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 +2387 -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="samyakjain/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/samyakjain/huggingface/runs/sq66qprs)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.17.0.dev0
|
| 38 |
+
- Transformers: 4.51.2
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 3.5.0
|
| 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": 1146719604572160.0,
|
| 3 |
+
"train_loss": 0.5249247749510886,
|
| 4 |
+
"train_runtime": 25895.7798,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 3.62,
|
| 7 |
+
"train_steps_per_second": 0.057
|
| 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": "4.51.2"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1146719604572160.0,
|
| 3 |
+
"train_loss": 0.5249247749510886,
|
| 4 |
+
"train_runtime": 25895.7798,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 3.62,
|
| 7 |
+
"train_steps_per_second": 0.057
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1465,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0034129692832764505,
|
| 14 |
+
"grad_norm": 2.548544966196333,
|
| 15 |
+
"learning_rate": 2.702702702702703e-06,
|
| 16 |
+
"loss": 0.8721,
|
| 17 |
+
"num_tokens": 1934239.0,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.006825938566552901,
|
| 22 |
+
"grad_norm": 1.626137083918253,
|
| 23 |
+
"learning_rate": 6.081081081081082e-06,
|
| 24 |
+
"loss": 0.8128,
|
| 25 |
+
"num_tokens": 3759778.0,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.010238907849829351,
|
| 30 |
+
"grad_norm": 0.9545778260789548,
|
| 31 |
+
"learning_rate": 9.45945945945946e-06,
|
| 32 |
+
"loss": 0.7786,
|
| 33 |
+
"num_tokens": 5645472.0,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.013651877133105802,
|
| 38 |
+
"grad_norm": 0.7154970291928818,
|
| 39 |
+
"learning_rate": 1.2837837837837838e-05,
|
| 40 |
+
"loss": 0.7226,
|
| 41 |
+
"num_tokens": 7670069.0,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.017064846416382253,
|
| 46 |
+
"grad_norm": 0.5846074395676264,
|
| 47 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 48 |
+
"loss": 0.6862,
|
| 49 |
+
"num_tokens": 9514590.0,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.020477815699658702,
|
| 54 |
+
"grad_norm": 0.5056753312651349,
|
| 55 |
+
"learning_rate": 1.9594594594594595e-05,
|
| 56 |
+
"loss": 0.6479,
|
| 57 |
+
"num_tokens": 11370767.0,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.023890784982935155,
|
| 62 |
+
"grad_norm": 0.47658516178480675,
|
| 63 |
+
"learning_rate": 2.2972972972972976e-05,
|
| 64 |
+
"loss": 0.6475,
|
| 65 |
+
"num_tokens": 13221634.0,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.027303754266211604,
|
| 70 |
+
"grad_norm": 0.4638027919687561,
|
| 71 |
+
"learning_rate": 2.635135135135135e-05,
|
| 72 |
+
"loss": 0.6257,
|
| 73 |
+
"num_tokens": 15120586.0,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.030716723549488054,
|
| 78 |
+
"grad_norm": 0.44358652185247893,
|
| 79 |
+
"learning_rate": 2.9729729729729733e-05,
|
| 80 |
+
"loss": 0.6281,
|
| 81 |
+
"num_tokens": 17045024.0,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.034129692832764506,
|
| 86 |
+
"grad_norm": 0.4651702936888929,
|
| 87 |
+
"learning_rate": 3.310810810810811e-05,
|
| 88 |
+
"loss": 0.6122,
|
| 89 |
+
"num_tokens": 18909989.0,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.03754266211604096,
|
| 94 |
+
"grad_norm": 0.49958203260966805,
|
| 95 |
+
"learning_rate": 3.648648648648649e-05,
|
| 96 |
+
"loss": 0.5997,
|
| 97 |
+
"num_tokens": 20794568.0,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.040955631399317405,
|
| 102 |
+
"grad_norm": 0.46234171042887173,
|
| 103 |
+
"learning_rate": 3.986486486486487e-05,
|
| 104 |
+
"loss": 0.608,
|
| 105 |
+
"num_tokens": 22645536.0,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.04436860068259386,
|
| 110 |
+
"grad_norm": 0.4700714246123513,
|
| 111 |
+
"learning_rate": 4.324324324324325e-05,
|
| 112 |
+
"loss": 0.6092,
|
| 113 |
+
"num_tokens": 24609009.0,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04778156996587031,
|
| 118 |
+
"grad_norm": 0.6093737475361762,
|
| 119 |
+
"learning_rate": 4.662162162162162e-05,
|
| 120 |
+
"loss": 0.6023,
|
| 121 |
+
"num_tokens": 26641035.0,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.051194539249146756,
|
| 126 |
+
"grad_norm": 0.6315502822311596,
|
| 127 |
+
"learning_rate": 5e-05,
|
| 128 |
+
"loss": 0.5699,
|
| 129 |
+
"num_tokens": 28445983.0,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05460750853242321,
|
| 134 |
+
"grad_norm": 0.5834830471152899,
|
| 135 |
+
"learning_rate": 4.999856539149453e-05,
|
| 136 |
+
"loss": 0.5927,
|
| 137 |
+
"num_tokens": 30423007.0,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.05802047781569966,
|
| 142 |
+
"grad_norm": 0.4530921543331263,
|
| 143 |
+
"learning_rate": 4.99942617489205e-05,
|
| 144 |
+
"loss": 0.588,
|
| 145 |
+
"num_tokens": 32356676.0,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.06143344709897611,
|
| 150 |
+
"grad_norm": 0.507488777452295,
|
| 151 |
+
"learning_rate": 4.998708962108165e-05,
|
| 152 |
+
"loss": 0.5875,
|
| 153 |
+
"num_tokens": 34237001.0,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.06484641638225255,
|
| 158 |
+
"grad_norm": 0.5280116393257583,
|
| 159 |
+
"learning_rate": 4.9977049922573155e-05,
|
| 160 |
+
"loss": 0.5841,
|
| 161 |
+
"num_tokens": 36074352.0,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.06825938566552901,
|
| 166 |
+
"grad_norm": 0.47581443558983,
|
| 167 |
+
"learning_rate": 4.9964143933664945e-05,
|
| 168 |
+
"loss": 0.5963,
|
| 169 |
+
"num_tokens": 37967720.0,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.07167235494880546,
|
| 174 |
+
"grad_norm": 0.5526167503268111,
|
| 175 |
+
"learning_rate": 4.99483733001385e-05,
|
| 176 |
+
"loss": 0.5952,
|
| 177 |
+
"num_tokens": 39853351.0,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07508532423208192,
|
| 182 |
+
"grad_norm": 0.5524917233180515,
|
| 183 |
+
"learning_rate": 4.9929740033076915e-05,
|
| 184 |
+
"loss": 0.5898,
|
| 185 |
+
"num_tokens": 41833783.0,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.07849829351535836,
|
| 190 |
+
"grad_norm": 0.5484490641540218,
|
| 191 |
+
"learning_rate": 4.9908246508608506e-05,
|
| 192 |
+
"loss": 0.5847,
|
| 193 |
+
"num_tokens": 43682290.0,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.08191126279863481,
|
| 198 |
+
"grad_norm": 0.46028213908049764,
|
| 199 |
+
"learning_rate": 4.9883895467603764e-05,
|
| 200 |
+
"loss": 0.5772,
|
| 201 |
+
"num_tokens": 45550959.0,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.08532423208191127,
|
| 206 |
+
"grad_norm": 0.45911611077545783,
|
| 207 |
+
"learning_rate": 4.985669001532583e-05,
|
| 208 |
+
"loss": 0.5904,
|
| 209 |
+
"num_tokens": 47474526.0,
|
| 210 |
+
"step": 125
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.08873720136518772,
|
| 214 |
+
"grad_norm": 0.4606567455923573,
|
| 215 |
+
"learning_rate": 4.982663362103456e-05,
|
| 216 |
+
"loss": 0.5818,
|
| 217 |
+
"num_tokens": 49377672.0,
|
| 218 |
+
"step": 130
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.09215017064846416,
|
| 222 |
+
"grad_norm": 0.534408944517721,
|
| 223 |
+
"learning_rate": 4.979373011754409e-05,
|
| 224 |
+
"loss": 0.5773,
|
| 225 |
+
"num_tokens": 51201531.0,
|
| 226 |
+
"step": 135
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.09556313993174062,
|
| 230 |
+
"grad_norm": 0.529142305766466,
|
| 231 |
+
"learning_rate": 4.975798370073404e-05,
|
| 232 |
+
"loss": 0.5765,
|
| 233 |
+
"num_tokens": 53019691.0,
|
| 234 |
+
"step": 140
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09897610921501707,
|
| 238 |
+
"grad_norm": 0.4792616482185223,
|
| 239 |
+
"learning_rate": 4.971939892901451e-05,
|
| 240 |
+
"loss": 0.5695,
|
| 241 |
+
"num_tokens": 54928756.0,
|
| 242 |
+
"step": 145
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.10238907849829351,
|
| 246 |
+
"grad_norm": 0.42280187007557707,
|
| 247 |
+
"learning_rate": 4.9677980722744774e-05,
|
| 248 |
+
"loss": 0.5881,
|
| 249 |
+
"num_tokens": 56919336.0,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.10580204778156997,
|
| 254 |
+
"grad_norm": 0.4606975501454269,
|
| 255 |
+
"learning_rate": 4.9633734363605805e-05,
|
| 256 |
+
"loss": 0.5585,
|
| 257 |
+
"num_tokens": 58769487.0,
|
| 258 |
+
"step": 155
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.10921501706484642,
|
| 262 |
+
"grad_norm": 0.43615006224860764,
|
| 263 |
+
"learning_rate": 4.9586665493926773e-05,
|
| 264 |
+
"loss": 0.5655,
|
| 265 |
+
"num_tokens": 60660649.0,
|
| 266 |
+
"step": 160
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.11262798634812286,
|
| 270 |
+
"grad_norm": 0.42375502492198164,
|
| 271 |
+
"learning_rate": 4.9536780115965514e-05,
|
| 272 |
+
"loss": 0.5497,
|
| 273 |
+
"num_tokens": 62673288.0,
|
| 274 |
+
"step": 165
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.11604095563139932,
|
| 278 |
+
"grad_norm": 0.4844961809839781,
|
| 279 |
+
"learning_rate": 4.9484084591143154e-05,
|
| 280 |
+
"loss": 0.562,
|
| 281 |
+
"num_tokens": 64575366.0,
|
| 282 |
+
"step": 170
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.11945392491467577,
|
| 286 |
+
"grad_norm": 0.43841808460586534,
|
| 287 |
+
"learning_rate": 4.942858563923285e-05,
|
| 288 |
+
"loss": 0.5668,
|
| 289 |
+
"num_tokens": 66496209.0,
|
| 290 |
+
"step": 175
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12286689419795221,
|
| 294 |
+
"grad_norm": 0.4766943001338558,
|
| 295 |
+
"learning_rate": 4.9370290337502924e-05,
|
| 296 |
+
"loss": 0.5804,
|
| 297 |
+
"num_tokens": 68438217.0,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.12627986348122866,
|
| 302 |
+
"grad_norm": 0.4198374036223196,
|
| 303 |
+
"learning_rate": 4.930920611981431e-05,
|
| 304 |
+
"loss": 0.5699,
|
| 305 |
+
"num_tokens": 70344364.0,
|
| 306 |
+
"step": 185
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.1296928327645051,
|
| 310 |
+
"grad_norm": 0.49422910711852325,
|
| 311 |
+
"learning_rate": 4.9245340775672634e-05,
|
| 312 |
+
"loss": 0.5691,
|
| 313 |
+
"num_tokens": 72264786.0,
|
| 314 |
+
"step": 190
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.13310580204778158,
|
| 318 |
+
"grad_norm": 0.453882616672693,
|
| 319 |
+
"learning_rate": 4.917870244923486e-05,
|
| 320 |
+
"loss": 0.5438,
|
| 321 |
+
"num_tokens": 74233642.0,
|
| 322 |
+
"step": 195
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.13651877133105803,
|
| 326 |
+
"grad_norm": 0.5756509603963873,
|
| 327 |
+
"learning_rate": 4.910929963827078e-05,
|
| 328 |
+
"loss": 0.5682,
|
| 329 |
+
"num_tokens": 76173511.0,
|
| 330 |
+
"step": 200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.13993174061433447,
|
| 334 |
+
"grad_norm": 0.3995662121963855,
|
| 335 |
+
"learning_rate": 4.903714119307929e-05,
|
| 336 |
+
"loss": 0.5562,
|
| 337 |
+
"num_tokens": 78183541.0,
|
| 338 |
+
"step": 205
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.14334470989761092,
|
| 342 |
+
"grad_norm": 0.45740572137939717,
|
| 343 |
+
"learning_rate": 4.8962236315359896e-05,
|
| 344 |
+
"loss": 0.5603,
|
| 345 |
+
"num_tokens": 80166162.0,
|
| 346 |
+
"step": 210
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14675767918088736,
|
| 350 |
+
"grad_norm": 0.48595500073515946,
|
| 351 |
+
"learning_rate": 4.8884594557039224e-05,
|
| 352 |
+
"loss": 0.5587,
|
| 353 |
+
"num_tokens": 81987283.0,
|
| 354 |
+
"step": 215
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.15017064846416384,
|
| 358 |
+
"grad_norm": 0.3983919021582111,
|
| 359 |
+
"learning_rate": 4.8804225819052994e-05,
|
| 360 |
+
"loss": 0.5663,
|
| 361 |
+
"num_tokens": 83915537.0,
|
| 362 |
+
"step": 220
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.15358361774744028,
|
| 366 |
+
"grad_norm": 0.50957500979544,
|
| 367 |
+
"learning_rate": 4.872114035008345e-05,
|
| 368 |
+
"loss": 0.5415,
|
| 369 |
+
"num_tokens": 85690047.0,
|
| 370 |
+
"step": 225
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.15699658703071673,
|
| 374 |
+
"grad_norm": 0.48795708834904034,
|
| 375 |
+
"learning_rate": 4.863534874525241e-05,
|
| 376 |
+
"loss": 0.5819,
|
| 377 |
+
"num_tokens": 87705484.0,
|
| 378 |
+
"step": 230
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.16040955631399317,
|
| 382 |
+
"grad_norm": 0.5161800295726106,
|
| 383 |
+
"learning_rate": 4.854686194477017e-05,
|
| 384 |
+
"loss": 0.5514,
|
| 385 |
+
"num_tokens": 89594618.0,
|
| 386 |
+
"step": 235
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.16382252559726962,
|
| 390 |
+
"grad_norm": 0.5012244000835477,
|
| 391 |
+
"learning_rate": 4.845569123254044e-05,
|
| 392 |
+
"loss": 0.5502,
|
| 393 |
+
"num_tokens": 91557529.0,
|
| 394 |
+
"step": 240
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.16723549488054607,
|
| 398 |
+
"grad_norm": 0.42989311927872176,
|
| 399 |
+
"learning_rate": 4.836184823472136e-05,
|
| 400 |
+
"loss": 0.5511,
|
| 401 |
+
"num_tokens": 93508244.0,
|
| 402 |
+
"step": 245
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.17064846416382254,
|
| 406 |
+
"grad_norm": 0.41302488702370377,
|
| 407 |
+
"learning_rate": 4.8265344918242974e-05,
|
| 408 |
+
"loss": 0.5649,
|
| 409 |
+
"num_tokens": 95453893.0,
|
| 410 |
+
"step": 250
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.17406143344709898,
|
| 414 |
+
"grad_norm": 0.49491941680853807,
|
| 415 |
+
"learning_rate": 4.8166193589281154e-05,
|
| 416 |
+
"loss": 0.5566,
|
| 417 |
+
"num_tokens": 97319183.0,
|
| 418 |
+
"step": 255
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.17747440273037543,
|
| 422 |
+
"grad_norm": 0.5757471149939514,
|
| 423 |
+
"learning_rate": 4.806440689168833e-05,
|
| 424 |
+
"loss": 0.5505,
|
| 425 |
+
"num_tokens": 99400041.0,
|
| 426 |
+
"step": 260
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.18088737201365188,
|
| 430 |
+
"grad_norm": 0.5963718594554642,
|
| 431 |
+
"learning_rate": 4.795999780538113e-05,
|
| 432 |
+
"loss": 0.5555,
|
| 433 |
+
"num_tokens": 101373875.0,
|
| 434 |
+
"step": 265
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.18430034129692832,
|
| 438 |
+
"grad_norm": 0.5140578914854042,
|
| 439 |
+
"learning_rate": 4.785297964468519e-05,
|
| 440 |
+
"loss": 0.5495,
|
| 441 |
+
"num_tokens": 103240516.0,
|
| 442 |
+
"step": 270
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.18771331058020477,
|
| 446 |
+
"grad_norm": 0.45078623474474316,
|
| 447 |
+
"learning_rate": 4.7743366056637266e-05,
|
| 448 |
+
"loss": 0.5608,
|
| 449 |
+
"num_tokens": 105061908.0,
|
| 450 |
+
"step": 275
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.19112627986348124,
|
| 454 |
+
"grad_norm": 0.4434221805602034,
|
| 455 |
+
"learning_rate": 4.7631171019244974e-05,
|
| 456 |
+
"loss": 0.569,
|
| 457 |
+
"num_tokens": 106919294.0,
|
| 458 |
+
"step": 280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.1945392491467577,
|
| 462 |
+
"grad_norm": 0.43898962747965786,
|
| 463 |
+
"learning_rate": 4.7516408839704316e-05,
|
| 464 |
+
"loss": 0.5251,
|
| 465 |
+
"num_tokens": 108819219.0,
|
| 466 |
+
"step": 285
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.19795221843003413,
|
| 470 |
+
"grad_norm": 0.4023251373416989,
|
| 471 |
+
"learning_rate": 4.739909415257518e-05,
|
| 472 |
+
"loss": 0.5488,
|
| 473 |
+
"num_tokens": 110858993.0,
|
| 474 |
+
"step": 290
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.20136518771331058,
|
| 478 |
+
"grad_norm": 0.38923943537180394,
|
| 479 |
+
"learning_rate": 4.727924191791518e-05,
|
| 480 |
+
"loss": 0.5519,
|
| 481 |
+
"num_tokens": 112732095.0,
|
| 482 |
+
"step": 295
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.20477815699658702,
|
| 486 |
+
"grad_norm": 0.42337753085194285,
|
| 487 |
+
"learning_rate": 4.7156867419371866e-05,
|
| 488 |
+
"loss": 0.5524,
|
| 489 |
+
"num_tokens": 114540376.0,
|
| 490 |
+
"step": 300
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.20819112627986347,
|
| 494 |
+
"grad_norm": 0.4036586615478129,
|
| 495 |
+
"learning_rate": 4.703198626223383e-05,
|
| 496 |
+
"loss": 0.5376,
|
| 497 |
+
"num_tokens": 116464215.0,
|
| 498 |
+
"step": 305
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.21160409556313994,
|
| 502 |
+
"grad_norm": 0.3864677056350506,
|
| 503 |
+
"learning_rate": 4.6904614371440654e-05,
|
| 504 |
+
"loss": 0.5373,
|
| 505 |
+
"num_tokens": 118465258.0,
|
| 506 |
+
"step": 310
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2150170648464164,
|
| 510 |
+
"grad_norm": 0.4313067695762533,
|
| 511 |
+
"learning_rate": 4.677476798955213e-05,
|
| 512 |
+
"loss": 0.544,
|
| 513 |
+
"num_tokens": 120323497.0,
|
| 514 |
+
"step": 315
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.21843003412969283,
|
| 518 |
+
"grad_norm": 0.43088190735255577,
|
| 519 |
+
"learning_rate": 4.664246367467707e-05,
|
| 520 |
+
"loss": 0.5483,
|
| 521 |
+
"num_tokens": 122331818.0,
|
| 522 |
+
"step": 320
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.22184300341296928,
|
| 526 |
+
"grad_norm": 0.3660236033022877,
|
| 527 |
+
"learning_rate": 4.6507718298361716e-05,
|
| 528 |
+
"loss": 0.5507,
|
| 529 |
+
"num_tokens": 124260967.0,
|
| 530 |
+
"step": 325
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.22525597269624573,
|
| 534 |
+
"grad_norm": 0.4004664272179976,
|
| 535 |
+
"learning_rate": 4.637054904343833e-05,
|
| 536 |
+
"loss": 0.5464,
|
| 537 |
+
"num_tokens": 126115279.0,
|
| 538 |
+
"step": 330
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.22866894197952217,
|
| 542 |
+
"grad_norm": 0.4212382875899973,
|
| 543 |
+
"learning_rate": 4.623097340183401e-05,
|
| 544 |
+
"loss": 0.5295,
|
| 545 |
+
"num_tokens": 128096244.0,
|
| 546 |
+
"step": 335
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.23208191126279865,
|
| 550 |
+
"grad_norm": 0.4455694065306531,
|
| 551 |
+
"learning_rate": 4.60890091723401e-05,
|
| 552 |
+
"loss": 0.5545,
|
| 553 |
+
"num_tokens": 129992439.0,
|
| 554 |
+
"step": 340
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.2354948805460751,
|
| 558 |
+
"grad_norm": 0.4410492860812032,
|
| 559 |
+
"learning_rate": 4.5944674458342473e-05,
|
| 560 |
+
"loss": 0.5534,
|
| 561 |
+
"num_tokens": 131869001.0,
|
| 562 |
+
"step": 345
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.23890784982935154,
|
| 566 |
+
"grad_norm": 0.4698122707585214,
|
| 567 |
+
"learning_rate": 4.579798766551298e-05,
|
| 568 |
+
"loss": 0.5602,
|
| 569 |
+
"num_tokens": 133787994.0,
|
| 570 |
+
"step": 350
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.24232081911262798,
|
| 574 |
+
"grad_norm": 0.3926247165354882,
|
| 575 |
+
"learning_rate": 4.564896749946234e-05,
|
| 576 |
+
"loss": 0.533,
|
| 577 |
+
"num_tokens": 135563718.0,
|
| 578 |
+
"step": 355
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.24573378839590443,
|
| 582 |
+
"grad_norm": 0.48875339008504026,
|
| 583 |
+
"learning_rate": 4.549763296335481e-05,
|
| 584 |
+
"loss": 0.5415,
|
| 585 |
+
"num_tokens": 137544925.0,
|
| 586 |
+
"step": 360
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.24914675767918087,
|
| 590 |
+
"grad_norm": 0.3914108658195032,
|
| 591 |
+
"learning_rate": 4.534400335548484e-05,
|
| 592 |
+
"loss": 0.5301,
|
| 593 |
+
"num_tokens": 139435802.0,
|
| 594 |
+
"step": 365
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.2525597269624573,
|
| 598 |
+
"grad_norm": 0.4239969743275553,
|
| 599 |
+
"learning_rate": 4.518809826681616e-05,
|
| 600 |
+
"loss": 0.5337,
|
| 601 |
+
"num_tokens": 141219364.0,
|
| 602 |
+
"step": 370
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.25597269624573377,
|
| 606 |
+
"grad_norm": 0.40065112223661187,
|
| 607 |
+
"learning_rate": 4.5029937578483566e-05,
|
| 608 |
+
"loss": 0.5545,
|
| 609 |
+
"num_tokens": 143301347.0,
|
| 610 |
+
"step": 375
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.2593856655290102,
|
| 614 |
+
"grad_norm": 0.41245952259823815,
|
| 615 |
+
"learning_rate": 4.486954145925761e-05,
|
| 616 |
+
"loss": 0.5325,
|
| 617 |
+
"num_tokens": 145160611.0,
|
| 618 |
+
"step": 380
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2627986348122867,
|
| 622 |
+
"grad_norm": 0.39486934538938195,
|
| 623 |
+
"learning_rate": 4.470693036297268e-05,
|
| 624 |
+
"loss": 0.5227,
|
| 625 |
+
"num_tokens": 147031619.0,
|
| 626 |
+
"step": 385
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.26621160409556316,
|
| 630 |
+
"grad_norm": 0.4122107449426131,
|
| 631 |
+
"learning_rate": 4.454212502591871e-05,
|
| 632 |
+
"loss": 0.5395,
|
| 633 |
+
"num_tokens": 148964661.0,
|
| 634 |
+
"step": 390
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.2696245733788396,
|
| 638 |
+
"grad_norm": 0.430372576227988,
|
| 639 |
+
"learning_rate": 4.437514646419687e-05,
|
| 640 |
+
"loss": 0.5473,
|
| 641 |
+
"num_tokens": 150937307.0,
|
| 642 |
+
"step": 395
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.27303754266211605,
|
| 646 |
+
"grad_norm": 0.4128699755590823,
|
| 647 |
+
"learning_rate": 4.4206015971039625e-05,
|
| 648 |
+
"loss": 0.5344,
|
| 649 |
+
"num_tokens": 152834849.0,
|
| 650 |
+
"step": 400
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.2764505119453925,
|
| 654 |
+
"grad_norm": 0.4634206495165695,
|
| 655 |
+
"learning_rate": 4.403475511409531e-05,
|
| 656 |
+
"loss": 0.5191,
|
| 657 |
+
"num_tokens": 154739335.0,
|
| 658 |
+
"step": 405
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.27986348122866894,
|
| 662 |
+
"grad_norm": 0.39101860237518965,
|
| 663 |
+
"learning_rate": 4.386138573267788e-05,
|
| 664 |
+
"loss": 0.5494,
|
| 665 |
+
"num_tokens": 156709373.0,
|
| 666 |
+
"step": 410
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.2832764505119454,
|
| 670 |
+
"grad_norm": 0.40407883950907425,
|
| 671 |
+
"learning_rate": 4.368592993498194e-05,
|
| 672 |
+
"loss": 0.5249,
|
| 673 |
+
"num_tokens": 158541316.0,
|
| 674 |
+
"step": 415
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.28668941979522183,
|
| 678 |
+
"grad_norm": 0.4835504660388713,
|
| 679 |
+
"learning_rate": 4.350841009526346e-05,
|
| 680 |
+
"loss": 0.5463,
|
| 681 |
+
"num_tokens": 160459756.0,
|
| 682 |
+
"step": 420
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.2901023890784983,
|
| 686 |
+
"grad_norm": 0.4304363809284002,
|
| 687 |
+
"learning_rate": 4.33288488509866e-05,
|
| 688 |
+
"loss": 0.5303,
|
| 689 |
+
"num_tokens": 162358277.0,
|
| 690 |
+
"step": 425
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2935153583617747,
|
| 694 |
+
"grad_norm": 0.45440256145504604,
|
| 695 |
+
"learning_rate": 4.3147269099937014e-05,
|
| 696 |
+
"loss": 0.5471,
|
| 697 |
+
"num_tokens": 164401378.0,
|
| 698 |
+
"step": 430
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.29692832764505117,
|
| 702 |
+
"grad_norm": 0.41253553496823814,
|
| 703 |
+
"learning_rate": 4.2963693997301814e-05,
|
| 704 |
+
"loss": 0.5138,
|
| 705 |
+
"num_tokens": 166276916.0,
|
| 706 |
+
"step": 435
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.3003412969283277,
|
| 710 |
+
"grad_norm": 0.37489839932208063,
|
| 711 |
+
"learning_rate": 4.2778146952716884e-05,
|
| 712 |
+
"loss": 0.5235,
|
| 713 |
+
"num_tokens": 168250987.0,
|
| 714 |
+
"step": 440
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.3037542662116041,
|
| 718 |
+
"grad_norm": 0.3787365196590386,
|
| 719 |
+
"learning_rate": 4.259065162728163e-05,
|
| 720 |
+
"loss": 0.5423,
|
| 721 |
+
"num_tokens": 170217424.0,
|
| 722 |
+
"step": 445
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.30716723549488056,
|
| 726 |
+
"grad_norm": 0.39718238812004736,
|
| 727 |
+
"learning_rate": 4.240123193054172e-05,
|
| 728 |
+
"loss": 0.5203,
|
| 729 |
+
"num_tokens": 172160313.0,
|
| 730 |
+
"step": 450
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.310580204778157,
|
| 734 |
+
"grad_norm": 0.4477023341378525,
|
| 735 |
+
"learning_rate": 4.2209912017440066e-05,
|
| 736 |
+
"loss": 0.5321,
|
| 737 |
+
"num_tokens": 174112017.0,
|
| 738 |
+
"step": 455
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.31399317406143346,
|
| 742 |
+
"grad_norm": 0.3706763806920432,
|
| 743 |
+
"learning_rate": 4.2016716285236655e-05,
|
| 744 |
+
"loss": 0.5212,
|
| 745 |
+
"num_tokens": 176115268.0,
|
| 746 |
+
"step": 460
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.3174061433447099,
|
| 750 |
+
"grad_norm": 0.4419336834715768,
|
| 751 |
+
"learning_rate": 4.182166937039731e-05,
|
| 752 |
+
"loss": 0.506,
|
| 753 |
+
"num_tokens": 178049137.0,
|
| 754 |
+
"step": 465
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.32081911262798635,
|
| 758 |
+
"grad_norm": 0.4021536966650696,
|
| 759 |
+
"learning_rate": 4.1624796145452075e-05,
|
| 760 |
+
"loss": 0.5326,
|
| 761 |
+
"num_tokens": 179947208.0,
|
| 762 |
+
"step": 470
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.3242320819112628,
|
| 766 |
+
"grad_norm": 0.35818670526347335,
|
| 767 |
+
"learning_rate": 4.1426121715823455e-05,
|
| 768 |
+
"loss": 0.5366,
|
| 769 |
+
"num_tokens": 181891310.0,
|
| 770 |
+
"step": 475
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.32764505119453924,
|
| 774 |
+
"grad_norm": 0.40438283737608033,
|
| 775 |
+
"learning_rate": 4.1225671416624886e-05,
|
| 776 |
+
"loss": 0.5265,
|
| 777 |
+
"num_tokens": 183776326.0,
|
| 778 |
+
"step": 480
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.3310580204778157,
|
| 782 |
+
"grad_norm": 0.42214780601925506,
|
| 783 |
+
"learning_rate": 4.1023470809430115e-05,
|
| 784 |
+
"loss": 0.543,
|
| 785 |
+
"num_tokens": 185721070.0,
|
| 786 |
+
"step": 485
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.33447098976109213,
|
| 790 |
+
"grad_norm": 0.4045159783954986,
|
| 791 |
+
"learning_rate": 4.081954567901341e-05,
|
| 792 |
+
"loss": 0.5362,
|
| 793 |
+
"num_tokens": 187730193.0,
|
| 794 |
+
"step": 490
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.3378839590443686,
|
| 798 |
+
"grad_norm": 0.4041539375920235,
|
| 799 |
+
"learning_rate": 4.0613922030061593e-05,
|
| 800 |
+
"loss": 0.5214,
|
| 801 |
+
"num_tokens": 189611145.0,
|
| 802 |
+
"step": 495
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.3412969283276451,
|
| 806 |
+
"grad_norm": 0.4416626187589487,
|
| 807 |
+
"learning_rate": 4.040662608385783e-05,
|
| 808 |
+
"loss": 0.5236,
|
| 809 |
+
"num_tokens": 191543591.0,
|
| 810 |
+
"step": 500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.3447098976109215,
|
| 814 |
+
"grad_norm": 0.40339880095982195,
|
| 815 |
+
"learning_rate": 4.019768427493792e-05,
|
| 816 |
+
"loss": 0.5195,
|
| 817 |
+
"num_tokens": 193451364.0,
|
| 818 |
+
"step": 505
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.34812286689419797,
|
| 822 |
+
"grad_norm": 0.36929819078368703,
|
| 823 |
+
"learning_rate": 3.99871232477193e-05,
|
| 824 |
+
"loss": 0.5276,
|
| 825 |
+
"num_tokens": 195399830.0,
|
| 826 |
+
"step": 510
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.3515358361774744,
|
| 830 |
+
"grad_norm": 0.37584853916938343,
|
| 831 |
+
"learning_rate": 3.9774969853103334e-05,
|
| 832 |
+
"loss": 0.5078,
|
| 833 |
+
"num_tokens": 197289380.0,
|
| 834 |
+
"step": 515
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.35494880546075086,
|
| 838 |
+
"grad_norm": 0.37209524558985846,
|
| 839 |
+
"learning_rate": 3.9561251145051325e-05,
|
| 840 |
+
"loss": 0.5171,
|
| 841 |
+
"num_tokens": 199248080.0,
|
| 842 |
+
"step": 520
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.3583617747440273,
|
| 846 |
+
"grad_norm": 0.40569837763495836,
|
| 847 |
+
"learning_rate": 3.934599437713449e-05,
|
| 848 |
+
"loss": 0.5435,
|
| 849 |
+
"num_tokens": 201135153.0,
|
| 850 |
+
"step": 525
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.36177474402730375,
|
| 854 |
+
"grad_norm": 0.4245059981016483,
|
| 855 |
+
"learning_rate": 3.912922699905861e-05,
|
| 856 |
+
"loss": 0.5202,
|
| 857 |
+
"num_tokens": 202936389.0,
|
| 858 |
+
"step": 530
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.3651877133105802,
|
| 862 |
+
"grad_norm": 0.46198327993992694,
|
| 863 |
+
"learning_rate": 3.8910976653163655e-05,
|
| 864 |
+
"loss": 0.5211,
|
| 865 |
+
"num_tokens": 204803047.0,
|
| 866 |
+
"step": 535
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.36860068259385664,
|
| 870 |
+
"grad_norm": 0.4101222090201111,
|
| 871 |
+
"learning_rate": 3.869127117089871e-05,
|
| 872 |
+
"loss": 0.5206,
|
| 873 |
+
"num_tokens": 206795183.0,
|
| 874 |
+
"step": 540
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.3720136518771331,
|
| 878 |
+
"grad_norm": 0.38657241963714845,
|
| 879 |
+
"learning_rate": 3.847013856927298e-05,
|
| 880 |
+
"loss": 0.517,
|
| 881 |
+
"num_tokens": 208806680.0,
|
| 882 |
+
"step": 545
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.37542662116040953,
|
| 886 |
+
"grad_norm": 0.4098353080317324,
|
| 887 |
+
"learning_rate": 3.824760704728303e-05,
|
| 888 |
+
"loss": 0.5168,
|
| 889 |
+
"num_tokens": 210620229.0,
|
| 890 |
+
"step": 550
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.378839590443686,
|
| 894 |
+
"grad_norm": 0.4155020536213452,
|
| 895 |
+
"learning_rate": 3.802370498231677e-05,
|
| 896 |
+
"loss": 0.5265,
|
| 897 |
+
"num_tokens": 212481056.0,
|
| 898 |
+
"step": 555
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.3822525597269625,
|
| 902 |
+
"grad_norm": 0.3865087375988852,
|
| 903 |
+
"learning_rate": 3.7798460926534814e-05,
|
| 904 |
+
"loss": 0.5185,
|
| 905 |
+
"num_tokens": 214296967.0,
|
| 906 |
+
"step": 560
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.3856655290102389,
|
| 910 |
+
"grad_norm": 0.3750956766555029,
|
| 911 |
+
"learning_rate": 3.757190360322943e-05,
|
| 912 |
+
"loss": 0.5329,
|
| 913 |
+
"num_tokens": 216266686.0,
|
| 914 |
+
"step": 565
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.3890784982935154,
|
| 918 |
+
"grad_norm": 0.39145392143957464,
|
| 919 |
+
"learning_rate": 3.7344061903161796e-05,
|
| 920 |
+
"loss": 0.5222,
|
| 921 |
+
"num_tokens": 218179883.0,
|
| 922 |
+
"step": 570
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3924914675767918,
|
| 926 |
+
"grad_norm": 0.3542307121338286,
|
| 927 |
+
"learning_rate": 3.711496488087775e-05,
|
| 928 |
+
"loss": 0.5212,
|
| 929 |
+
"num_tokens": 220144855.0,
|
| 930 |
+
"step": 575
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.39590443686006827,
|
| 934 |
+
"grad_norm": 0.3595510161682466,
|
| 935 |
+
"learning_rate": 3.6884641751002784e-05,
|
| 936 |
+
"loss": 0.5236,
|
| 937 |
+
"num_tokens": 222093783.0,
|
| 938 |
+
"step": 580
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.3993174061433447,
|
| 942 |
+
"grad_norm": 0.35062232858339965,
|
| 943 |
+
"learning_rate": 3.6653121884516555e-05,
|
| 944 |
+
"loss": 0.5092,
|
| 945 |
+
"num_tokens": 223929151.0,
|
| 946 |
+
"step": 585
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.40273037542662116,
|
| 950 |
+
"grad_norm": 0.3285591426879405,
|
| 951 |
+
"learning_rate": 3.6420434805007476e-05,
|
| 952 |
+
"loss": 0.5179,
|
| 953 |
+
"num_tokens": 225865685.0,
|
| 954 |
+
"step": 590
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.4061433447098976,
|
| 958 |
+
"grad_norm": 0.3510115101982655,
|
| 959 |
+
"learning_rate": 3.618661018490784e-05,
|
| 960 |
+
"loss": 0.5133,
|
| 961 |
+
"num_tokens": 227786006.0,
|
| 962 |
+
"step": 595
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.40955631399317405,
|
| 966 |
+
"grad_norm": 0.3274016432969718,
|
| 967 |
+
"learning_rate": 3.595167784170998e-05,
|
| 968 |
+
"loss": 0.512,
|
| 969 |
+
"num_tokens": 229748231.0,
|
| 970 |
+
"step": 600
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.4129692832764505,
|
| 974 |
+
"grad_norm": 0.4305124152729843,
|
| 975 |
+
"learning_rate": 3.571566773416394e-05,
|
| 976 |
+
"loss": 0.5192,
|
| 977 |
+
"num_tokens": 231716185.0,
|
| 978 |
+
"step": 605
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.41638225255972694,
|
| 982 |
+
"grad_norm": 0.39601357885456295,
|
| 983 |
+
"learning_rate": 3.5478609958457056e-05,
|
| 984 |
+
"loss": 0.5367,
|
| 985 |
+
"num_tokens": 233655900.0,
|
| 986 |
+
"step": 610
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.4197952218430034,
|
| 990 |
+
"grad_norm": 0.3545126035973363,
|
| 991 |
+
"learning_rate": 3.524053474437611e-05,
|
| 992 |
+
"loss": 0.523,
|
| 993 |
+
"num_tokens": 235502719.0,
|
| 994 |
+
"step": 615
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.4232081911262799,
|
| 998 |
+
"grad_norm": 0.36135199086071684,
|
| 999 |
+
"learning_rate": 3.500147245145238e-05,
|
| 1000 |
+
"loss": 0.5279,
|
| 1001 |
+
"num_tokens": 237433481.0,
|
| 1002 |
+
"step": 620
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.42662116040955633,
|
| 1006 |
+
"grad_norm": 0.36125748407184816,
|
| 1007 |
+
"learning_rate": 3.476145356509023e-05,
|
| 1008 |
+
"loss": 0.5179,
|
| 1009 |
+
"num_tokens": 239310469.0,
|
| 1010 |
+
"step": 625
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4300341296928328,
|
| 1014 |
+
"grad_norm": 0.3614233986459319,
|
| 1015 |
+
"learning_rate": 3.452050869267951e-05,
|
| 1016 |
+
"loss": 0.5223,
|
| 1017 |
+
"num_tokens": 241153898.0,
|
| 1018 |
+
"step": 630
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.4334470989761092,
|
| 1022 |
+
"grad_norm": 0.315710878713846,
|
| 1023 |
+
"learning_rate": 3.427866855969249e-05,
|
| 1024 |
+
"loss": 0.5326,
|
| 1025 |
+
"num_tokens": 243032696.0,
|
| 1026 |
+
"step": 635
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.43686006825938567,
|
| 1030 |
+
"grad_norm": 0.3606231876607955,
|
| 1031 |
+
"learning_rate": 3.4035964005765786e-05,
|
| 1032 |
+
"loss": 0.5079,
|
| 1033 |
+
"num_tokens": 245008254.0,
|
| 1034 |
+
"step": 640
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.4402730375426621,
|
| 1038 |
+
"grad_norm": 0.4513708700325408,
|
| 1039 |
+
"learning_rate": 3.379242598076761e-05,
|
| 1040 |
+
"loss": 0.5425,
|
| 1041 |
+
"num_tokens": 247016964.0,
|
| 1042 |
+
"step": 645
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.44368600682593856,
|
| 1046 |
+
"grad_norm": 0.3698676634761792,
|
| 1047 |
+
"learning_rate": 3.354808554085103e-05,
|
| 1048 |
+
"loss": 0.5105,
|
| 1049 |
+
"num_tokens": 248791992.0,
|
| 1050 |
+
"step": 650
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.447098976109215,
|
| 1054 |
+
"grad_norm": 0.39124843901075274,
|
| 1055 |
+
"learning_rate": 3.330297384449369e-05,
|
| 1056 |
+
"loss": 0.5197,
|
| 1057 |
+
"num_tokens": 250713070.0,
|
| 1058 |
+
"step": 655
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.45051194539249145,
|
| 1062 |
+
"grad_norm": 0.4062019607006225,
|
| 1063 |
+
"learning_rate": 3.3057122148524394e-05,
|
| 1064 |
+
"loss": 0.5081,
|
| 1065 |
+
"num_tokens": 252648795.0,
|
| 1066 |
+
"step": 660
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4539249146757679,
|
| 1070 |
+
"grad_norm": 0.4006003770025269,
|
| 1071 |
+
"learning_rate": 3.2810561804137316e-05,
|
| 1072 |
+
"loss": 0.5213,
|
| 1073 |
+
"num_tokens": 254539106.0,
|
| 1074 |
+
"step": 665
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.45733788395904434,
|
| 1078 |
+
"grad_norm": 0.37560165760494274,
|
| 1079 |
+
"learning_rate": 3.2563324252893964e-05,
|
| 1080 |
+
"loss": 0.5203,
|
| 1081 |
+
"num_tokens": 256460069.0,
|
| 1082 |
+
"step": 670
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.46075085324232085,
|
| 1086 |
+
"grad_norm": 0.3458666124165467,
|
| 1087 |
+
"learning_rate": 3.2315441022713796e-05,
|
| 1088 |
+
"loss": 0.5024,
|
| 1089 |
+
"num_tokens": 258439462.0,
|
| 1090 |
+
"step": 675
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.4641638225255973,
|
| 1094 |
+
"grad_norm": 0.35359019104452666,
|
| 1095 |
+
"learning_rate": 3.206694372385375e-05,
|
| 1096 |
+
"loss": 0.5239,
|
| 1097 |
+
"num_tokens": 260499223.0,
|
| 1098 |
+
"step": 680
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.46757679180887374,
|
| 1102 |
+
"grad_norm": 0.342259069898162,
|
| 1103 |
+
"learning_rate": 3.1817864044877236e-05,
|
| 1104 |
+
"loss": 0.5041,
|
| 1105 |
+
"num_tokens": 262428104.0,
|
| 1106 |
+
"step": 685
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.4709897610921502,
|
| 1110 |
+
"grad_norm": 0.33344593459988975,
|
| 1111 |
+
"learning_rate": 3.156823374861324e-05,
|
| 1112 |
+
"loss": 0.5077,
|
| 1113 |
+
"num_tokens": 264331327.0,
|
| 1114 |
+
"step": 690
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.47440273037542663,
|
| 1118 |
+
"grad_norm": 0.3570463424581151,
|
| 1119 |
+
"learning_rate": 3.131808466810586e-05,
|
| 1120 |
+
"loss": 0.5146,
|
| 1121 |
+
"num_tokens": 266242185.0,
|
| 1122 |
+
"step": 695
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.4778156996587031,
|
| 1126 |
+
"grad_norm": 0.3663607069094498,
|
| 1127 |
+
"learning_rate": 3.1067448702554976e-05,
|
| 1128 |
+
"loss": 0.5143,
|
| 1129 |
+
"num_tokens": 268142845.0,
|
| 1130 |
+
"step": 700
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.4812286689419795,
|
| 1134 |
+
"grad_norm": 0.3283477895544097,
|
| 1135 |
+
"learning_rate": 3.08163578132484e-05,
|
| 1136 |
+
"loss": 0.5256,
|
| 1137 |
+
"num_tokens": 270078357.0,
|
| 1138 |
+
"step": 705
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.48464163822525597,
|
| 1142 |
+
"grad_norm": 0.3331929822400331,
|
| 1143 |
+
"learning_rate": 3.056484401948618e-05,
|
| 1144 |
+
"loss": 0.522,
|
| 1145 |
+
"num_tokens": 272018748.0,
|
| 1146 |
+
"step": 710
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.4880546075085324,
|
| 1150 |
+
"grad_norm": 0.3919088866331423,
|
| 1151 |
+
"learning_rate": 3.0312939394497442e-05,
|
| 1152 |
+
"loss": 0.5317,
|
| 1153 |
+
"num_tokens": 274027158.0,
|
| 1154 |
+
"step": 715
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.49146757679180886,
|
| 1158 |
+
"grad_norm": 0.4042974409716166,
|
| 1159 |
+
"learning_rate": 3.0060676061350423e-05,
|
| 1160 |
+
"loss": 0.5238,
|
| 1161 |
+
"num_tokens": 275897357.0,
|
| 1162 |
+
"step": 720
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.4948805460750853,
|
| 1166 |
+
"grad_norm": 0.3372872560948971,
|
| 1167 |
+
"learning_rate": 2.9808086188856084e-05,
|
| 1168 |
+
"loss": 0.494,
|
| 1169 |
+
"num_tokens": 277733458.0,
|
| 1170 |
+
"step": 725
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.49829351535836175,
|
| 1174 |
+
"grad_norm": 0.3316688077958623,
|
| 1175 |
+
"learning_rate": 2.9555201987465932e-05,
|
| 1176 |
+
"loss": 0.5169,
|
| 1177 |
+
"num_tokens": 279550428.0,
|
| 1178 |
+
"step": 730
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5017064846416383,
|
| 1182 |
+
"grad_norm": 0.3472850891150428,
|
| 1183 |
+
"learning_rate": 2.9302055705164516e-05,
|
| 1184 |
+
"loss": 0.5018,
|
| 1185 |
+
"num_tokens": 281502549.0,
|
| 1186 |
+
"step": 735
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.5051194539249146,
|
| 1190 |
+
"grad_norm": 0.3341089195458149,
|
| 1191 |
+
"learning_rate": 2.9048679623357155e-05,
|
| 1192 |
+
"loss": 0.5131,
|
| 1193 |
+
"num_tokens": 283508120.0,
|
| 1194 |
+
"step": 740
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.5085324232081911,
|
| 1198 |
+
"grad_norm": 0.37260085647239954,
|
| 1199 |
+
"learning_rate": 2.8795106052753356e-05,
|
| 1200 |
+
"loss": 0.5086,
|
| 1201 |
+
"num_tokens": 285480194.0,
|
| 1202 |
+
"step": 745
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.5119453924914675,
|
| 1206 |
+
"grad_norm": 0.3385876655652841,
|
| 1207 |
+
"learning_rate": 2.854136732924656e-05,
|
| 1208 |
+
"loss": 0.5218,
|
| 1209 |
+
"num_tokens": 287419124.0,
|
| 1210 |
+
"step": 750
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.515358361774744,
|
| 1214 |
+
"grad_norm": 0.41573862092710284,
|
| 1215 |
+
"learning_rate": 2.828749580979061e-05,
|
| 1216 |
+
"loss": 0.494,
|
| 1217 |
+
"num_tokens": 289306762.0,
|
| 1218 |
+
"step": 755
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.5187713310580204,
|
| 1222 |
+
"grad_norm": 0.38243799044252413,
|
| 1223 |
+
"learning_rate": 2.8033523868273625e-05,
|
| 1224 |
+
"loss": 0.5105,
|
| 1225 |
+
"num_tokens": 291105578.0,
|
| 1226 |
+
"step": 760
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.5221843003412969,
|
| 1230 |
+
"grad_norm": 0.3246196947109855,
|
| 1231 |
+
"learning_rate": 2.777948389138959e-05,
|
| 1232 |
+
"loss": 0.5156,
|
| 1233 |
+
"num_tokens": 293082816.0,
|
| 1234 |
+
"step": 765
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5255972696245734,
|
| 1238 |
+
"grad_norm": 0.34632256376609033,
|
| 1239 |
+
"learning_rate": 2.7525408274508424e-05,
|
| 1240 |
+
"loss": 0.5061,
|
| 1241 |
+
"num_tokens": 294930434.0,
|
| 1242 |
+
"step": 770
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.5290102389078498,
|
| 1246 |
+
"grad_norm": 0.32742026006864583,
|
| 1247 |
+
"learning_rate": 2.727132941754488e-05,
|
| 1248 |
+
"loss": 0.5144,
|
| 1249 |
+
"num_tokens": 296842807.0,
|
| 1250 |
+
"step": 775
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.5324232081911263,
|
| 1254 |
+
"grad_norm": 0.37969890983588345,
|
| 1255 |
+
"learning_rate": 2.70172797208269e-05,
|
| 1256 |
+
"loss": 0.5124,
|
| 1257 |
+
"num_tokens": 298726998.0,
|
| 1258 |
+
"step": 780
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.5358361774744027,
|
| 1262 |
+
"grad_norm": 0.32045333869967124,
|
| 1263 |
+
"learning_rate": 2.676329158096388e-05,
|
| 1264 |
+
"loss": 0.5031,
|
| 1265 |
+
"num_tokens": 300660125.0,
|
| 1266 |
+
"step": 785
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5392491467576792,
|
| 1270 |
+
"grad_norm": 0.3351867492058869,
|
| 1271 |
+
"learning_rate": 2.650939738671543e-05,
|
| 1272 |
+
"loss": 0.4923,
|
| 1273 |
+
"num_tokens": 302437719.0,
|
| 1274 |
+
"step": 790
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.5426621160409556,
|
| 1278 |
+
"grad_norm": 0.32870638608190494,
|
| 1279 |
+
"learning_rate": 2.6255629514861156e-05,
|
| 1280 |
+
"loss": 0.5223,
|
| 1281 |
+
"num_tokens": 304343518.0,
|
| 1282 |
+
"step": 795
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.5460750853242321,
|
| 1286 |
+
"grad_norm": 0.3968416703427151,
|
| 1287 |
+
"learning_rate": 2.6002020326071958e-05,
|
| 1288 |
+
"loss": 0.5171,
|
| 1289 |
+
"num_tokens": 306180961.0,
|
| 1290 |
+
"step": 800
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5494880546075085,
|
| 1294 |
+
"grad_norm": 0.3315903513365704,
|
| 1295 |
+
"learning_rate": 2.5748602160783308e-05,
|
| 1296 |
+
"loss": 0.5222,
|
| 1297 |
+
"num_tokens": 308076053.0,
|
| 1298 |
+
"step": 805
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.552901023890785,
|
| 1302 |
+
"grad_norm": 0.38906545880748405,
|
| 1303 |
+
"learning_rate": 2.5495407335071247e-05,
|
| 1304 |
+
"loss": 0.512,
|
| 1305 |
+
"num_tokens": 310003006.0,
|
| 1306 |
+
"step": 810
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.5563139931740614,
|
| 1310 |
+
"grad_norm": 0.3682396569712196,
|
| 1311 |
+
"learning_rate": 2.5242468136531354e-05,
|
| 1312 |
+
"loss": 0.4992,
|
| 1313 |
+
"num_tokens": 311908102.0,
|
| 1314 |
+
"step": 815
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.5597269624573379,
|
| 1318 |
+
"grad_norm": 0.3785702552869352,
|
| 1319 |
+
"learning_rate": 2.4989816820161497e-05,
|
| 1320 |
+
"loss": 0.5054,
|
| 1321 |
+
"num_tokens": 313777123.0,
|
| 1322 |
+
"step": 820
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5631399317406144,
|
| 1326 |
+
"grad_norm": 0.37341815423961633,
|
| 1327 |
+
"learning_rate": 2.4737485604248534e-05,
|
| 1328 |
+
"loss": 0.5038,
|
| 1329 |
+
"num_tokens": 315742426.0,
|
| 1330 |
+
"step": 825
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.5665529010238908,
|
| 1334 |
+
"grad_norm": 0.3458678436661955,
|
| 1335 |
+
"learning_rate": 2.4485506666259895e-05,
|
| 1336 |
+
"loss": 0.511,
|
| 1337 |
+
"num_tokens": 317577413.0,
|
| 1338 |
+
"step": 830
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.5699658703071673,
|
| 1342 |
+
"grad_norm": 0.3253720525524336,
|
| 1343 |
+
"learning_rate": 2.4233912138740244e-05,
|
| 1344 |
+
"loss": 0.5051,
|
| 1345 |
+
"num_tokens": 319557900.0,
|
| 1346 |
+
"step": 835
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.5733788395904437,
|
| 1350 |
+
"grad_norm": 0.3277044845073884,
|
| 1351 |
+
"learning_rate": 2.3982734105213967e-05,
|
| 1352 |
+
"loss": 0.5087,
|
| 1353 |
+
"num_tokens": 321462994.0,
|
| 1354 |
+
"step": 840
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.5767918088737202,
|
| 1358 |
+
"grad_norm": 0.3353261014918948,
|
| 1359 |
+
"learning_rate": 2.373200459609379e-05,
|
| 1360 |
+
"loss": 0.5007,
|
| 1361 |
+
"num_tokens": 323355363.0,
|
| 1362 |
+
"step": 845
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.5802047781569966,
|
| 1366 |
+
"grad_norm": 0.37710402047600067,
|
| 1367 |
+
"learning_rate": 2.348175558459628e-05,
|
| 1368 |
+
"loss": 0.5037,
|
| 1369 |
+
"num_tokens": 325155802.0,
|
| 1370 |
+
"step": 850
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.5836177474402731,
|
| 1374 |
+
"grad_norm": 0.3756854288213979,
|
| 1375 |
+
"learning_rate": 2.323201898266458e-05,
|
| 1376 |
+
"loss": 0.5081,
|
| 1377 |
+
"num_tokens": 326956942.0,
|
| 1378 |
+
"step": 855
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5870307167235495,
|
| 1382 |
+
"grad_norm": 0.41618577986099176,
|
| 1383 |
+
"learning_rate": 2.2982826636898975e-05,
|
| 1384 |
+
"loss": 0.5056,
|
| 1385 |
+
"num_tokens": 328885222.0,
|
| 1386 |
+
"step": 860
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.590443686006826,
|
| 1390 |
+
"grad_norm": 0.37271507651921243,
|
| 1391 |
+
"learning_rate": 2.2734210324495812e-05,
|
| 1392 |
+
"loss": 0.5041,
|
| 1393 |
+
"num_tokens": 330878184.0,
|
| 1394 |
+
"step": 865
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.5938566552901023,
|
| 1398 |
+
"grad_norm": 0.37465375112588745,
|
| 1399 |
+
"learning_rate": 2.24862017491952e-05,
|
| 1400 |
+
"loss": 0.4885,
|
| 1401 |
+
"num_tokens": 332821824.0,
|
| 1402 |
+
"step": 870
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5972696245733788,
|
| 1406 |
+
"grad_norm": 0.3408803266885978,
|
| 1407 |
+
"learning_rate": 2.2238832537238174e-05,
|
| 1408 |
+
"loss": 0.5073,
|
| 1409 |
+
"num_tokens": 334798404.0,
|
| 1410 |
+
"step": 875
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.6006825938566553,
|
| 1414 |
+
"grad_norm": 0.3143548306738324,
|
| 1415 |
+
"learning_rate": 2.199213423333365e-05,
|
| 1416 |
+
"loss": 0.4798,
|
| 1417 |
+
"num_tokens": 336651049.0,
|
| 1418 |
+
"step": 880
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.6040955631399317,
|
| 1422 |
+
"grad_norm": 0.3416215101555348,
|
| 1423 |
+
"learning_rate": 2.174613829663587e-05,
|
| 1424 |
+
"loss": 0.5019,
|
| 1425 |
+
"num_tokens": 338438000.0,
|
| 1426 |
+
"step": 885
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.6075085324232082,
|
| 1430 |
+
"grad_norm": 0.31294368402349476,
|
| 1431 |
+
"learning_rate": 2.1500876096732664e-05,
|
| 1432 |
+
"loss": 0.5112,
|
| 1433 |
+
"num_tokens": 340414967.0,
|
| 1434 |
+
"step": 890
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.6109215017064846,
|
| 1438 |
+
"grad_norm": 0.3673235151939777,
|
| 1439 |
+
"learning_rate": 2.1256378909645187e-05,
|
| 1440 |
+
"loss": 0.5098,
|
| 1441 |
+
"num_tokens": 342244656.0,
|
| 1442 |
+
"step": 895
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.6143344709897611,
|
| 1446 |
+
"grad_norm": 0.35244592236676237,
|
| 1447 |
+
"learning_rate": 2.101267791383959e-05,
|
| 1448 |
+
"loss": 0.501,
|
| 1449 |
+
"num_tokens": 344295726.0,
|
| 1450 |
+
"step": 900
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.6177474402730375,
|
| 1454 |
+
"grad_norm": 0.35200599500626856,
|
| 1455 |
+
"learning_rate": 2.0769804186251096e-05,
|
| 1456 |
+
"loss": 0.5114,
|
| 1457 |
+
"num_tokens": 346263433.0,
|
| 1458 |
+
"step": 905
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.621160409556314,
|
| 1462 |
+
"grad_norm": 0.34317209619836014,
|
| 1463 |
+
"learning_rate": 2.052778869832108e-05,
|
| 1464 |
+
"loss": 0.5065,
|
| 1465 |
+
"num_tokens": 348137882.0,
|
| 1466 |
+
"step": 910
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.6245733788395904,
|
| 1470 |
+
"grad_norm": 0.37373559254371336,
|
| 1471 |
+
"learning_rate": 2.0286662312047537e-05,
|
| 1472 |
+
"loss": 0.5137,
|
| 1473 |
+
"num_tokens": 349987787.0,
|
| 1474 |
+
"step": 915
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.6279863481228669,
|
| 1478 |
+
"grad_norm": 0.30613532369092317,
|
| 1479 |
+
"learning_rate": 2.0046455776049545e-05,
|
| 1480 |
+
"loss": 0.4909,
|
| 1481 |
+
"num_tokens": 351875623.0,
|
| 1482 |
+
"step": 920
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.6313993174061433,
|
| 1486 |
+
"grad_norm": 0.35535165912939776,
|
| 1487 |
+
"learning_rate": 1.980719972164617e-05,
|
| 1488 |
+
"loss": 0.4965,
|
| 1489 |
+
"num_tokens": 353796065.0,
|
| 1490 |
+
"step": 925
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.6348122866894198,
|
| 1494 |
+
"grad_norm": 0.3319979859298165,
|
| 1495 |
+
"learning_rate": 1.9568924658950376e-05,
|
| 1496 |
+
"loss": 0.4969,
|
| 1497 |
+
"num_tokens": 355697743.0,
|
| 1498 |
+
"step": 930
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.6382252559726962,
|
| 1502 |
+
"grad_norm": 0.3298377848139942,
|
| 1503 |
+
"learning_rate": 1.9331660972978294e-05,
|
| 1504 |
+
"loss": 0.517,
|
| 1505 |
+
"num_tokens": 357607500.0,
|
| 1506 |
+
"step": 935
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.6416382252559727,
|
| 1510 |
+
"grad_norm": 0.33034399537498454,
|
| 1511 |
+
"learning_rate": 1.909543891977454e-05,
|
| 1512 |
+
"loss": 0.5133,
|
| 1513 |
+
"num_tokens": 359496768.0,
|
| 1514 |
+
"step": 940
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6450511945392492,
|
| 1518 |
+
"grad_norm": 0.4018049967603805,
|
| 1519 |
+
"learning_rate": 1.8860288622553922e-05,
|
| 1520 |
+
"loss": 0.489,
|
| 1521 |
+
"num_tokens": 361389017.0,
|
| 1522 |
+
"step": 945
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.6484641638225256,
|
| 1526 |
+
"grad_norm": 0.3270103830352738,
|
| 1527 |
+
"learning_rate": 1.862624006786014e-05,
|
| 1528 |
+
"loss": 0.4934,
|
| 1529 |
+
"num_tokens": 363249804.0,
|
| 1530 |
+
"step": 950
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.6518771331058021,
|
| 1534 |
+
"grad_norm": 0.3655301387344971,
|
| 1535 |
+
"learning_rate": 1.839332310174184e-05,
|
| 1536 |
+
"loss": 0.4984,
|
| 1537 |
+
"num_tokens": 365084839.0,
|
| 1538 |
+
"step": 955
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.6552901023890785,
|
| 1542 |
+
"grad_norm": 0.3154502369564001,
|
| 1543 |
+
"learning_rate": 1.8161567425946623e-05,
|
| 1544 |
+
"loss": 0.4888,
|
| 1545 |
+
"num_tokens": 366923656.0,
|
| 1546 |
+
"step": 960
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.658703071672355,
|
| 1550 |
+
"grad_norm": 0.33083205949502437,
|
| 1551 |
+
"learning_rate": 1.7931002594133494e-05,
|
| 1552 |
+
"loss": 0.5157,
|
| 1553 |
+
"num_tokens": 368897813.0,
|
| 1554 |
+
"step": 965
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.6621160409556314,
|
| 1558 |
+
"grad_norm": 0.30905828126663726,
|
| 1559 |
+
"learning_rate": 1.7701658008104122e-05,
|
| 1560 |
+
"loss": 0.4993,
|
| 1561 |
+
"num_tokens": 370786942.0,
|
| 1562 |
+
"step": 970
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.6655290102389079,
|
| 1566 |
+
"grad_norm": 0.303606580745798,
|
| 1567 |
+
"learning_rate": 1.7473562914053505e-05,
|
| 1568 |
+
"loss": 0.4815,
|
| 1569 |
+
"num_tokens": 372630696.0,
|
| 1570 |
+
"step": 975
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.6689419795221843,
|
| 1574 |
+
"grad_norm": 0.31898403092667915,
|
| 1575 |
+
"learning_rate": 1.7246746398840484e-05,
|
| 1576 |
+
"loss": 0.5044,
|
| 1577 |
+
"num_tokens": 374628223.0,
|
| 1578 |
+
"step": 980
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.6723549488054608,
|
| 1582 |
+
"grad_norm": 0.32842850216800784,
|
| 1583 |
+
"learning_rate": 1.702123738627857e-05,
|
| 1584 |
+
"loss": 0.4853,
|
| 1585 |
+
"num_tokens": 376493989.0,
|
| 1586 |
+
"step": 985
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.6757679180887372,
|
| 1590 |
+
"grad_norm": 0.3412895224218707,
|
| 1591 |
+
"learning_rate": 1.679706463344754e-05,
|
| 1592 |
+
"loss": 0.486,
|
| 1593 |
+
"num_tokens": 378392822.0,
|
| 1594 |
+
"step": 990
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.6791808873720137,
|
| 1598 |
+
"grad_norm": 0.30952639808604665,
|
| 1599 |
+
"learning_rate": 1.657425672702631e-05,
|
| 1600 |
+
"loss": 0.4785,
|
| 1601 |
+
"num_tokens": 380308538.0,
|
| 1602 |
+
"step": 995
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.6825938566552902,
|
| 1606 |
+
"grad_norm": 0.3177429345877287,
|
| 1607 |
+
"learning_rate": 1.6352842079647567e-05,
|
| 1608 |
+
"loss": 0.5023,
|
| 1609 |
+
"num_tokens": 382166430.0,
|
| 1610 |
+
"step": 1000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.6860068259385665,
|
| 1614 |
+
"grad_norm": 0.35202245429789475,
|
| 1615 |
+
"learning_rate": 1.6132848926274537e-05,
|
| 1616 |
+
"loss": 0.511,
|
| 1617 |
+
"num_tokens": 384075218.0,
|
| 1618 |
+
"step": 1005
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 0.689419795221843,
|
| 1622 |
+
"grad_norm": 0.33432081351038906,
|
| 1623 |
+
"learning_rate": 1.5914305320600474e-05,
|
| 1624 |
+
"loss": 0.4873,
|
| 1625 |
+
"num_tokens": 385900887.0,
|
| 1626 |
+
"step": 1010
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6928327645051194,
|
| 1630 |
+
"grad_norm": 0.4575749516026993,
|
| 1631 |
+
"learning_rate": 1.5697239131471175e-05,
|
| 1632 |
+
"loss": 0.5009,
|
| 1633 |
+
"num_tokens": 387782669.0,
|
| 1634 |
+
"step": 1015
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.6962457337883959,
|
| 1638 |
+
"grad_norm": 0.3427554874886022,
|
| 1639 |
+
"learning_rate": 1.5481678039331217e-05,
|
| 1640 |
+
"loss": 0.4907,
|
| 1641 |
+
"num_tokens": 389650899.0,
|
| 1642 |
+
"step": 1020
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.6996587030716723,
|
| 1646 |
+
"grad_norm": 0.3341947344865459,
|
| 1647 |
+
"learning_rate": 1.526764953269403e-05,
|
| 1648 |
+
"loss": 0.5079,
|
| 1649 |
+
"num_tokens": 391632321.0,
|
| 1650 |
+
"step": 1025
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.7030716723549488,
|
| 1654 |
+
"grad_norm": 0.3134997794047425,
|
| 1655 |
+
"learning_rate": 1.5055180904636602e-05,
|
| 1656 |
+
"loss": 0.4922,
|
| 1657 |
+
"num_tokens": 393493604.0,
|
| 1658 |
+
"step": 1030
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.7064846416382252,
|
| 1662 |
+
"grad_norm": 0.3255780696887481,
|
| 1663 |
+
"learning_rate": 1.4844299249319e-05,
|
| 1664 |
+
"loss": 0.5086,
|
| 1665 |
+
"num_tokens": 395329185.0,
|
| 1666 |
+
"step": 1035
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.7098976109215017,
|
| 1670 |
+
"grad_norm": 0.3263522826995175,
|
| 1671 |
+
"learning_rate": 1.4635031458529366e-05,
|
| 1672 |
+
"loss": 0.5155,
|
| 1673 |
+
"num_tokens": 397224172.0,
|
| 1674 |
+
"step": 1040
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.7133105802047781,
|
| 1678 |
+
"grad_norm": 0.31638467306204077,
|
| 1679 |
+
"learning_rate": 1.4427404218254598e-05,
|
| 1680 |
+
"loss": 0.4875,
|
| 1681 |
+
"num_tokens": 399158135.0,
|
| 1682 |
+
"step": 1045
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.7167235494880546,
|
| 1686 |
+
"grad_norm": 0.3362768703429673,
|
| 1687 |
+
"learning_rate": 1.422144400527733e-05,
|
| 1688 |
+
"loss": 0.5054,
|
| 1689 |
+
"num_tokens": 400990040.0,
|
| 1690 |
+
"step": 1050
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.7201365187713311,
|
| 1694 |
+
"grad_norm": 0.34232433433385795,
|
| 1695 |
+
"learning_rate": 1.401717708379964e-05,
|
| 1696 |
+
"loss": 0.4849,
|
| 1697 |
+
"num_tokens": 402861165.0,
|
| 1698 |
+
"step": 1055
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.7235494880546075,
|
| 1702 |
+
"grad_norm": 0.33348559187447124,
|
| 1703 |
+
"learning_rate": 1.3814629502093803e-05,
|
| 1704 |
+
"loss": 0.4959,
|
| 1705 |
+
"num_tokens": 404752387.0,
|
| 1706 |
+
"step": 1060
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.726962457337884,
|
| 1710 |
+
"grad_norm": 0.285504003948951,
|
| 1711 |
+
"learning_rate": 1.3613827089180576e-05,
|
| 1712 |
+
"loss": 0.4965,
|
| 1713 |
+
"num_tokens": 406680793.0,
|
| 1714 |
+
"step": 1065
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.7303754266211604,
|
| 1718 |
+
"grad_norm": 0.3273130414117694,
|
| 1719 |
+
"learning_rate": 1.3414795451535448e-05,
|
| 1720 |
+
"loss": 0.4954,
|
| 1721 |
+
"num_tokens": 408650161.0,
|
| 1722 |
+
"step": 1070
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.7337883959044369,
|
| 1726 |
+
"grad_norm": 0.31857752981344567,
|
| 1727 |
+
"learning_rate": 1.3217559969823334e-05,
|
| 1728 |
+
"loss": 0.504,
|
| 1729 |
+
"num_tokens": 410510602.0,
|
| 1730 |
+
"step": 1075
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 0.7372013651877133,
|
| 1734 |
+
"grad_norm": 0.2952465736185969,
|
| 1735 |
+
"learning_rate": 1.3022145795661988e-05,
|
| 1736 |
+
"loss": 0.5001,
|
| 1737 |
+
"num_tokens": 412454003.0,
|
| 1738 |
+
"step": 1080
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7406143344709898,
|
| 1742 |
+
"grad_norm": 0.318606614875486,
|
| 1743 |
+
"learning_rate": 1.2828577848414636e-05,
|
| 1744 |
+
"loss": 0.5101,
|
| 1745 |
+
"num_tokens": 414425737.0,
|
| 1746 |
+
"step": 1085
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.7440273037542662,
|
| 1750 |
+
"grad_norm": 0.2888251922437897,
|
| 1751 |
+
"learning_rate": 1.2636880812012253e-05,
|
| 1752 |
+
"loss": 0.4989,
|
| 1753 |
+
"num_tokens": 416440659.0,
|
| 1754 |
+
"step": 1090
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.7474402730375427,
|
| 1758 |
+
"grad_norm": 0.31759019068524147,
|
| 1759 |
+
"learning_rate": 1.2447079131805857e-05,
|
| 1760 |
+
"loss": 0.4955,
|
| 1761 |
+
"num_tokens": 418334906.0,
|
| 1762 |
+
"step": 1095
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 0.7508532423208191,
|
| 1766 |
+
"grad_norm": 0.3030516712247083,
|
| 1767 |
+
"learning_rate": 1.2259197011449203e-05,
|
| 1768 |
+
"loss": 0.4828,
|
| 1769 |
+
"num_tokens": 420121223.0,
|
| 1770 |
+
"step": 1100
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.7542662116040956,
|
| 1774 |
+
"grad_norm": 0.29738105299870915,
|
| 1775 |
+
"learning_rate": 1.2073258409812328e-05,
|
| 1776 |
+
"loss": 0.4844,
|
| 1777 |
+
"num_tokens": 421975487.0,
|
| 1778 |
+
"step": 1105
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.757679180887372,
|
| 1782 |
+
"grad_norm": 0.3265201499041776,
|
| 1783 |
+
"learning_rate": 1.1889287037926289e-05,
|
| 1784 |
+
"loss": 0.4947,
|
| 1785 |
+
"num_tokens": 423755589.0,
|
| 1786 |
+
"step": 1110
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.7610921501706485,
|
| 1790 |
+
"grad_norm": 0.3290192276540849,
|
| 1791 |
+
"learning_rate": 1.1707306355959516e-05,
|
| 1792 |
+
"loss": 0.4858,
|
| 1793 |
+
"num_tokens": 425585640.0,
|
| 1794 |
+
"step": 1115
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.764505119453925,
|
| 1798 |
+
"grad_norm": 0.28188493797407055,
|
| 1799 |
+
"learning_rate": 1.152733957022617e-05,
|
| 1800 |
+
"loss": 0.4854,
|
| 1801 |
+
"num_tokens": 427476418.0,
|
| 1802 |
+
"step": 1120
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.7679180887372014,
|
| 1806 |
+
"grad_norm": 0.29040278518135143,
|
| 1807 |
+
"learning_rate": 1.1349409630226804e-05,
|
| 1808 |
+
"loss": 0.4885,
|
| 1809 |
+
"num_tokens": 429400796.0,
|
| 1810 |
+
"step": 1125
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.7713310580204779,
|
| 1814 |
+
"grad_norm": 0.2931581985039031,
|
| 1815 |
+
"learning_rate": 1.1173539225721916e-05,
|
| 1816 |
+
"loss": 0.484,
|
| 1817 |
+
"num_tokens": 431359520.0,
|
| 1818 |
+
"step": 1130
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.7747440273037542,
|
| 1822 |
+
"grad_norm": 0.29868639262957064,
|
| 1823 |
+
"learning_rate": 1.0999750783838442e-05,
|
| 1824 |
+
"loss": 0.493,
|
| 1825 |
+
"num_tokens": 433284774.0,
|
| 1826 |
+
"step": 1135
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.7781569965870307,
|
| 1830 |
+
"grad_norm": 0.30419738121172896,
|
| 1831 |
+
"learning_rate": 1.0828066466209891e-05,
|
| 1832 |
+
"loss": 0.4851,
|
| 1833 |
+
"num_tokens": 435149765.0,
|
| 1834 |
+
"step": 1140
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 0.7815699658703071,
|
| 1838 |
+
"grad_norm": 0.3058153428671149,
|
| 1839 |
+
"learning_rate": 1.0658508166150224e-05,
|
| 1840 |
+
"loss": 0.4901,
|
| 1841 |
+
"num_tokens": 437135437.0,
|
| 1842 |
+
"step": 1145
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.7849829351535836,
|
| 1846 |
+
"grad_norm": 0.28771661136300736,
|
| 1847 |
+
"learning_rate": 1.0491097505862085e-05,
|
| 1848 |
+
"loss": 0.4875,
|
| 1849 |
+
"num_tokens": 439079263.0,
|
| 1850 |
+
"step": 1150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.78839590443686,
|
| 1854 |
+
"grad_norm": 0.28657822934185523,
|
| 1855 |
+
"learning_rate": 1.0325855833679438e-05,
|
| 1856 |
+
"loss": 0.5037,
|
| 1857 |
+
"num_tokens": 441195758.0,
|
| 1858 |
+
"step": 1155
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.7918088737201365,
|
| 1862 |
+
"grad_norm": 0.3112063201486636,
|
| 1863 |
+
"learning_rate": 1.0162804221345235e-05,
|
| 1864 |
+
"loss": 0.5036,
|
| 1865 |
+
"num_tokens": 443118717.0,
|
| 1866 |
+
"step": 1160
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.7952218430034129,
|
| 1870 |
+
"grad_norm": 0.316085459773578,
|
| 1871 |
+
"learning_rate": 1.0001963461324357e-05,
|
| 1872 |
+
"loss": 0.4924,
|
| 1873 |
+
"num_tokens": 444948197.0,
|
| 1874 |
+
"step": 1165
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.7986348122866894,
|
| 1878 |
+
"grad_norm": 0.3477741279618012,
|
| 1879 |
+
"learning_rate": 9.843354064152135e-06,
|
| 1880 |
+
"loss": 0.4899,
|
| 1881 |
+
"num_tokens": 446925677.0,
|
| 1882 |
+
"step": 1170
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.8020477815699659,
|
| 1886 |
+
"grad_norm": 0.29942909638368426,
|
| 1887 |
+
"learning_rate": 9.686996255818815e-06,
|
| 1888 |
+
"loss": 0.4966,
|
| 1889 |
+
"num_tokens": 448739177.0,
|
| 1890 |
+
"step": 1175
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.8054607508532423,
|
| 1894 |
+
"grad_norm": 0.28514176817206044,
|
| 1895 |
+
"learning_rate": 9.532909975190317e-06,
|
| 1896 |
+
"loss": 0.5136,
|
| 1897 |
+
"num_tokens": 450761568.0,
|
| 1898 |
+
"step": 1180
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.8088737201365188,
|
| 1902 |
+
"grad_norm": 0.3094546662478333,
|
| 1903 |
+
"learning_rate": 9.381114871465644e-06,
|
| 1904 |
+
"loss": 0.4906,
|
| 1905 |
+
"num_tokens": 452625293.0,
|
| 1906 |
+
"step": 1185
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.8122866894197952,
|
| 1910 |
+
"grad_norm": 0.31150839407313774,
|
| 1911 |
+
"learning_rate": 9.231630301671188e-06,
|
| 1912 |
+
"loss": 0.4906,
|
| 1913 |
+
"num_tokens": 454558803.0,
|
| 1914 |
+
"step": 1190
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.8156996587030717,
|
| 1918 |
+
"grad_norm": 0.2985040893913103,
|
| 1919 |
+
"learning_rate": 9.084475328192308e-06,
|
| 1920 |
+
"loss": 0.4758,
|
| 1921 |
+
"num_tokens": 456494011.0,
|
| 1922 |
+
"step": 1195
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.8191126279863481,
|
| 1926 |
+
"grad_norm": 0.3637634369298376,
|
| 1927 |
+
"learning_rate": 8.939668716342473e-06,
|
| 1928 |
+
"loss": 0.5014,
|
| 1929 |
+
"num_tokens": 458401399.0,
|
| 1930 |
+
"step": 1200
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 0.8225255972696246,
|
| 1934 |
+
"grad_norm": 0.3194790785969208,
|
| 1935 |
+
"learning_rate": 8.797228931970305e-06,
|
| 1936 |
+
"loss": 0.5069,
|
| 1937 |
+
"num_tokens": 460303546.0,
|
| 1938 |
+
"step": 1205
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.825938566552901,
|
| 1942 |
+
"grad_norm": 0.2948153613485649,
|
| 1943 |
+
"learning_rate": 8.657174139104807e-06,
|
| 1944 |
+
"loss": 0.4806,
|
| 1945 |
+
"num_tokens": 462132037.0,
|
| 1946 |
+
"step": 1210
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.8293515358361775,
|
| 1950 |
+
"grad_norm": 0.27931990685331665,
|
| 1951 |
+
"learning_rate": 8.519522197639043e-06,
|
| 1952 |
+
"loss": 0.4808,
|
| 1953 |
+
"num_tokens": 464065062.0,
|
| 1954 |
+
"step": 1215
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.8327645051194539,
|
| 1958 |
+
"grad_norm": 0.28537230710379463,
|
| 1959 |
+
"learning_rate": 8.384290661052662e-06,
|
| 1960 |
+
"loss": 0.4954,
|
| 1961 |
+
"num_tokens": 466050672.0,
|
| 1962 |
+
"step": 1220
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.8361774744027304,
|
| 1966 |
+
"grad_norm": 0.2949548548412219,
|
| 1967 |
+
"learning_rate": 8.251496774173451e-06,
|
| 1968 |
+
"loss": 0.4887,
|
| 1969 |
+
"num_tokens": 468039326.0,
|
| 1970 |
+
"step": 1225
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.8395904436860068,
|
| 1974 |
+
"grad_norm": 0.309004242742462,
|
| 1975 |
+
"learning_rate": 8.121157470978268e-06,
|
| 1976 |
+
"loss": 0.4826,
|
| 1977 |
+
"num_tokens": 469868923.0,
|
| 1978 |
+
"step": 1230
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.8430034129692833,
|
| 1982 |
+
"grad_norm": 0.29893983344310443,
|
| 1983 |
+
"learning_rate": 7.993289372433582e-06,
|
| 1984 |
+
"loss": 0.4844,
|
| 1985 |
+
"num_tokens": 471694644.0,
|
| 1986 |
+
"step": 1235
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 0.8464163822525598,
|
| 1990 |
+
"grad_norm": 0.2998742298370736,
|
| 1991 |
+
"learning_rate": 7.867908784376006e-06,
|
| 1992 |
+
"loss": 0.4818,
|
| 1993 |
+
"num_tokens": 473648633.0,
|
| 1994 |
+
"step": 1240
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.8498293515358362,
|
| 1998 |
+
"grad_norm": 0.3106689260243709,
|
| 1999 |
+
"learning_rate": 7.745031695432923e-06,
|
| 2000 |
+
"loss": 0.4959,
|
| 2001 |
+
"num_tokens": 475597050.0,
|
| 2002 |
+
"step": 1245
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.8532423208191127,
|
| 2006 |
+
"grad_norm": 0.31175199327450004,
|
| 2007 |
+
"learning_rate": 7.624673774983614e-06,
|
| 2008 |
+
"loss": 0.5023,
|
| 2009 |
+
"num_tokens": 477480036.0,
|
| 2010 |
+
"step": 1250
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.856655290102389,
|
| 2014 |
+
"grad_norm": 0.2902204878647725,
|
| 2015 |
+
"learning_rate": 7.506850371161078e-06,
|
| 2016 |
+
"loss": 0.4969,
|
| 2017 |
+
"num_tokens": 479450987.0,
|
| 2018 |
+
"step": 1255
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.8600682593856656,
|
| 2022 |
+
"grad_norm": 0.28336060373274513,
|
| 2023 |
+
"learning_rate": 7.391576508894865e-06,
|
| 2024 |
+
"loss": 0.4994,
|
| 2025 |
+
"num_tokens": 481428209.0,
|
| 2026 |
+
"step": 1260
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.863481228668942,
|
| 2030 |
+
"grad_norm": 0.3024009234719193,
|
| 2031 |
+
"learning_rate": 7.27886688799504e-06,
|
| 2032 |
+
"loss": 0.4857,
|
| 2033 |
+
"num_tokens": 483299671.0,
|
| 2034 |
+
"step": 1265
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.8668941979522184,
|
| 2038 |
+
"grad_norm": 0.29589514082391644,
|
| 2039 |
+
"learning_rate": 7.1687358812776715e-06,
|
| 2040 |
+
"loss": 0.5069,
|
| 2041 |
+
"num_tokens": 485251856.0,
|
| 2042 |
+
"step": 1270
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 0.8703071672354948,
|
| 2046 |
+
"grad_norm": 0.3072244457427502,
|
| 2047 |
+
"learning_rate": 7.061197532731992e-06,
|
| 2048 |
+
"loss": 0.4834,
|
| 2049 |
+
"num_tokens": 487198446.0,
|
| 2050 |
+
"step": 1275
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 0.8737201365187713,
|
| 2054 |
+
"grad_norm": 0.3031088646151408,
|
| 2055 |
+
"learning_rate": 6.956265555729524e-06,
|
| 2056 |
+
"loss": 0.48,
|
| 2057 |
+
"num_tokens": 489140124.0,
|
| 2058 |
+
"step": 1280
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.8771331058020477,
|
| 2062 |
+
"grad_norm": 0.2657716624231455,
|
| 2063 |
+
"learning_rate": 6.853953331275304e-06,
|
| 2064 |
+
"loss": 0.4834,
|
| 2065 |
+
"num_tokens": 491054868.0,
|
| 2066 |
+
"step": 1285
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.8805460750853242,
|
| 2070 |
+
"grad_norm": 0.29059952440409315,
|
| 2071 |
+
"learning_rate": 6.754273906301544e-06,
|
| 2072 |
+
"loss": 0.4868,
|
| 2073 |
+
"num_tokens": 492974236.0,
|
| 2074 |
+
"step": 1290
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.8839590443686007,
|
| 2078 |
+
"grad_norm": 0.26536176362219127,
|
| 2079 |
+
"learning_rate": 6.6572399920038775e-06,
|
| 2080 |
+
"loss": 0.5059,
|
| 2081 |
+
"num_tokens": 495062198.0,
|
| 2082 |
+
"step": 1295
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.8873720136518771,
|
| 2086 |
+
"grad_norm": 0.27938069658048914,
|
| 2087 |
+
"learning_rate": 6.562863962220414e-06,
|
| 2088 |
+
"loss": 0.4782,
|
| 2089 |
+
"num_tokens": 496987511.0,
|
| 2090 |
+
"step": 1300
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.8907849829351536,
|
| 2094 |
+
"grad_norm": 0.2784966508742894,
|
| 2095 |
+
"learning_rate": 6.47115785185384e-06,
|
| 2096 |
+
"loss": 0.4921,
|
| 2097 |
+
"num_tokens": 498971917.0,
|
| 2098 |
+
"step": 1305
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.89419795221843,
|
| 2102 |
+
"grad_norm": 0.31369357806862264,
|
| 2103 |
+
"learning_rate": 6.382133355336667e-06,
|
| 2104 |
+
"loss": 0.4831,
|
| 2105 |
+
"num_tokens": 500947010.0,
|
| 2106 |
+
"step": 1310
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 0.8976109215017065,
|
| 2110 |
+
"grad_norm": 0.28093807954237954,
|
| 2111 |
+
"learning_rate": 6.29580182514e-06,
|
| 2112 |
+
"loss": 0.4999,
|
| 2113 |
+
"num_tokens": 502958987.0,
|
| 2114 |
+
"step": 1315
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.9010238907849829,
|
| 2118 |
+
"grad_norm": 0.26894509796917526,
|
| 2119 |
+
"learning_rate": 6.212174270325845e-06,
|
| 2120 |
+
"loss": 0.4827,
|
| 2121 |
+
"num_tokens": 504893463.0,
|
| 2122 |
+
"step": 1320
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 0.9044368600682594,
|
| 2126 |
+
"grad_norm": 0.26574090941363004,
|
| 2127 |
+
"learning_rate": 6.1312613551432135e-06,
|
| 2128 |
+
"loss": 0.4865,
|
| 2129 |
+
"num_tokens": 506861395.0,
|
| 2130 |
+
"step": 1325
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.9078498293515358,
|
| 2134 |
+
"grad_norm": 0.28992628858941305,
|
| 2135 |
+
"learning_rate": 6.053073397668226e-06,
|
| 2136 |
+
"loss": 0.4886,
|
| 2137 |
+
"num_tokens": 508690960.0,
|
| 2138 |
+
"step": 1330
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.9112627986348123,
|
| 2142 |
+
"grad_norm": 0.2955031546908338,
|
| 2143 |
+
"learning_rate": 5.977620368488328e-06,
|
| 2144 |
+
"loss": 0.4881,
|
| 2145 |
+
"num_tokens": 510627944.0,
|
| 2146 |
+
"step": 1335
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.9146757679180887,
|
| 2150 |
+
"grad_norm": 0.30834008521444456,
|
| 2151 |
+
"learning_rate": 5.904911889430853e-06,
|
| 2152 |
+
"loss": 0.5009,
|
| 2153 |
+
"num_tokens": 512558436.0,
|
| 2154 |
+
"step": 1340
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.9180887372013652,
|
| 2158 |
+
"grad_norm": 0.27959724193187036,
|
| 2159 |
+
"learning_rate": 5.834957232336018e-06,
|
| 2160 |
+
"loss": 0.4762,
|
| 2161 |
+
"num_tokens": 514407245.0,
|
| 2162 |
+
"step": 1345
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.9215017064846417,
|
| 2166 |
+
"grad_norm": 0.29085310073740844,
|
| 2167 |
+
"learning_rate": 5.7677653178745805e-06,
|
| 2168 |
+
"loss": 0.4939,
|
| 2169 |
+
"num_tokens": 516301089.0,
|
| 2170 |
+
"step": 1350
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.9249146757679181,
|
| 2174 |
+
"grad_norm": 0.27390984744911256,
|
| 2175 |
+
"learning_rate": 5.7033447144102785e-06,
|
| 2176 |
+
"loss": 0.4992,
|
| 2177 |
+
"num_tokens": 518223298.0,
|
| 2178 |
+
"step": 1355
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 0.9283276450511946,
|
| 2182 |
+
"grad_norm": 0.3033170282507272,
|
| 2183 |
+
"learning_rate": 5.641703636907171e-06,
|
| 2184 |
+
"loss": 0.4894,
|
| 2185 |
+
"num_tokens": 520051962.0,
|
| 2186 |
+
"step": 1360
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.931740614334471,
|
| 2190 |
+
"grad_norm": 0.2792351438599578,
|
| 2191 |
+
"learning_rate": 5.582849945882055e-06,
|
| 2192 |
+
"loss": 0.4754,
|
| 2193 |
+
"num_tokens": 521910187.0,
|
| 2194 |
+
"step": 1365
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.9351535836177475,
|
| 2198 |
+
"grad_norm": 0.2983027455701448,
|
| 2199 |
+
"learning_rate": 5.526791146402112e-06,
|
| 2200 |
+
"loss": 0.4849,
|
| 2201 |
+
"num_tokens": 523880084.0,
|
| 2202 |
+
"step": 1370
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.9385665529010239,
|
| 2206 |
+
"grad_norm": 0.26604753293732786,
|
| 2207 |
+
"learning_rate": 5.473534387127838e-06,
|
| 2208 |
+
"loss": 0.492,
|
| 2209 |
+
"num_tokens": 525832920.0,
|
| 2210 |
+
"step": 1375
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.9419795221843004,
|
| 2214 |
+
"grad_norm": 0.2836516428880197,
|
| 2215 |
+
"learning_rate": 5.423086459401437e-06,
|
| 2216 |
+
"loss": 0.4959,
|
| 2217 |
+
"num_tokens": 527753736.0,
|
| 2218 |
+
"step": 1380
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 0.9453924914675768,
|
| 2222 |
+
"grad_norm": 0.2781237565619907,
|
| 2223 |
+
"learning_rate": 5.37545379638079e-06,
|
| 2224 |
+
"loss": 0.4945,
|
| 2225 |
+
"num_tokens": 529711197.0,
|
| 2226 |
+
"step": 1385
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 0.9488054607508533,
|
| 2230 |
+
"grad_norm": 0.29180621738637313,
|
| 2231 |
+
"learning_rate": 5.330642472219102e-06,
|
| 2232 |
+
"loss": 0.4882,
|
| 2233 |
+
"num_tokens": 531553862.0,
|
| 2234 |
+
"step": 1390
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.9522184300341296,
|
| 2238 |
+
"grad_norm": 0.2911236184686604,
|
| 2239 |
+
"learning_rate": 5.28865820129031e-06,
|
| 2240 |
+
"loss": 0.5028,
|
| 2241 |
+
"num_tokens": 533448215.0,
|
| 2242 |
+
"step": 1395
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.9556313993174061,
|
| 2246 |
+
"grad_norm": 0.29787157610965465,
|
| 2247 |
+
"learning_rate": 5.24950633746038e-06,
|
| 2248 |
+
"loss": 0.4847,
|
| 2249 |
+
"num_tokens": 535341346.0,
|
| 2250 |
+
"step": 1400
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.9590443686006825,
|
| 2254 |
+
"grad_norm": 0.2689157035396268,
|
| 2255 |
+
"learning_rate": 5.213191873404592e-06,
|
| 2256 |
+
"loss": 0.4752,
|
| 2257 |
+
"num_tokens": 537336227.0,
|
| 2258 |
+
"step": 1405
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.962457337883959,
|
| 2262 |
+
"grad_norm": 0.2674314375267255,
|
| 2263 |
+
"learning_rate": 5.179719439970854e-06,
|
| 2264 |
+
"loss": 0.4811,
|
| 2265 |
+
"num_tokens": 539226192.0,
|
| 2266 |
+
"step": 1410
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.9658703071672355,
|
| 2270 |
+
"grad_norm": 0.30068740436809055,
|
| 2271 |
+
"learning_rate": 5.14909330558919e-06,
|
| 2272 |
+
"loss": 0.4856,
|
| 2273 |
+
"num_tokens": 541043880.0,
|
| 2274 |
+
"step": 1415
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.9692832764505119,
|
| 2278 |
+
"grad_norm": 0.2743214968622806,
|
| 2279 |
+
"learning_rate": 5.121317375727405e-06,
|
| 2280 |
+
"loss": 0.4919,
|
| 2281 |
+
"num_tokens": 542913487.0,
|
| 2282 |
+
"step": 1420
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.9726962457337884,
|
| 2286 |
+
"grad_norm": 0.2853333647970851,
|
| 2287 |
+
"learning_rate": 5.0963951923930745e-06,
|
| 2288 |
+
"loss": 0.5046,
|
| 2289 |
+
"num_tokens": 544851416.0,
|
| 2290 |
+
"step": 1425
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 0.9761092150170648,
|
| 2294 |
+
"grad_norm": 0.31164662692603995,
|
| 2295 |
+
"learning_rate": 5.074329933681866e-06,
|
| 2296 |
+
"loss": 0.4941,
|
| 2297 |
+
"num_tokens": 546668069.0,
|
| 2298 |
+
"step": 1430
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.9795221843003413,
|
| 2302 |
+
"grad_norm": 0.28240271505587017,
|
| 2303 |
+
"learning_rate": 5.055124413372245e-06,
|
| 2304 |
+
"loss": 0.4854,
|
| 2305 |
+
"num_tokens": 548580998.0,
|
| 2306 |
+
"step": 1435
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.9829351535836177,
|
| 2310 |
+
"grad_norm": 0.2854804492704272,
|
| 2311 |
+
"learning_rate": 5.038781080566688e-06,
|
| 2312 |
+
"loss": 0.4853,
|
| 2313 |
+
"num_tokens": 550468465.0,
|
| 2314 |
+
"step": 1440
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.9863481228668942,
|
| 2318 |
+
"grad_norm": 0.29878095344993955,
|
| 2319 |
+
"learning_rate": 5.025302019379348e-06,
|
| 2320 |
+
"loss": 0.489,
|
| 2321 |
+
"num_tokens": 552397091.0,
|
| 2322 |
+
"step": 1445
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 0.9897610921501706,
|
| 2326 |
+
"grad_norm": 0.26876544482436127,
|
| 2327 |
+
"learning_rate": 5.014688948670296e-06,
|
| 2328 |
+
"loss": 0.4739,
|
| 2329 |
+
"num_tokens": 554315309.0,
|
| 2330 |
+
"step": 1450
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 0.9931740614334471,
|
| 2334 |
+
"grad_norm": 0.3327715880783554,
|
| 2335 |
+
"learning_rate": 5.006943221826337e-06,
|
| 2336 |
+
"loss": 0.4954,
|
| 2337 |
+
"num_tokens": 556147373.0,
|
| 2338 |
+
"step": 1455
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 0.9965870307167235,
|
| 2342 |
+
"grad_norm": 0.2602240612874206,
|
| 2343 |
+
"learning_rate": 5.002065826588409e-06,
|
| 2344 |
+
"loss": 0.4832,
|
| 2345 |
+
"num_tokens": 558093284.0,
|
| 2346 |
+
"step": 1460
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 1.0,
|
| 2350 |
+
"grad_norm": 0.2666803143124106,
|
| 2351 |
+
"learning_rate": 5.000057384925645e-06,
|
| 2352 |
+
"loss": 0.4886,
|
| 2353 |
+
"num_tokens": 560009809.0,
|
| 2354 |
+
"step": 1465
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.0,
|
| 2358 |
+
"step": 1465,
|
| 2359 |
+
"total_flos": 1146719604572160.0,
|
| 2360 |
+
"train_loss": 0.5249247749510886,
|
| 2361 |
+
"train_runtime": 25895.7798,
|
| 2362 |
+
"train_samples_per_second": 3.62,
|
| 2363 |
+
"train_steps_per_second": 0.057
|
| 2364 |
+
}
|
| 2365 |
+
],
|
| 2366 |
+
"logging_steps": 5,
|
| 2367 |
+
"max_steps": 1465,
|
| 2368 |
+
"num_input_tokens_seen": 0,
|
| 2369 |
+
"num_train_epochs": 1,
|
| 2370 |
+
"save_steps": 100,
|
| 2371 |
+
"stateful_callbacks": {
|
| 2372 |
+
"TrainerControl": {
|
| 2373 |
+
"args": {
|
| 2374 |
+
"should_epoch_stop": false,
|
| 2375 |
+
"should_evaluate": false,
|
| 2376 |
+
"should_log": false,
|
| 2377 |
+
"should_save": true,
|
| 2378 |
+
"should_training_stop": true
|
| 2379 |
+
},
|
| 2380 |
+
"attributes": {}
|
| 2381 |
+
}
|
| 2382 |
+
},
|
| 2383 |
+
"total_flos": 1146719604572160.0,
|
| 2384 |
+
"train_batch_size": 16,
|
| 2385 |
+
"trial_name": null,
|
| 2386 |
+
"trial_params": null
|
| 2387 |
+
}
|