Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +14 -0
- train_results.json +8 -0
- trainer_state.json +1211 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-3B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-3B-R1-Distill
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-3B-R1-Distill
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
|
| 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="dekangli/Qwen2.5-3B-R1-Distill", 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/dekangli-bytedance/huggingface/runs/x7bsomd3)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.17.0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 3.6.0
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1913806159609856.0,
|
| 3 |
+
"train_loss": 0.48002010657061983,
|
| 4 |
+
"train_runtime": 43121.1313,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.174,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.49.0"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1913806159609856.0,
|
| 3 |
+
"train_loss": 0.48002010657061983,
|
| 4 |
+
"train_runtime": 43121.1313,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.174,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 733,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0068212824010914054,
|
| 13 |
+
"grad_norm": 2.859520152533828,
|
| 14 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 15 |
+
"loss": 0.8358,
|
| 16 |
+
"num_tokens": 3759146.0,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.013642564802182811,
|
| 21 |
+
"grad_norm": 1.9018163630483922,
|
| 22 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 23 |
+
"loss": 0.7639,
|
| 24 |
+
"num_tokens": 7668808.0,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.020463847203274217,
|
| 29 |
+
"grad_norm": 0.5801403334832769,
|
| 30 |
+
"learning_rate": 2.0270270270270273e-05,
|
| 31 |
+
"loss": 0.6614,
|
| 32 |
+
"num_tokens": 11368873.0,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.027285129604365622,
|
| 37 |
+
"grad_norm": 0.572102113014263,
|
| 38 |
+
"learning_rate": 2.702702702702703e-05,
|
| 39 |
+
"loss": 0.6119,
|
| 40 |
+
"num_tokens": 15118063.0,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.034106412005457026,
|
| 45 |
+
"grad_norm": 0.4278039947946872,
|
| 46 |
+
"learning_rate": 3.3783783783783784e-05,
|
| 47 |
+
"loss": 0.5902,
|
| 48 |
+
"num_tokens": 18906839.0,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.040927694406548434,
|
| 53 |
+
"grad_norm": 0.38997902119107797,
|
| 54 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 55 |
+
"loss": 0.5683,
|
| 56 |
+
"num_tokens": 22641755.0,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.047748976807639835,
|
| 61 |
+
"grad_norm": 0.3731809054939738,
|
| 62 |
+
"learning_rate": 4.72972972972973e-05,
|
| 63 |
+
"loss": 0.5642,
|
| 64 |
+
"num_tokens": 26636629.0,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.054570259208731244,
|
| 69 |
+
"grad_norm": 0.3482748515886515,
|
| 70 |
+
"learning_rate": 4.999793714044176e-05,
|
| 71 |
+
"loss": 0.5359,
|
| 72 |
+
"num_tokens": 30417967.0,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.061391541609822645,
|
| 77 |
+
"grad_norm": 0.37293778656884924,
|
| 78 |
+
"learning_rate": 4.9985332146267735e-05,
|
| 79 |
+
"loss": 0.5384,
|
| 80 |
+
"num_tokens": 34231333.0,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06821282401091405,
|
| 85 |
+
"grad_norm": 0.36563686554902025,
|
| 86 |
+
"learning_rate": 4.996127460337901e-05,
|
| 87 |
+
"loss": 0.539,
|
| 88 |
+
"num_tokens": 37961424.0,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.07503410641200546,
|
| 93 |
+
"grad_norm": 0.49916502547033137,
|
| 94 |
+
"learning_rate": 4.992577676510502e-05,
|
| 95 |
+
"loss": 0.5403,
|
| 96 |
+
"num_tokens": 41826860.0,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.08185538881309687,
|
| 101 |
+
"grad_norm": 0.4663794674995223,
|
| 102 |
+
"learning_rate": 4.987885671170889e-05,
|
| 103 |
+
"loss": 0.5286,
|
| 104 |
+
"num_tokens": 45543403.0,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08867667121418826,
|
| 109 |
+
"grad_norm": 0.47229935539155693,
|
| 110 |
+
"learning_rate": 4.9820538341178595e-05,
|
| 111 |
+
"loss": 0.5321,
|
| 112 |
+
"num_tokens": 49369486.0,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.09549795361527967,
|
| 117 |
+
"grad_norm": 0.3986951551087616,
|
| 118 |
+
"learning_rate": 4.97508513570549e-05,
|
| 119 |
+
"loss": 0.5227,
|
| 120 |
+
"num_tokens": 53010874.0,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10231923601637108,
|
| 125 |
+
"grad_norm": 0.40140582830322363,
|
| 126 |
+
"learning_rate": 4.966983125330225e-05,
|
| 127 |
+
"loss": 0.5244,
|
| 128 |
+
"num_tokens": 56909889.0,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.10914051841746249,
|
| 133 |
+
"grad_norm": 0.4349545422715694,
|
| 134 |
+
"learning_rate": 4.957751929623059e-05,
|
| 135 |
+
"loss": 0.5094,
|
| 136 |
+
"num_tokens": 60650570.0,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.11596180081855388,
|
| 141 |
+
"grad_norm": 0.3803902727248126,
|
| 142 |
+
"learning_rate": 4.947396250347695e-05,
|
| 143 |
+
"loss": 0.5033,
|
| 144 |
+
"num_tokens": 64564660.0,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.12278308321964529,
|
| 149 |
+
"grad_norm": 0.3736381760976187,
|
| 150 |
+
"learning_rate": 4.9359213620057766e-05,
|
| 151 |
+
"loss": 0.5192,
|
| 152 |
+
"num_tokens": 68426882.0,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1296043656207367,
|
| 157 |
+
"grad_norm": 0.33996053767832096,
|
| 158 |
+
"learning_rate": 4.9233331091504034e-05,
|
| 159 |
+
"loss": 0.5154,
|
| 160 |
+
"num_tokens": 72252819.0,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.1364256480218281,
|
| 165 |
+
"grad_norm": 0.4698197228973068,
|
| 166 |
+
"learning_rate": 4.909637903409306e-05,
|
| 167 |
+
"loss": 0.504,
|
| 168 |
+
"num_tokens": 76160914.0,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.1432469304229195,
|
| 173 |
+
"grad_norm": 0.3493439695910741,
|
| 174 |
+
"learning_rate": 4.8948427202191766e-05,
|
| 175 |
+
"loss": 0.5057,
|
| 176 |
+
"num_tokens": 80152955.0,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15006821282401092,
|
| 181 |
+
"grad_norm": 0.3516586136746583,
|
| 182 |
+
"learning_rate": 4.878955095272844e-05,
|
| 183 |
+
"loss": 0.5098,
|
| 184 |
+
"num_tokens": 83901702.0,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15688949522510232,
|
| 189 |
+
"grad_norm": 0.42408743833551077,
|
| 190 |
+
"learning_rate": 4.861983120681089e-05,
|
| 191 |
+
"loss": 0.5088,
|
| 192 |
+
"num_tokens": 87691018.0,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.16371077762619374,
|
| 197 |
+
"grad_norm": 0.3475562440630165,
|
| 198 |
+
"learning_rate": 4.8439354408510536e-05,
|
| 199 |
+
"loss": 0.4976,
|
| 200 |
+
"num_tokens": 91542428.0,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.17053206002728513,
|
| 205 |
+
"grad_norm": 0.36672881758295617,
|
| 206 |
+
"learning_rate": 4.82482124808335e-05,
|
| 207 |
+
"loss": 0.5047,
|
| 208 |
+
"num_tokens": 95438170.0,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.17735334242837653,
|
| 213 |
+
"grad_norm": 0.3716213307471467,
|
| 214 |
+
"learning_rate": 4.804650277890105e-05,
|
| 215 |
+
"loss": 0.4993,
|
| 216 |
+
"num_tokens": 99383692.0,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.18417462482946795,
|
| 221 |
+
"grad_norm": 0.4114376174123406,
|
| 222 |
+
"learning_rate": 4.783432804036335e-05,
|
| 223 |
+
"loss": 0.4997,
|
| 224 |
+
"num_tokens": 103223537.0,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.19099590723055934,
|
| 229 |
+
"grad_norm": 0.417963130595086,
|
| 230 |
+
"learning_rate": 4.761179633307163e-05,
|
| 231 |
+
"loss": 0.511,
|
| 232 |
+
"num_tokens": 106901687.0,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.19781718963165076,
|
| 237 |
+
"grad_norm": 0.3590365052314863,
|
| 238 |
+
"learning_rate": 4.737902100003552e-05,
|
| 239 |
+
"loss": 0.4863,
|
| 240 |
+
"num_tokens": 110840758.0,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.20463847203274216,
|
| 245 |
+
"grad_norm": 0.3336081440893747,
|
| 246 |
+
"learning_rate": 4.713612060169362e-05,
|
| 247 |
+
"loss": 0.5005,
|
| 248 |
+
"num_tokens": 114521504.0,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.21145975443383355,
|
| 253 |
+
"grad_norm": 0.3185236733259455,
|
| 254 |
+
"learning_rate": 4.688321885552659e-05,
|
| 255 |
+
"loss": 0.4875,
|
| 256 |
+
"num_tokens": 118445759.0,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.21828103683492497,
|
| 261 |
+
"grad_norm": 0.3596258991525576,
|
| 262 |
+
"learning_rate": 4.662044457304359e-05,
|
| 263 |
+
"loss": 0.4952,
|
| 264 |
+
"num_tokens": 122311693.0,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.22510231923601637,
|
| 269 |
+
"grad_norm": 0.31478964913575963,
|
| 270 |
+
"learning_rate": 4.634793159417421e-05,
|
| 271 |
+
"loss": 0.498,
|
| 272 |
+
"num_tokens": 126094524.0,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.23192360163710776,
|
| 277 |
+
"grad_norm": 0.339405025728744,
|
| 278 |
+
"learning_rate": 4.606581871909919e-05,
|
| 279 |
+
"loss": 0.492,
|
| 280 |
+
"num_tokens": 129971056.0,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.23874488403819918,
|
| 285 |
+
"grad_norm": 0.3817665665912771,
|
| 286 |
+
"learning_rate": 4.577424963755475e-05,
|
| 287 |
+
"loss": 0.5052,
|
| 288 |
+
"num_tokens": 133765982.0,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.24556616643929058,
|
| 293 |
+
"grad_norm": 0.455088588103575,
|
| 294 |
+
"learning_rate": 4.547337285564649e-05,
|
| 295 |
+
"loss": 0.4874,
|
| 296 |
+
"num_tokens": 137522281.0,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.252387448840382,
|
| 301 |
+
"grad_norm": 0.3863705096212881,
|
| 302 |
+
"learning_rate": 4.516334162021013e-05,
|
| 303 |
+
"loss": 0.4826,
|
| 304 |
+
"num_tokens": 141196084.0,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.2592087312414734,
|
| 309 |
+
"grad_norm": 0.36548889219989195,
|
| 310 |
+
"learning_rate": 4.484431384075771e-05,
|
| 311 |
+
"loss": 0.4923,
|
| 312 |
+
"num_tokens": 145136704.0,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.2660300136425648,
|
| 317 |
+
"grad_norm": 0.3282797740156995,
|
| 318 |
+
"learning_rate": 4.4516452009048814e-05,
|
| 319 |
+
"loss": 0.4813,
|
| 320 |
+
"num_tokens": 148940122.0,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.2728512960436562,
|
| 325 |
+
"grad_norm": 0.3373945226676213,
|
| 326 |
+
"learning_rate": 4.4179923116328005e-05,
|
| 327 |
+
"loss": 0.4911,
|
| 328 |
+
"num_tokens": 152809678.0,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.27967257844474763,
|
| 333 |
+
"grad_norm": 0.2988913432631945,
|
| 334 |
+
"learning_rate": 4.3834898568270444e-05,
|
| 335 |
+
"loss": 0.4848,
|
| 336 |
+
"num_tokens": 156683573.0,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.286493860845839,
|
| 341 |
+
"grad_norm": 0.32252594879192,
|
| 342 |
+
"learning_rate": 4.348155409767913e-05,
|
| 343 |
+
"loss": 0.486,
|
| 344 |
+
"num_tokens": 160433326.0,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2933151432469304,
|
| 349 |
+
"grad_norm": 0.30855373605724573,
|
| 350 |
+
"learning_rate": 4.3120069674978156e-05,
|
| 351 |
+
"loss": 0.4883,
|
| 352 |
+
"num_tokens": 164374316.0,
|
| 353 |
+
"step": 215
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.30013642564802184,
|
| 357 |
+
"grad_norm": 0.30234329464930193,
|
| 358 |
+
"learning_rate": 4.275062941654767e-05,
|
| 359 |
+
"loss": 0.4702,
|
| 360 |
+
"num_tokens": 168223299.0,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.3069577080491132,
|
| 365 |
+
"grad_norm": 0.2841369078220348,
|
| 366 |
+
"learning_rate": 4.237342149094701e-05,
|
| 367 |
+
"loss": 0.4815,
|
| 368 |
+
"num_tokens": 172132000.0,
|
| 369 |
+
"step": 225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.31377899045020463,
|
| 373 |
+
"grad_norm": 0.32791055661062934,
|
| 374 |
+
"learning_rate": 4.1988638023074116e-05,
|
| 375 |
+
"loss": 0.4787,
|
| 376 |
+
"num_tokens": 176086331.0,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.32060027285129605,
|
| 381 |
+
"grad_norm": 0.3356851421085584,
|
| 382 |
+
"learning_rate": 4.159647499630971e-05,
|
| 383 |
+
"loss": 0.4708,
|
| 384 |
+
"num_tokens": 179917640.0,
|
| 385 |
+
"step": 235
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.3274215552523875,
|
| 389 |
+
"grad_norm": 0.3037114872946393,
|
| 390 |
+
"learning_rate": 4.1197132152696215e-05,
|
| 391 |
+
"loss": 0.4822,
|
| 392 |
+
"num_tokens": 183746129.0,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.33424283765347884,
|
| 397 |
+
"grad_norm": 0.30572141355536847,
|
| 398 |
+
"learning_rate": 4.07908128912024e-05,
|
| 399 |
+
"loss": 0.4895,
|
| 400 |
+
"num_tokens": 187699370.0,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.34106412005457026,
|
| 405 |
+
"grad_norm": 0.3102442024034853,
|
| 406 |
+
"learning_rate": 4.037772416412524e-05,
|
| 407 |
+
"loss": 0.4739,
|
| 408 |
+
"num_tokens": 191512142.0,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.3478854024556617,
|
| 413 |
+
"grad_norm": 0.3059715305515258,
|
| 414 |
+
"learning_rate": 3.995807637168205e-05,
|
| 415 |
+
"loss": 0.4751,
|
| 416 |
+
"num_tokens": 195367749.0,
|
| 417 |
+
"step": 255
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.35470668485675305,
|
| 421 |
+
"grad_norm": 0.2904211221393888,
|
| 422 |
+
"learning_rate": 3.9532083254846505e-05,
|
| 423 |
+
"loss": 0.4648,
|
| 424 |
+
"num_tokens": 199215371.0,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.3615279672578445,
|
| 429 |
+
"grad_norm": 0.33681948143185453,
|
| 430 |
+
"learning_rate": 3.909996178648299e-05,
|
| 431 |
+
"loss": 0.4826,
|
| 432 |
+
"num_tokens": 202903048.0,
|
| 433 |
+
"step": 265
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.3683492496589359,
|
| 437 |
+
"grad_norm": 0.3285871766466283,
|
| 438 |
+
"learning_rate": 3.866193206083494e-05,
|
| 439 |
+
"loss": 0.4727,
|
| 440 |
+
"num_tokens": 206761213.0,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.37517053206002726,
|
| 445 |
+
"grad_norm": 0.33670385009296144,
|
| 446 |
+
"learning_rate": 3.821821718142332e-05,
|
| 447 |
+
"loss": 0.4694,
|
| 448 |
+
"num_tokens": 210585632.0,
|
| 449 |
+
"step": 275
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.3819918144611187,
|
| 453 |
+
"grad_norm": 0.3305593264219332,
|
| 454 |
+
"learning_rate": 3.77690431474123e-05,
|
| 455 |
+
"loss": 0.4744,
|
| 456 |
+
"num_tokens": 214261738.0,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3888130968622101,
|
| 461 |
+
"grad_norm": 0.29054732905430486,
|
| 462 |
+
"learning_rate": 3.7314638738500265e-05,
|
| 463 |
+
"loss": 0.479,
|
| 464 |
+
"num_tokens": 218144024.0,
|
| 465 |
+
"step": 285
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3956343792633015,
|
| 469 |
+
"grad_norm": 0.2919105758915809,
|
| 470 |
+
"learning_rate": 3.685523539839439e-05,
|
| 471 |
+
"loss": 0.4752,
|
| 472 |
+
"num_tokens": 222057295.0,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.4024556616643929,
|
| 477 |
+
"grad_norm": 0.2954441471813468,
|
| 478 |
+
"learning_rate": 3.63910671169285e-05,
|
| 479 |
+
"loss": 0.4671,
|
| 480 |
+
"num_tokens": 225828573.0,
|
| 481 |
+
"step": 295
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.4092769440654843,
|
| 485 |
+
"grad_norm": 0.33726151653757314,
|
| 486 |
+
"learning_rate": 3.5922370310884014e-05,
|
| 487 |
+
"loss": 0.4664,
|
| 488 |
+
"num_tokens": 229710487.0,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.41609822646657574,
|
| 493 |
+
"grad_norm": 0.2994069615286232,
|
| 494 |
+
"learning_rate": 3.5449383703574806e-05,
|
| 495 |
+
"loss": 0.4801,
|
| 496 |
+
"num_tokens": 233617525.0,
|
| 497 |
+
"step": 305
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.4229195088676671,
|
| 501 |
+
"grad_norm": 0.321770217300059,
|
| 502 |
+
"learning_rate": 3.4972348203257274e-05,
|
| 503 |
+
"loss": 0.4774,
|
| 504 |
+
"num_tokens": 237394471.0,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.4297407912687585,
|
| 509 |
+
"grad_norm": 0.3342140614239043,
|
| 510 |
+
"learning_rate": 3.449150678042748e-05,
|
| 511 |
+
"loss": 0.4732,
|
| 512 |
+
"num_tokens": 241114261.0,
|
| 513 |
+
"step": 315
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.43656207366984995,
|
| 517 |
+
"grad_norm": 0.311787983749093,
|
| 518 |
+
"learning_rate": 3.400710434406803e-05,
|
| 519 |
+
"loss": 0.4727,
|
| 520 |
+
"num_tokens": 244967987.0,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4433833560709413,
|
| 525 |
+
"grad_norm": 0.3125973899622851,
|
| 526 |
+
"learning_rate": 3.351938761690748e-05,
|
| 527 |
+
"loss": 0.4789,
|
| 528 |
+
"num_tokens": 248751095.0,
|
| 529 |
+
"step": 325
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.45020463847203274,
|
| 533 |
+
"grad_norm": 0.3128243315361879,
|
| 534 |
+
"learning_rate": 3.302860500975605e-05,
|
| 535 |
+
"loss": 0.4678,
|
| 536 |
+
"num_tokens": 252607265.0,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.45702592087312416,
|
| 541 |
+
"grad_norm": 0.2899975717949231,
|
| 542 |
+
"learning_rate": 3.253500649498153e-05,
|
| 543 |
+
"loss": 0.4736,
|
| 544 |
+
"num_tokens": 256417909.0,
|
| 545 |
+
"step": 335
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.4638472032742155,
|
| 549 |
+
"grad_norm": 0.2947121469603074,
|
| 550 |
+
"learning_rate": 3.203884347918975e-05,
|
| 551 |
+
"loss": 0.4663,
|
| 552 |
+
"num_tokens": 260456429.0,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.47066848567530695,
|
| 557 |
+
"grad_norm": 0.2747115046593522,
|
| 558 |
+
"learning_rate": 3.154036867517462e-05,
|
| 559 |
+
"loss": 0.4601,
|
| 560 |
+
"num_tokens": 264287905.0,
|
| 561 |
+
"step": 345
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.47748976807639837,
|
| 565 |
+
"grad_norm": 0.2684844916597318,
|
| 566 |
+
"learning_rate": 3.1039835973202865e-05,
|
| 567 |
+
"loss": 0.4689,
|
| 568 |
+
"num_tokens": 268098790.0,
|
| 569 |
+
"step": 350
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4843110504774898,
|
| 573 |
+
"grad_norm": 0.271171033537078,
|
| 574 |
+
"learning_rate": 3.053750031169903e-05,
|
| 575 |
+
"loss": 0.4769,
|
| 576 |
+
"num_tokens": 271974065.0,
|
| 577 |
+
"step": 355
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.49113233287858116,
|
| 581 |
+
"grad_norm": 0.29862281272985114,
|
| 582 |
+
"learning_rate": 3.0033617547396614e-05,
|
| 583 |
+
"loss": 0.4804,
|
| 584 |
+
"num_tokens": 275852045.0,
|
| 585 |
+
"step": 360
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.4979536152796726,
|
| 589 |
+
"grad_norm": 0.2791498620793116,
|
| 590 |
+
"learning_rate": 2.9528444325021477e-05,
|
| 591 |
+
"loss": 0.4603,
|
| 592 |
+
"num_tokens": 279504484.0,
|
| 593 |
+
"step": 365
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.504774897680764,
|
| 597 |
+
"grad_norm": 0.27773797940501777,
|
| 598 |
+
"learning_rate": 2.902223794657391e-05,
|
| 599 |
+
"loss": 0.4623,
|
| 600 |
+
"num_tokens": 283461546.0,
|
| 601 |
+
"step": 370
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.5115961800818554,
|
| 605 |
+
"grad_norm": 0.2501959816908535,
|
| 606 |
+
"learning_rate": 2.8515256240275946e-05,
|
| 607 |
+
"loss": 0.4692,
|
| 608 |
+
"num_tokens": 287371918.0,
|
| 609 |
+
"step": 375
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.5184174624829468,
|
| 613 |
+
"grad_norm": 0.2508499415881564,
|
| 614 |
+
"learning_rate": 2.8007757429250597e-05,
|
| 615 |
+
"loss": 0.4575,
|
| 616 |
+
"num_tokens": 291057738.0,
|
| 617 |
+
"step": 380
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.5252387448840382,
|
| 621 |
+
"grad_norm": 0.23841623530318584,
|
| 622 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 623 |
+
"loss": 0.4657,
|
| 624 |
+
"num_tokens": 294881963.0,
|
| 625 |
+
"step": 385
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5320600272851296,
|
| 629 |
+
"grad_norm": 0.27722631135406894,
|
| 630 |
+
"learning_rate": 2.699224257074941e-05,
|
| 631 |
+
"loss": 0.4666,
|
| 632 |
+
"num_tokens": 298677895.0,
|
| 633 |
+
"step": 390
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.538881309686221,
|
| 637 |
+
"grad_norm": 0.26944884620681187,
|
| 638 |
+
"learning_rate": 2.6484743759724062e-05,
|
| 639 |
+
"loss": 0.4528,
|
| 640 |
+
"num_tokens": 302387985.0,
|
| 641 |
+
"step": 395
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.5457025920873124,
|
| 645 |
+
"grad_norm": 0.2683881461913158,
|
| 646 |
+
"learning_rate": 2.5977762053426098e-05,
|
| 647 |
+
"loss": 0.4698,
|
| 648 |
+
"num_tokens": 306130593.0,
|
| 649 |
+
"step": 400
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.5525238744884038,
|
| 653 |
+
"grad_norm": 0.2292317979583899,
|
| 654 |
+
"learning_rate": 2.547155567497854e-05,
|
| 655 |
+
"loss": 0.4706,
|
| 656 |
+
"num_tokens": 309952008.0,
|
| 657 |
+
"step": 405
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.5593451568894953,
|
| 661 |
+
"grad_norm": 0.262653672464314,
|
| 662 |
+
"learning_rate": 2.496638245260339e-05,
|
| 663 |
+
"loss": 0.4576,
|
| 664 |
+
"num_tokens": 313725489.0,
|
| 665 |
+
"step": 410
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.5661664392905866,
|
| 669 |
+
"grad_norm": 0.31628174437057555,
|
| 670 |
+
"learning_rate": 2.446249968830097e-05,
|
| 671 |
+
"loss": 0.4621,
|
| 672 |
+
"num_tokens": 317525148.0,
|
| 673 |
+
"step": 415
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.572987721691678,
|
| 677 |
+
"grad_norm": 0.2971582407388678,
|
| 678 |
+
"learning_rate": 2.3960164026797137e-05,
|
| 679 |
+
"loss": 0.4625,
|
| 680 |
+
"num_tokens": 321410101.0,
|
| 681 |
+
"step": 420
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5798090040927695,
|
| 685 |
+
"grad_norm": 0.2736258492313367,
|
| 686 |
+
"learning_rate": 2.3459631324825388e-05,
|
| 687 |
+
"loss": 0.4579,
|
| 688 |
+
"num_tokens": 325102278.0,
|
| 689 |
+
"step": 425
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5866302864938608,
|
| 693 |
+
"grad_norm": 0.27230747471072914,
|
| 694 |
+
"learning_rate": 2.2961156520810255e-05,
|
| 695 |
+
"loss": 0.4623,
|
| 696 |
+
"num_tokens": 328831071.0,
|
| 697 |
+
"step": 430
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5934515688949522,
|
| 701 |
+
"grad_norm": 0.2870356128439239,
|
| 702 |
+
"learning_rate": 2.246499350501848e-05,
|
| 703 |
+
"loss": 0.4527,
|
| 704 |
+
"num_tokens": 332767044.0,
|
| 705 |
+
"step": 435
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.6002728512960437,
|
| 709 |
+
"grad_norm": 0.23826692416074355,
|
| 710 |
+
"learning_rate": 2.197139499024396e-05,
|
| 711 |
+
"loss": 0.4503,
|
| 712 |
+
"num_tokens": 336595638.0,
|
| 713 |
+
"step": 440
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.607094133697135,
|
| 717 |
+
"grad_norm": 0.26903175563152104,
|
| 718 |
+
"learning_rate": 2.1480612383092536e-05,
|
| 719 |
+
"loss": 0.4621,
|
| 720 |
+
"num_tokens": 340358925.0,
|
| 721 |
+
"step": 445
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.6139154160982264,
|
| 725 |
+
"grad_norm": 0.23858645047531596,
|
| 726 |
+
"learning_rate": 2.0992895655931984e-05,
|
| 727 |
+
"loss": 0.4606,
|
| 728 |
+
"num_tokens": 344239058.0,
|
| 729 |
+
"step": 450
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.6207366984993179,
|
| 733 |
+
"grad_norm": 0.26224623620936377,
|
| 734 |
+
"learning_rate": 2.0508493219572522e-05,
|
| 735 |
+
"loss": 0.4638,
|
| 736 |
+
"num_tokens": 348080585.0,
|
| 737 |
+
"step": 455
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.6275579809004093,
|
| 741 |
+
"grad_norm": 0.22212001743500964,
|
| 742 |
+
"learning_rate": 2.0027651796742735e-05,
|
| 743 |
+
"loss": 0.4578,
|
| 744 |
+
"num_tokens": 351817695.0,
|
| 745 |
+
"step": 460
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.6343792633015006,
|
| 749 |
+
"grad_norm": 0.24324689513326436,
|
| 750 |
+
"learning_rate": 1.95506162964252e-05,
|
| 751 |
+
"loss": 0.4537,
|
| 752 |
+
"num_tokens": 355639183.0,
|
| 753 |
+
"step": 465
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.6412005457025921,
|
| 757 |
+
"grad_norm": 0.2377209139662622,
|
| 758 |
+
"learning_rate": 1.9077629689115995e-05,
|
| 759 |
+
"loss": 0.4697,
|
| 760 |
+
"num_tokens": 359437581.0,
|
| 761 |
+
"step": 470
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.6480218281036835,
|
| 765 |
+
"grad_norm": 0.2525718316267335,
|
| 766 |
+
"learning_rate": 1.8608932883071507e-05,
|
| 767 |
+
"loss": 0.4483,
|
| 768 |
+
"num_tokens": 363189983.0,
|
| 769 |
+
"step": 475
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.654843110504775,
|
| 773 |
+
"grad_norm": 0.24386193951321106,
|
| 774 |
+
"learning_rate": 1.8144764601605613e-05,
|
| 775 |
+
"loss": 0.4503,
|
| 776 |
+
"num_tokens": 366863209.0,
|
| 777 |
+
"step": 480
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6616643929058663,
|
| 781 |
+
"grad_norm": 0.22335725928265934,
|
| 782 |
+
"learning_rate": 1.7685361261499733e-05,
|
| 783 |
+
"loss": 0.4631,
|
| 784 |
+
"num_tokens": 370725860.0,
|
| 785 |
+
"step": 485
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.6684856753069577,
|
| 789 |
+
"grad_norm": 0.22739365537182124,
|
| 790 |
+
"learning_rate": 1.72309568525877e-05,
|
| 791 |
+
"loss": 0.4493,
|
| 792 |
+
"num_tokens": 374566515.0,
|
| 793 |
+
"step": 490
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6753069577080492,
|
| 797 |
+
"grad_norm": 0.2518810180466547,
|
| 798 |
+
"learning_rate": 1.6781782818576686e-05,
|
| 799 |
+
"loss": 0.4434,
|
| 800 |
+
"num_tokens": 378330489.0,
|
| 801 |
+
"step": 495
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6821282401091405,
|
| 805 |
+
"grad_norm": 0.22437165048428956,
|
| 806 |
+
"learning_rate": 1.6338067939165058e-05,
|
| 807 |
+
"loss": 0.4475,
|
| 808 |
+
"num_tokens": 382103468.0,
|
| 809 |
+
"step": 500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.6889495225102319,
|
| 813 |
+
"grad_norm": 0.24484654505585532,
|
| 814 |
+
"learning_rate": 1.590003821351701e-05,
|
| 815 |
+
"loss": 0.4558,
|
| 816 |
+
"num_tokens": 385837297.0,
|
| 817 |
+
"step": 505
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.6957708049113234,
|
| 821 |
+
"grad_norm": 0.25262167850764056,
|
| 822 |
+
"learning_rate": 1.54679167451535e-05,
|
| 823 |
+
"loss": 0.4522,
|
| 824 |
+
"num_tokens": 389586680.0,
|
| 825 |
+
"step": 510
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.7025920873124147,
|
| 829 |
+
"grad_norm": 0.25644327559623603,
|
| 830 |
+
"learning_rate": 1.5041923628317948e-05,
|
| 831 |
+
"loss": 0.4569,
|
| 832 |
+
"num_tokens": 393428760.0,
|
| 833 |
+
"step": 515
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.7094133697135061,
|
| 837 |
+
"grad_norm": 0.24914618478726863,
|
| 838 |
+
"learning_rate": 1.4622275835874766e-05,
|
| 839 |
+
"loss": 0.4677,
|
| 840 |
+
"num_tokens": 397158700.0,
|
| 841 |
+
"step": 520
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.7162346521145976,
|
| 845 |
+
"grad_norm": 0.2404286713923951,
|
| 846 |
+
"learning_rate": 1.4209187108797607e-05,
|
| 847 |
+
"loss": 0.4533,
|
| 848 |
+
"num_tokens": 400923938.0,
|
| 849 |
+
"step": 525
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.723055934515689,
|
| 853 |
+
"grad_norm": 0.22063525670425096,
|
| 854 |
+
"learning_rate": 1.3802867847303785e-05,
|
| 855 |
+
"loss": 0.4483,
|
| 856 |
+
"num_tokens": 404685655.0,
|
| 857 |
+
"step": 530
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7298772169167803,
|
| 861 |
+
"grad_norm": 0.21801652381587655,
|
| 862 |
+
"learning_rate": 1.3403525003690304e-05,
|
| 863 |
+
"loss": 0.4532,
|
| 864 |
+
"num_tokens": 408582799.0,
|
| 865 |
+
"step": 535
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.7366984993178718,
|
| 869 |
+
"grad_norm": 0.20892765769673624,
|
| 870 |
+
"learning_rate": 1.3011361976925884e-05,
|
| 871 |
+
"loss": 0.4584,
|
| 872 |
+
"num_tokens": 412386009.0,
|
| 873 |
+
"step": 540
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.7435197817189632,
|
| 877 |
+
"grad_norm": 0.21186026658080837,
|
| 878 |
+
"learning_rate": 1.2626578509052997e-05,
|
| 879 |
+
"loss": 0.4603,
|
| 880 |
+
"num_tokens": 416372039.0,
|
| 881 |
+
"step": 545
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.7503410641200545,
|
| 885 |
+
"grad_norm": 0.21768800059481686,
|
| 886 |
+
"learning_rate": 1.2249370583452342e-05,
|
| 887 |
+
"loss": 0.4468,
|
| 888 |
+
"num_tokens": 420051975.0,
|
| 889 |
+
"step": 550
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.757162346521146,
|
| 893 |
+
"grad_norm": 0.2204584535704754,
|
| 894 |
+
"learning_rate": 1.1879930325021841e-05,
|
| 895 |
+
"loss": 0.447,
|
| 896 |
+
"num_tokens": 423685709.0,
|
| 897 |
+
"step": 555
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.7639836289222374,
|
| 901 |
+
"grad_norm": 0.24319632994282764,
|
| 902 |
+
"learning_rate": 1.1518445902320878e-05,
|
| 903 |
+
"loss": 0.4439,
|
| 904 |
+
"num_tokens": 427405904.0,
|
| 905 |
+
"step": 560
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.7708049113233287,
|
| 909 |
+
"grad_norm": 0.23395443194660598,
|
| 910 |
+
"learning_rate": 1.1165101431729561e-05,
|
| 911 |
+
"loss": 0.4442,
|
| 912 |
+
"num_tokens": 431288378.0,
|
| 913 |
+
"step": 565
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7776261937244202,
|
| 917 |
+
"grad_norm": 0.2353220319536335,
|
| 918 |
+
"learning_rate": 1.0820076883671999e-05,
|
| 919 |
+
"loss": 0.4467,
|
| 920 |
+
"num_tokens": 435077995.0,
|
| 921 |
+
"step": 570
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.7844474761255116,
|
| 925 |
+
"grad_norm": 0.23920963211303678,
|
| 926 |
+
"learning_rate": 1.0483547990951195e-05,
|
| 927 |
+
"loss": 0.4464,
|
| 928 |
+
"num_tokens": 439006864.0,
|
| 929 |
+
"step": 575
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.791268758526603,
|
| 933 |
+
"grad_norm": 0.23845367222027455,
|
| 934 |
+
"learning_rate": 1.0155686159242297e-05,
|
| 935 |
+
"loss": 0.4602,
|
| 936 |
+
"num_tokens": 443045688.0,
|
| 937 |
+
"step": 580
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.7980900409276944,
|
| 941 |
+
"grad_norm": 0.23878766406558552,
|
| 942 |
+
"learning_rate": 9.836658379789875e-06,
|
| 943 |
+
"loss": 0.4487,
|
| 944 |
+
"num_tokens": 446852018.0,
|
| 945 |
+
"step": 585
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.8049113233287858,
|
| 949 |
+
"grad_norm": 0.21045206753906473,
|
| 950 |
+
"learning_rate": 9.52662714435352e-06,
|
| 951 |
+
"loss": 0.4619,
|
| 952 |
+
"num_tokens": 450687287.0,
|
| 953 |
+
"step": 590
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.8117326057298773,
|
| 957 |
+
"grad_norm": 0.24180115500464866,
|
| 958 |
+
"learning_rate": 9.225750362445255e-06,
|
| 959 |
+
"loss": 0.4478,
|
| 960 |
+
"num_tokens": 454483896.0,
|
| 961 |
+
"step": 595
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.8185538881309686,
|
| 965 |
+
"grad_norm": 0.22414629123508337,
|
| 966 |
+
"learning_rate": 8.93418128090081e-06,
|
| 967 |
+
"loss": 0.4464,
|
| 968 |
+
"num_tokens": 458325861.0,
|
| 969 |
+
"step": 600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.82537517053206,
|
| 973 |
+
"grad_norm": 0.22622883948448075,
|
| 974 |
+
"learning_rate": 8.652068405825798e-06,
|
| 975 |
+
"loss": 0.4519,
|
| 976 |
+
"num_tokens": 462055868.0,
|
| 977 |
+
"step": 605
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.8321964529331515,
|
| 981 |
+
"grad_norm": 0.2002504054474251,
|
| 982 |
+
"learning_rate": 8.379555426956415e-06,
|
| 983 |
+
"loss": 0.4461,
|
| 984 |
+
"num_tokens": 465973876.0,
|
| 985 |
+
"step": 610
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.8390177353342428,
|
| 989 |
+
"grad_norm": 0.2196686538554551,
|
| 990 |
+
"learning_rate": 8.11678114447342e-06,
|
| 991 |
+
"loss": 0.4446,
|
| 992 |
+
"num_tokens": 469791498.0,
|
| 993 |
+
"step": 615
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.8458390177353342,
|
| 997 |
+
"grad_norm": 0.21537486730907285,
|
| 998 |
+
"learning_rate": 7.863879398306385e-06,
|
| 999 |
+
"loss": 0.4419,
|
| 1000 |
+
"num_tokens": 473570581.0,
|
| 1001 |
+
"step": 620
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.8526603001364257,
|
| 1005 |
+
"grad_norm": 0.2386317506871887,
|
| 1006 |
+
"learning_rate": 7.620978999964487e-06,
|
| 1007 |
+
"loss": 0.4558,
|
| 1008 |
+
"num_tokens": 477401353.0,
|
| 1009 |
+
"step": 625
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.859481582537517,
|
| 1013 |
+
"grad_norm": 0.20977878997335292,
|
| 1014 |
+
"learning_rate": 7.3882036669283754e-06,
|
| 1015 |
+
"loss": 0.4553,
|
| 1016 |
+
"num_tokens": 481348892.0,
|
| 1017 |
+
"step": 630
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.8663028649386084,
|
| 1021 |
+
"grad_norm": 0.21563339045910554,
|
| 1022 |
+
"learning_rate": 7.16567195963665e-06,
|
| 1023 |
+
"loss": 0.4544,
|
| 1024 |
+
"num_tokens": 485171910.0,
|
| 1025 |
+
"step": 635
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.8731241473396999,
|
| 1029 |
+
"grad_norm": 0.20119697622543456,
|
| 1030 |
+
"learning_rate": 6.953497221098949e-06,
|
| 1031 |
+
"loss": 0.4413,
|
| 1032 |
+
"num_tokens": 489059548.0,
|
| 1033 |
+
"step": 640
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.8799454297407913,
|
| 1037 |
+
"grad_norm": 0.20245196883946875,
|
| 1038 |
+
"learning_rate": 6.751787519166505e-06,
|
| 1039 |
+
"loss": 0.4431,
|
| 1040 |
+
"num_tokens": 492893029.0,
|
| 1041 |
+
"step": 645
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.8867667121418826,
|
| 1045 |
+
"grad_norm": 0.2144202772255573,
|
| 1046 |
+
"learning_rate": 6.560645591489468e-06,
|
| 1047 |
+
"loss": 0.45,
|
| 1048 |
+
"num_tokens": 496905674.0,
|
| 1049 |
+
"step": 650
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.8935879945429741,
|
| 1053 |
+
"grad_norm": 0.1960337560239353,
|
| 1054 |
+
"learning_rate": 6.380168793189115e-06,
|
| 1055 |
+
"loss": 0.4464,
|
| 1056 |
+
"num_tokens": 500864542.0,
|
| 1057 |
+
"step": 655
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.9004092769440655,
|
| 1061 |
+
"grad_norm": 0.19741690445074656,
|
| 1062 |
+
"learning_rate": 6.210449047271566e-06,
|
| 1063 |
+
"loss": 0.4492,
|
| 1064 |
+
"num_tokens": 504810366.0,
|
| 1065 |
+
"step": 660
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.9072305593451568,
|
| 1069 |
+
"grad_norm": 0.203527801548371,
|
| 1070 |
+
"learning_rate": 6.0515727978082415e-06,
|
| 1071 |
+
"loss": 0.446,
|
| 1072 |
+
"num_tokens": 508607232.0,
|
| 1073 |
+
"step": 665
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.9140518417462483,
|
| 1077 |
+
"grad_norm": 0.2114927842592368,
|
| 1078 |
+
"learning_rate": 5.9036209659069404e-06,
|
| 1079 |
+
"loss": 0.4519,
|
| 1080 |
+
"num_tokens": 512474084.0,
|
| 1081 |
+
"step": 670
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.9208731241473397,
|
| 1085 |
+
"grad_norm": 0.21111293452840946,
|
| 1086 |
+
"learning_rate": 5.766668908495966e-06,
|
| 1087 |
+
"loss": 0.4438,
|
| 1088 |
+
"num_tokens": 516216104.0,
|
| 1089 |
+
"step": 675
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.927694406548431,
|
| 1093 |
+
"grad_norm": 0.2020840535619729,
|
| 1094 |
+
"learning_rate": 5.64078637994224e-06,
|
| 1095 |
+
"loss": 0.453,
|
| 1096 |
+
"num_tokens": 519966345.0,
|
| 1097 |
+
"step": 680
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.9345156889495225,
|
| 1101 |
+
"grad_norm": 0.19990572835537956,
|
| 1102 |
+
"learning_rate": 5.526037496523051e-06,
|
| 1103 |
+
"loss": 0.4393,
|
| 1104 |
+
"num_tokens": 523793837.0,
|
| 1105 |
+
"step": 685
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.9413369713506139,
|
| 1109 |
+
"grad_norm": 0.21501511467608375,
|
| 1110 |
+
"learning_rate": 5.422480703769408e-06,
|
| 1111 |
+
"loss": 0.4523,
|
| 1112 |
+
"num_tokens": 527666864.0,
|
| 1113 |
+
"step": 690
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.9481582537517054,
|
| 1117 |
+
"grad_norm": 0.20500881616784905,
|
| 1118 |
+
"learning_rate": 5.330168746697747e-06,
|
| 1119 |
+
"loss": 0.4494,
|
| 1120 |
+
"num_tokens": 531466359.0,
|
| 1121 |
+
"step": 695
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.9549795361527967,
|
| 1125 |
+
"grad_norm": 0.19384439762912464,
|
| 1126 |
+
"learning_rate": 5.249148642945106e-06,
|
| 1127 |
+
"loss": 0.4513,
|
| 1128 |
+
"num_tokens": 535253217.0,
|
| 1129 |
+
"step": 700
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.9618008185538881,
|
| 1133 |
+
"grad_norm": 0.20677675163076573,
|
| 1134 |
+
"learning_rate": 5.179461658821403e-06,
|
| 1135 |
+
"loss": 0.4372,
|
| 1136 |
+
"num_tokens": 539137436.0,
|
| 1137 |
+
"step": 705
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9686221009549796,
|
| 1141 |
+
"grad_norm": 0.2176204558853245,
|
| 1142 |
+
"learning_rate": 5.121143288291119e-06,
|
| 1143 |
+
"loss": 0.447,
|
| 1144 |
+
"num_tokens": 542824098.0,
|
| 1145 |
+
"step": 710
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.975443383356071,
|
| 1149 |
+
"grad_norm": 0.20886934132711027,
|
| 1150 |
+
"learning_rate": 5.07422323489499e-06,
|
| 1151 |
+
"loss": 0.4566,
|
| 1152 |
+
"num_tokens": 546578047.0,
|
| 1153 |
+
"step": 715
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.9822646657571623,
|
| 1157 |
+
"grad_norm": 0.20458382129158925,
|
| 1158 |
+
"learning_rate": 5.03872539662099e-06,
|
| 1159 |
+
"loss": 0.4446,
|
| 1160 |
+
"num_tokens": 550377811.0,
|
| 1161 |
+
"step": 720
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.9890859481582538,
|
| 1165 |
+
"grad_norm": 0.18980320361368563,
|
| 1166 |
+
"learning_rate": 5.014667853732269e-06,
|
| 1167 |
+
"loss": 0.4403,
|
| 1168 |
+
"num_tokens": 554224024.0,
|
| 1169 |
+
"step": 725
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.9959072305593452,
|
| 1173 |
+
"grad_norm": 0.18951137695952713,
|
| 1174 |
+
"learning_rate": 5.00206285955824e-06,
|
| 1175 |
+
"loss": 0.4485,
|
| 1176 |
+
"num_tokens": 558001366.0,
|
| 1177 |
+
"step": 730
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.0,
|
| 1181 |
+
"num_tokens": 560311272.0,
|
| 1182 |
+
"step": 733,
|
| 1183 |
+
"total_flos": 1913806159609856.0,
|
| 1184 |
+
"train_loss": 0.48002010657061983,
|
| 1185 |
+
"train_runtime": 43121.1313,
|
| 1186 |
+
"train_samples_per_second": 2.174,
|
| 1187 |
+
"train_steps_per_second": 0.017
|
| 1188 |
+
}
|
| 1189 |
+
],
|
| 1190 |
+
"logging_steps": 5,
|
| 1191 |
+
"max_steps": 733,
|
| 1192 |
+
"num_input_tokens_seen": 0,
|
| 1193 |
+
"num_train_epochs": 1,
|
| 1194 |
+
"save_steps": 50,
|
| 1195 |
+
"stateful_callbacks": {
|
| 1196 |
+
"TrainerControl": {
|
| 1197 |
+
"args": {
|
| 1198 |
+
"should_epoch_stop": false,
|
| 1199 |
+
"should_evaluate": false,
|
| 1200 |
+
"should_log": false,
|
| 1201 |
+
"should_save": true,
|
| 1202 |
+
"should_training_stop": true
|
| 1203 |
+
},
|
| 1204 |
+
"attributes": {}
|
| 1205 |
+
}
|
| 1206 |
+
},
|
| 1207 |
+
"total_flos": 1913806159609856.0,
|
| 1208 |
+
"train_batch_size": 16,
|
| 1209 |
+
"trial_name": null,
|
| 1210 |
+
"trial_params": null
|
| 1211 |
+
}
|