Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +11 -0
- train_results.json +8 -0
- trainer_state.json +1723 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: PreThink_MemAgent
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for PreThink_MemAgent
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-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="ucmp137538/PreThink_MemAgent", 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/mingzeli/PreThink_MemAgent/runs/umrk1n8k)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.18.0
|
| 38 |
+
- Transformers: 4.52.3
|
| 39 |
+
- Pytorch: 2.7.0
|
| 40 |
+
- Datasets: 4.3.0
|
| 41 |
+
- Tokenizers: 0.21.4
|
| 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": 2.7972111648056934e+17,
|
| 3 |
+
"train_loss": 1.0216455256655104,
|
| 4 |
+
"train_runtime": 2780.2712,
|
| 5 |
+
"train_samples": 5375,
|
| 6 |
+
"train_samples_per_second": 9.666,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"pad_token_id": 151643,
|
| 6 |
+
"repetition_penalty": 1.05,
|
| 7 |
+
"temperature": 0.7,
|
| 8 |
+
"top_k": 20,
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"transformers_version": "4.52.3"
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 2.7972111648056934e+17,
|
| 3 |
+
"train_loss": 1.0216455256655104,
|
| 4 |
+
"train_runtime": 2780.2712,
|
| 5 |
+
"train_samples": 5375,
|
| 6 |
+
"train_samples_per_second": 9.666,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 210,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.023809523809523808,
|
| 14 |
+
"grad_norm": 6.538216213930027,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.9338,
|
| 17 |
+
"num_tokens": 301499.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.047619047619047616,
|
| 22 |
+
"grad_norm": 6.773412169837184,
|
| 23 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 24 |
+
"loss": 1.9236,
|
| 25 |
+
"num_tokens": 603383.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07142857142857142,
|
| 30 |
+
"grad_norm": 4.749957858339624,
|
| 31 |
+
"learning_rate": 8.571428571428571e-06,
|
| 32 |
+
"loss": 1.8766,
|
| 33 |
+
"num_tokens": 863622.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.09523809523809523,
|
| 38 |
+
"grad_norm": 2.2238600419377277,
|
| 39 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 40 |
+
"loss": 1.7506,
|
| 41 |
+
"num_tokens": 1179346.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.11904761904761904,
|
| 46 |
+
"grad_norm": 3.7552483574413404,
|
| 47 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 48 |
+
"loss": 1.7277,
|
| 49 |
+
"num_tokens": 1490946.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.14285714285714285,
|
| 54 |
+
"grad_norm": 4.15755928790991,
|
| 55 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 56 |
+
"loss": 1.658,
|
| 57 |
+
"num_tokens": 1719799.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16666666666666666,
|
| 62 |
+
"grad_norm": 2.245417974821929,
|
| 63 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 64 |
+
"loss": 1.6608,
|
| 65 |
+
"num_tokens": 2009958.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.19047619047619047,
|
| 70 |
+
"grad_norm": 3.1872785546255233,
|
| 71 |
+
"learning_rate": 3e-05,
|
| 72 |
+
"loss": 1.6032,
|
| 73 |
+
"num_tokens": 2334131.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21428571428571427,
|
| 78 |
+
"grad_norm": 2.062217429493514,
|
| 79 |
+
"learning_rate": 2.999838339925525e-05,
|
| 80 |
+
"loss": 1.6093,
|
| 81 |
+
"num_tokens": 2659726.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.23809523809523808,
|
| 86 |
+
"grad_norm": 30.952811910237916,
|
| 87 |
+
"learning_rate": 2.9993533984191048e-05,
|
| 88 |
+
"loss": 1.6153,
|
| 89 |
+
"num_tokens": 2997515.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.2619047619047619,
|
| 94 |
+
"grad_norm": 5.437630168475735,
|
| 95 |
+
"learning_rate": 2.9985452916224895e-05,
|
| 96 |
+
"loss": 1.6272,
|
| 97 |
+
"num_tokens": 3298571.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.2857142857142857,
|
| 102 |
+
"grad_norm": 9.067784859415095,
|
| 103 |
+
"learning_rate": 2.9974142130743523e-05,
|
| 104 |
+
"loss": 1.6427,
|
| 105 |
+
"num_tokens": 3621523.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.30952380952380953,
|
| 110 |
+
"grad_norm": 8.297445832624902,
|
| 111 |
+
"learning_rate": 2.9959604336639406e-05,
|
| 112 |
+
"loss": 1.6557,
|
| 113 |
+
"num_tokens": 3918652.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3333333333333333,
|
| 118 |
+
"grad_norm": 18.611016423707234,
|
| 119 |
+
"learning_rate": 2.9941843015662005e-05,
|
| 120 |
+
"loss": 1.6543,
|
| 121 |
+
"num_tokens": 4189760.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.35714285714285715,
|
| 126 |
+
"grad_norm": 37.588129897999515,
|
| 127 |
+
"learning_rate": 2.9920862421583856e-05,
|
| 128 |
+
"loss": 1.6303,
|
| 129 |
+
"num_tokens": 4543297.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.38095238095238093,
|
| 134 |
+
"grad_norm": 4.123366988000153,
|
| 135 |
+
"learning_rate": 2.9896667579181855e-05,
|
| 136 |
+
"loss": 1.6285,
|
| 137 |
+
"num_tokens": 4829061.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.40476190476190477,
|
| 142 |
+
"grad_norm": 11.611181067813334,
|
| 143 |
+
"learning_rate": 2.9869264283033827e-05,
|
| 144 |
+
"loss": 1.5812,
|
| 145 |
+
"num_tokens": 5089606.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.42857142857142855,
|
| 150 |
+
"grad_norm": 2.2261338342365398,
|
| 151 |
+
"learning_rate": 2.9838659096130715e-05,
|
| 152 |
+
"loss": 1.5597,
|
| 153 |
+
"num_tokens": 5390312.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.4523809523809524,
|
| 158 |
+
"grad_norm": 2.1851134690595377,
|
| 159 |
+
"learning_rate": 2.9804859348304814e-05,
|
| 160 |
+
"loss": 1.5541,
|
| 161 |
+
"num_tokens": 5637391.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.47619047619047616,
|
| 166 |
+
"grad_norm": 19.42274392919098,
|
| 167 |
+
"learning_rate": 2.976787313447427e-05,
|
| 168 |
+
"loss": 1.5582,
|
| 169 |
+
"num_tokens": 5900436.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5,
|
| 174 |
+
"grad_norm": 2.743718856278709,
|
| 175 |
+
"learning_rate": 2.9727709312704392e-05,
|
| 176 |
+
"loss": 1.5783,
|
| 177 |
+
"num_tokens": 6208557.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5238095238095238,
|
| 182 |
+
"grad_norm": 1.270567239695732,
|
| 183 |
+
"learning_rate": 2.968437750208617e-05,
|
| 184 |
+
"loss": 1.571,
|
| 185 |
+
"num_tokens": 6508211.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.5476190476190477,
|
| 190 |
+
"grad_norm": 1.3295343234029675,
|
| 191 |
+
"learning_rate": 2.963788808043254e-05,
|
| 192 |
+
"loss": 1.5558,
|
| 193 |
+
"num_tokens": 6815212.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.5714285714285714,
|
| 198 |
+
"grad_norm": 1.0645487974082066,
|
| 199 |
+
"learning_rate": 2.9588252181792933e-05,
|
| 200 |
+
"loss": 1.5579,
|
| 201 |
+
"num_tokens": 7165341.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.5952380952380952,
|
| 206 |
+
"grad_norm": 0.8618665557232967,
|
| 207 |
+
"learning_rate": 2.953548169378672e-05,
|
| 208 |
+
"loss": 1.5311,
|
| 209 |
+
"num_tokens": 7446406.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.6190476190476191,
|
| 214 |
+
"grad_norm": 0.8833172294647831,
|
| 215 |
+
"learning_rate": 2.9479589254756145e-05,
|
| 216 |
+
"loss": 1.5395,
|
| 217 |
+
"num_tokens": 7716401.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.6428571428571429,
|
| 222 |
+
"grad_norm": 0.8730876262810777,
|
| 223 |
+
"learning_rate": 2.9420588250739514e-05,
|
| 224 |
+
"loss": 1.5083,
|
| 225 |
+
"num_tokens": 7991093.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6666666666666666,
|
| 230 |
+
"grad_norm": 9.830926234059927,
|
| 231 |
+
"learning_rate": 2.9358492812265286e-05,
|
| 232 |
+
"loss": 1.562,
|
| 233 |
+
"num_tokens": 8326807.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6904761904761905,
|
| 238 |
+
"grad_norm": 3.439648574877625,
|
| 239 |
+
"learning_rate": 2.9293317810967836e-05,
|
| 240 |
+
"loss": 1.5434,
|
| 241 |
+
"num_tokens": 8608746.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.7142857142857143,
|
| 246 |
+
"grad_norm": 1.4403398373980578,
|
| 247 |
+
"learning_rate": 2.9225078856025776e-05,
|
| 248 |
+
"loss": 1.55,
|
| 249 |
+
"num_tokens": 8887444.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.7380952380952381,
|
| 254 |
+
"grad_norm": 0.9256924750760002,
|
| 255 |
+
"learning_rate": 2.915379229042361e-05,
|
| 256 |
+
"loss": 1.5387,
|
| 257 |
+
"num_tokens": 9158119.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.7619047619047619,
|
| 262 |
+
"grad_norm": 0.9693333317012788,
|
| 263 |
+
"learning_rate": 2.9079475187037645e-05,
|
| 264 |
+
"loss": 1.5525,
|
| 265 |
+
"num_tokens": 9455380.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.7857142857142857,
|
| 270 |
+
"grad_norm": 4.418422539715986,
|
| 271 |
+
"learning_rate": 2.900214534454708e-05,
|
| 272 |
+
"loss": 1.562,
|
| 273 |
+
"num_tokens": 9819963.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.8095238095238095,
|
| 278 |
+
"grad_norm": 1.4976653598911862,
|
| 279 |
+
"learning_rate": 2.8921821283171333e-05,
|
| 280 |
+
"loss": 1.5134,
|
| 281 |
+
"num_tokens": 10120795.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8333333333333334,
|
| 286 |
+
"grad_norm": 0.9155113033240181,
|
| 287 |
+
"learning_rate": 2.883852224023446e-05,
|
| 288 |
+
"loss": 1.5485,
|
| 289 |
+
"num_tokens": 10448963.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.8571428571428571,
|
| 294 |
+
"grad_norm": 1.078789553362349,
|
| 295 |
+
"learning_rate": 2.875226816555792e-05,
|
| 296 |
+
"loss": 1.5239,
|
| 297 |
+
"num_tokens": 10726463.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.8809523809523809,
|
| 302 |
+
"grad_norm": 0.8912072449466584,
|
| 303 |
+
"learning_rate": 2.8663079716682657e-05,
|
| 304 |
+
"loss": 1.5328,
|
| 305 |
+
"num_tokens": 11034561.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.9047619047619048,
|
| 310 |
+
"grad_norm": 0.8137040759182133,
|
| 311 |
+
"learning_rate": 2.8570978253921695e-05,
|
| 312 |
+
"loss": 1.5173,
|
| 313 |
+
"num_tokens": 11357514.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.9285714285714286,
|
| 318 |
+
"grad_norm": 0.9066560545161888,
|
| 319 |
+
"learning_rate": 2.8475985835244395e-05,
|
| 320 |
+
"loss": 1.5032,
|
| 321 |
+
"num_tokens": 11618431.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.9523809523809523,
|
| 326 |
+
"grad_norm": 0.789402718151679,
|
| 327 |
+
"learning_rate": 2.8378125210993705e-05,
|
| 328 |
+
"loss": 1.5219,
|
| 329 |
+
"num_tokens": 11938221.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.9761904761904762,
|
| 334 |
+
"grad_norm": 0.984207528765468,
|
| 335 |
+
"learning_rate": 2.8277419818437477e-05,
|
| 336 |
+
"loss": 1.536,
|
| 337 |
+
"num_tokens": 12260374.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0,
|
| 342 |
+
"grad_norm": 0.7141475421535004,
|
| 343 |
+
"learning_rate": 2.817389377615535e-05,
|
| 344 |
+
"loss": 1.5138,
|
| 345 |
+
"num_tokens": 12557020.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.0238095238095237,
|
| 350 |
+
"grad_norm": 0.9363198060842514,
|
| 351 |
+
"learning_rate": 2.8067571878262455e-05,
|
| 352 |
+
"loss": 1.3474,
|
| 353 |
+
"num_tokens": 12816238.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0476190476190477,
|
| 358 |
+
"grad_norm": 0.6926582015960785,
|
| 359 |
+
"learning_rate": 2.7958479588471274e-05,
|
| 360 |
+
"loss": 1.3267,
|
| 361 |
+
"num_tokens": 13122015.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.0714285714285714,
|
| 366 |
+
"grad_norm": 0.9454215939995514,
|
| 367 |
+
"learning_rate": 2.784664303399321e-05,
|
| 368 |
+
"loss": 1.339,
|
| 369 |
+
"num_tokens": 13397622.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.0952380952380953,
|
| 374 |
+
"grad_norm": 0.7721777219877292,
|
| 375 |
+
"learning_rate": 2.7732088999281182e-05,
|
| 376 |
+
"loss": 1.3203,
|
| 377 |
+
"num_tokens": 13699593.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.119047619047619,
|
| 382 |
+
"grad_norm": 0.8317013732600135,
|
| 383 |
+
"learning_rate": 2.7614844919614878e-05,
|
| 384 |
+
"loss": 1.3393,
|
| 385 |
+
"num_tokens": 14012389.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.1428571428571428,
|
| 390 |
+
"grad_norm": 0.8420079333202011,
|
| 391 |
+
"learning_rate": 2.749493887453007e-05,
|
| 392 |
+
"loss": 1.321,
|
| 393 |
+
"num_tokens": 14310791.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.1666666666666667,
|
| 398 |
+
"grad_norm": 0.808825236941867,
|
| 399 |
+
"learning_rate": 2.7372399581093692e-05,
|
| 400 |
+
"loss": 1.3444,
|
| 401 |
+
"num_tokens": 14658237.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1904761904761905,
|
| 406 |
+
"grad_norm": 0.9423947902880564,
|
| 407 |
+
"learning_rate": 2.724725638702619e-05,
|
| 408 |
+
"loss": 1.3208,
|
| 409 |
+
"num_tokens": 14932524.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.2142857142857142,
|
| 414 |
+
"grad_norm": 0.8920368672000416,
|
| 415 |
+
"learning_rate": 2.7119539263672863e-05,
|
| 416 |
+
"loss": 1.3663,
|
| 417 |
+
"num_tokens": 15221313.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.2380952380952381,
|
| 422 |
+
"grad_norm": 1.037715092791166,
|
| 423 |
+
"learning_rate": 2.698927879882581e-05,
|
| 424 |
+
"loss": 1.3133,
|
| 425 |
+
"num_tokens": 15503438.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.2619047619047619,
|
| 430 |
+
"grad_norm": 0.9566394653382752,
|
| 431 |
+
"learning_rate": 2.6856506189398304e-05,
|
| 432 |
+
"loss": 1.3418,
|
| 433 |
+
"num_tokens": 15812209.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.2857142857142856,
|
| 438 |
+
"grad_norm": 0.7773982206501678,
|
| 439 |
+
"learning_rate": 2.672125323395319e-05,
|
| 440 |
+
"loss": 1.3214,
|
| 441 |
+
"num_tokens": 16133281.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.3095238095238095,
|
| 446 |
+
"grad_norm": 0.7309052587570527,
|
| 447 |
+
"learning_rate": 2.6583552325087277e-05,
|
| 448 |
+
"loss": 1.3106,
|
| 449 |
+
"num_tokens": 16469546.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.3333333333333333,
|
| 454 |
+
"grad_norm": 0.731975052614095,
|
| 455 |
+
"learning_rate": 2.644343644167344e-05,
|
| 456 |
+
"loss": 1.315,
|
| 457 |
+
"num_tokens": 16740412.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.3571428571428572,
|
| 462 |
+
"grad_norm": 0.888533248470318,
|
| 463 |
+
"learning_rate": 2.6300939140962265e-05,
|
| 464 |
+
"loss": 1.3347,
|
| 465 |
+
"num_tokens": 17069209.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.380952380952381,
|
| 470 |
+
"grad_norm": 0.8174152731954014,
|
| 471 |
+
"learning_rate": 2.615609455054523e-05,
|
| 472 |
+
"loss": 1.3252,
|
| 473 |
+
"num_tokens": 17390230.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4047619047619047,
|
| 478 |
+
"grad_norm": 0.7703407162710431,
|
| 479 |
+
"learning_rate": 2.6008937360181247e-05,
|
| 480 |
+
"loss": 1.333,
|
| 481 |
+
"num_tokens": 17751056.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.4285714285714286,
|
| 486 |
+
"grad_norm": 0.8093422656169592,
|
| 487 |
+
"learning_rate": 2.5859502813488634e-05,
|
| 488 |
+
"loss": 1.2688,
|
| 489 |
+
"num_tokens": 18029513.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.4523809523809523,
|
| 494 |
+
"grad_norm": 0.7448128748019907,
|
| 495 |
+
"learning_rate": 2.570782669950435e-05,
|
| 496 |
+
"loss": 1.2866,
|
| 497 |
+
"num_tokens": 18342199.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.4761904761904763,
|
| 502 |
+
"grad_norm": 0.797247555706446,
|
| 503 |
+
"learning_rate": 2.5553945344112646e-05,
|
| 504 |
+
"loss": 1.3474,
|
| 505 |
+
"num_tokens": 18654129.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.5,
|
| 510 |
+
"grad_norm": 0.8270748581084111,
|
| 511 |
+
"learning_rate": 2.539789560134521e-05,
|
| 512 |
+
"loss": 1.3099,
|
| 513 |
+
"num_tokens": 18959464.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.5238095238095237,
|
| 518 |
+
"grad_norm": 0.813301315394994,
|
| 519 |
+
"learning_rate": 2.5239714844554674e-05,
|
| 520 |
+
"loss": 1.3041,
|
| 521 |
+
"num_tokens": 19214541.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.5476190476190477,
|
| 526 |
+
"grad_norm": 0.951995926855497,
|
| 527 |
+
"learning_rate": 2.5079440957463894e-05,
|
| 528 |
+
"loss": 1.2476,
|
| 529 |
+
"num_tokens": 19491950.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.5714285714285714,
|
| 534 |
+
"grad_norm": 0.7172356466200617,
|
| 535 |
+
"learning_rate": 2.4917112325092904e-05,
|
| 536 |
+
"loss": 1.2979,
|
| 537 |
+
"num_tokens": 19789279.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.5952380952380953,
|
| 542 |
+
"grad_norm": 0.842364452878783,
|
| 543 |
+
"learning_rate": 2.475276782456585e-05,
|
| 544 |
+
"loss": 1.2964,
|
| 545 |
+
"num_tokens": 20050385.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.619047619047619,
|
| 550 |
+
"grad_norm": 0.8775202665218085,
|
| 551 |
+
"learning_rate": 2.4586446815800056e-05,
|
| 552 |
+
"loss": 1.2306,
|
| 553 |
+
"num_tokens": 20293468.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.6428571428571428,
|
| 558 |
+
"grad_norm": 0.8077565121484018,
|
| 559 |
+
"learning_rate": 2.441818913207947e-05,
|
| 560 |
+
"loss": 1.2124,
|
| 561 |
+
"num_tokens": 20548563.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.6666666666666665,
|
| 566 |
+
"grad_norm": 0.7891520078797498,
|
| 567 |
+
"learning_rate": 2.4248035070514732e-05,
|
| 568 |
+
"loss": 1.31,
|
| 569 |
+
"num_tokens": 20899914.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.6904761904761905,
|
| 574 |
+
"grad_norm": 0.8935642914804406,
|
| 575 |
+
"learning_rate": 2.4076025382392166e-05,
|
| 576 |
+
"loss": 1.2904,
|
| 577 |
+
"num_tokens": 21207831.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.7142857142857144,
|
| 582 |
+
"grad_norm": 0.7791700089762551,
|
| 583 |
+
"learning_rate": 2.3902201263413968e-05,
|
| 584 |
+
"loss": 1.3009,
|
| 585 |
+
"num_tokens": 21535523.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.7380952380952381,
|
| 590 |
+
"grad_norm": 0.6803499303828192,
|
| 591 |
+
"learning_rate": 2.372660434383203e-05,
|
| 592 |
+
"loss": 1.3084,
|
| 593 |
+
"num_tokens": 21866131.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.7619047619047619,
|
| 598 |
+
"grad_norm": 0.8712043390870515,
|
| 599 |
+
"learning_rate": 2.3549276678477605e-05,
|
| 600 |
+
"loss": 1.2974,
|
| 601 |
+
"num_tokens": 22201523.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.7857142857142856,
|
| 606 |
+
"grad_norm": 0.8755800517621928,
|
| 607 |
+
"learning_rate": 2.337026073668934e-05,
|
| 608 |
+
"loss": 1.2914,
|
| 609 |
+
"num_tokens": 22488112.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.8095238095238095,
|
| 614 |
+
"grad_norm": 0.6269216466100511,
|
| 615 |
+
"learning_rate": 2.3189599392142027e-05,
|
| 616 |
+
"loss": 1.3065,
|
| 617 |
+
"num_tokens": 22813071.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.8333333333333335,
|
| 622 |
+
"grad_norm": 0.8732441594396502,
|
| 623 |
+
"learning_rate": 2.3007335912578496e-05,
|
| 624 |
+
"loss": 1.2387,
|
| 625 |
+
"num_tokens": 23107173.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.8571428571428572,
|
| 630 |
+
"grad_norm": 0.8321205173092046,
|
| 631 |
+
"learning_rate": 2.282351394944717e-05,
|
| 632 |
+
"loss": 1.3084,
|
| 633 |
+
"num_tokens": 23422105.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.880952380952381,
|
| 638 |
+
"grad_norm": 0.6201826285098905,
|
| 639 |
+
"learning_rate": 2.263817752744767e-05,
|
| 640 |
+
"loss": 1.2937,
|
| 641 |
+
"num_tokens": 23788463.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.9047619047619047,
|
| 646 |
+
"grad_norm": 0.864663931903862,
|
| 647 |
+
"learning_rate": 2.2451371033987086e-05,
|
| 648 |
+
"loss": 1.2315,
|
| 649 |
+
"num_tokens": 24016057.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.9285714285714286,
|
| 654 |
+
"grad_norm": 0.8151031466504542,
|
| 655 |
+
"learning_rate": 2.226313920854934e-05,
|
| 656 |
+
"loss": 1.2065,
|
| 657 |
+
"num_tokens": 24286443.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.9523809523809523,
|
| 662 |
+
"grad_norm": 0.69377209773933,
|
| 663 |
+
"learning_rate": 2.207352713198024e-05,
|
| 664 |
+
"loss": 1.2522,
|
| 665 |
+
"num_tokens": 24564564.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.9761904761904763,
|
| 670 |
+
"grad_norm": 0.7749074972232748,
|
| 671 |
+
"learning_rate": 2.1882580215690765e-05,
|
| 672 |
+
"loss": 1.3075,
|
| 673 |
+
"num_tokens": 24856761.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.0,
|
| 678 |
+
"grad_norm": 0.836947163785287,
|
| 679 |
+
"learning_rate": 2.169034419078124e-05,
|
| 680 |
+
"loss": 1.2472,
|
| 681 |
+
"num_tokens": 25119155.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.0238095238095237,
|
| 686 |
+
"grad_norm": 1.302298749181937,
|
| 687 |
+
"learning_rate": 2.1496865097088846e-05,
|
| 688 |
+
"loss": 1.0524,
|
| 689 |
+
"num_tokens": 25461378.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.0476190476190474,
|
| 694 |
+
"grad_norm": 0.9938997123428022,
|
| 695 |
+
"learning_rate": 2.130218927216128e-05,
|
| 696 |
+
"loss": 0.9867,
|
| 697 |
+
"num_tokens": 25757738.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.0714285714285716,
|
| 702 |
+
"grad_norm": 2.239246853283492,
|
| 703 |
+
"learning_rate": 2.110636334015907e-05,
|
| 704 |
+
"loss": 0.9849,
|
| 705 |
+
"num_tokens": 26050090.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.0952380952380953,
|
| 710 |
+
"grad_norm": 2.255240802193634,
|
| 711 |
+
"learning_rate": 2.0909434200689264e-05,
|
| 712 |
+
"loss": 1.0166,
|
| 713 |
+
"num_tokens": 26323746.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.119047619047619,
|
| 718 |
+
"grad_norm": 1.0279577082424196,
|
| 719 |
+
"learning_rate": 2.0711449017573122e-05,
|
| 720 |
+
"loss": 1.016,
|
| 721 |
+
"num_tokens": 26607004.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.142857142857143,
|
| 726 |
+
"grad_norm": 0.8902435973371925,
|
| 727 |
+
"learning_rate": 2.0512455207550557e-05,
|
| 728 |
+
"loss": 0.9812,
|
| 729 |
+
"num_tokens": 26898427.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.1666666666666665,
|
| 734 |
+
"grad_norm": 0.9183593054714583,
|
| 735 |
+
"learning_rate": 2.0312500428924023e-05,
|
| 736 |
+
"loss": 1.0121,
|
| 737 |
+
"num_tokens": 27205357.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.1904761904761907,
|
| 742 |
+
"grad_norm": 0.9376600266290521,
|
| 743 |
+
"learning_rate": 2.0111632570144487e-05,
|
| 744 |
+
"loss": 0.988,
|
| 745 |
+
"num_tokens": 27496694.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.2142857142857144,
|
| 750 |
+
"grad_norm": 0.7220165463532561,
|
| 751 |
+
"learning_rate": 1.9909899738342324e-05,
|
| 752 |
+
"loss": 1.0119,
|
| 753 |
+
"num_tokens": 27794697.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.238095238095238,
|
| 758 |
+
"grad_norm": 0.9053661036106623,
|
| 759 |
+
"learning_rate": 1.9707350247805862e-05,
|
| 760 |
+
"loss": 1.0194,
|
| 761 |
+
"num_tokens": 28115378.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.261904761904762,
|
| 766 |
+
"grad_norm": 0.8729413169116081,
|
| 767 |
+
"learning_rate": 1.9504032608410243e-05,
|
| 768 |
+
"loss": 0.9866,
|
| 769 |
+
"num_tokens": 28404844.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.2857142857142856,
|
| 774 |
+
"grad_norm": 0.7627072905875467,
|
| 775 |
+
"learning_rate": 1.9299995513999512e-05,
|
| 776 |
+
"loss": 1.0105,
|
| 777 |
+
"num_tokens": 28717491.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.3095238095238093,
|
| 782 |
+
"grad_norm": 0.7347382833732581,
|
| 783 |
+
"learning_rate": 1.90952878307246e-05,
|
| 784 |
+
"loss": 0.9667,
|
| 785 |
+
"num_tokens": 28969175.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.3333333333333335,
|
| 790 |
+
"grad_norm": 0.8054230888254635,
|
| 791 |
+
"learning_rate": 1.888995858534005e-05,
|
| 792 |
+
"loss": 1.0089,
|
| 793 |
+
"num_tokens": 29278525.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.357142857142857,
|
| 798 |
+
"grad_norm": 0.7107149711009891,
|
| 799 |
+
"learning_rate": 1.8684056953462328e-05,
|
| 800 |
+
"loss": 0.9881,
|
| 801 |
+
"num_tokens": 29589990.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.380952380952381,
|
| 806 |
+
"grad_norm": 0.709536600984241,
|
| 807 |
+
"learning_rate": 1.8477632247792365e-05,
|
| 808 |
+
"loss": 0.9676,
|
| 809 |
+
"num_tokens": 29851176.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.4047619047619047,
|
| 814 |
+
"grad_norm": 0.7059346761233823,
|
| 815 |
+
"learning_rate": 1.827073390630542e-05,
|
| 816 |
+
"loss": 0.9866,
|
| 817 |
+
"num_tokens": 30150417.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.4285714285714284,
|
| 822 |
+
"grad_norm": 0.6475677168167608,
|
| 823 |
+
"learning_rate": 1.806341148041082e-05,
|
| 824 |
+
"loss": 0.9679,
|
| 825 |
+
"num_tokens": 30476868.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.4523809523809526,
|
| 830 |
+
"grad_norm": 0.6574153556079124,
|
| 831 |
+
"learning_rate": 1.785571462308458e-05,
|
| 832 |
+
"loss": 0.961,
|
| 833 |
+
"num_tokens": 30720675.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.4761904761904763,
|
| 838 |
+
"grad_norm": 0.782684876535666,
|
| 839 |
+
"learning_rate": 1.764769307697769e-05,
|
| 840 |
+
"loss": 0.9449,
|
| 841 |
+
"num_tokens": 30943687.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.5,
|
| 846 |
+
"grad_norm": 0.6959657002281912,
|
| 847 |
+
"learning_rate": 1.7439396662502947e-05,
|
| 848 |
+
"loss": 0.9588,
|
| 849 |
+
"num_tokens": 31226585.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.5238095238095237,
|
| 854 |
+
"grad_norm": 0.6638836519525753,
|
| 855 |
+
"learning_rate": 1.723087526590314e-05,
|
| 856 |
+
"loss": 0.9657,
|
| 857 |
+
"num_tokens": 31536165.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.5476190476190474,
|
| 862 |
+
"grad_norm": 0.5543755171176452,
|
| 863 |
+
"learning_rate": 1.702217882730345e-05,
|
| 864 |
+
"loss": 0.9605,
|
| 865 |
+
"num_tokens": 31859352.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.571428571428571,
|
| 870 |
+
"grad_norm": 0.7519329941062585,
|
| 871 |
+
"learning_rate": 1.6813357328751003e-05,
|
| 872 |
+
"loss": 0.951,
|
| 873 |
+
"num_tokens": 32141589.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.5952380952380953,
|
| 878 |
+
"grad_norm": 0.6384580732849452,
|
| 879 |
+
"learning_rate": 1.660446078224433e-05,
|
| 880 |
+
"loss": 0.9641,
|
| 881 |
+
"num_tokens": 32415823.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.619047619047619,
|
| 886 |
+
"grad_norm": 0.6375498198212793,
|
| 887 |
+
"learning_rate": 1.6395539217755673e-05,
|
| 888 |
+
"loss": 0.9767,
|
| 889 |
+
"num_tokens": 32738959.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.642857142857143,
|
| 894 |
+
"grad_norm": 0.5909380929927559,
|
| 895 |
+
"learning_rate": 1.6186642671249e-05,
|
| 896 |
+
"loss": 0.9553,
|
| 897 |
+
"num_tokens": 33046758.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.6666666666666665,
|
| 902 |
+
"grad_norm": 0.6627084816829975,
|
| 903 |
+
"learning_rate": 1.597782117269655e-05,
|
| 904 |
+
"loss": 0.9918,
|
| 905 |
+
"num_tokens": 33356268.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.6904761904761907,
|
| 910 |
+
"grad_norm": 0.6209028590481098,
|
| 911 |
+
"learning_rate": 1.5769124734096862e-05,
|
| 912 |
+
"loss": 0.9946,
|
| 913 |
+
"num_tokens": 33669521.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.7142857142857144,
|
| 918 |
+
"grad_norm": 0.5682420553998002,
|
| 919 |
+
"learning_rate": 1.5560603337497055e-05,
|
| 920 |
+
"loss": 0.9809,
|
| 921 |
+
"num_tokens": 34006046.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.738095238095238,
|
| 926 |
+
"grad_norm": 0.6102593452284443,
|
| 927 |
+
"learning_rate": 1.5352306923022314e-05,
|
| 928 |
+
"loss": 0.9949,
|
| 929 |
+
"num_tokens": 34329314.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.761904761904762,
|
| 934 |
+
"grad_norm": 0.5963721089952566,
|
| 935 |
+
"learning_rate": 1.5144285376915424e-05,
|
| 936 |
+
"loss": 0.9496,
|
| 937 |
+
"num_tokens": 34649593.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.7857142857142856,
|
| 942 |
+
"grad_norm": 0.6334479812477452,
|
| 943 |
+
"learning_rate": 1.4936588519589182e-05,
|
| 944 |
+
"loss": 0.9865,
|
| 945 |
+
"num_tokens": 34968486.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.8095238095238093,
|
| 950 |
+
"grad_norm": 0.579179313504508,
|
| 951 |
+
"learning_rate": 1.4729266093694578e-05,
|
| 952 |
+
"loss": 1.0112,
|
| 953 |
+
"num_tokens": 35335674.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.8333333333333335,
|
| 958 |
+
"grad_norm": 0.6547466538591331,
|
| 959 |
+
"learning_rate": 1.4522367752207636e-05,
|
| 960 |
+
"loss": 0.9476,
|
| 961 |
+
"num_tokens": 35620162.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.857142857142857,
|
| 966 |
+
"grad_norm": 0.6519356419157716,
|
| 967 |
+
"learning_rate": 1.4315943046537676e-05,
|
| 968 |
+
"loss": 0.9574,
|
| 969 |
+
"num_tokens": 35888853.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.880952380952381,
|
| 974 |
+
"grad_norm": 0.6056113333547287,
|
| 975 |
+
"learning_rate": 1.411004141465995e-05,
|
| 976 |
+
"loss": 0.9453,
|
| 977 |
+
"num_tokens": 36190378.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.9047619047619047,
|
| 982 |
+
"grad_norm": 0.5999985950614662,
|
| 983 |
+
"learning_rate": 1.3904712169275403e-05,
|
| 984 |
+
"loss": 0.9878,
|
| 985 |
+
"num_tokens": 36499565.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.928571428571429,
|
| 990 |
+
"grad_norm": 0.6170461063881166,
|
| 991 |
+
"learning_rate": 1.3700004486000488e-05,
|
| 992 |
+
"loss": 1.003,
|
| 993 |
+
"num_tokens": 36819385.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.9523809523809526,
|
| 998 |
+
"grad_norm": 0.5609993983165859,
|
| 999 |
+
"learning_rate": 1.3495967391589758e-05,
|
| 1000 |
+
"loss": 0.9709,
|
| 1001 |
+
"num_tokens": 37126003.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.9761904761904763,
|
| 1006 |
+
"grad_norm": 0.686886397394039,
|
| 1007 |
+
"learning_rate": 1.3292649752194144e-05,
|
| 1008 |
+
"loss": 0.9514,
|
| 1009 |
+
"num_tokens": 37385037.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.0,
|
| 1014 |
+
"grad_norm": 0.6489847174148443,
|
| 1015 |
+
"learning_rate": 1.309010026165768e-05,
|
| 1016 |
+
"loss": 0.9919,
|
| 1017 |
+
"num_tokens": 37681802.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.0238095238095237,
|
| 1022 |
+
"grad_norm": 1.3407025275092483,
|
| 1023 |
+
"learning_rate": 1.288836742985552e-05,
|
| 1024 |
+
"loss": 0.7691,
|
| 1025 |
+
"num_tokens": 37984864.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.0476190476190474,
|
| 1030 |
+
"grad_norm": 1.1240882365427978,
|
| 1031 |
+
"learning_rate": 1.2687499571075978e-05,
|
| 1032 |
+
"loss": 0.7481,
|
| 1033 |
+
"num_tokens": 38255245.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.0714285714285716,
|
| 1038 |
+
"grad_norm": 0.7591608642049189,
|
| 1039 |
+
"learning_rate": 1.2487544792449443e-05,
|
| 1040 |
+
"loss": 0.7418,
|
| 1041 |
+
"num_tokens": 38525517.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.0952380952380953,
|
| 1046 |
+
"grad_norm": 1.4687837390641727,
|
| 1047 |
+
"learning_rate": 1.2288550982426879e-05,
|
| 1048 |
+
"loss": 0.7639,
|
| 1049 |
+
"num_tokens": 38849309.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.119047619047619,
|
| 1054 |
+
"grad_norm": 1.6813633030275168,
|
| 1055 |
+
"learning_rate": 1.2090565799310738e-05,
|
| 1056 |
+
"loss": 0.7419,
|
| 1057 |
+
"num_tokens": 39220621.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.142857142857143,
|
| 1062 |
+
"grad_norm": 1.5003572460299635,
|
| 1063 |
+
"learning_rate": 1.1893636659840927e-05,
|
| 1064 |
+
"loss": 0.7561,
|
| 1065 |
+
"num_tokens": 39564336.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.1666666666666665,
|
| 1070 |
+
"grad_norm": 1.0050005240430444,
|
| 1071 |
+
"learning_rate": 1.169781072783872e-05,
|
| 1072 |
+
"loss": 0.7044,
|
| 1073 |
+
"num_tokens": 39847434.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.1904761904761907,
|
| 1078 |
+
"grad_norm": 0.8969397973329072,
|
| 1079 |
+
"learning_rate": 1.1503134902911155e-05,
|
| 1080 |
+
"loss": 0.722,
|
| 1081 |
+
"num_tokens": 40157495.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.2142857142857144,
|
| 1086 |
+
"grad_norm": 0.8424389883668345,
|
| 1087 |
+
"learning_rate": 1.1309655809218764e-05,
|
| 1088 |
+
"loss": 0.7033,
|
| 1089 |
+
"num_tokens": 40469966.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.238095238095238,
|
| 1094 |
+
"grad_norm": 0.8450270760954434,
|
| 1095 |
+
"learning_rate": 1.1117419784309236e-05,
|
| 1096 |
+
"loss": 0.7047,
|
| 1097 |
+
"num_tokens": 40771634.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 3.261904761904762,
|
| 1102 |
+
"grad_norm": 0.7538567142823028,
|
| 1103 |
+
"learning_rate": 1.0926472868019764e-05,
|
| 1104 |
+
"loss": 0.715,
|
| 1105 |
+
"num_tokens": 41087014.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.2857142857142856,
|
| 1110 |
+
"grad_norm": 0.799941449070327,
|
| 1111 |
+
"learning_rate": 1.0736860791450658e-05,
|
| 1112 |
+
"loss": 0.7477,
|
| 1113 |
+
"num_tokens": 41435947.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 3.3095238095238093,
|
| 1118 |
+
"grad_norm": 0.821321998423862,
|
| 1119 |
+
"learning_rate": 1.0548628966012917e-05,
|
| 1120 |
+
"loss": 0.7057,
|
| 1121 |
+
"num_tokens": 41733553.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.3333333333333335,
|
| 1126 |
+
"grad_norm": 0.8039593601908853,
|
| 1127 |
+
"learning_rate": 1.036182247255233e-05,
|
| 1128 |
+
"loss": 0.6771,
|
| 1129 |
+
"num_tokens": 41998508.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.357142857142857,
|
| 1134 |
+
"grad_norm": 0.7486362398650765,
|
| 1135 |
+
"learning_rate": 1.0176486050552834e-05,
|
| 1136 |
+
"loss": 0.7025,
|
| 1137 |
+
"num_tokens": 42328033.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 3.380952380952381,
|
| 1142 |
+
"grad_norm": 0.7435262398434506,
|
| 1143 |
+
"learning_rate": 9.99266408742151e-06,
|
| 1144 |
+
"loss": 0.6721,
|
| 1145 |
+
"num_tokens": 42576679.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 3.4047619047619047,
|
| 1150 |
+
"grad_norm": 0.640772240723941,
|
| 1151 |
+
"learning_rate": 9.810400607857975e-06,
|
| 1152 |
+
"loss": 0.7008,
|
| 1153 |
+
"num_tokens": 42881848.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 3.4285714285714284,
|
| 1158 |
+
"grad_norm": 0.6750307967979159,
|
| 1159 |
+
"learning_rate": 9.629739263310663e-06,
|
| 1160 |
+
"loss": 0.6576,
|
| 1161 |
+
"num_tokens": 43180370.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.4523809523809526,
|
| 1166 |
+
"grad_norm": 0.6349593868773542,
|
| 1167 |
+
"learning_rate": 9.4507233215224e-06,
|
| 1168 |
+
"loss": 0.6895,
|
| 1169 |
+
"num_tokens": 43485194.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 3.4761904761904763,
|
| 1174 |
+
"grad_norm": 0.7007765296778146,
|
| 1175 |
+
"learning_rate": 9.273395656167974e-06,
|
| 1176 |
+
"loss": 0.6616,
|
| 1177 |
+
"num_tokens": 43735211.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.5,
|
| 1182 |
+
"grad_norm": 0.6838183617031265,
|
| 1183 |
+
"learning_rate": 9.097798736586033e-06,
|
| 1184 |
+
"loss": 0.6899,
|
| 1185 |
+
"num_tokens": 44018672.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.5238095238095237,
|
| 1190 |
+
"grad_norm": 0.6632040105335824,
|
| 1191 |
+
"learning_rate": 8.92397461760784e-06,
|
| 1192 |
+
"loss": 0.6846,
|
| 1193 |
+
"num_tokens": 44328901.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.5476190476190474,
|
| 1198 |
+
"grad_norm": 0.6283627701359418,
|
| 1199 |
+
"learning_rate": 8.751964929485264e-06,
|
| 1200 |
+
"loss": 0.7087,
|
| 1201 |
+
"num_tokens": 44639895.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.571428571428571,
|
| 1206 |
+
"grad_norm": 0.6949482066022805,
|
| 1207 |
+
"learning_rate": 8.58181086792053e-06,
|
| 1208 |
+
"loss": 0.7229,
|
| 1209 |
+
"num_tokens": 44912674.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 3.5952380952380953,
|
| 1214 |
+
"grad_norm": 0.6161930464924805,
|
| 1215 |
+
"learning_rate": 8.413553184199947e-06,
|
| 1216 |
+
"loss": 0.7318,
|
| 1217 |
+
"num_tokens": 45239369.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 3.619047619047619,
|
| 1222 |
+
"grad_norm": 0.6775157046640012,
|
| 1223 |
+
"learning_rate": 8.247232175434151e-06,
|
| 1224 |
+
"loss": 0.69,
|
| 1225 |
+
"num_tokens": 45487078.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.642857142857143,
|
| 1230 |
+
"grad_norm": 0.6598743917563118,
|
| 1231 |
+
"learning_rate": 8.082887674907099e-06,
|
| 1232 |
+
"loss": 0.6823,
|
| 1233 |
+
"num_tokens": 45764060.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.6666666666666665,
|
| 1238 |
+
"grad_norm": 0.6389058360603095,
|
| 1239 |
+
"learning_rate": 7.92055904253611e-06,
|
| 1240 |
+
"loss": 0.7304,
|
| 1241 |
+
"num_tokens": 46055608.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.6904761904761907,
|
| 1246 |
+
"grad_norm": 0.6077489003813343,
|
| 1247 |
+
"learning_rate": 7.760285155445328e-06,
|
| 1248 |
+
"loss": 0.7093,
|
| 1249 |
+
"num_tokens": 46359953.0,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.7142857142857144,
|
| 1254 |
+
"grad_norm": 0.5967397524054626,
|
| 1255 |
+
"learning_rate": 7.602104398654793e-06,
|
| 1256 |
+
"loss": 0.7066,
|
| 1257 |
+
"num_tokens": 46668754.0,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 3.738095238095238,
|
| 1262 |
+
"grad_norm": 0.6350745338711014,
|
| 1263 |
+
"learning_rate": 7.446054655887351e-06,
|
| 1264 |
+
"loss": 0.7024,
|
| 1265 |
+
"num_tokens": 46984092.0,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 3.761904761904762,
|
| 1270 |
+
"grad_norm": 0.654479549343766,
|
| 1271 |
+
"learning_rate": 7.292173300495655e-06,
|
| 1272 |
+
"loss": 0.7024,
|
| 1273 |
+
"num_tokens": 47279370.0,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 3.7857142857142856,
|
| 1278 |
+
"grad_norm": 0.6241512933913473,
|
| 1279 |
+
"learning_rate": 7.140497186511365e-06,
|
| 1280 |
+
"loss": 0.6782,
|
| 1281 |
+
"num_tokens": 47607126.0,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 3.8095238095238093,
|
| 1286 |
+
"grad_norm": 0.6892381674511956,
|
| 1287 |
+
"learning_rate": 6.99106263981875e-06,
|
| 1288 |
+
"loss": 0.6708,
|
| 1289 |
+
"num_tokens": 47854285.0,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 3.8333333333333335,
|
| 1294 |
+
"grad_norm": 0.6054186909041117,
|
| 1295 |
+
"learning_rate": 6.843905449454775e-06,
|
| 1296 |
+
"loss": 0.7098,
|
| 1297 |
+
"num_tokens": 48172146.0,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.857142857142857,
|
| 1302 |
+
"grad_norm": 0.5956432849446107,
|
| 1303 |
+
"learning_rate": 6.699060859037737e-06,
|
| 1304 |
+
"loss": 0.7313,
|
| 1305 |
+
"num_tokens": 48512170.0,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 3.880952380952381,
|
| 1310 |
+
"grad_norm": 0.6733062415864223,
|
| 1311 |
+
"learning_rate": 6.556563558326561e-06,
|
| 1312 |
+
"loss": 0.7001,
|
| 1313 |
+
"num_tokens": 48798674.0,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.9047619047619047,
|
| 1318 |
+
"grad_norm": 0.6484125556278886,
|
| 1319 |
+
"learning_rate": 6.416447674912726e-06,
|
| 1320 |
+
"loss": 0.7064,
|
| 1321 |
+
"num_tokens": 49078950.0,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 3.928571428571429,
|
| 1326 |
+
"grad_norm": 0.6651238762004111,
|
| 1327 |
+
"learning_rate": 6.278746766046815e-06,
|
| 1328 |
+
"loss": 0.6613,
|
| 1329 |
+
"num_tokens": 49321513.0,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 3.9523809523809526,
|
| 1334 |
+
"grad_norm": 0.6123780278745324,
|
| 1335 |
+
"learning_rate": 6.143493810601696e-06,
|
| 1336 |
+
"loss": 0.6737,
|
| 1337 |
+
"num_tokens": 49622007.0,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 3.9761904761904763,
|
| 1342 |
+
"grad_norm": 0.6147575021892541,
|
| 1343 |
+
"learning_rate": 6.010721201174187e-06,
|
| 1344 |
+
"loss": 0.7213,
|
| 1345 |
+
"num_tokens": 49949396.0,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.0,
|
| 1350 |
+
"grad_norm": 0.6525996500721447,
|
| 1351 |
+
"learning_rate": 5.880460736327139e-06,
|
| 1352 |
+
"loss": 0.6751,
|
| 1353 |
+
"num_tokens": 50240879.0,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.023809523809524,
|
| 1358 |
+
"grad_norm": 1.1945930661064657,
|
| 1359 |
+
"learning_rate": 5.7527436129738094e-06,
|
| 1360 |
+
"loss": 0.5781,
|
| 1361 |
+
"num_tokens": 50522550.0,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.0476190476190474,
|
| 1366 |
+
"grad_norm": 1.0060804692820782,
|
| 1367 |
+
"learning_rate": 5.62760041890631e-06,
|
| 1368 |
+
"loss": 0.5498,
|
| 1369 |
+
"num_tokens": 50813206.0,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 4.071428571428571,
|
| 1374 |
+
"grad_norm": 0.751291910016424,
|
| 1375 |
+
"learning_rate": 5.505061125469931e-06,
|
| 1376 |
+
"loss": 0.5308,
|
| 1377 |
+
"num_tokens": 51062794.0,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 4.095238095238095,
|
| 1382 |
+
"grad_norm": 0.7527801055673746,
|
| 1383 |
+
"learning_rate": 5.385155080385125e-06,
|
| 1384 |
+
"loss": 0.5223,
|
| 1385 |
+
"num_tokens": 51335547.0,
|
| 1386 |
+
"step": 172
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.119047619047619,
|
| 1390 |
+
"grad_norm": 0.9363987669688705,
|
| 1391 |
+
"learning_rate": 5.267911000718819e-06,
|
| 1392 |
+
"loss": 0.5258,
|
| 1393 |
+
"num_tokens": 51637656.0,
|
| 1394 |
+
"step": 173
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 4.142857142857143,
|
| 1398 |
+
"grad_norm": 1.1015381943904987,
|
| 1399 |
+
"learning_rate": 5.153356966006791e-06,
|
| 1400 |
+
"loss": 0.5196,
|
| 1401 |
+
"num_tokens": 51953140.0,
|
| 1402 |
+
"step": 174
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.166666666666667,
|
| 1406 |
+
"grad_norm": 1.0393498678201005,
|
| 1407 |
+
"learning_rate": 5.041520411528727e-06,
|
| 1408 |
+
"loss": 0.55,
|
| 1409 |
+
"num_tokens": 52262499.0,
|
| 1410 |
+
"step": 175
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 4.190476190476191,
|
| 1414 |
+
"grad_norm": 0.8250332666446762,
|
| 1415 |
+
"learning_rate": 4.932428121737547e-06,
|
| 1416 |
+
"loss": 0.5226,
|
| 1417 |
+
"num_tokens": 52568631.0,
|
| 1418 |
+
"step": 176
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.214285714285714,
|
| 1422 |
+
"grad_norm": 0.7655426183040523,
|
| 1423 |
+
"learning_rate": 4.826106223844648e-06,
|
| 1424 |
+
"loss": 0.5127,
|
| 1425 |
+
"num_tokens": 52834140.0,
|
| 1426 |
+
"step": 177
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 4.238095238095238,
|
| 1430 |
+
"grad_norm": 0.6995684804290214,
|
| 1431 |
+
"learning_rate": 4.722580181562527e-06,
|
| 1432 |
+
"loss": 0.494,
|
| 1433 |
+
"num_tokens": 53156720.0,
|
| 1434 |
+
"step": 178
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.261904761904762,
|
| 1438 |
+
"grad_norm": 0.7748083731595724,
|
| 1439 |
+
"learning_rate": 4.621874789006295e-06,
|
| 1440 |
+
"loss": 0.5381,
|
| 1441 |
+
"num_tokens": 53491051.0,
|
| 1442 |
+
"step": 179
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 4.285714285714286,
|
| 1446 |
+
"grad_norm": 0.8131952113654631,
|
| 1447 |
+
"learning_rate": 4.524014164755603e-06,
|
| 1448 |
+
"loss": 0.4968,
|
| 1449 |
+
"num_tokens": 53787155.0,
|
| 1450 |
+
"step": 180
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 4.309523809523809,
|
| 1454 |
+
"grad_norm": 0.7367042370774411,
|
| 1455 |
+
"learning_rate": 4.429021746078311e-06,
|
| 1456 |
+
"loss": 0.4861,
|
| 1457 |
+
"num_tokens": 54049978.0,
|
| 1458 |
+
"step": 181
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.333333333333333,
|
| 1462 |
+
"grad_norm": 0.7194704571250619,
|
| 1463 |
+
"learning_rate": 4.336920283317344e-06,
|
| 1464 |
+
"loss": 0.5212,
|
| 1465 |
+
"num_tokens": 54305304.0,
|
| 1466 |
+
"step": 182
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 4.357142857142857,
|
| 1470 |
+
"grad_norm": 0.6527660461115374,
|
| 1471 |
+
"learning_rate": 4.247731834442083e-06,
|
| 1472 |
+
"loss": 0.5263,
|
| 1473 |
+
"num_tokens": 54632438.0,
|
| 1474 |
+
"step": 183
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 4.380952380952381,
|
| 1478 |
+
"grad_norm": 0.7266514800309486,
|
| 1479 |
+
"learning_rate": 4.161477759765542e-06,
|
| 1480 |
+
"loss": 0.5202,
|
| 1481 |
+
"num_tokens": 54954887.0,
|
| 1482 |
+
"step": 184
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 4.404761904761905,
|
| 1486 |
+
"grad_norm": 0.761296256236184,
|
| 1487 |
+
"learning_rate": 4.078178716828666e-06,
|
| 1488 |
+
"loss": 0.5379,
|
| 1489 |
+
"num_tokens": 55245795.0,
|
| 1490 |
+
"step": 185
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 4.428571428571429,
|
| 1494 |
+
"grad_norm": 0.7945856951237223,
|
| 1495 |
+
"learning_rate": 3.9978546554529185e-06,
|
| 1496 |
+
"loss": 0.5176,
|
| 1497 |
+
"num_tokens": 55546573.0,
|
| 1498 |
+
"step": 186
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 4.4523809523809526,
|
| 1502 |
+
"grad_norm": 0.7468660256983087,
|
| 1503 |
+
"learning_rate": 3.920524812962359e-06,
|
| 1504 |
+
"loss": 0.5096,
|
| 1505 |
+
"num_tokens": 55843166.0,
|
| 1506 |
+
"step": 187
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 4.476190476190476,
|
| 1510 |
+
"grad_norm": 0.7193745095120948,
|
| 1511 |
+
"learning_rate": 3.846207709576389e-06,
|
| 1512 |
+
"loss": 0.5205,
|
| 1513 |
+
"num_tokens": 56138218.0,
|
| 1514 |
+
"step": 188
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 4.5,
|
| 1518 |
+
"grad_norm": 0.6655820277052442,
|
| 1519 |
+
"learning_rate": 3.7749211439742257e-06,
|
| 1520 |
+
"loss": 0.5041,
|
| 1521 |
+
"num_tokens": 56417291.0,
|
| 1522 |
+
"step": 189
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 4.523809523809524,
|
| 1526 |
+
"grad_norm": 0.7239518179183401,
|
| 1527 |
+
"learning_rate": 3.7066821890321687e-06,
|
| 1528 |
+
"loss": 0.4846,
|
| 1529 |
+
"num_tokens": 56692919.0,
|
| 1530 |
+
"step": 190
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.5476190476190474,
|
| 1534 |
+
"grad_norm": 0.6477616515263318,
|
| 1535 |
+
"learning_rate": 3.6415071877347165e-06,
|
| 1536 |
+
"loss": 0.539,
|
| 1537 |
+
"num_tokens": 57031682.0,
|
| 1538 |
+
"step": 191
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 4.571428571428571,
|
| 1542 |
+
"grad_norm": 0.6640615854897481,
|
| 1543 |
+
"learning_rate": 3.579411749260486e-06,
|
| 1544 |
+
"loss": 0.4944,
|
| 1545 |
+
"num_tokens": 57344445.0,
|
| 1546 |
+
"step": 192
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.595238095238095,
|
| 1550 |
+
"grad_norm": 0.6848846128939778,
|
| 1551 |
+
"learning_rate": 3.520410745243858e-06,
|
| 1552 |
+
"loss": 0.5121,
|
| 1553 |
+
"num_tokens": 57613210.0,
|
| 1554 |
+
"step": 193
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 4.619047619047619,
|
| 1558 |
+
"grad_norm": 0.6422019750084208,
|
| 1559 |
+
"learning_rate": 3.4645183062132826e-06,
|
| 1560 |
+
"loss": 0.5193,
|
| 1561 |
+
"num_tokens": 57942367.0,
|
| 1562 |
+
"step": 194
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 4.642857142857143,
|
| 1566 |
+
"grad_norm": 0.7657789249156284,
|
| 1567 |
+
"learning_rate": 3.411747818207066e-06,
|
| 1568 |
+
"loss": 0.4979,
|
| 1569 |
+
"num_tokens": 58201641.0,
|
| 1570 |
+
"step": 195
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 4.666666666666667,
|
| 1574 |
+
"grad_norm": 0.6739307543671282,
|
| 1575 |
+
"learning_rate": 3.3621119195674597e-06,
|
| 1576 |
+
"loss": 0.4888,
|
| 1577 |
+
"num_tokens": 58517521.0,
|
| 1578 |
+
"step": 196
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 4.690476190476191,
|
| 1582 |
+
"grad_norm": 0.6865319310088059,
|
| 1583 |
+
"learning_rate": 3.3156224979138306e-06,
|
| 1584 |
+
"loss": 0.494,
|
| 1585 |
+
"num_tokens": 58816395.0,
|
| 1586 |
+
"step": 197
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 4.714285714285714,
|
| 1590 |
+
"grad_norm": 0.6584126661804732,
|
| 1591 |
+
"learning_rate": 3.2722906872956088e-06,
|
| 1592 |
+
"loss": 0.5181,
|
| 1593 |
+
"num_tokens": 59120541.0,
|
| 1594 |
+
"step": 198
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 4.738095238095238,
|
| 1598 |
+
"grad_norm": 0.6099916205741043,
|
| 1599 |
+
"learning_rate": 3.232126865525731e-06,
|
| 1600 |
+
"loss": 0.5293,
|
| 1601 |
+
"num_tokens": 59461204.0,
|
| 1602 |
+
"step": 199
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 4.761904761904762,
|
| 1606 |
+
"grad_norm": 0.667910578763116,
|
| 1607 |
+
"learning_rate": 3.1951406516951874e-06,
|
| 1608 |
+
"loss": 0.5116,
|
| 1609 |
+
"num_tokens": 59751334.0,
|
| 1610 |
+
"step": 200
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 4.785714285714286,
|
| 1614 |
+
"grad_norm": 0.6141509992681458,
|
| 1615 |
+
"learning_rate": 3.1613409038692853e-06,
|
| 1616 |
+
"loss": 0.5124,
|
| 1617 |
+
"num_tokens": 60077027.0,
|
| 1618 |
+
"step": 201
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 4.809523809523809,
|
| 1622 |
+
"grad_norm": 0.6302007739092258,
|
| 1623 |
+
"learning_rate": 3.130735716966174e-06,
|
| 1624 |
+
"loss": 0.5405,
|
| 1625 |
+
"num_tokens": 60408543.0,
|
| 1626 |
+
"step": 202
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 4.833333333333333,
|
| 1630 |
+
"grad_norm": 0.6664208365053094,
|
| 1631 |
+
"learning_rate": 3.1033324208181422e-06,
|
| 1632 |
+
"loss": 0.5142,
|
| 1633 |
+
"num_tokens": 60702718.0,
|
| 1634 |
+
"step": 203
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 4.857142857142857,
|
| 1638 |
+
"grad_norm": 0.6536331401194854,
|
| 1639 |
+
"learning_rate": 3.0791375784161456e-06,
|
| 1640 |
+
"loss": 0.5193,
|
| 1641 |
+
"num_tokens": 61018938.0,
|
| 1642 |
+
"step": 204
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 4.880952380952381,
|
| 1646 |
+
"grad_norm": 0.6969216972121804,
|
| 1647 |
+
"learning_rate": 3.058156984337999e-06,
|
| 1648 |
+
"loss": 0.5061,
|
| 1649 |
+
"num_tokens": 61279305.0,
|
| 1650 |
+
"step": 205
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 4.904761904761905,
|
| 1654 |
+
"grad_norm": 0.6535453587519624,
|
| 1655 |
+
"learning_rate": 3.0403956633605944e-06,
|
| 1656 |
+
"loss": 0.4729,
|
| 1657 |
+
"num_tokens": 61565633.0,
|
| 1658 |
+
"step": 206
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 4.928571428571429,
|
| 1662 |
+
"grad_norm": 0.6753649990944919,
|
| 1663 |
+
"learning_rate": 3.0258578692564804e-06,
|
| 1664 |
+
"loss": 0.4772,
|
| 1665 |
+
"num_tokens": 61841335.0,
|
| 1666 |
+
"step": 207
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 4.9523809523809526,
|
| 1670 |
+
"grad_norm": 0.6358980505171887,
|
| 1671 |
+
"learning_rate": 3.014547083775106e-06,
|
| 1672 |
+
"loss": 0.5398,
|
| 1673 |
+
"num_tokens": 62169402.0,
|
| 1674 |
+
"step": 208
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 4.976190476190476,
|
| 1678 |
+
"grad_norm": 0.5805504932681311,
|
| 1679 |
+
"learning_rate": 3.0064660158089516e-06,
|
| 1680 |
+
"loss": 0.524,
|
| 1681 |
+
"num_tokens": 62538856.0,
|
| 1682 |
+
"step": 209
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 5.0,
|
| 1686 |
+
"grad_norm": 0.6817532772499482,
|
| 1687 |
+
"learning_rate": 3.001616600744755e-06,
|
| 1688 |
+
"loss": 0.5121,
|
| 1689 |
+
"num_tokens": 62797894.0,
|
| 1690 |
+
"step": 210
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 5.0,
|
| 1694 |
+
"step": 210,
|
| 1695 |
+
"total_flos": 2.7972111648056934e+17,
|
| 1696 |
+
"train_loss": 1.0216455256655104,
|
| 1697 |
+
"train_runtime": 2780.2712,
|
| 1698 |
+
"train_samples_per_second": 9.666,
|
| 1699 |
+
"train_steps_per_second": 0.076
|
| 1700 |
+
}
|
| 1701 |
+
],
|
| 1702 |
+
"logging_steps": 1,
|
| 1703 |
+
"max_steps": 210,
|
| 1704 |
+
"num_input_tokens_seen": 0,
|
| 1705 |
+
"num_train_epochs": 5,
|
| 1706 |
+
"save_steps": 500,
|
| 1707 |
+
"stateful_callbacks": {
|
| 1708 |
+
"TrainerControl": {
|
| 1709 |
+
"args": {
|
| 1710 |
+
"should_epoch_stop": false,
|
| 1711 |
+
"should_evaluate": false,
|
| 1712 |
+
"should_log": false,
|
| 1713 |
+
"should_save": true,
|
| 1714 |
+
"should_training_stop": true
|
| 1715 |
+
},
|
| 1716 |
+
"attributes": {}
|
| 1717 |
+
}
|
| 1718 |
+
},
|
| 1719 |
+
"total_flos": 2.7972111648056934e+17,
|
| 1720 |
+
"train_batch_size": 2,
|
| 1721 |
+
"trial_name": null,
|
| 1722 |
+
"trial_params": null
|
| 1723 |
+
}
|