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 +1540 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Open-R1-Distill
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Open-R1-Distill
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-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="leonardozzy/Qwen2.5-1.5B-Open-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/leonardozzy-openai/huggingface/runs/yiokb3ox)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.4.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 486995857768448.0,
|
| 3 |
+
"train_loss": 0.5541811234532507,
|
| 4 |
+
"train_runtime": 156721.9484,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.219,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 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": 1.1,
|
| 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": 486995857768448.0,
|
| 3 |
+
"train_loss": 0.5541811234532507,
|
| 4 |
+
"train_runtime": 156721.9484,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.219,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9991254154276719,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1071,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004664451052416769,
|
| 13 |
+
"grad_norm": 0.0,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 0.8476,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009328902104833538,
|
| 20 |
+
"grad_norm": 0.0,
|
| 21 |
+
"learning_rate": 0.0,
|
| 22 |
+
"loss": 0.861,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013993353157250307,
|
| 27 |
+
"grad_norm": 0.0,
|
| 28 |
+
"learning_rate": 0.0,
|
| 29 |
+
"loss": 0.8574,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018657804209667075,
|
| 34 |
+
"grad_norm": 1.7217303169710205,
|
| 35 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 36 |
+
"loss": 0.8586,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023322255262083844,
|
| 41 |
+
"grad_norm": 1.0811304401552388,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 0.8027,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.027986706314500613,
|
| 48 |
+
"grad_norm": 0.6678730431826253,
|
| 49 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 50 |
+
"loss": 0.7386,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03265115736691738,
|
| 55 |
+
"grad_norm": 0.49414971424324633,
|
| 56 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 57 |
+
"loss": 0.6911,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03731560841933415,
|
| 62 |
+
"grad_norm": 0.4956290038506038,
|
| 63 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 64 |
+
"loss": 0.6738,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.041980059471750916,
|
| 69 |
+
"grad_norm": 0.45113968047451636,
|
| 70 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 71 |
+
"loss": 0.6615,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04664451052416769,
|
| 76 |
+
"grad_norm": 0.4151578102626258,
|
| 77 |
+
"learning_rate": 3.148148148148148e-05,
|
| 78 |
+
"loss": 0.637,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.051308961576584454,
|
| 83 |
+
"grad_norm": 0.41598749293660114,
|
| 84 |
+
"learning_rate": 3.611111111111111e-05,
|
| 85 |
+
"loss": 0.6521,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.055973412629001226,
|
| 90 |
+
"grad_norm": 0.44364992697109346,
|
| 91 |
+
"learning_rate": 4.074074074074074e-05,
|
| 92 |
+
"loss": 0.6416,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06063786368141799,
|
| 97 |
+
"grad_norm": 0.4334859115222668,
|
| 98 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 99 |
+
"loss": 0.6179,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06530231473383476,
|
| 104 |
+
"grad_norm": 0.4168421218480663,
|
| 105 |
+
"learning_rate": 5e-05,
|
| 106 |
+
"loss": 0.6455,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06996676578625154,
|
| 111 |
+
"grad_norm": 0.5598377478471296,
|
| 112 |
+
"learning_rate": 4.999731625198103e-05,
|
| 113 |
+
"loss": 0.6218,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0746312168386683,
|
| 118 |
+
"grad_norm": 0.5562791478235322,
|
| 119 |
+
"learning_rate": 4.998926564814665e-05,
|
| 120 |
+
"loss": 0.6164,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07929566789108507,
|
| 125 |
+
"grad_norm": 0.494836009809662,
|
| 126 |
+
"learning_rate": 4.997585010901171e-05,
|
| 127 |
+
"loss": 0.6083,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08396011894350183,
|
| 132 |
+
"grad_norm": 0.47761536307054875,
|
| 133 |
+
"learning_rate": 4.995707283492525e-05,
|
| 134 |
+
"loss": 0.597,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08862456999591861,
|
| 139 |
+
"grad_norm": 0.5012276873640602,
|
| 140 |
+
"learning_rate": 4.9932938305306997e-05,
|
| 141 |
+
"loss": 0.5986,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09328902104833538,
|
| 146 |
+
"grad_norm": 0.558780335812584,
|
| 147 |
+
"learning_rate": 4.990345227757883e-05,
|
| 148 |
+
"loss": 0.6108,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09795347210075214,
|
| 153 |
+
"grad_norm": 0.5027530843851625,
|
| 154 |
+
"learning_rate": 4.986862178579129e-05,
|
| 155 |
+
"loss": 0.616,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10261792315316891,
|
| 160 |
+
"grad_norm": 0.5276174777450547,
|
| 161 |
+
"learning_rate": 4.982845513894555e-05,
|
| 162 |
+
"loss": 0.6028,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10728237420558567,
|
| 167 |
+
"grad_norm": 0.48105561141886855,
|
| 168 |
+
"learning_rate": 4.9782961919011294e-05,
|
| 169 |
+
"loss": 0.5926,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11194682525800245,
|
| 174 |
+
"grad_norm": 0.5884754531701646,
|
| 175 |
+
"learning_rate": 4.973215297864088e-05,
|
| 176 |
+
"loss": 0.5997,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11661127631041922,
|
| 181 |
+
"grad_norm": 0.5038947888532336,
|
| 182 |
+
"learning_rate": 4.967604043858034e-05,
|
| 183 |
+
"loss": 0.5966,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12127572736283598,
|
| 188 |
+
"grad_norm": 0.4628854625972218,
|
| 189 |
+
"learning_rate": 4.9614637684777964e-05,
|
| 190 |
+
"loss": 0.5889,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12594017841525276,
|
| 195 |
+
"grad_norm": 0.369569834468325,
|
| 196 |
+
"learning_rate": 4.954795936519099e-05,
|
| 197 |
+
"loss": 0.5886,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.13060462946766951,
|
| 202 |
+
"grad_norm": 0.510224312267307,
|
| 203 |
+
"learning_rate": 4.9476021386291255e-05,
|
| 204 |
+
"loss": 0.5904,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1352690805200863,
|
| 209 |
+
"grad_norm": 0.5165955737252187,
|
| 210 |
+
"learning_rate": 4.93988409092706e-05,
|
| 211 |
+
"loss": 0.5931,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13993353157250307,
|
| 216 |
+
"grad_norm": 0.45509182070489973,
|
| 217 |
+
"learning_rate": 4.931643634594701e-05,
|
| 218 |
+
"loss": 0.5764,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14459798262491982,
|
| 223 |
+
"grad_norm": 0.41968982538759186,
|
| 224 |
+
"learning_rate": 4.9228827354372374e-05,
|
| 225 |
+
"loss": 0.5809,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1492624336773366,
|
| 230 |
+
"grad_norm": 0.41229365733365814,
|
| 231 |
+
"learning_rate": 4.9136034834142906e-05,
|
| 232 |
+
"loss": 0.5886,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15392688472975335,
|
| 237 |
+
"grad_norm": 0.3826932795909075,
|
| 238 |
+
"learning_rate": 4.9038080921413485e-05,
|
| 239 |
+
"loss": 0.5842,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15859133578217013,
|
| 244 |
+
"grad_norm": 0.41134892045101074,
|
| 245 |
+
"learning_rate": 4.893498898361693e-05,
|
| 246 |
+
"loss": 0.5946,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1632557868345869,
|
| 251 |
+
"grad_norm": 0.38992267173979334,
|
| 252 |
+
"learning_rate": 4.882678361388958e-05,
|
| 253 |
+
"loss": 0.5885,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16792023788700366,
|
| 258 |
+
"grad_norm": 0.40073952235248766,
|
| 259 |
+
"learning_rate": 4.871349062520448e-05,
|
| 260 |
+
"loss": 0.5841,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17258468893942044,
|
| 265 |
+
"grad_norm": 0.4200184545679776,
|
| 266 |
+
"learning_rate": 4.859513704421353e-05,
|
| 267 |
+
"loss": 0.5771,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17724913999183722,
|
| 272 |
+
"grad_norm": 0.4292182704616412,
|
| 273 |
+
"learning_rate": 4.847175110480015e-05,
|
| 274 |
+
"loss": 0.5708,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18191359104425397,
|
| 279 |
+
"grad_norm": 0.450661348267434,
|
| 280 |
+
"learning_rate": 4.8343362241343944e-05,
|
| 281 |
+
"loss": 0.5708,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18657804209667075,
|
| 286 |
+
"grad_norm": 0.3869287419256418,
|
| 287 |
+
"learning_rate": 4.8210001081698954e-05,
|
| 288 |
+
"loss": 0.5708,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1912424931490875,
|
| 293 |
+
"grad_norm": 0.42553333511533853,
|
| 294 |
+
"learning_rate": 4.8071699439887215e-05,
|
| 295 |
+
"loss": 0.5845,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19590694420150429,
|
| 300 |
+
"grad_norm": 0.4146813048215204,
|
| 301 |
+
"learning_rate": 4.792849030850938e-05,
|
| 302 |
+
"loss": 0.5762,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20057139525392106,
|
| 307 |
+
"grad_norm": 0.5810537942195573,
|
| 308 |
+
"learning_rate": 4.778040785087412e-05,
|
| 309 |
+
"loss": 0.5736,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20523584630633782,
|
| 314 |
+
"grad_norm": 0.4540901088901895,
|
| 315 |
+
"learning_rate": 4.762748739284831e-05,
|
| 316 |
+
"loss": 0.5695,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2099002973587546,
|
| 321 |
+
"grad_norm": 0.39778098326448963,
|
| 322 |
+
"learning_rate": 4.746976541442986e-05,
|
| 323 |
+
"loss": 0.562,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21456474841117135,
|
| 328 |
+
"grad_norm": 0.45060914716273687,
|
| 329 |
+
"learning_rate": 4.730727954104515e-05,
|
| 330 |
+
"loss": 0.5708,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21922919946358813,
|
| 335 |
+
"grad_norm": 0.40075705306410814,
|
| 336 |
+
"learning_rate": 4.714006853457339e-05,
|
| 337 |
+
"loss": 0.5779,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.2238936505160049,
|
| 342 |
+
"grad_norm": 0.3988838422959827,
|
| 343 |
+
"learning_rate": 4.6968172284099654e-05,
|
| 344 |
+
"loss": 0.5769,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22855810156842166,
|
| 349 |
+
"grad_norm": 0.40730912286641724,
|
| 350 |
+
"learning_rate": 4.679163179639923e-05,
|
| 351 |
+
"loss": 0.5622,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23322255262083844,
|
| 356 |
+
"grad_norm": 0.41570250249981516,
|
| 357 |
+
"learning_rate": 4.661048918615513e-05,
|
| 358 |
+
"loss": 0.5626,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23788700367325522,
|
| 363 |
+
"grad_norm": 0.37266061168544923,
|
| 364 |
+
"learning_rate": 4.642478766591148e-05,
|
| 365 |
+
"loss": 0.5603,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24255145472567197,
|
| 370 |
+
"grad_norm": 0.41204417027814066,
|
| 371 |
+
"learning_rate": 4.623457153576493e-05,
|
| 372 |
+
"loss": 0.5692,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24721590577808875,
|
| 377 |
+
"grad_norm": 0.3517500791021223,
|
| 378 |
+
"learning_rate": 4.603988617279655e-05,
|
| 379 |
+
"loss": 0.5575,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2518803568305055,
|
| 384 |
+
"grad_norm": 0.3626203299511348,
|
| 385 |
+
"learning_rate": 4.5840778020247025e-05,
|
| 386 |
+
"loss": 0.5561,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2565448078829223,
|
| 391 |
+
"grad_norm": 0.4323865340964901,
|
| 392 |
+
"learning_rate": 4.56372945764372e-05,
|
| 393 |
+
"loss": 0.5605,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26120925893533903,
|
| 398 |
+
"grad_norm": 0.4558769125407336,
|
| 399 |
+
"learning_rate": 4.542948438343725e-05,
|
| 400 |
+
"loss": 0.564,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.26587370998775584,
|
| 405 |
+
"grad_norm": 0.3788810919577419,
|
| 406 |
+
"learning_rate": 4.521739701548662e-05,
|
| 407 |
+
"loss": 0.5689,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2705381610401726,
|
| 412 |
+
"grad_norm": 0.3494299182914199,
|
| 413 |
+
"learning_rate": 4.500108306716784e-05,
|
| 414 |
+
"loss": 0.5532,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.27520261209258934,
|
| 419 |
+
"grad_norm": 0.3243682374762204,
|
| 420 |
+
"learning_rate": 4.478059414133695e-05,
|
| 421 |
+
"loss": 0.5472,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27986706314500615,
|
| 426 |
+
"grad_norm": 0.3774629263697534,
|
| 427 |
+
"learning_rate": 4.455598283681331e-05,
|
| 428 |
+
"loss": 0.5631,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2845315141974229,
|
| 433 |
+
"grad_norm": 0.3590842486979046,
|
| 434 |
+
"learning_rate": 4.43273027358319e-05,
|
| 435 |
+
"loss": 0.5473,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.28919596524983965,
|
| 440 |
+
"grad_norm": 0.33869526982866255,
|
| 441 |
+
"learning_rate": 4.4094608391260996e-05,
|
| 442 |
+
"loss": 0.5556,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.29386041630225646,
|
| 447 |
+
"grad_norm": 0.3740834437948184,
|
| 448 |
+
"learning_rate": 4.3857955313588256e-05,
|
| 449 |
+
"loss": 0.5586,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2985248673546732,
|
| 454 |
+
"grad_norm": 0.4069053631763161,
|
| 455 |
+
"learning_rate": 4.3617399957678426e-05,
|
| 456 |
+
"loss": 0.5699,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.30318931840708996,
|
| 461 |
+
"grad_norm": 0.42775595832918634,
|
| 462 |
+
"learning_rate": 4.3372999709305726e-05,
|
| 463 |
+
"loss": 0.5541,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3078537694595067,
|
| 468 |
+
"grad_norm": 0.4225047260621452,
|
| 469 |
+
"learning_rate": 4.3124812871464146e-05,
|
| 470 |
+
"loss": 0.5612,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3125182205119235,
|
| 475 |
+
"grad_norm": 0.4064532119864525,
|
| 476 |
+
"learning_rate": 4.287289865045895e-05,
|
| 477 |
+
"loss": 0.5566,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.31718267156434027,
|
| 482 |
+
"grad_norm": 0.40813784397443764,
|
| 483 |
+
"learning_rate": 4.261731714178274e-05,
|
| 484 |
+
"loss": 0.5427,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.321847122616757,
|
| 489 |
+
"grad_norm": 0.37505518830201817,
|
| 490 |
+
"learning_rate": 4.23581293157793e-05,
|
| 491 |
+
"loss": 0.5573,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3265115736691738,
|
| 496 |
+
"grad_norm": 0.40656917887904453,
|
| 497 |
+
"learning_rate": 4.20953970030988e-05,
|
| 498 |
+
"loss": 0.5531,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3311760247215906,
|
| 503 |
+
"grad_norm": 0.39600365804673093,
|
| 504 |
+
"learning_rate": 4.182918287994781e-05,
|
| 505 |
+
"loss": 0.5475,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.33584047577400733,
|
| 510 |
+
"grad_norm": 0.3703296359847103,
|
| 511 |
+
"learning_rate": 4.155955045313748e-05,
|
| 512 |
+
"loss": 0.5651,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.34050492682642414,
|
| 517 |
+
"grad_norm": 0.3666872032980013,
|
| 518 |
+
"learning_rate": 4.128656404493371e-05,
|
| 519 |
+
"loss": 0.559,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3451693778788409,
|
| 524 |
+
"grad_norm": 0.33550827998787563,
|
| 525 |
+
"learning_rate": 4.10102887777127e-05,
|
| 526 |
+
"loss": 0.5609,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.34983382893125764,
|
| 531 |
+
"grad_norm": 0.3730387291098042,
|
| 532 |
+
"learning_rate": 4.073079055842566e-05,
|
| 533 |
+
"loss": 0.5485,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35449827998367445,
|
| 538 |
+
"grad_norm": 0.3970093889085142,
|
| 539 |
+
"learning_rate": 4.044813606287634e-05,
|
| 540 |
+
"loss": 0.5475,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3591627310360912,
|
| 545 |
+
"grad_norm": 0.32485469708579506,
|
| 546 |
+
"learning_rate": 4.016239271981519e-05,
|
| 547 |
+
"loss": 0.5461,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36382718208850795,
|
| 552 |
+
"grad_norm": 0.3382837402395568,
|
| 553 |
+
"learning_rate": 3.987362869485384e-05,
|
| 554 |
+
"loss": 0.5496,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3684916331409247,
|
| 559 |
+
"grad_norm": 0.3609893182037058,
|
| 560 |
+
"learning_rate": 3.9581912874203854e-05,
|
| 561 |
+
"loss": 0.5561,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3731560841933415,
|
| 566 |
+
"grad_norm": 0.35168703173333654,
|
| 567 |
+
"learning_rate": 3.928731484824351e-05,
|
| 568 |
+
"loss": 0.5479,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.37782053524575826,
|
| 573 |
+
"grad_norm": 0.3629018488370036,
|
| 574 |
+
"learning_rate": 3.898990489491668e-05,
|
| 575 |
+
"loss": 0.5501,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.382484986298175,
|
| 580 |
+
"grad_norm": 0.37390402781019416,
|
| 581 |
+
"learning_rate": 3.8689753962967636e-05,
|
| 582 |
+
"loss": 0.5354,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3871494373505918,
|
| 587 |
+
"grad_norm": 0.335380363177113,
|
| 588 |
+
"learning_rate": 3.838693365501586e-05,
|
| 589 |
+
"loss": 0.5469,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.39181388840300857,
|
| 594 |
+
"grad_norm": 0.3424832891358978,
|
| 595 |
+
"learning_rate": 3.80815162104748e-05,
|
| 596 |
+
"loss": 0.552,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.3964783394554253,
|
| 601 |
+
"grad_norm": 0.37221668230659216,
|
| 602 |
+
"learning_rate": 3.7773574488318854e-05,
|
| 603 |
+
"loss": 0.5553,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.40114279050784213,
|
| 608 |
+
"grad_norm": 0.37074728239538524,
|
| 609 |
+
"learning_rate": 3.746318194970239e-05,
|
| 610 |
+
"loss": 0.5523,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4058072415602589,
|
| 615 |
+
"grad_norm": 0.38839870040744245,
|
| 616 |
+
"learning_rate": 3.715041264043525e-05,
|
| 617 |
+
"loss": 0.556,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.41047169261267563,
|
| 622 |
+
"grad_norm": 0.3575823882886992,
|
| 623 |
+
"learning_rate": 3.683534117331869e-05,
|
| 624 |
+
"loss": 0.5485,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.41513614366509244,
|
| 629 |
+
"grad_norm": 0.3161641377206891,
|
| 630 |
+
"learning_rate": 3.65180427103461e-05,
|
| 631 |
+
"loss": 0.5467,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4198005947175092,
|
| 636 |
+
"grad_norm": 0.3703781300095459,
|
| 637 |
+
"learning_rate": 3.619859294477273e-05,
|
| 638 |
+
"loss": 0.5492,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42446504576992594,
|
| 643 |
+
"grad_norm": 0.3492760299630012,
|
| 644 |
+
"learning_rate": 3.587706808305861e-05,
|
| 645 |
+
"loss": 0.5421,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4291294968223427,
|
| 650 |
+
"grad_norm": 0.3267136941264168,
|
| 651 |
+
"learning_rate": 3.5553544826689145e-05,
|
| 652 |
+
"loss": 0.538,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.4337939478747595,
|
| 657 |
+
"grad_norm": 0.29422503748430795,
|
| 658 |
+
"learning_rate": 3.522810035387752e-05,
|
| 659 |
+
"loss": 0.5288,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.43845839892717625,
|
| 664 |
+
"grad_norm": 0.34737447664291465,
|
| 665 |
+
"learning_rate": 3.490081230115343e-05,
|
| 666 |
+
"loss": 0.5525,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.443122849979593,
|
| 671 |
+
"grad_norm": 0.3404046261795078,
|
| 672 |
+
"learning_rate": 3.4571758744842507e-05,
|
| 673 |
+
"loss": 0.5522,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4477873010320098,
|
| 678 |
+
"grad_norm": 0.36447616317715154,
|
| 679 |
+
"learning_rate": 3.4241018182440735e-05,
|
| 680 |
+
"loss": 0.5441,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.45245175208442656,
|
| 685 |
+
"grad_norm": 0.31157047733964094,
|
| 686 |
+
"learning_rate": 3.390866951388847e-05,
|
| 687 |
+
"loss": 0.5391,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4571162031368433,
|
| 692 |
+
"grad_norm": 0.3116582428424639,
|
| 693 |
+
"learning_rate": 3.3574792022748466e-05,
|
| 694 |
+
"loss": 0.5535,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4617806541892601,
|
| 699 |
+
"grad_norm": 0.3279027907069977,
|
| 700 |
+
"learning_rate": 3.3239465357292304e-05,
|
| 701 |
+
"loss": 0.5376,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.46644510524167687,
|
| 706 |
+
"grad_norm": 0.3484015010403029,
|
| 707 |
+
"learning_rate": 3.290276951149992e-05,
|
| 708 |
+
"loss": 0.5336,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4711095562940936,
|
| 713 |
+
"grad_norm": 0.33469705746842926,
|
| 714 |
+
"learning_rate": 3.256478480597656e-05,
|
| 715 |
+
"loss": 0.546,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.47577400734651043,
|
| 720 |
+
"grad_norm": 0.30392678850247695,
|
| 721 |
+
"learning_rate": 3.222559186879191e-05,
|
| 722 |
+
"loss": 0.5407,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4804384583989272,
|
| 727 |
+
"grad_norm": 0.29705201467826636,
|
| 728 |
+
"learning_rate": 3.18852716162458e-05,
|
| 729 |
+
"loss": 0.5395,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.48510290945134393,
|
| 734 |
+
"grad_norm": 0.31309471816872475,
|
| 735 |
+
"learning_rate": 3.154390523356523e-05,
|
| 736 |
+
"loss": 0.5309,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.48976736050376074,
|
| 741 |
+
"grad_norm": 0.3532094930450357,
|
| 742 |
+
"learning_rate": 3.1201574155537155e-05,
|
| 743 |
+
"loss": 0.5341,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4944318115561775,
|
| 748 |
+
"grad_norm": 0.3130231914781531,
|
| 749 |
+
"learning_rate": 3.085836004708179e-05,
|
| 750 |
+
"loss": 0.5243,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.49909626260859424,
|
| 755 |
+
"grad_norm": 0.32746390804605524,
|
| 756 |
+
"learning_rate": 3.0514344783771015e-05,
|
| 757 |
+
"loss": 0.5458,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.503760713661011,
|
| 762 |
+
"grad_norm": 0.3140774516982654,
|
| 763 |
+
"learning_rate": 3.0169610432296513e-05,
|
| 764 |
+
"loss": 0.542,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5084251647134278,
|
| 769 |
+
"grad_norm": 0.33623222677088005,
|
| 770 |
+
"learning_rate": 2.9824239230892316e-05,
|
| 771 |
+
"loss": 0.5449,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5130896157658446,
|
| 776 |
+
"grad_norm": 0.34034229987032566,
|
| 777 |
+
"learning_rate": 2.9478313569716425e-05,
|
| 778 |
+
"loss": 0.5399,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5177540668182613,
|
| 783 |
+
"grad_norm": 0.31316724089217596,
|
| 784 |
+
"learning_rate": 2.9131915971196216e-05,
|
| 785 |
+
"loss": 0.538,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5224185178706781,
|
| 790 |
+
"grad_norm": 0.3088718959081153,
|
| 791 |
+
"learning_rate": 2.8785129070342247e-05,
|
| 792 |
+
"loss": 0.5415,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5270829689230948,
|
| 797 |
+
"grad_norm": 0.34309616279067395,
|
| 798 |
+
"learning_rate": 2.8438035595035235e-05,
|
| 799 |
+
"loss": 0.5323,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5317474199755117,
|
| 804 |
+
"grad_norm": 0.3160243240149518,
|
| 805 |
+
"learning_rate": 2.8090718346290902e-05,
|
| 806 |
+
"loss": 0.5227,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5364118710279284,
|
| 811 |
+
"grad_norm": 0.30318761428213864,
|
| 812 |
+
"learning_rate": 2.77432601785073e-05,
|
| 813 |
+
"loss": 0.538,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5410763220803452,
|
| 818 |
+
"grad_norm": 0.33554969124573514,
|
| 819 |
+
"learning_rate": 2.7395743979699527e-05,
|
| 820 |
+
"loss": 0.5423,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5457407731327619,
|
| 825 |
+
"grad_norm": 0.29358246176347985,
|
| 826 |
+
"learning_rate": 2.7048252651726237e-05,
|
| 827 |
+
"loss": 0.5302,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5504052241851787,
|
| 832 |
+
"grad_norm": 0.27227963891831986,
|
| 833 |
+
"learning_rate": 2.6700869090513025e-05,
|
| 834 |
+
"loss": 0.5276,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5550696752375954,
|
| 839 |
+
"grad_norm": 0.3315788476523275,
|
| 840 |
+
"learning_rate": 2.6353676166277175e-05,
|
| 841 |
+
"loss": 0.5375,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5597341262900123,
|
| 846 |
+
"grad_norm": 0.29167775719810907,
|
| 847 |
+
"learning_rate": 2.6006756703758462e-05,
|
| 848 |
+
"loss": 0.5287,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.564398577342429,
|
| 853 |
+
"grad_norm": 0.2836903485895201,
|
| 854 |
+
"learning_rate": 2.5660193462460914e-05,
|
| 855 |
+
"loss": 0.5209,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5690630283948458,
|
| 860 |
+
"grad_norm": 0.312902944542489,
|
| 861 |
+
"learning_rate": 2.5314069116910073e-05,
|
| 862 |
+
"loss": 0.5352,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5737274794472625,
|
| 867 |
+
"grad_norm": 0.3061911987604843,
|
| 868 |
+
"learning_rate": 2.496846623693052e-05,
|
| 869 |
+
"loss": 0.5418,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5783919304996793,
|
| 874 |
+
"grad_norm": 0.30918289084780787,
|
| 875 |
+
"learning_rate": 2.4623467267948453e-05,
|
| 876 |
+
"loss": 0.5264,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.583056381552096,
|
| 881 |
+
"grad_norm": 0.29432202760005055,
|
| 882 |
+
"learning_rate": 2.427915451132382e-05,
|
| 883 |
+
"loss": 0.5303,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5877208326045129,
|
| 888 |
+
"grad_norm": 0.30248260299992763,
|
| 889 |
+
"learning_rate": 2.3935610104716934e-05,
|
| 890 |
+
"loss": 0.5318,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5923852836569297,
|
| 895 |
+
"grad_norm": 0.2921703613190239,
|
| 896 |
+
"learning_rate": 2.359291600249407e-05,
|
| 897 |
+
"loss": 0.5351,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5970497347093464,
|
| 902 |
+
"grad_norm": 0.2861561331468405,
|
| 903 |
+
"learning_rate": 2.325115395617683e-05,
|
| 904 |
+
"loss": 0.5191,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6017141857617632,
|
| 909 |
+
"grad_norm": 0.29199262406988685,
|
| 910 |
+
"learning_rate": 2.291040549493985e-05,
|
| 911 |
+
"loss": 0.5314,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6063786368141799,
|
| 916 |
+
"grad_norm": 0.28022740610521435,
|
| 917 |
+
"learning_rate": 2.2570751906161624e-05,
|
| 918 |
+
"loss": 0.5189,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6110430878665967,
|
| 923 |
+
"grad_norm": 0.32229685451288487,
|
| 924 |
+
"learning_rate": 2.223227421603289e-05,
|
| 925 |
+
"loss": 0.5277,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6157075389190134,
|
| 930 |
+
"grad_norm": 0.2812720351153964,
|
| 931 |
+
"learning_rate": 2.1895053170227464e-05,
|
| 932 |
+
"loss": 0.5315,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6203719899714303,
|
| 937 |
+
"grad_norm": 0.2888622086540738,
|
| 938 |
+
"learning_rate": 2.1559169214639884e-05,
|
| 939 |
+
"loss": 0.5277,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.625036441023847,
|
| 944 |
+
"grad_norm": 0.3120048352568711,
|
| 945 |
+
"learning_rate": 2.122470247619464e-05,
|
| 946 |
+
"loss": 0.525,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6297008920762638,
|
| 951 |
+
"grad_norm": 0.2818693243090786,
|
| 952 |
+
"learning_rate": 2.0891732743731434e-05,
|
| 953 |
+
"loss": 0.5322,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6343653431286805,
|
| 958 |
+
"grad_norm": 0.2926059214892839,
|
| 959 |
+
"learning_rate": 2.0560339448971146e-05,
|
| 960 |
+
"loss": 0.525,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6390297941810973,
|
| 965 |
+
"grad_norm": 0.29268503655464984,
|
| 966 |
+
"learning_rate": 2.0230601647566966e-05,
|
| 967 |
+
"loss": 0.5247,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.643694245233514,
|
| 972 |
+
"grad_norm": 0.2728644227058383,
|
| 973 |
+
"learning_rate": 1.9902598000245222e-05,
|
| 974 |
+
"loss": 0.5185,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6483586962859309,
|
| 979 |
+
"grad_norm": 0.25962809295866146,
|
| 980 |
+
"learning_rate": 1.9576406754040467e-05,
|
| 981 |
+
"loss": 0.5228,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6530231473383477,
|
| 986 |
+
"grad_norm": 0.2939794591562482,
|
| 987 |
+
"learning_rate": 1.925210572362922e-05,
|
| 988 |
+
"loss": 0.5402,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6576875983907644,
|
| 993 |
+
"grad_norm": 0.2675031379318846,
|
| 994 |
+
"learning_rate": 1.892977227276685e-05,
|
| 995 |
+
"loss": 0.5224,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6623520494431812,
|
| 1000 |
+
"grad_norm": 0.33077413707192227,
|
| 1001 |
+
"learning_rate": 1.8609483295832036e-05,
|
| 1002 |
+
"loss": 0.5145,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6670165004955979,
|
| 1007 |
+
"grad_norm": 0.28316621823190463,
|
| 1008 |
+
"learning_rate": 1.829131519948323e-05,
|
| 1009 |
+
"loss": 0.518,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6716809515480147,
|
| 1014 |
+
"grad_norm": 0.28091675149417483,
|
| 1015 |
+
"learning_rate": 1.7975343884431357e-05,
|
| 1016 |
+
"loss": 0.5204,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6763454026004314,
|
| 1021 |
+
"grad_norm": 0.30963978843403667,
|
| 1022 |
+
"learning_rate": 1.7661644727333403e-05,
|
| 1023 |
+
"loss": 0.524,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6810098536528483,
|
| 1028 |
+
"grad_norm": 0.27818187692784135,
|
| 1029 |
+
"learning_rate": 1.7350292562810832e-05,
|
| 1030 |
+
"loss": 0.5202,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.685674304705265,
|
| 1035 |
+
"grad_norm": 0.28024391562302353,
|
| 1036 |
+
"learning_rate": 1.704136166559737e-05,
|
| 1037 |
+
"loss": 0.5216,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6903387557576818,
|
| 1042 |
+
"grad_norm": 0.25776425960390403,
|
| 1043 |
+
"learning_rate": 1.6734925732820454e-05,
|
| 1044 |
+
"loss": 0.5201,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6950032068100985,
|
| 1049 |
+
"grad_norm": 0.25912854344445496,
|
| 1050 |
+
"learning_rate": 1.6431057866420313e-05,
|
| 1051 |
+
"loss": 0.5154,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6996676578625153,
|
| 1056 |
+
"grad_norm": 0.288843246635576,
|
| 1057 |
+
"learning_rate": 1.61298305557111e-05,
|
| 1058 |
+
"loss": 0.5319,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.704332108914932,
|
| 1063 |
+
"grad_norm": 0.27843803013272117,
|
| 1064 |
+
"learning_rate": 1.583131566008825e-05,
|
| 1065 |
+
"loss": 0.5322,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7089965599673489,
|
| 1070 |
+
"grad_norm": 0.2724850636300469,
|
| 1071 |
+
"learning_rate": 1.553558439188594e-05,
|
| 1072 |
+
"loss": 0.5188,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7136610110197656,
|
| 1077 |
+
"grad_norm": 0.27405031166570964,
|
| 1078 |
+
"learning_rate": 1.5242707299389086e-05,
|
| 1079 |
+
"loss": 0.5264,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7183254620721824,
|
| 1084 |
+
"grad_norm": 0.28279666997673636,
|
| 1085 |
+
"learning_rate": 1.4952754250003637e-05,
|
| 1086 |
+
"loss": 0.5296,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7229899131245991,
|
| 1091 |
+
"grad_norm": 0.276837438024271,
|
| 1092 |
+
"learning_rate": 1.4665794413589298e-05,
|
| 1093 |
+
"loss": 0.5364,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7276543641770159,
|
| 1098 |
+
"grad_norm": 0.2724777598286785,
|
| 1099 |
+
"learning_rate": 1.4381896245958752e-05,
|
| 1100 |
+
"loss": 0.5158,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7323188152294327,
|
| 1105 |
+
"grad_norm": 0.2649273346430747,
|
| 1106 |
+
"learning_rate": 1.4101127472547084e-05,
|
| 1107 |
+
"loss": 0.519,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7369832662818494,
|
| 1112 |
+
"grad_norm": 0.2699794671741458,
|
| 1113 |
+
"learning_rate": 1.3823555072255606e-05,
|
| 1114 |
+
"loss": 0.5276,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7416477173342663,
|
| 1119 |
+
"grad_norm": 0.2597781223574146,
|
| 1120 |
+
"learning_rate": 1.354924526147357e-05,
|
| 1121 |
+
"loss": 0.5158,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.746312168386683,
|
| 1126 |
+
"grad_norm": 0.28723301584203204,
|
| 1127 |
+
"learning_rate": 1.3278263478281994e-05,
|
| 1128 |
+
"loss": 0.5224,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7509766194390998,
|
| 1133 |
+
"grad_norm": 0.2535306464938602,
|
| 1134 |
+
"learning_rate": 1.3010674366843001e-05,
|
| 1135 |
+
"loss": 0.5361,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7556410704915165,
|
| 1140 |
+
"grad_norm": 0.27848610430564497,
|
| 1141 |
+
"learning_rate": 1.2746541761978592e-05,
|
| 1142 |
+
"loss": 0.5148,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7603055215439333,
|
| 1147 |
+
"grad_norm": 0.26508085752140736,
|
| 1148 |
+
"learning_rate": 1.2485928673942568e-05,
|
| 1149 |
+
"loss": 0.5197,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.76496997259635,
|
| 1154 |
+
"grad_norm": 0.2765576189082103,
|
| 1155 |
+
"learning_rate": 1.2228897273389022e-05,
|
| 1156 |
+
"loss": 0.5043,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7696344236487669,
|
| 1161 |
+
"grad_norm": 0.25179624599466677,
|
| 1162 |
+
"learning_rate": 1.1975508876541262e-05,
|
| 1163 |
+
"loss": 0.5252,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7742988747011836,
|
| 1168 |
+
"grad_norm": 0.2597455495271655,
|
| 1169 |
+
"learning_rate": 1.1725823930564436e-05,
|
| 1170 |
+
"loss": 0.5292,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7789633257536004,
|
| 1175 |
+
"grad_norm": 0.2525298953468885,
|
| 1176 |
+
"learning_rate": 1.1479901999145583e-05,
|
| 1177 |
+
"loss": 0.5194,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7836277768060171,
|
| 1182 |
+
"grad_norm": 0.26668419176346814,
|
| 1183 |
+
"learning_rate": 1.1237801748284375e-05,
|
| 1184 |
+
"loss": 0.5183,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7882922278584339,
|
| 1189 |
+
"grad_norm": 0.2576707752493972,
|
| 1190 |
+
"learning_rate": 1.099958093229802e-05,
|
| 1191 |
+
"loss": 0.5145,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7929566789108506,
|
| 1196 |
+
"grad_norm": 0.2519900873666899,
|
| 1197 |
+
"learning_rate": 1.0765296380043684e-05,
|
| 1198 |
+
"loss": 0.52,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7976211299632674,
|
| 1203 |
+
"grad_norm": 0.25029147728099826,
|
| 1204 |
+
"learning_rate": 1.0535003981361613e-05,
|
| 1205 |
+
"loss": 0.5085,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8022855810156843,
|
| 1210 |
+
"grad_norm": 0.25974689320051614,
|
| 1211 |
+
"learning_rate": 1.030875867374238e-05,
|
| 1212 |
+
"loss": 0.5276,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.806950032068101,
|
| 1217 |
+
"grad_norm": 0.2750183412160561,
|
| 1218 |
+
"learning_rate": 1.008661442922118e-05,
|
| 1219 |
+
"loss": 0.5288,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8116144831205178,
|
| 1224 |
+
"grad_norm": 0.24684508884873066,
|
| 1225 |
+
"learning_rate": 9.868624241502573e-06,
|
| 1226 |
+
"loss": 0.5108,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8162789341729345,
|
| 1231 |
+
"grad_norm": 0.24917506535926326,
|
| 1232 |
+
"learning_rate": 9.654840113318506e-06,
|
| 1233 |
+
"loss": 0.5153,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8209433852253513,
|
| 1238 |
+
"grad_norm": 0.26588122762475325,
|
| 1239 |
+
"learning_rate": 9.445313044022797e-06,
|
| 1240 |
+
"loss": 0.5134,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.825607836277768,
|
| 1245 |
+
"grad_norm": 0.25205075163043134,
|
| 1246 |
+
"learning_rate": 9.240093017424978e-06,
|
| 1247 |
+
"loss": 0.5234,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8302722873301849,
|
| 1252 |
+
"grad_norm": 0.24453056572204862,
|
| 1253 |
+
"learning_rate": 9.039228989866358e-06,
|
| 1254 |
+
"loss": 0.5256,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8349367383826016,
|
| 1259 |
+
"grad_norm": 0.25964646851376255,
|
| 1260 |
+
"learning_rate": 8.84276887854126e-06,
|
| 1261 |
+
"loss": 0.5197,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8396011894350184,
|
| 1266 |
+
"grad_norm": 0.2380789074605979,
|
| 1267 |
+
"learning_rate": 8.650759550066084e-06,
|
| 1268 |
+
"loss": 0.5226,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8442656404874351,
|
| 1273 |
+
"grad_norm": 0.25537829061619166,
|
| 1274 |
+
"learning_rate": 8.46324680929905e-06,
|
| 1275 |
+
"loss": 0.5109,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8489300915398519,
|
| 1280 |
+
"grad_norm": 0.24326625950869546,
|
| 1281 |
+
"learning_rate": 8.280275388413186e-06,
|
| 1282 |
+
"loss": 0.5171,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8535945425922686,
|
| 1287 |
+
"grad_norm": 0.283956175304338,
|
| 1288 |
+
"learning_rate": 8.10188893622523e-06,
|
| 1289 |
+
"loss": 0.5138,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8582589936446854,
|
| 1294 |
+
"grad_norm": 0.26712492993115533,
|
| 1295 |
+
"learning_rate": 7.928130007782977e-06,
|
| 1296 |
+
"loss": 0.5347,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8629234446971022,
|
| 1301 |
+
"grad_norm": 0.2770179693009444,
|
| 1302 |
+
"learning_rate": 7.759040054213531e-06,
|
| 1303 |
+
"loss": 0.5332,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.867587895749519,
|
| 1308 |
+
"grad_norm": 0.25471359044347464,
|
| 1309 |
+
"learning_rate": 7.59465941283494e-06,
|
| 1310 |
+
"loss": 0.5245,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8722523468019358,
|
| 1315 |
+
"grad_norm": 0.2474269162576819,
|
| 1316 |
+
"learning_rate": 7.435027297533474e-06,
|
| 1317 |
+
"loss": 0.5122,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8769167978543525,
|
| 1322 |
+
"grad_norm": 0.25130162397546496,
|
| 1323 |
+
"learning_rate": 7.2801817894089756e-06,
|
| 1324 |
+
"loss": 0.5063,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.8815812489067693,
|
| 1329 |
+
"grad_norm": 0.24881956227908078,
|
| 1330 |
+
"learning_rate": 7.130159827690404e-06,
|
| 1331 |
+
"loss": 0.5177,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.886245699959186,
|
| 1336 |
+
"grad_norm": 0.25545295509666294,
|
| 1337 |
+
"learning_rate": 6.98499720092375e-06,
|
| 1338 |
+
"loss": 0.508,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8909101510116029,
|
| 1343 |
+
"grad_norm": 0.24814116495940802,
|
| 1344 |
+
"learning_rate": 6.844728538434536e-06,
|
| 1345 |
+
"loss": 0.5156,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8955746020640196,
|
| 1350 |
+
"grad_norm": 0.24345586049308032,
|
| 1351 |
+
"learning_rate": 6.709387302066758e-06,
|
| 1352 |
+
"loss": 0.5192,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.9002390531164364,
|
| 1357 |
+
"grad_norm": 0.25035521575621933,
|
| 1358 |
+
"learning_rate": 6.579005778200434e-06,
|
| 1359 |
+
"loss": 0.5253,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9049035041688531,
|
| 1364 |
+
"grad_norm": 0.2580394858408089,
|
| 1365 |
+
"learning_rate": 6.453615070049447e-06,
|
| 1366 |
+
"loss": 0.5251,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9095679552212699,
|
| 1371 |
+
"grad_norm": 0.23956216998636262,
|
| 1372 |
+
"learning_rate": 6.3332450902417666e-06,
|
| 1373 |
+
"loss": 0.5107,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9142324062736866,
|
| 1378 |
+
"grad_norm": 0.23764348877193034,
|
| 1379 |
+
"learning_rate": 6.21792455368361e-06,
|
| 1380 |
+
"loss": 0.5129,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9188968573261035,
|
| 1385 |
+
"grad_norm": 0.2520198832874535,
|
| 1386 |
+
"learning_rate": 6.1076809707093225e-06,
|
| 1387 |
+
"loss": 0.5208,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9235613083785202,
|
| 1392 |
+
"grad_norm": 0.23664963056881916,
|
| 1393 |
+
"learning_rate": 6.002540640518684e-06,
|
| 1394 |
+
"loss": 0.5066,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.928225759430937,
|
| 1399 |
+
"grad_norm": 0.3088138680489082,
|
| 1400 |
+
"learning_rate": 5.902528644903055e-06,
|
| 1401 |
+
"loss": 0.5153,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9328902104833537,
|
| 1406 |
+
"grad_norm": 0.24722065847341207,
|
| 1407 |
+
"learning_rate": 5.807668842262004e-06,
|
| 1408 |
+
"loss": 0.5169,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.9375546615357705,
|
| 1413 |
+
"grad_norm": 0.2351634623111495,
|
| 1414 |
+
"learning_rate": 5.7179838619117394e-06,
|
| 1415 |
+
"loss": 0.5097,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9422191125881872,
|
| 1420 |
+
"grad_norm": 0.2422992129098815,
|
| 1421 |
+
"learning_rate": 5.633495098686789e-06,
|
| 1422 |
+
"loss": 0.5119,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.946883563640604,
|
| 1427 |
+
"grad_norm": 0.2550904076289393,
|
| 1428 |
+
"learning_rate": 5.554222707836121e-06,
|
| 1429 |
+
"loss": 0.5147,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9515480146930209,
|
| 1434 |
+
"grad_norm": 0.25885529407119634,
|
| 1435 |
+
"learning_rate": 5.480185600215012e-06,
|
| 1436 |
+
"loss": 0.5079,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9562124657454376,
|
| 1441 |
+
"grad_norm": 0.23792385142576641,
|
| 1442 |
+
"learning_rate": 5.411401437773773e-06,
|
| 1443 |
+
"loss": 0.5143,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9608769167978544,
|
| 1448 |
+
"grad_norm": 0.24312465281652115,
|
| 1449 |
+
"learning_rate": 5.347886629344369e-06,
|
| 1450 |
+
"loss": 0.5107,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9655413678502711,
|
| 1455 |
+
"grad_norm": 0.23595847074173298,
|
| 1456 |
+
"learning_rate": 5.28965632672603e-06,
|
| 1457 |
+
"loss": 0.5187,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9702058189026879,
|
| 1462 |
+
"grad_norm": 0.2479378393066615,
|
| 1463 |
+
"learning_rate": 5.236724421070693e-06,
|
| 1464 |
+
"loss": 0.5144,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9748702699551046,
|
| 1469 |
+
"grad_norm": 0.24722093987308796,
|
| 1470 |
+
"learning_rate": 5.189103539569195e-06,
|
| 1471 |
+
"loss": 0.5215,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9795347210075215,
|
| 1476 |
+
"grad_norm": 0.23704918121696106,
|
| 1477 |
+
"learning_rate": 5.146805042438997e-06,
|
| 1478 |
+
"loss": 0.516,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9841991720599382,
|
| 1483 |
+
"grad_norm": 0.2499713377733996,
|
| 1484 |
+
"learning_rate": 5.10983902021413e-06,
|
| 1485 |
+
"loss": 0.5086,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.988863623112355,
|
| 1490 |
+
"grad_norm": 0.24126794921726105,
|
| 1491 |
+
"learning_rate": 5.078214291338054e-06,
|
| 1492 |
+
"loss": 0.5263,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9935280741647717,
|
| 1497 |
+
"grad_norm": 0.2575581210389819,
|
| 1498 |
+
"learning_rate": 5.051938400059965e-06,
|
| 1499 |
+
"loss": 0.5173,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9981925252171885,
|
| 1504 |
+
"grad_norm": 0.24967221419990557,
|
| 1505 |
+
"learning_rate": 5.031017614635082e-06,
|
| 1506 |
+
"loss": 0.5177,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.9991254154276719,
|
| 1511 |
+
"step": 1071,
|
| 1512 |
+
"total_flos": 486995857768448.0,
|
| 1513 |
+
"train_loss": 0.5541811234532507,
|
| 1514 |
+
"train_runtime": 156721.9484,
|
| 1515 |
+
"train_samples_per_second": 0.219,
|
| 1516 |
+
"train_steps_per_second": 0.007
|
| 1517 |
+
}
|
| 1518 |
+
],
|
| 1519 |
+
"logging_steps": 5,
|
| 1520 |
+
"max_steps": 1071,
|
| 1521 |
+
"num_input_tokens_seen": 0,
|
| 1522 |
+
"num_train_epochs": 1,
|
| 1523 |
+
"save_steps": 100,
|
| 1524 |
+
"stateful_callbacks": {
|
| 1525 |
+
"TrainerControl": {
|
| 1526 |
+
"args": {
|
| 1527 |
+
"should_epoch_stop": false,
|
| 1528 |
+
"should_evaluate": false,
|
| 1529 |
+
"should_log": false,
|
| 1530 |
+
"should_save": true,
|
| 1531 |
+
"should_training_stop": true
|
| 1532 |
+
},
|
| 1533 |
+
"attributes": {}
|
| 1534 |
+
}
|
| 1535 |
+
},
|
| 1536 |
+
"total_flos": 486995857768448.0,
|
| 1537 |
+
"train_batch_size": 1,
|
| 1538 |
+
"trial_name": null,
|
| 1539 |
+
"trial_params": null
|
| 1540 |
+
}
|