|
| 1490 |
+
"entropy": 0.37353515625,
|
| 1491 |
+
"epoch": 0.07771428571428571,
|
| 1492 |
+
"grad_norm": 0.3267475962638855,
|
| 1493 |
+
"kl": 0.0064449310302734375,
|
| 1494 |
+
"learning_rate": 3.5273298394491515e-07,
|
| 1495 |
+
"loss": -0.0214,
|
| 1496 |
+
"reward": 0.822916679084301,
|
| 1497 |
+
"reward_std": 0.39656912535429,
|
| 1498 |
+
"rewards/accuracy_reward": 0.2187500074505806,
|
| 1499 |
+
"rewards/format_reward": 0.6041666716337204,
|
| 1500 |
+
"step": 68,
|
| 1501 |
+
"w_high_ratio": 0.028063589707016945,
|
| 1502 |
+
"w_low_ratio": 0.029913824051618576,
|
| 1503 |
+
"w_max": 1.8040810525417328,
|
| 1504 |
+
"w_mean": 1.316351056098938,
|
| 1505 |
+
"w_min": 0.25,
|
| 1506 |
+
"w_std": 0.17742961645126343
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"completion_length": 2790.5730590820312,
|
| 1510 |
+
"cov_mean": 3.09187362290686e-05,
|
| 1511 |
+
"cov_std": 0.42568420618772507,
|
| 1512 |
+
"entropy": 0.4453125,
|
| 1513 |
+
"epoch": 0.07885714285714286,
|
| 1514 |
+
"grad_norm": 0.7317398190498352,
|
| 1515 |
+
"kl": 0.006710052490234375,
|
| 1516 |
+
"learning_rate": 3.387377967463493e-07,
|
| 1517 |
+
"loss": -0.0192,
|
| 1518 |
+
"reward": 0.4895833358168602,
|
| 1519 |
+
"reward_std": 0.41857269406318665,
|
| 1520 |
+
"rewards/accuracy_reward": 0.08333333674818277,
|
| 1521 |
+
"rewards/format_reward": 0.4062500074505806,
|
| 1522 |
+
"step": 69,
|
| 1523 |
+
"w_high_ratio": 0.19593259878456593,
|
| 1524 |
+
"w_low_ratio": 0.036022237967699766,
|
| 1525 |
+
"w_max": 3.16190242767334,
|
| 1526 |
+
"w_mean": 1.5170519053936005,
|
| 1527 |
+
"w_min": 0.0,
|
| 1528 |
+
"w_std": 0.3000602051615715
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"completion_length": 3255.7709350585938,
|
| 1532 |
+
"cov_mean": -6.321061573544284e-05,
|
| 1533 |
+
"cov_std": 0.31040842086076736,
|
| 1534 |
+
"entropy": 0.34765625,
|
| 1535 |
+
"epoch": 0.08,
|
| 1536 |
+
"grad_norm": 0.2253309190273285,
|
| 1537 |
+
"kl": 0.0019707679748535156,
|
| 1538 |
+
"learning_rate": 3.250000000000001e-07,
|
| 1539 |
+
"loss": 0.038,
|
| 1540 |
+
"reward": 0.5104166679084301,
|
| 1541 |
+
"reward_std": 0.3943600133061409,
|
| 1542 |
+
"rewards/accuracy_reward": 0.09375000093132257,
|
| 1543 |
+
"rewards/format_reward": 0.4166666716337204,
|
| 1544 |
+
"step": 70,
|
| 1545 |
+
"w_high_ratio": 0.0,
|
| 1546 |
+
"w_low_ratio": 0.04103634599596262,
|
| 1547 |
+
"w_max": 1.2795763909816742,
|
| 1548 |
+
"w_mean": 1.0765459537506104,
|
| 1549 |
+
"w_min": 0.0,
|
| 1550 |
+
"w_std": 0.15424982458353043
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"completion_length": 2893.093795776367,
|
| 1554 |
+
"cov_mean": -5.907902482249483e-05,
|
| 1555 |
+
"cov_std": 0.28848100267350674,
|
| 1556 |
+
"entropy": 0.39111328125,
|
| 1557 |
+
"epoch": 0.08114285714285714,
|
| 1558 |
+
"grad_norm": 0.4800524115562439,
|
| 1559 |
+
"kl": 0.0017595291137695312,
|
| 1560 |
+
"learning_rate": 3.115363310950578e-07,
|
| 1561 |
+
"loss": 0.0284,
|
| 1562 |
+
"reward": 0.562500030733645,
|
| 1563 |
+
"reward_std": 0.3276159390807152,
|
| 1564 |
+
"rewards/accuracy_reward": 0.18750000651925802,
|
| 1565 |
+
"rewards/format_reward": 0.37500000558793545,
|
| 1566 |
+
"step": 71,
|
| 1567 |
+
"w_high_ratio": 0.07317740470170975,
|
| 1568 |
+
"w_low_ratio": 0.03526141308248043,
|
| 1569 |
+
"w_max": 2.095757156610489,
|
| 1570 |
+
"w_mean": 1.278771072626114,
|
| 1571 |
+
"w_min": 4.3955273748636295e-36,
|
| 1572 |
+
"w_std": 0.23910818807780743
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"completion_length": 3460.354248046875,
|
| 1576 |
+
"cov_mean": 6.12462517892709e-05,
|
| 1577 |
+
"cov_std": 0.36787012219429016,
|
| 1578 |
+
"entropy": 0.4931640625,
|
| 1579 |
+
"epoch": 0.08228571428571428,
|
| 1580 |
+
"grad_norm": 0.39541420340538025,
|
| 1581 |
+
"kl": 0.0038938522338867188,
|
| 1582 |
+
"learning_rate": 2.9836319343816397e-07,
|
| 1583 |
+
"loss": -0.0245,
|
| 1584 |
+
"reward": 0.3333333469927311,
|
| 1585 |
+
"reward_std": 0.4593120887875557,
|
| 1586 |
+
"rewards/accuracy_reward": 0.06250000093132257,
|
| 1587 |
+
"rewards/format_reward": 0.2708333395421505,
|
| 1588 |
+
"step": 72,
|
| 1589 |
+
"w_high_ratio": 0.040276188403367996,
|
| 1590 |
+
"w_low_ratio": 0.046780284494161606,
|
| 1591 |
+
"w_max": 1.6123959422111511,
|
| 1592 |
+
"w_mean": 1.1790215075016022,
|
| 1593 |
+
"w_min": 0.0,
|
| 1594 |
+
"w_std": 0.24864742159843445
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"completion_length": 3808.166748046875,
|
| 1598 |
+
"cov_mean": 2.382581669735373e-05,
|
| 1599 |
+
"cov_std": 0.26704882457852364,
|
| 1600 |
+
"entropy": 0.4677734375,
|
| 1601 |
+
"epoch": 0.08342857142857144,
|
| 1602 |
+
"grad_norm": 0.39250648021698,
|
| 1603 |
+
"kl": 0.0005078315734863281,
|
| 1604 |
+
"learning_rate": 2.854966364683872e-07,
|
| 1605 |
+
"loss": 0.0333,
|
| 1606 |
+
"reward": 0.21875001024454832,
|
| 1607 |
+
"reward_std": 0.34505901485681534,
|
| 1608 |
+
"rewards/accuracy_reward": 0.0729166679084301,
|
| 1609 |
+
"rewards/format_reward": 0.14583333488553762,
|
| 1610 |
+
"step": 73,
|
| 1611 |
+
"w_high_ratio": 0.0,
|
| 1612 |
+
"w_low_ratio": 0.031687673181295395,
|
| 1613 |
+
"w_max": 1.3024969696998596,
|
| 1614 |
+
"w_mean": 1.03611221909523,
|
| 1615 |
+
"w_min": 0.0,
|
| 1616 |
+
"w_std": 0.13818097487092018
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"completion_length": 3584.8438110351562,
|
| 1620 |
+
"cov_mean": -4.775809429702349e-05,
|
| 1621 |
+
"cov_std": 0.3642261065542698,
|
| 1622 |
+
"entropy": 0.42138671875,
|
| 1623 |
+
"epoch": 0.08457142857142858,
|
| 1624 |
+
"grad_norm": 0.22599299252033234,
|
| 1625 |
+
"kl": 0.002000570297241211,
|
| 1626 |
+
"learning_rate": 2.729523361034538e-07,
|
| 1627 |
+
"loss": 0.0465,
|
| 1628 |
+
"reward": 0.552083358168602,
|
| 1629 |
+
"reward_std": 0.47496967762708664,
|
| 1630 |
+
"rewards/accuracy_reward": 0.2604166679084301,
|
| 1631 |
+
"rewards/format_reward": 0.2916666753590107,
|
| 1632 |
+
"step": 74,
|
| 1633 |
+
"w_high_ratio": 0.0,
|
| 1634 |
+
"w_low_ratio": 0.04971347749233246,
|
| 1635 |
+
"w_max": 1.3916961252689362,
|
| 1636 |
+
"w_mean": 1.079592913389206,
|
| 1637 |
+
"w_min": 0.0,
|
| 1638 |
+
"w_std": 0.20160867273807526
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"completion_length": 3403.7188720703125,
|
| 1642 |
+
"cov_mean": 4.775901288667228e-06,
|
| 1643 |
+
"cov_std": 0.31741658970713615,
|
| 1644 |
+
"entropy": 0.39208984375,
|
| 1645 |
+
"epoch": 0.08571428571428572,
|
| 1646 |
+
"grad_norm": 0.28842759132385254,
|
| 1647 |
+
"kl": 0.002251148223876953,
|
| 1648 |
+
"learning_rate": 2.6074557564105724e-07,
|
| 1649 |
+
"loss": -0.0149,
|
| 1650 |
+
"reward": 0.5312500074505806,
|
| 1651 |
+
"reward_std": 0.3348959684371948,
|
| 1652 |
+
"rewards/accuracy_reward": 0.1770833358168602,
|
| 1653 |
+
"rewards/format_reward": 0.3541666744276881,
|
| 1654 |
+
"step": 75,
|
| 1655 |
+
"w_high_ratio": 0.05775141716003418,
|
| 1656 |
+
"w_low_ratio": 0.04404309671372175,
|
| 1657 |
+
"w_max": 1.7450213432312012,
|
| 1658 |
+
"w_mean": 1.203758329153061,
|
| 1659 |
+
"w_min": 0.25,
|
| 1660 |
+
"w_std": 0.19945883378386497
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"completion_length": 3129.885498046875,
|
| 1664 |
+
"cov_mean": 1.2703612810582854e-05,
|
| 1665 |
+
"cov_std": 0.2526189871132374,
|
| 1666 |
+
"entropy": 0.396484375,
|
| 1667 |
+
"epoch": 0.08685714285714285,
|
| 1668 |
+
"grad_norm": 0.15439313650131226,
|
| 1669 |
+
"kl": 0.0004563331604003906,
|
| 1670 |
+
"learning_rate": 2.488912271385139e-07,
|
| 1671 |
+
"loss": 0.0167,
|
| 1672 |
+
"reward": 0.572916679084301,
|
| 1673 |
+
"reward_std": 0.2542962171137333,
|
| 1674 |
+
"rewards/accuracy_reward": 0.1041666716337204,
|
| 1675 |
+
"rewards/format_reward": 0.4687500074505806,
|
| 1676 |
+
"step": 76,
|
| 1677 |
+
"w_high_ratio": 0.0,
|
| 1678 |
+
"w_low_ratio": 0.03176691988483071,
|
| 1679 |
+
"w_max": 1.4051032662391663,
|
| 1680 |
+
"w_mean": 1.1220950484275818,
|
| 1681 |
+
"w_min": 0.25,
|
| 1682 |
+
"w_std": 0.1384560540318489
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"completion_length": 3342.510498046875,
|
| 1686 |
+
"cov_mean": 4.0359717786486726e-05,
|
| 1687 |
+
"cov_std": 0.2773597203195095,
|
| 1688 |
+
"entropy": 0.3876953125,
|
| 1689 |
+
"epoch": 0.088,
|
| 1690 |
+
"grad_norm": 0.39251646399497986,
|
| 1691 |
+
"kl": 0.0005764961242675781,
|
| 1692 |
+
"learning_rate": 2.374037332934512e-07,
|
| 1693 |
+
"loss": 0.0041,
|
| 1694 |
+
"reward": 0.552083333954215,
|
| 1695 |
+
"reward_std": 0.26390674337744713,
|
| 1696 |
+
"rewards/accuracy_reward": 0.1458333432674408,
|
| 1697 |
+
"rewards/format_reward": 0.40625000558793545,
|
| 1698 |
+
"step": 77,
|
| 1699 |
+
"w_high_ratio": 0.0,
|
| 1700 |
+
"w_low_ratio": 0.035081148613244295,
|
| 1701 |
+
"w_max": 1.4559779465198517,
|
| 1702 |
+
"w_mean": 1.158086121082306,
|
| 1703 |
+
"w_min": 0.0,
|
| 1704 |
+
"w_std": 0.16358545422554016
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"completion_length": 3630.3438720703125,
|
| 1708 |
+
"cov_mean": 2.0063042029505596e-05,
|
| 1709 |
+
"cov_std": 0.3748911917209625,
|
| 1710 |
+
"entropy": 0.39599609375,
|
| 1711 |
+
"epoch": 0.08914285714285715,
|
| 1712 |
+
"grad_norm": 0.50286865234375,
|
| 1713 |
+
"kl": 0.013364076614379883,
|
| 1714 |
+
"learning_rate": 2.2629708984760706e-07,
|
| 1715 |
+
"loss": 0.0002,
|
| 1716 |
+
"reward": 0.4479166939854622,
|
| 1717 |
+
"reward_std": 0.5592645406723022,
|
| 1718 |
+
"rewards/accuracy_reward": 0.1770833432674408,
|
| 1719 |
+
"rewards/format_reward": 0.2708333469927311,
|
| 1720 |
+
"step": 78,
|
| 1721 |
+
"w_high_ratio": 0.04053416848182678,
|
| 1722 |
+
"w_low_ratio": 0.047788419760763645,
|
| 1723 |
+
"w_max": 1.5594379305839539,
|
| 1724 |
+
"w_mean": 1.1108087003231049,
|
| 1725 |
+
"w_min": 0.0,
|
| 1726 |
+
"w_std": 0.2227778285741806
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"completion_length": 2405.6354598999023,
|
| 1730 |
+
"cov_mean": 9.158174270851305e-05,
|
| 1731 |
+
"cov_std": 0.34057875350117683,
|
| 1732 |
+
"entropy": 0.326171875,
|
| 1733 |
+
"epoch": 0.09028571428571429,
|
| 1734 |
+
"grad_norm": 0.4699649214744568,
|
| 1735 |
+
"kl": 0.0014543533325195312,
|
| 1736 |
+
"learning_rate": 2.1558482853517253e-07,
|
| 1737 |
+
"loss": 0.0159,
|
| 1738 |
+
"reward": 0.8750000223517418,
|
| 1739 |
+
"reward_std": 0.34952742606401443,
|
| 1740 |
+
"rewards/accuracy_reward": 0.250000006519258,
|
| 1741 |
+
"rewards/format_reward": 0.6250000298023224,
|
| 1742 |
+
"step": 79,
|
| 1743 |
+
"w_high_ratio": 0.11352726817131042,
|
| 1744 |
+
"w_low_ratio": 0.03820635436568409,
|
| 1745 |
+
"w_max": 1.81002277135849,
|
| 1746 |
+
"w_mean": 1.309929370880127,
|
| 1747 |
+
"w_min": 0.0,
|
| 1748 |
+
"w_std": 0.2257107077166438
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"completion_length": 3596.3750610351562,
|
| 1752 |
+
"cov_mean": 7.016459858277813e-05,
|
| 1753 |
+
"cov_std": 0.21266964823007584,
|
| 1754 |
+
"entropy": 0.46337890625,
|
| 1755 |
+
"epoch": 0.09142857142857143,
|
| 1756 |
+
"grad_norm": 0.224221870303154,
|
| 1757 |
+
"kl": 0.0014083385467529297,
|
| 1758 |
+
"learning_rate": 2.0528000059645995e-07,
|
| 1759 |
+
"loss": 0.0048,
|
| 1760 |
+
"reward": 0.5520833348855376,
|
| 1761 |
+
"reward_std": 0.33429770916700363,
|
| 1762 |
+
"rewards/accuracy_reward": 0.20833333395421505,
|
| 1763 |
+
"rewards/format_reward": 0.3437500009313226,
|
| 1764 |
+
"step": 80,
|
| 1765 |
+
"w_high_ratio": 0.0,
|
| 1766 |
+
"w_low_ratio": 0.029426061548292637,
|
| 1767 |
+
"w_max": 1.2386472523212433,
|
| 1768 |
+
"w_mean": 1.0539521872997284,
|
| 1769 |
+
"w_min": 0.25,
|
| 1770 |
+
"w_std": 0.11237771809101105
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"completion_length": 3377.5521240234375,
|
| 1774 |
+
"cov_mean": 1.5553408047708217e-05,
|
| 1775 |
+
"cov_std": 0.22893034294247627,
|
| 1776 |
+
"entropy": 0.52197265625,
|
| 1777 |
+
"epoch": 0.09257142857142857,
|
| 1778 |
+
"grad_norm": 0.27431702613830566,
|
| 1779 |
+
"kl": 0.0027017593383789062,
|
| 1780 |
+
"learning_rate": 1.9539516087697517e-07,
|
| 1781 |
+
"loss": 0.0442,
|
| 1782 |
+
"reward": 0.3125000027939677,
|
| 1783 |
+
"reward_std": 0.3139677047729492,
|
| 1784 |
+
"rewards/accuracy_reward": 0.0833333358168602,
|
| 1785 |
+
"rewards/format_reward": 0.22916666697710752,
|
| 1786 |
+
"step": 81,
|
| 1787 |
+
"w_high_ratio": 0.0,
|
| 1788 |
+
"w_low_ratio": 0.03366563096642494,
|
| 1789 |
+
"w_max": 1.3624085187911987,
|
| 1790 |
+
"w_mean": 1.1045191884040833,
|
| 1791 |
+
"w_min": 0.25,
|
| 1792 |
+
"w_std": 0.13904165104031563
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"completion_length": 3133.4583740234375,
|
| 1796 |
+
"cov_mean": -1.667316132625274e-05,
|
| 1797 |
+
"cov_std": 0.27454316802322865,
|
| 1798 |
+
"entropy": 0.408203125,
|
| 1799 |
+
"epoch": 0.09371428571428571,
|
| 1800 |
+
"grad_norm": 0.38514095544815063,
|
| 1801 |
+
"kl": 0.0017423629760742188,
|
| 1802 |
+
"learning_rate": 1.8594235253127372e-07,
|
| 1803 |
+
"loss": -0.0213,
|
| 1804 |
+
"reward": 0.5937500149011612,
|
| 1805 |
+
"reward_std": 0.35102832317352295,
|
| 1806 |
+
"rewards/accuracy_reward": 0.18750000465661287,
|
| 1807 |
+
"rewards/format_reward": 0.4062500074505806,
|
| 1808 |
+
"step": 82,
|
| 1809 |
+
"w_high_ratio": 0.0,
|
| 1810 |
+
"w_low_ratio": 0.034213229548186064,
|
| 1811 |
+
"w_max": 1.6117319464683533,
|
| 1812 |
+
"w_mean": 1.1832448840141296,
|
| 1813 |
+
"w_min": 9.42250974980716e-31,
|
| 1814 |
+
"w_std": 0.1813708432018757
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"completion_length": 3142.1771240234375,
|
| 1818 |
+
"cov_mean": 4.071597049914999e-05,
|
| 1819 |
+
"cov_std": 0.17724395170807838,
|
| 1820 |
+
"entropy": 0.45751953125,
|
| 1821 |
+
"epoch": 0.09485714285714286,
|
| 1822 |
+
"grad_norm": 0.3409688472747803,
|
| 1823 |
+
"kl": 0.001071929931640625,
|
| 1824 |
+
"learning_rate": 1.7693309235023127e-07,
|
| 1825 |
+
"loss": 0.0102,
|
| 1826 |
+
"reward": 0.38541667722165585,
|
| 1827 |
+
"reward_std": 0.20087094232439995,
|
| 1828 |
+
"rewards/accuracy_reward": 0.11458333395421505,
|
| 1829 |
+
"rewards/format_reward": 0.2708333386108279,
|
| 1830 |
+
"step": 83,
|
| 1831 |
+
"w_high_ratio": 0.0,
|
| 1832 |
+
"w_low_ratio": 0.023759393487125635,
|
| 1833 |
+
"w_max": 1.2598195374011993,
|
| 1834 |
+
"w_mean": 1.0758444666862488,
|
| 1835 |
+
"w_min": 0.25,
|
| 1836 |
+
"w_std": 0.10355101153254509
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"completion_length": 3299.4271850585938,
|
| 1840 |
+
"cov_mean": 1.610395520401653e-05,
|
| 1841 |
+
"cov_std": 0.3381447046995163,
|
| 1842 |
+
"entropy": 0.43505859375,
|
| 1843 |
+
"epoch": 0.096,
|
| 1844 |
+
"grad_norm": 0.3248639404773712,
|
| 1845 |
+
"kl": 0.0011587142944335938,
|
| 1846 |
+
"learning_rate": 1.6837835672960831e-07,
|
| 1847 |
+
"loss": -0.0241,
|
| 1848 |
+
"reward": 0.7500000298023224,
|
| 1849 |
+
"reward_std": 0.4175455719232559,
|
| 1850 |
+
"rewards/accuracy_reward": 0.3020833358168602,
|
| 1851 |
+
"rewards/format_reward": 0.4479166865348816,
|
| 1852 |
+
"step": 84,
|
| 1853 |
+
"w_high_ratio": 0.0,
|
| 1854 |
+
"w_low_ratio": 0.034003185108304024,
|
| 1855 |
+
"w_max": 1.4201359450817108,
|
| 1856 |
+
"w_mean": 1.1546694040298462,
|
| 1857 |
+
"w_min": 0.25,
|
| 1858 |
+
"w_std": 0.19938229769468307
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"completion_length": 3368.1146240234375,
|
| 1862 |
+
"cov_mean": 1.1272636584180873e-05,
|
| 1863 |
+
"cov_std": 0.3433619923889637,
|
| 1864 |
+
"entropy": 0.353515625,
|
| 1865 |
+
"epoch": 0.09714285714285714,
|
| 1866 |
+
"grad_norm": 0.2291695475578308,
|
| 1867 |
+
"kl": 0.0006651878356933594,
|
| 1868 |
+
"learning_rate": 1.6028856829700258e-07,
|
| 1869 |
+
"loss": 0.0156,
|
| 1870 |
+
"reward": 0.552083333954215,
|
| 1871 |
+
"reward_std": 0.5098650455474854,
|
| 1872 |
+
"rewards/accuracy_reward": 0.17708334233611822,
|
| 1873 |
+
"rewards/format_reward": 0.3750000102445483,
|
| 1874 |
+
"step": 85,
|
| 1875 |
+
"w_high_ratio": 0.05620652809739113,
|
| 1876 |
+
"w_low_ratio": 0.04038320202380419,
|
| 1877 |
+
"w_max": 1.5647819340229034,
|
| 1878 |
+
"w_mean": 1.2357110977172852,
|
| 1879 |
+
"w_min": 1.9246834407501362e-42,
|
| 1880 |
+
"w_std": 0.2121213562786579
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"completion_length": 3338.4479370117188,
|
| 1884 |
+
"cov_mean": 6.590973612219386e-06,
|
| 1885 |
+
"cov_std": 0.2853589281439781,
|
| 1886 |
+
"entropy": 0.45654296875,
|
| 1887 |
+
"epoch": 0.09828571428571428,
|
| 1888 |
+
"grad_norm": 0.3797212839126587,
|
| 1889 |
+
"kl": 0.0021305084228515625,
|
| 1890 |
+
"learning_rate": 1.5267358321348285e-07,
|
| 1891 |
+
"loss": -0.0236,
|
| 1892 |
+
"reward": 0.5208333432674408,
|
| 1893 |
+
"reward_std": 0.299550324678421,
|
| 1894 |
+
"rewards/accuracy_reward": 0.1770833395421505,
|
| 1895 |
+
"rewards/format_reward": 0.34375,
|
| 1896 |
+
"step": 86,
|
| 1897 |
+
"w_high_ratio": 0.05717267841100693,
|
| 1898 |
+
"w_low_ratio": 0.02882188046351075,
|
| 1899 |
+
"w_max": 1.963057816028595,
|
| 1900 |
+
"w_mean": 1.2316765785217285,
|
| 1901 |
+
"w_min": 0.25,
|
| 1902 |
+
"w_std": 0.1924368217587471
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"completion_length": 3156.2188110351562,
|
| 1906 |
+
"cov_mean": 8.500453259330243e-05,
|
| 1907 |
+
"cov_std": 0.5130489468574524,
|
| 1908 |
+
"entropy": 0.5185546875,
|
| 1909 |
+
"epoch": 0.09942857142857142,
|
| 1910 |
+
"grad_norm": 0.46258026361465454,
|
| 1911 |
+
"kl": 0.00295257568359375,
|
| 1912 |
+
"learning_rate": 1.4554267916537495e-07,
|
| 1913 |
+
"loss": -0.0212,
|
| 1914 |
+
"reward": 0.5833333432674408,
|
| 1915 |
+
"reward_std": 0.5054471418261528,
|
| 1916 |
+
"rewards/accuracy_reward": 0.14583333674818277,
|
| 1917 |
+
"rewards/format_reward": 0.4375000074505806,
|
| 1918 |
+
"step": 87,
|
| 1919 |
+
"w_high_ratio": 0.13361193798482418,
|
| 1920 |
+
"w_low_ratio": 0.05879375524818897,
|
| 1921 |
+
"w_max": 1.8866381645202637,
|
| 1922 |
+
"w_mean": 1.3355560600757599,
|
| 1923 |
+
"w_min": 0.0,
|
| 1924 |
+
"w_std": 0.33218564838171005
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"completion_length": 2856.8959350585938,
|
| 1928 |
+
"cov_mean": -5.945291923126206e-05,
|
| 1929 |
+
"cov_std": 0.5394940003752708,
|
| 1930 |
+
"entropy": 0.44140625,
|
| 1931 |
+
"epoch": 0.10057142857142858,
|
| 1932 |
+
"grad_norm": 0.890120804309845,
|
| 1933 |
+
"kl": 0.02105236053466797,
|
| 1934 |
+
"learning_rate": 1.3890454406082956e-07,
|
| 1935 |
+
"loss": -0.0362,
|
| 1936 |
+
"reward": 0.8958333730697632,
|
| 1937 |
+
"reward_std": 0.7090653479099274,
|
| 1938 |
+
"rewards/accuracy_reward": 0.3645833432674408,
|
| 1939 |
+
"rewards/format_reward": 0.5312500149011612,
|
| 1940 |
+
"step": 88,
|
| 1941 |
+
"w_high_ratio": 0.21772565320134163,
|
| 1942 |
+
"w_low_ratio": 0.049323974177241325,
|
| 1943 |
+
"w_max": 2.266294479370117,
|
| 1944 |
+
"w_mean": 1.4745216369628906,
|
| 1945 |
+
"w_min": 0.0,
|
| 1946 |
+
"w_std": 0.3573007620871067
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"completion_length": 3663.3021850585938,
|
| 1950 |
+
"cov_mean": -5.7599154160925536e-05,
|
| 1951 |
+
"cov_std": 0.2993681877851486,
|
| 1952 |
+
"entropy": 0.43505859375,
|
| 1953 |
+
"epoch": 0.10171428571428572,
|
| 1954 |
+
"grad_norm": 0.3626137971878052,
|
| 1955 |
+
"kl": 0.00238800048828125,
|
| 1956 |
+
"learning_rate": 1.3276726544494571e-07,
|
| 1957 |
+
"loss": 0.0099,
|
| 1958 |
+
"reward": 0.3645833469927311,
|
| 1959 |
+
"reward_std": 0.47493190318346024,
|
| 1960 |
+
"rewards/accuracy_reward": 0.12500000651925802,
|
| 1961 |
+
"rewards/format_reward": 0.23958334513008595,
|
| 1962 |
+
"step": 89,
|
| 1963 |
+
"w_high_ratio": 0.0,
|
| 1964 |
+
"w_low_ratio": 0.0442591137252748,
|
| 1965 |
+
"w_max": 1.4542400240898132,
|
| 1966 |
+
"w_mean": 1.079471230506897,
|
| 1967 |
+
"w_min": 0.0,
|
| 1968 |
+
"w_std": 0.18644139170646667
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"completion_length": 2692.8125610351562,
|
| 1972 |
+
"cov_mean": 4.647310163363727e-06,
|
| 1973 |
+
"cov_std": 0.3419715017080307,
|
| 1974 |
+
"entropy": 0.5390625,
|
| 1975 |
+
"epoch": 0.10285714285714286,
|
| 1976 |
+
"grad_norm": 0.36119693517684937,
|
| 1977 |
+
"kl": 0.0059909820556640625,
|
| 1978 |
+
"learning_rate": 1.2713832064634125e-07,
|
| 1979 |
+
"loss": 0.0442,
|
| 1980 |
+
"reward": 0.5729166697710752,
|
| 1981 |
+
"reward_std": 0.3239624537527561,
|
| 1982 |
+
"rewards/accuracy_reward": 0.06250000279396772,
|
| 1983 |
+
"rewards/format_reward": 0.5104166744276881,
|
| 1984 |
+
"step": 90,
|
| 1985 |
+
"w_high_ratio": 0.14126155525445938,
|
| 1986 |
+
"w_low_ratio": 0.02876184810884297,
|
| 1987 |
+
"w_max": 2.2300167977809906,
|
| 1988 |
+
"w_mean": 1.42653489112854,
|
| 1989 |
+
"w_min": 1.471363387541058e-44,
|
| 1990 |
+
"w_std": 0.21830591186881065
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"completion_length": 3451.5313110351562,
|
| 1994 |
+
"cov_mean": 1.8957917745865416e-05,
|
| 1995 |
+
"cov_std": 0.4000442400574684,
|
| 1996 |
+
"entropy": 0.45654296875,
|
| 1997 |
+
"epoch": 0.104,
|
| 1998 |
+
"grad_norm": 0.4046555459499359,
|
| 1999 |
+
"kl": 0.0024518966674804688,
|
| 2000 |
+
"learning_rate": 1.220245676671809e-07,
|
| 2001 |
+
"loss": -0.0665,
|
| 2002 |
+
"reward": 0.6770833730697632,
|
| 2003 |
+
"reward_std": 0.40345774590969086,
|
| 2004 |
+
"rewards/accuracy_reward": 0.260416679084301,
|
| 2005 |
+
"rewards/format_reward": 0.4166666865348816,
|
| 2006 |
+
"step": 91,
|
| 2007 |
+
"w_high_ratio": 0.06697376817464828,
|
| 2008 |
+
"w_low_ratio": 0.0342584103345871,
|
| 2009 |
+
"w_max": 1.4452155828475952,
|
| 2010 |
+
"w_mean": 1.1833300292491913,
|
| 2011 |
+
"w_min": 0.25,
|
| 2012 |
+
"w_std": 0.2148173823952675
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"completion_length": 3021.2188110351562,
|
| 2016 |
+
"cov_mean": -6.440309425670421e-05,
|
| 2017 |
+
"cov_std": 0.45011676102876663,
|
| 2018 |
+
"entropy": 0.38720703125,
|
| 2019 |
+
"epoch": 0.10514285714285715,
|
| 2020 |
+
"grad_norm": 0.44917768239974976,
|
| 2021 |
+
"kl": 0.007047891616821289,
|
| 2022 |
+
"learning_rate": 1.1743223682775649e-07,
|
| 2023 |
+
"loss": 0.0015,
|
| 2024 |
+
"reward": 0.7291666865348816,
|
| 2025 |
+
"reward_std": 0.5440528020262718,
|
| 2026 |
+
"rewards/accuracy_reward": 0.19791667256504297,
|
| 2027 |
+
"rewards/format_reward": 0.5312500074505806,
|
| 2028 |
+
"step": 92,
|
| 2029 |
+
"w_high_ratio": 0.060439030872657895,
|
| 2030 |
+
"w_low_ratio": 0.046312456484884024,
|
| 2031 |
+
"w_max": 2.021807760000229,
|
| 2032 |
+
"w_mean": 1.2982419431209564,
|
| 2033 |
+
"w_min": 0.0,
|
| 2034 |
+
"w_std": 0.2590548172593117
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"completion_length": 3865.6250610351562,
|
| 2038 |
+
"cov_mean": 1.7783165276341606e-05,
|
| 2039 |
+
"cov_std": 0.23176611587405205,
|
| 2040 |
+
"entropy": 0.52880859375,
|
| 2041 |
+
"epoch": 0.10628571428571429,
|
| 2042 |
+
"grad_norm": 0.2683483958244324,
|
| 2043 |
+
"kl": 0.002590179443359375,
|
| 2044 |
+
"learning_rate": 1.1336692317580158e-07,
|
| 2045 |
+
"loss": 0.0487,
|
| 2046 |
+
"reward": 0.1145833358168602,
|
| 2047 |
+
"reward_std": 0.27467070147395134,
|
| 2048 |
+
"rewards/accuracy_reward": 0.031250000931322575,
|
| 2049 |
+
"rewards/format_reward": 0.08333333488553762,
|
| 2050 |
+
"step": 93,
|
| 2051 |
+
"w_high_ratio": 0.0,
|
| 2052 |
+
"w_low_ratio": 0.03534638648852706,
|
| 2053 |
+
"w_max": 1.232116162776947,
|
| 2054 |
+
"w_mean": 1.0145132839679718,
|
| 2055 |
+
"w_min": 4.369921683443164e-37,
|
| 2056 |
+
"w_std": 0.12999964877963066
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"completion_length": 3234.9271850585938,
|
| 2060 |
+
"cov_mean": 1.053587311616866e-05,
|
| 2061 |
+
"cov_std": 0.20603487268090248,
|
| 2062 |
+
"entropy": 0.52490234375,
|
| 2063 |
+
"epoch": 0.10742857142857143,
|
| 2064 |
+
"grad_norm": 0.25439760088920593,
|
| 2065 |
+
"kl": 0.0029878616333007812,
|
| 2066 |
+
"learning_rate": 1.0983357966978745e-07,
|
| 2067 |
+
"loss": 0.0214,
|
| 2068 |
+
"reward": 0.4270833348855376,
|
| 2069 |
+
"reward_std": 0.17300797998905182,
|
| 2070 |
+
"rewards/accuracy_reward": 0.14583333395421505,
|
| 2071 |
+
"rewards/format_reward": 0.281250006519258,
|
| 2072 |
+
"step": 94,
|
| 2073 |
+
"w_high_ratio": 0.0574149414896965,
|
| 2074 |
+
"w_low_ratio": 0.021458564791828394,
|
| 2075 |
+
"w_max": 1.955292284488678,
|
| 2076 |
+
"w_mean": 1.259522944688797,
|
| 2077 |
+
"w_min": 0.25,
|
| 2078 |
+
"w_std": 0.14511701837182045
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"completion_length": 3710.2396240234375,
|
| 2082 |
+
"cov_mean": 1.0393607226433232e-05,
|
| 2083 |
+
"cov_std": 0.3523143231868744,
|
| 2084 |
+
"entropy": 0.42578125,
|
| 2085 |
+
"epoch": 0.10857142857142857,
|
| 2086 |
+
"grad_norm": 0.20859070122241974,
|
| 2087 |
+
"kl": 0.0004982948303222656,
|
| 2088 |
+
"learning_rate": 1.068365111445064e-07,
|
| 2089 |
+
"loss": 0.0209,
|
| 2090 |
+
"reward": 0.34375,
|
| 2091 |
+
"reward_std": 0.45749304443597794,
|
| 2092 |
+
"rewards/accuracy_reward": 0.11458333488553762,
|
| 2093 |
+
"rewards/format_reward": 0.2291666716337204,
|
| 2094 |
+
"step": 95,
|
| 2095 |
+
"w_high_ratio": 0.0,
|
| 2096 |
+
"w_low_ratio": 0.04463845491409302,
|
| 2097 |
+
"w_max": 1.3612166047096252,
|
| 2098 |
+
"w_mean": 1.0816101431846619,
|
| 2099 |
+
"w_min": 0.25,
|
| 2100 |
+
"w_std": 0.20336205884814262
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"completion_length": 3114.041748046875,
|
| 2104 |
+
"cov_mean": -6.73702224958106e-05,
|
| 2105 |
+
"cov_std": 0.36486806720495224,
|
| 2106 |
+
"entropy": 0.4013671875,
|
| 2107 |
+
"epoch": 0.10971428571428571,
|
| 2108 |
+
"grad_norm": 0.3484714925289154,
|
| 2109 |
+
"kl": 0.002678394317626953,
|
| 2110 |
+
"learning_rate": 1.0437936906629334e-07,
|
| 2111 |
+
"loss": -0.0171,
|
| 2112 |
+
"reward": 0.6979166865348816,
|
| 2113 |
+
"reward_std": 0.46633855253458023,
|
| 2114 |
+
"rewards/accuracy_reward": 0.26041666977107525,
|
| 2115 |
+
"rewards/format_reward": 0.4375000074505806,
|
| 2116 |
+
"step": 96,
|
| 2117 |
+
"w_high_ratio": 0.1971779614686966,
|
| 2118 |
+
"w_low_ratio": 0.04042420396581292,
|
| 2119 |
+
"w_max": 2.1471228301525116,
|
| 2120 |
+
"w_mean": 1.42051500082016,
|
| 2121 |
+
"w_min": 1.9142914218395184e-30,
|
| 2122 |
+
"w_std": 0.24729400128126144
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"completion_length": 3457.760498046875,
|
| 2126 |
+
"cov_mean": -1.2597635304700816e-05,
|
| 2127 |
+
"cov_std": 0.2245815545320511,
|
| 2128 |
+
"entropy": 0.41552734375,
|
| 2129 |
+
"epoch": 0.11085714285714286,
|
| 2130 |
+
"grad_norm": 0.24951718747615814,
|
| 2131 |
+
"kl": 0.0011386871337890625,
|
| 2132 |
+
"learning_rate": 1.0246514708427701e-07,
|
| 2133 |
+
"loss": -0.0394,
|
| 2134 |
+
"reward": 0.5625000055879354,
|
| 2135 |
+
"reward_std": 0.30785489082336426,
|
| 2136 |
+
"rewards/accuracy_reward": 0.23958333395421505,
|
| 2137 |
+
"rewards/format_reward": 0.32291666977107525,
|
| 2138 |
+
"step": 97,
|
| 2139 |
+
"w_high_ratio": 0.0,
|
| 2140 |
+
"w_low_ratio": 0.02458228124305606,
|
| 2141 |
+
"w_max": 1.5016373097896576,
|
| 2142 |
+
"w_mean": 1.1687426269054413,
|
| 2143 |
+
"w_min": 0.25,
|
| 2144 |
+
"w_std": 0.14521248266100883
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"completion_length": 3134.1251220703125,
|
| 2148 |
+
"cov_mean": 8.062847064138623e-05,
|
| 2149 |
+
"cov_std": 0.3362714499235153,
|
| 2150 |
+
"entropy": 0.384765625,
|
| 2151 |
+
"epoch": 0.112,
|
| 2152 |
+
"grad_norm": 0.3256186544895172,
|
| 2153 |
+
"kl": 0.0006456375122070312,
|
| 2154 |
+
"learning_rate": 1.0109617738307911e-07,
|
| 2155 |
+
"loss": -0.0102,
|
| 2156 |
+
"reward": 0.572916679084301,
|
| 2157 |
+
"reward_std": 0.3148062378168106,
|
| 2158 |
+
"rewards/accuracy_reward": 0.14583333395421505,
|
| 2159 |
+
"rewards/format_reward": 0.4270833432674408,
|
| 2160 |
+
"step": 98,
|
| 2161 |
+
"w_high_ratio": 0.00467883562669158,
|
| 2162 |
+
"w_low_ratio": 0.039873864501714706,
|
| 2163 |
+
"w_max": 1.795419156551361,
|
| 2164 |
+
"w_mean": 1.266855150461197,
|
| 2165 |
+
"w_min": 0.25,
|
| 2166 |
+
"w_std": 0.22055331617593765
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"completion_length": 3086.7395935058594,
|
| 2170 |
+
"cov_mean": 1.7768036741472315e-05,
|
| 2171 |
+
"cov_std": 0.15420139580965042,
|
| 2172 |
+
"entropy": 0.35205078125,
|
| 2173 |
+
"epoch": 0.11314285714285714,
|
| 2174 |
+
"grad_norm": 0.3351471722126007,
|
| 2175 |
+
"kl": 0.0013794898986816406,
|
| 2176 |
+
"learning_rate": 1.002741278414069e-07,
|
| 2177 |
+
"loss": 0.0477,
|
| 2178 |
+
"reward": 0.5000000223517418,
|
| 2179 |
+
"reward_std": 0.22891659289598465,
|
| 2180 |
+
"rewards/accuracy_reward": 0.1875000074505806,
|
| 2181 |
+
"rewards/format_reward": 0.3125,
|
| 2182 |
+
"step": 99,
|
| 2183 |
+
"w_high_ratio": 0.055527687072753906,
|
| 2184 |
+
"w_low_ratio": 0.02032439224421978,
|
| 2185 |
+
"w_max": 1.390455573797226,
|
| 2186 |
+
"w_mean": 1.1158559024333954,
|
| 2187 |
+
"w_min": 0.5,
|
| 2188 |
+
"w_std": 0.11466998234391212
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"completion_length": 3004.6354370117188,
|
| 2192 |
+
"cov_mean": 2.6663584918651395e-05,
|
| 2193 |
+
"cov_std": 0.3363041579723358,
|
| 2194 |
+
"entropy": 0.36181640625,
|
| 2195 |
+
"epoch": 0.11428571428571428,
|
| 2196 |
+
"grad_norm": 0.40786388516426086,
|
| 2197 |
+
"kl": 0.002788543701171875,
|
| 2198 |
+
"learning_rate": 1e-07,
|
| 2199 |
+
"loss": -0.0227,
|
| 2200 |
+
"reward": 0.7187500149011612,
|
| 2201 |
+
"reward_std": 0.4770490266382694,
|
| 2202 |
+
"rewards/accuracy_reward": 0.2500000074505806,
|
| 2203 |
+
"rewards/format_reward": 0.4687500149011612,
|
| 2204 |
+
"step": 100,
|
| 2205 |
+
"w_high_ratio": 0.01440071314573288,
|
| 2206 |
+
"w_low_ratio": 0.04455719655379653,
|
| 2207 |
+
"w_max": 1.8046407103538513,
|
| 2208 |
+
"w_mean": 1.2536596357822418,
|
| 2209 |
+
"w_min": 2.0318827732709848e-44,
|
| 2210 |
+
"w_std": 0.2585573047399521
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.11428571428571428,
|
| 2214 |
+
"step": 100,
|
| 2215 |
+
"total_flos": 0.0,
|
| 2216 |
+
"train_loss": -0.004574703625403345,
|
| 2217 |
+
"train_runtime": 8361.7209,
|
| 2218 |
+
"train_samples_per_second": 1.148,
|
| 2219 |
+
"train_steps_per_second": 0.012
|
| 2220 |
+
}
|
| 2221 |
+
],
|
| 2222 |
+
"logging_steps": 1,
|
| 2223 |
+
"max_steps": 100,
|
| 2224 |
+
"num_input_tokens_seen": 0,
|
| 2225 |
+
"num_train_epochs": 1,
|
| 2226 |
+
"save_steps": 50,
|
| 2227 |
+
"stateful_callbacks": {
|
| 2228 |
+
"TrainerControl": {
|
| 2229 |
+
"args": {
|
| 2230 |
+
"should_epoch_stop": false,
|
| 2231 |
+
"should_evaluate": false,
|
| 2232 |
+
"should_log": false,
|
| 2233 |
+
"should_save": true,
|
| 2234 |
+
"should_training_stop": true
|
| 2235 |
+
},
|
| 2236 |
+
"attributes": {}
|
| 2237 |
+
}
|
| 2238 |
+
},
|
| 2239 |
+
"total_flos": 0.0,
|
| 2240 |
+
"train_batch_size": 6,
|
| 2241 |
+
"trial_name": null,
|
| 2242 |
+
"trial_params": null
|
| 2243 |
+
}
|