Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +6 -0
- train_results.json +8 -0
- trainer_state.json +1275 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: allenai/OLMo-2-1124-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: OLMo-2-1124-7B-Instruct_SFTv02.09
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for OLMo-2-1124-7B-Instruct_SFTv02.09
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-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="Neelectric/OLMo-2-1124-7B-Instruct_SFTv02.09", 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/neelectric/open-r1_SFT/runs/69k5ooy4)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.17.0
|
| 38 |
+
- Transformers: 4.51.3
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 3.6.0
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6.182777521931551e+18,
|
| 3 |
+
"train_loss": 0.45148222612870204,
|
| 4 |
+
"train_runtime": 6331.7497,
|
| 5 |
+
"train_samples": 69132,
|
| 6 |
+
"train_samples_per_second": 10.918,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 100257,
|
| 4 |
+
"pad_token_id": 100277,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6.182777521931551e+18,
|
| 3 |
+
"train_loss": 0.45148222612870204,
|
| 4 |
+
"train_runtime": 6331.7497,
|
| 5 |
+
"train_samples": 69132,
|
| 6 |
+
"train_samples_per_second": 10.918,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1275 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9967637540453075,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 154,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006472491909385114,
|
| 14 |
+
"grad_norm": 5.306152820587158,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.1501,
|
| 17 |
+
"num_tokens": 963559.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.012944983818770227,
|
| 22 |
+
"grad_norm": 5.30831241607666,
|
| 23 |
+
"learning_rate": 3.125e-06,
|
| 24 |
+
"loss": 1.1455,
|
| 25 |
+
"num_tokens": 1927760.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.019417475728155338,
|
| 30 |
+
"grad_norm": 4.913212776184082,
|
| 31 |
+
"learning_rate": 6.25e-06,
|
| 32 |
+
"loss": 1.1166,
|
| 33 |
+
"num_tokens": 2896369.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.025889967637540454,
|
| 38 |
+
"grad_norm": 3.081620693206787,
|
| 39 |
+
"learning_rate": 9.375000000000001e-06,
|
| 40 |
+
"loss": 0.9608,
|
| 41 |
+
"num_tokens": 3886583.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.032362459546925564,
|
| 46 |
+
"grad_norm": 1.7735857963562012,
|
| 47 |
+
"learning_rate": 1.25e-05,
|
| 48 |
+
"loss": 0.8154,
|
| 49 |
+
"num_tokens": 4864476.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.038834951456310676,
|
| 54 |
+
"grad_norm": 1.088880181312561,
|
| 55 |
+
"learning_rate": 1.5625e-05,
|
| 56 |
+
"loss": 0.7392,
|
| 57 |
+
"num_tokens": 5873295.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.045307443365695796,
|
| 62 |
+
"grad_norm": 1.3550297021865845,
|
| 63 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 64 |
+
"loss": 0.7001,
|
| 65 |
+
"num_tokens": 6876484.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05177993527508091,
|
| 70 |
+
"grad_norm": 0.829587459564209,
|
| 71 |
+
"learning_rate": 2.1875e-05,
|
| 72 |
+
"loss": 0.6502,
|
| 73 |
+
"num_tokens": 7871664.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.05825242718446602,
|
| 78 |
+
"grad_norm": 0.7649633884429932,
|
| 79 |
+
"learning_rate": 2.5e-05,
|
| 80 |
+
"loss": 0.6416,
|
| 81 |
+
"num_tokens": 8869931.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.06472491909385113,
|
| 86 |
+
"grad_norm": 0.45778265595436096,
|
| 87 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 88 |
+
"loss": 0.6089,
|
| 89 |
+
"num_tokens": 9874687.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.07119741100323625,
|
| 94 |
+
"grad_norm": 0.4382297396659851,
|
| 95 |
+
"learning_rate": 3.125e-05,
|
| 96 |
+
"loss": 0.5773,
|
| 97 |
+
"num_tokens": 10842628.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.07766990291262135,
|
| 102 |
+
"grad_norm": 0.3832113742828369,
|
| 103 |
+
"learning_rate": 3.4375e-05,
|
| 104 |
+
"loss": 0.5753,
|
| 105 |
+
"num_tokens": 11815438.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.08414239482200647,
|
| 110 |
+
"grad_norm": 0.3748774826526642,
|
| 111 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 112 |
+
"loss": 0.5573,
|
| 113 |
+
"num_tokens": 12788222.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09061488673139159,
|
| 118 |
+
"grad_norm": 0.30577632784843445,
|
| 119 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 120 |
+
"loss": 0.5465,
|
| 121 |
+
"num_tokens": 13756270.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0970873786407767,
|
| 126 |
+
"grad_norm": 0.41811254620552063,
|
| 127 |
+
"learning_rate": 4.375e-05,
|
| 128 |
+
"loss": 0.5319,
|
| 129 |
+
"num_tokens": 14689813.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.10355987055016182,
|
| 134 |
+
"grad_norm": 0.4227692782878876,
|
| 135 |
+
"learning_rate": 4.6875e-05,
|
| 136 |
+
"loss": 0.5342,
|
| 137 |
+
"num_tokens": 15670657.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.11003236245954692,
|
| 142 |
+
"grad_norm": 0.435629278421402,
|
| 143 |
+
"learning_rate": 5e-05,
|
| 144 |
+
"loss": 0.525,
|
| 145 |
+
"num_tokens": 16640491.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.11650485436893204,
|
| 150 |
+
"grad_norm": 0.4427894055843353,
|
| 151 |
+
"learning_rate": 5e-05,
|
| 152 |
+
"loss": 0.5201,
|
| 153 |
+
"num_tokens": 17611388.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.12297734627831715,
|
| 158 |
+
"grad_norm": 0.31779494881629944,
|
| 159 |
+
"learning_rate": 5e-05,
|
| 160 |
+
"loss": 0.5159,
|
| 161 |
+
"num_tokens": 18582653.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.12944983818770225,
|
| 166 |
+
"grad_norm": 0.3481353223323822,
|
| 167 |
+
"learning_rate": 5e-05,
|
| 168 |
+
"loss": 0.5073,
|
| 169 |
+
"num_tokens": 19557459.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13592233009708737,
|
| 174 |
+
"grad_norm": 0.33009734749794006,
|
| 175 |
+
"learning_rate": 5e-05,
|
| 176 |
+
"loss": 0.5093,
|
| 177 |
+
"num_tokens": 20524158.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1423948220064725,
|
| 182 |
+
"grad_norm": 0.28723859786987305,
|
| 183 |
+
"learning_rate": 5e-05,
|
| 184 |
+
"loss": 0.492,
|
| 185 |
+
"num_tokens": 21502674.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.1488673139158576,
|
| 190 |
+
"grad_norm": 0.4183823764324188,
|
| 191 |
+
"learning_rate": 5e-05,
|
| 192 |
+
"loss": 0.4929,
|
| 193 |
+
"num_tokens": 22446294.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1553398058252427,
|
| 198 |
+
"grad_norm": 0.2560422718524933,
|
| 199 |
+
"learning_rate": 5e-05,
|
| 200 |
+
"loss": 0.4857,
|
| 201 |
+
"num_tokens": 23430225.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.16181229773462782,
|
| 206 |
+
"grad_norm": 0.33394595980644226,
|
| 207 |
+
"learning_rate": 5e-05,
|
| 208 |
+
"loss": 0.4821,
|
| 209 |
+
"num_tokens": 24380419.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.16828478964401294,
|
| 214 |
+
"grad_norm": 0.2930145561695099,
|
| 215 |
+
"learning_rate": 5e-05,
|
| 216 |
+
"loss": 0.4761,
|
| 217 |
+
"num_tokens": 25343499.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.17475728155339806,
|
| 222 |
+
"grad_norm": 0.3544153869152069,
|
| 223 |
+
"learning_rate": 5e-05,
|
| 224 |
+
"loss": 0.474,
|
| 225 |
+
"num_tokens": 26315921.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.18122977346278318,
|
| 230 |
+
"grad_norm": 0.252056747674942,
|
| 231 |
+
"learning_rate": 5e-05,
|
| 232 |
+
"loss": 0.4789,
|
| 233 |
+
"num_tokens": 27255686.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.18770226537216828,
|
| 238 |
+
"grad_norm": 0.32653287053108215,
|
| 239 |
+
"learning_rate": 5e-05,
|
| 240 |
+
"loss": 0.4702,
|
| 241 |
+
"num_tokens": 28232449.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.1941747572815534,
|
| 246 |
+
"grad_norm": 0.22704653441905975,
|
| 247 |
+
"learning_rate": 5e-05,
|
| 248 |
+
"loss": 0.4684,
|
| 249 |
+
"num_tokens": 29213099.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.20064724919093851,
|
| 254 |
+
"grad_norm": 0.26220372319221497,
|
| 255 |
+
"learning_rate": 5e-05,
|
| 256 |
+
"loss": 0.4674,
|
| 257 |
+
"num_tokens": 30210546.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.20711974110032363,
|
| 262 |
+
"grad_norm": 0.2697650194168091,
|
| 263 |
+
"learning_rate": 5e-05,
|
| 264 |
+
"loss": 0.4567,
|
| 265 |
+
"num_tokens": 31190215.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.21359223300970873,
|
| 270 |
+
"grad_norm": 0.32852447032928467,
|
| 271 |
+
"learning_rate": 5e-05,
|
| 272 |
+
"loss": 0.4553,
|
| 273 |
+
"num_tokens": 32152368.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.22006472491909385,
|
| 278 |
+
"grad_norm": 0.28994324803352356,
|
| 279 |
+
"learning_rate": 5e-05,
|
| 280 |
+
"loss": 0.4629,
|
| 281 |
+
"num_tokens": 33138410.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.22653721682847897,
|
| 286 |
+
"grad_norm": 0.2590140998363495,
|
| 287 |
+
"learning_rate": 5e-05,
|
| 288 |
+
"loss": 0.4555,
|
| 289 |
+
"num_tokens": 34103559.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.23300970873786409,
|
| 294 |
+
"grad_norm": 0.262189120054245,
|
| 295 |
+
"learning_rate": 5e-05,
|
| 296 |
+
"loss": 0.4572,
|
| 297 |
+
"num_tokens": 35099702.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.23948220064724918,
|
| 302 |
+
"grad_norm": 0.2498801201581955,
|
| 303 |
+
"learning_rate": 5e-05,
|
| 304 |
+
"loss": 0.4578,
|
| 305 |
+
"num_tokens": 36067246.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.2459546925566343,
|
| 310 |
+
"grad_norm": 0.2775033414363861,
|
| 311 |
+
"learning_rate": 5e-05,
|
| 312 |
+
"loss": 0.4476,
|
| 313 |
+
"num_tokens": 37074157.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.2524271844660194,
|
| 318 |
+
"grad_norm": 0.2648180425167084,
|
| 319 |
+
"learning_rate": 5e-05,
|
| 320 |
+
"loss": 0.4457,
|
| 321 |
+
"num_tokens": 38026864.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2588996763754045,
|
| 326 |
+
"grad_norm": 0.2547140419483185,
|
| 327 |
+
"learning_rate": 5e-05,
|
| 328 |
+
"loss": 0.4406,
|
| 329 |
+
"num_tokens": 39007950.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.26537216828478966,
|
| 334 |
+
"grad_norm": 0.21876376867294312,
|
| 335 |
+
"learning_rate": 5e-05,
|
| 336 |
+
"loss": 0.4487,
|
| 337 |
+
"num_tokens": 40004404.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.27184466019417475,
|
| 342 |
+
"grad_norm": 0.2548466920852661,
|
| 343 |
+
"learning_rate": 5e-05,
|
| 344 |
+
"loss": 0.4442,
|
| 345 |
+
"num_tokens": 40979367.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2783171521035599,
|
| 350 |
+
"grad_norm": 0.2996249496936798,
|
| 351 |
+
"learning_rate": 5e-05,
|
| 352 |
+
"loss": 0.4438,
|
| 353 |
+
"num_tokens": 41954716.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.284789644012945,
|
| 358 |
+
"grad_norm": 0.22016839683055878,
|
| 359 |
+
"learning_rate": 5e-05,
|
| 360 |
+
"loss": 0.4496,
|
| 361 |
+
"num_tokens": 42927994.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.2912621359223301,
|
| 366 |
+
"grad_norm": 0.24306082725524902,
|
| 367 |
+
"learning_rate": 5e-05,
|
| 368 |
+
"loss": 0.4384,
|
| 369 |
+
"num_tokens": 43870458.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.2977346278317152,
|
| 374 |
+
"grad_norm": 0.2156415581703186,
|
| 375 |
+
"learning_rate": 5e-05,
|
| 376 |
+
"loss": 0.4389,
|
| 377 |
+
"num_tokens": 44845205.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.3042071197411003,
|
| 382 |
+
"grad_norm": 0.2775454521179199,
|
| 383 |
+
"learning_rate": 5e-05,
|
| 384 |
+
"loss": 0.4376,
|
| 385 |
+
"num_tokens": 45817785.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.3106796116504854,
|
| 390 |
+
"grad_norm": 0.2171974927186966,
|
| 391 |
+
"learning_rate": 5e-05,
|
| 392 |
+
"loss": 0.441,
|
| 393 |
+
"num_tokens": 46768552.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.31715210355987056,
|
| 398 |
+
"grad_norm": 0.2566312253475189,
|
| 399 |
+
"learning_rate": 5e-05,
|
| 400 |
+
"loss": 0.4263,
|
| 401 |
+
"num_tokens": 47720390.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.32362459546925565,
|
| 406 |
+
"grad_norm": 0.27443766593933105,
|
| 407 |
+
"learning_rate": 5e-05,
|
| 408 |
+
"loss": 0.4372,
|
| 409 |
+
"num_tokens": 48659119.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.3300970873786408,
|
| 414 |
+
"grad_norm": 0.24743640422821045,
|
| 415 |
+
"learning_rate": 5e-05,
|
| 416 |
+
"loss": 0.4366,
|
| 417 |
+
"num_tokens": 49635896.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.3365695792880259,
|
| 422 |
+
"grad_norm": 0.2662995457649231,
|
| 423 |
+
"learning_rate": 5e-05,
|
| 424 |
+
"loss": 0.4365,
|
| 425 |
+
"num_tokens": 50617481.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.343042071197411,
|
| 430 |
+
"grad_norm": 0.21216490864753723,
|
| 431 |
+
"learning_rate": 5e-05,
|
| 432 |
+
"loss": 0.4314,
|
| 433 |
+
"num_tokens": 51580322.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.34951456310679613,
|
| 438 |
+
"grad_norm": 0.22929856181144714,
|
| 439 |
+
"learning_rate": 5e-05,
|
| 440 |
+
"loss": 0.4345,
|
| 441 |
+
"num_tokens": 52544983.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.3559870550161812,
|
| 446 |
+
"grad_norm": 0.29387667775154114,
|
| 447 |
+
"learning_rate": 5e-05,
|
| 448 |
+
"loss": 0.4276,
|
| 449 |
+
"num_tokens": 53538431.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.36245954692556637,
|
| 454 |
+
"grad_norm": 0.2514965832233429,
|
| 455 |
+
"learning_rate": 5e-05,
|
| 456 |
+
"loss": 0.4288,
|
| 457 |
+
"num_tokens": 54497097.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.36893203883495146,
|
| 462 |
+
"grad_norm": 0.21859632432460785,
|
| 463 |
+
"learning_rate": 5e-05,
|
| 464 |
+
"loss": 0.4193,
|
| 465 |
+
"num_tokens": 55515695.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.37540453074433655,
|
| 470 |
+
"grad_norm": 0.2738589346408844,
|
| 471 |
+
"learning_rate": 5e-05,
|
| 472 |
+
"loss": 0.4218,
|
| 473 |
+
"num_tokens": 56471100.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3818770226537217,
|
| 478 |
+
"grad_norm": 0.2491186559200287,
|
| 479 |
+
"learning_rate": 5e-05,
|
| 480 |
+
"loss": 0.4275,
|
| 481 |
+
"num_tokens": 57460948.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.3883495145631068,
|
| 486 |
+
"grad_norm": 0.2803933620452881,
|
| 487 |
+
"learning_rate": 5e-05,
|
| 488 |
+
"loss": 0.4279,
|
| 489 |
+
"num_tokens": 58450663.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.3948220064724919,
|
| 494 |
+
"grad_norm": 0.25655433535575867,
|
| 495 |
+
"learning_rate": 5e-05,
|
| 496 |
+
"loss": 0.422,
|
| 497 |
+
"num_tokens": 59407638.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.40129449838187703,
|
| 502 |
+
"grad_norm": 0.20261798799037933,
|
| 503 |
+
"learning_rate": 5e-05,
|
| 504 |
+
"loss": 0.4171,
|
| 505 |
+
"num_tokens": 60358388.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4077669902912621,
|
| 510 |
+
"grad_norm": 0.22351031005382538,
|
| 511 |
+
"learning_rate": 5e-05,
|
| 512 |
+
"loss": 0.4138,
|
| 513 |
+
"num_tokens": 61306137.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.41423948220064727,
|
| 518 |
+
"grad_norm": 0.18309737741947174,
|
| 519 |
+
"learning_rate": 5e-05,
|
| 520 |
+
"loss": 0.4246,
|
| 521 |
+
"num_tokens": 62298616.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.42071197411003236,
|
| 526 |
+
"grad_norm": 0.23639380931854248,
|
| 527 |
+
"learning_rate": 5e-05,
|
| 528 |
+
"loss": 0.4155,
|
| 529 |
+
"num_tokens": 63242620.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.42718446601941745,
|
| 534 |
+
"grad_norm": 0.25539568066596985,
|
| 535 |
+
"learning_rate": 5e-05,
|
| 536 |
+
"loss": 0.4315,
|
| 537 |
+
"num_tokens": 64231555.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.4336569579288026,
|
| 542 |
+
"grad_norm": 0.24605165421962738,
|
| 543 |
+
"learning_rate": 5e-05,
|
| 544 |
+
"loss": 0.4206,
|
| 545 |
+
"num_tokens": 65190302.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.4401294498381877,
|
| 550 |
+
"grad_norm": 0.22667379677295685,
|
| 551 |
+
"learning_rate": 5e-05,
|
| 552 |
+
"loss": 0.4206,
|
| 553 |
+
"num_tokens": 66175194.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.44660194174757284,
|
| 558 |
+
"grad_norm": 0.21500389277935028,
|
| 559 |
+
"learning_rate": 5e-05,
|
| 560 |
+
"loss": 0.4162,
|
| 561 |
+
"num_tokens": 67146659.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.45307443365695793,
|
| 566 |
+
"grad_norm": 0.2856912612915039,
|
| 567 |
+
"learning_rate": 5e-05,
|
| 568 |
+
"loss": 0.4024,
|
| 569 |
+
"num_tokens": 68115421.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.459546925566343,
|
| 574 |
+
"grad_norm": 0.2476225644350052,
|
| 575 |
+
"learning_rate": 5e-05,
|
| 576 |
+
"loss": 0.4009,
|
| 577 |
+
"num_tokens": 69078962.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.46601941747572817,
|
| 582 |
+
"grad_norm": 0.25628218054771423,
|
| 583 |
+
"learning_rate": 5e-05,
|
| 584 |
+
"loss": 0.4251,
|
| 585 |
+
"num_tokens": 70056552.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.47249190938511326,
|
| 590 |
+
"grad_norm": 0.21366733312606812,
|
| 591 |
+
"learning_rate": 5e-05,
|
| 592 |
+
"loss": 0.4182,
|
| 593 |
+
"num_tokens": 71056405.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.47896440129449835,
|
| 598 |
+
"grad_norm": 0.2592005431652069,
|
| 599 |
+
"learning_rate": 5e-05,
|
| 600 |
+
"loss": 0.4288,
|
| 601 |
+
"num_tokens": 72011963.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.4854368932038835,
|
| 606 |
+
"grad_norm": 0.20503440499305725,
|
| 607 |
+
"learning_rate": 5e-05,
|
| 608 |
+
"loss": 0.4154,
|
| 609 |
+
"num_tokens": 72974088.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.4919093851132686,
|
| 614 |
+
"grad_norm": 0.2591334581375122,
|
| 615 |
+
"learning_rate": 5e-05,
|
| 616 |
+
"loss": 0.4117,
|
| 617 |
+
"num_tokens": 73963066.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.49838187702265374,
|
| 622 |
+
"grad_norm": 0.2317359298467636,
|
| 623 |
+
"learning_rate": 5e-05,
|
| 624 |
+
"loss": 0.4047,
|
| 625 |
+
"num_tokens": 74927507.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5048543689320388,
|
| 630 |
+
"grad_norm": 0.22618205845355988,
|
| 631 |
+
"learning_rate": 5e-05,
|
| 632 |
+
"loss": 0.4095,
|
| 633 |
+
"num_tokens": 75913302.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.511326860841424,
|
| 638 |
+
"grad_norm": 0.2665836215019226,
|
| 639 |
+
"learning_rate": 5e-05,
|
| 640 |
+
"loss": 0.4189,
|
| 641 |
+
"num_tokens": 76871637.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.517799352750809,
|
| 646 |
+
"grad_norm": 0.2659549117088318,
|
| 647 |
+
"learning_rate": 5e-05,
|
| 648 |
+
"loss": 0.4131,
|
| 649 |
+
"num_tokens": 77844738.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.5242718446601942,
|
| 654 |
+
"grad_norm": 0.19478461146354675,
|
| 655 |
+
"learning_rate": 5e-05,
|
| 656 |
+
"loss": 0.4062,
|
| 657 |
+
"num_tokens": 78789735.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.5307443365695793,
|
| 662 |
+
"grad_norm": 0.23357832431793213,
|
| 663 |
+
"learning_rate": 5e-05,
|
| 664 |
+
"loss": 0.4036,
|
| 665 |
+
"num_tokens": 79740057.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.5372168284789643,
|
| 670 |
+
"grad_norm": 0.26218855381011963,
|
| 671 |
+
"learning_rate": 5e-05,
|
| 672 |
+
"loss": 0.4104,
|
| 673 |
+
"num_tokens": 80691344.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5436893203883495,
|
| 678 |
+
"grad_norm": 0.22175249457359314,
|
| 679 |
+
"learning_rate": 5e-05,
|
| 680 |
+
"loss": 0.411,
|
| 681 |
+
"num_tokens": 81695065.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5501618122977346,
|
| 686 |
+
"grad_norm": 0.21215109527111053,
|
| 687 |
+
"learning_rate": 5e-05,
|
| 688 |
+
"loss": 0.4074,
|
| 689 |
+
"num_tokens": 82670591.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.5566343042071198,
|
| 694 |
+
"grad_norm": 0.2303503453731537,
|
| 695 |
+
"learning_rate": 5e-05,
|
| 696 |
+
"loss": 0.4074,
|
| 697 |
+
"num_tokens": 83619525.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.5631067961165048,
|
| 702 |
+
"grad_norm": 0.23206549882888794,
|
| 703 |
+
"learning_rate": 5e-05,
|
| 704 |
+
"loss": 0.4074,
|
| 705 |
+
"num_tokens": 84583829.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.56957928802589,
|
| 710 |
+
"grad_norm": 0.25276947021484375,
|
| 711 |
+
"learning_rate": 5e-05,
|
| 712 |
+
"loss": 0.4079,
|
| 713 |
+
"num_tokens": 85554557.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5760517799352751,
|
| 718 |
+
"grad_norm": 0.2507737874984741,
|
| 719 |
+
"learning_rate": 5e-05,
|
| 720 |
+
"loss": 0.4098,
|
| 721 |
+
"num_tokens": 86534800.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.5825242718446602,
|
| 726 |
+
"grad_norm": 0.31349480152130127,
|
| 727 |
+
"learning_rate": 5e-05,
|
| 728 |
+
"loss": 0.4133,
|
| 729 |
+
"num_tokens": 87479322.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5889967637540453,
|
| 734 |
+
"grad_norm": 0.19707591831684113,
|
| 735 |
+
"learning_rate": 5e-05,
|
| 736 |
+
"loss": 0.4102,
|
| 737 |
+
"num_tokens": 88440604.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5954692556634305,
|
| 742 |
+
"grad_norm": 0.2872115671634674,
|
| 743 |
+
"learning_rate": 5e-05,
|
| 744 |
+
"loss": 0.4084,
|
| 745 |
+
"num_tokens": 89440902.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.6019417475728155,
|
| 750 |
+
"grad_norm": 0.24344055354595184,
|
| 751 |
+
"learning_rate": 5e-05,
|
| 752 |
+
"loss": 0.4012,
|
| 753 |
+
"num_tokens": 90420292.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.6084142394822006,
|
| 758 |
+
"grad_norm": 0.2181190550327301,
|
| 759 |
+
"learning_rate": 5e-05,
|
| 760 |
+
"loss": 0.4081,
|
| 761 |
+
"num_tokens": 91365927.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.6148867313915858,
|
| 766 |
+
"grad_norm": 0.27730515599250793,
|
| 767 |
+
"learning_rate": 5e-05,
|
| 768 |
+
"loss": 0.4047,
|
| 769 |
+
"num_tokens": 92339481.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.6213592233009708,
|
| 774 |
+
"grad_norm": 0.19435158371925354,
|
| 775 |
+
"learning_rate": 5e-05,
|
| 776 |
+
"loss": 0.3992,
|
| 777 |
+
"num_tokens": 93277920.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.627831715210356,
|
| 782 |
+
"grad_norm": 0.2744201719760895,
|
| 783 |
+
"learning_rate": 5e-05,
|
| 784 |
+
"loss": 0.399,
|
| 785 |
+
"num_tokens": 94233058.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6343042071197411,
|
| 790 |
+
"grad_norm": 0.21480068564414978,
|
| 791 |
+
"learning_rate": 5e-05,
|
| 792 |
+
"loss": 0.4118,
|
| 793 |
+
"num_tokens": 95195865.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6407766990291263,
|
| 798 |
+
"grad_norm": 0.2238287776708603,
|
| 799 |
+
"learning_rate": 5e-05,
|
| 800 |
+
"loss": 0.3948,
|
| 801 |
+
"num_tokens": 96165533.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.6472491909385113,
|
| 806 |
+
"grad_norm": 0.21964621543884277,
|
| 807 |
+
"learning_rate": 5e-05,
|
| 808 |
+
"loss": 0.3969,
|
| 809 |
+
"num_tokens": 97128908.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.6537216828478964,
|
| 814 |
+
"grad_norm": 0.25009796023368835,
|
| 815 |
+
"learning_rate": 5e-05,
|
| 816 |
+
"loss": 0.3982,
|
| 817 |
+
"num_tokens": 98137812.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.6601941747572816,
|
| 822 |
+
"grad_norm": 0.20820799469947815,
|
| 823 |
+
"learning_rate": 5e-05,
|
| 824 |
+
"loss": 0.3949,
|
| 825 |
+
"num_tokens": 99133445.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.6666666666666666,
|
| 830 |
+
"grad_norm": 0.23642897605895996,
|
| 831 |
+
"learning_rate": 5e-05,
|
| 832 |
+
"loss": 0.3886,
|
| 833 |
+
"num_tokens": 100106034.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.6731391585760518,
|
| 838 |
+
"grad_norm": 0.2794768512248993,
|
| 839 |
+
"learning_rate": 5e-05,
|
| 840 |
+
"loss": 0.416,
|
| 841 |
+
"num_tokens": 101060830.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6796116504854369,
|
| 846 |
+
"grad_norm": 0.24419237673282623,
|
| 847 |
+
"learning_rate": 5e-05,
|
| 848 |
+
"loss": 0.4007,
|
| 849 |
+
"num_tokens": 102032708.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.686084142394822,
|
| 854 |
+
"grad_norm": 0.17757025361061096,
|
| 855 |
+
"learning_rate": 5e-05,
|
| 856 |
+
"loss": 0.3835,
|
| 857 |
+
"num_tokens": 103020888.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.6925566343042071,
|
| 862 |
+
"grad_norm": 0.18630194664001465,
|
| 863 |
+
"learning_rate": 5e-05,
|
| 864 |
+
"loss": 0.4049,
|
| 865 |
+
"num_tokens": 103986883.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.6990291262135923,
|
| 870 |
+
"grad_norm": 0.2557118535041809,
|
| 871 |
+
"learning_rate": 5e-05,
|
| 872 |
+
"loss": 0.403,
|
| 873 |
+
"num_tokens": 104978514.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.7055016181229773,
|
| 878 |
+
"grad_norm": 0.2527202069759369,
|
| 879 |
+
"learning_rate": 5e-05,
|
| 880 |
+
"loss": 0.3917,
|
| 881 |
+
"num_tokens": 105938542.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.7119741100323624,
|
| 886 |
+
"grad_norm": 0.22235515713691711,
|
| 887 |
+
"learning_rate": 5e-05,
|
| 888 |
+
"loss": 0.394,
|
| 889 |
+
"num_tokens": 106909993.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.7184466019417476,
|
| 894 |
+
"grad_norm": 0.20143969357013702,
|
| 895 |
+
"learning_rate": 5e-05,
|
| 896 |
+
"loss": 0.3972,
|
| 897 |
+
"num_tokens": 107872313.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7249190938511327,
|
| 902 |
+
"grad_norm": 0.23038484156131744,
|
| 903 |
+
"learning_rate": 5e-05,
|
| 904 |
+
"loss": 0.3914,
|
| 905 |
+
"num_tokens": 108876000.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7313915857605178,
|
| 910 |
+
"grad_norm": 0.2074708789587021,
|
| 911 |
+
"learning_rate": 5e-05,
|
| 912 |
+
"loss": 0.3919,
|
| 913 |
+
"num_tokens": 109857790.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.7378640776699029,
|
| 918 |
+
"grad_norm": 0.2153213620185852,
|
| 919 |
+
"learning_rate": 5e-05,
|
| 920 |
+
"loss": 0.3928,
|
| 921 |
+
"num_tokens": 110826497.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.7443365695792881,
|
| 926 |
+
"grad_norm": 0.19306710362434387,
|
| 927 |
+
"learning_rate": 5e-05,
|
| 928 |
+
"loss": 0.3911,
|
| 929 |
+
"num_tokens": 111775780.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.7508090614886731,
|
| 934 |
+
"grad_norm": 0.24334612488746643,
|
| 935 |
+
"learning_rate": 5e-05,
|
| 936 |
+
"loss": 0.394,
|
| 937 |
+
"num_tokens": 112755203.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.7572815533980582,
|
| 942 |
+
"grad_norm": 0.20348411798477173,
|
| 943 |
+
"learning_rate": 5e-05,
|
| 944 |
+
"loss": 0.394,
|
| 945 |
+
"num_tokens": 113720983.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.7637540453074434,
|
| 950 |
+
"grad_norm": 0.21235860884189606,
|
| 951 |
+
"learning_rate": 5e-05,
|
| 952 |
+
"loss": 0.3853,
|
| 953 |
+
"num_tokens": 114690500.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7702265372168284,
|
| 958 |
+
"grad_norm": 0.23257102072238922,
|
| 959 |
+
"learning_rate": 5e-05,
|
| 960 |
+
"loss": 0.3859,
|
| 961 |
+
"num_tokens": 115663752.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7766990291262136,
|
| 966 |
+
"grad_norm": 0.27572208642959595,
|
| 967 |
+
"learning_rate": 5e-05,
|
| 968 |
+
"loss": 0.3848,
|
| 969 |
+
"num_tokens": 116656118.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.7831715210355987,
|
| 974 |
+
"grad_norm": 0.19343547523021698,
|
| 975 |
+
"learning_rate": 5e-05,
|
| 976 |
+
"loss": 0.3928,
|
| 977 |
+
"num_tokens": 117647006.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.7896440129449838,
|
| 982 |
+
"grad_norm": 0.1798018366098404,
|
| 983 |
+
"learning_rate": 5e-05,
|
| 984 |
+
"loss": 0.3837,
|
| 985 |
+
"num_tokens": 118637898.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.7961165048543689,
|
| 990 |
+
"grad_norm": 0.19484922289848328,
|
| 991 |
+
"learning_rate": 5e-05,
|
| 992 |
+
"loss": 0.3922,
|
| 993 |
+
"num_tokens": 119611539.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.8025889967637541,
|
| 998 |
+
"grad_norm": 0.2517184615135193,
|
| 999 |
+
"learning_rate": 5e-05,
|
| 1000 |
+
"loss": 0.3946,
|
| 1001 |
+
"num_tokens": 120576485.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.8090614886731392,
|
| 1006 |
+
"grad_norm": 0.24293893575668335,
|
| 1007 |
+
"learning_rate": 5e-05,
|
| 1008 |
+
"loss": 0.395,
|
| 1009 |
+
"num_tokens": 121567862.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.8155339805825242,
|
| 1014 |
+
"grad_norm": 0.18879574537277222,
|
| 1015 |
+
"learning_rate": 5e-05,
|
| 1016 |
+
"loss": 0.3865,
|
| 1017 |
+
"num_tokens": 122530893.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.8220064724919094,
|
| 1022 |
+
"grad_norm": 0.2343464493751526,
|
| 1023 |
+
"learning_rate": 5e-05,
|
| 1024 |
+
"loss": 0.3874,
|
| 1025 |
+
"num_tokens": 123480227.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.8284789644012945,
|
| 1030 |
+
"grad_norm": 0.2789117395877838,
|
| 1031 |
+
"learning_rate": 5e-05,
|
| 1032 |
+
"loss": 0.4024,
|
| 1033 |
+
"num_tokens": 124462070.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.8349514563106796,
|
| 1038 |
+
"grad_norm": 0.19395191967487335,
|
| 1039 |
+
"learning_rate": 5e-05,
|
| 1040 |
+
"loss": 0.3954,
|
| 1041 |
+
"num_tokens": 125440428.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.8414239482200647,
|
| 1046 |
+
"grad_norm": 0.2792704999446869,
|
| 1047 |
+
"learning_rate": 5e-05,
|
| 1048 |
+
"loss": 0.392,
|
| 1049 |
+
"num_tokens": 126416310.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.8478964401294499,
|
| 1054 |
+
"grad_norm": 0.1961115151643753,
|
| 1055 |
+
"learning_rate": 5e-05,
|
| 1056 |
+
"loss": 0.391,
|
| 1057 |
+
"num_tokens": 127406436.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.8543689320388349,
|
| 1062 |
+
"grad_norm": 0.2553383708000183,
|
| 1063 |
+
"learning_rate": 5e-05,
|
| 1064 |
+
"loss": 0.39,
|
| 1065 |
+
"num_tokens": 128372197.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.86084142394822,
|
| 1070 |
+
"grad_norm": 0.22742581367492676,
|
| 1071 |
+
"learning_rate": 5e-05,
|
| 1072 |
+
"loss": 0.3868,
|
| 1073 |
+
"num_tokens": 129371264.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.8673139158576052,
|
| 1078 |
+
"grad_norm": 0.1949053853750229,
|
| 1079 |
+
"learning_rate": 5e-05,
|
| 1080 |
+
"loss": 0.3739,
|
| 1081 |
+
"num_tokens": 130306080.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.8737864077669902,
|
| 1086 |
+
"grad_norm": 0.2624325156211853,
|
| 1087 |
+
"learning_rate": 5e-05,
|
| 1088 |
+
"loss": 0.3934,
|
| 1089 |
+
"num_tokens": 131261937.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.8802588996763754,
|
| 1094 |
+
"grad_norm": 0.20789428055286407,
|
| 1095 |
+
"learning_rate": 5e-05,
|
| 1096 |
+
"loss": 0.3863,
|
| 1097 |
+
"num_tokens": 132223182.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.8867313915857605,
|
| 1102 |
+
"grad_norm": 0.18370160460472107,
|
| 1103 |
+
"learning_rate": 5e-05,
|
| 1104 |
+
"loss": 0.3891,
|
| 1105 |
+
"num_tokens": 133211562.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.8932038834951457,
|
| 1110 |
+
"grad_norm": 0.21121914684772491,
|
| 1111 |
+
"learning_rate": 5e-05,
|
| 1112 |
+
"loss": 0.3871,
|
| 1113 |
+
"num_tokens": 134208133.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.8996763754045307,
|
| 1118 |
+
"grad_norm": 0.2258581966161728,
|
| 1119 |
+
"learning_rate": 5e-05,
|
| 1120 |
+
"loss": 0.3896,
|
| 1121 |
+
"num_tokens": 135194807.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.9061488673139159,
|
| 1126 |
+
"grad_norm": 0.1952882707118988,
|
| 1127 |
+
"learning_rate": 5e-05,
|
| 1128 |
+
"loss": 0.3882,
|
| 1129 |
+
"num_tokens": 136175941.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.912621359223301,
|
| 1134 |
+
"grad_norm": 0.18488478660583496,
|
| 1135 |
+
"learning_rate": 5e-05,
|
| 1136 |
+
"loss": 0.3982,
|
| 1137 |
+
"num_tokens": 137117638.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.919093851132686,
|
| 1142 |
+
"grad_norm": 0.18382813036441803,
|
| 1143 |
+
"learning_rate": 5e-05,
|
| 1144 |
+
"loss": 0.3775,
|
| 1145 |
+
"num_tokens": 138102412.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.9255663430420712,
|
| 1150 |
+
"grad_norm": 0.21119241416454315,
|
| 1151 |
+
"learning_rate": 5e-05,
|
| 1152 |
+
"loss": 0.3798,
|
| 1153 |
+
"num_tokens": 139056304.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.9320388349514563,
|
| 1158 |
+
"grad_norm": 0.22714336216449738,
|
| 1159 |
+
"learning_rate": 5e-05,
|
| 1160 |
+
"loss": 0.3858,
|
| 1161 |
+
"num_tokens": 140002988.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.9385113268608414,
|
| 1166 |
+
"grad_norm": 0.21165476739406586,
|
| 1167 |
+
"learning_rate": 5e-05,
|
| 1168 |
+
"loss": 0.3888,
|
| 1169 |
+
"num_tokens": 140939323.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.9449838187702265,
|
| 1174 |
+
"grad_norm": 0.20293815433979034,
|
| 1175 |
+
"learning_rate": 5e-05,
|
| 1176 |
+
"loss": 0.3828,
|
| 1177 |
+
"num_tokens": 141898246.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.9514563106796117,
|
| 1182 |
+
"grad_norm": 0.23398885130882263,
|
| 1183 |
+
"learning_rate": 5e-05,
|
| 1184 |
+
"loss": 0.3908,
|
| 1185 |
+
"num_tokens": 142861118.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.9579288025889967,
|
| 1190 |
+
"grad_norm": 0.2187807410955429,
|
| 1191 |
+
"learning_rate": 5e-05,
|
| 1192 |
+
"loss": 0.3847,
|
| 1193 |
+
"num_tokens": 143845628.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.9644012944983819,
|
| 1198 |
+
"grad_norm": 0.17871342599391937,
|
| 1199 |
+
"learning_rate": 5e-05,
|
| 1200 |
+
"loss": 0.3951,
|
| 1201 |
+
"num_tokens": 144816454.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.970873786407767,
|
| 1206 |
+
"grad_norm": 0.2050437331199646,
|
| 1207 |
+
"learning_rate": 5e-05,
|
| 1208 |
+
"loss": 0.3847,
|
| 1209 |
+
"num_tokens": 145791528.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.9773462783171522,
|
| 1214 |
+
"grad_norm": 0.22501951456069946,
|
| 1215 |
+
"learning_rate": 5e-05,
|
| 1216 |
+
"loss": 0.3975,
|
| 1217 |
+
"num_tokens": 146776225.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.9838187702265372,
|
| 1222 |
+
"grad_norm": 0.20222684741020203,
|
| 1223 |
+
"learning_rate": 5e-05,
|
| 1224 |
+
"loss": 0.3807,
|
| 1225 |
+
"num_tokens": 147716038.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.9902912621359223,
|
| 1230 |
+
"grad_norm": 0.17697201669216156,
|
| 1231 |
+
"learning_rate": 5e-05,
|
| 1232 |
+
"loss": 0.3773,
|
| 1233 |
+
"num_tokens": 148641036.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9967637540453075,
|
| 1238 |
+
"grad_norm": 0.1858855038881302,
|
| 1239 |
+
"learning_rate": 5e-05,
|
| 1240 |
+
"loss": 0.3807,
|
| 1241 |
+
"num_tokens": 149611850.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.9967637540453075,
|
| 1246 |
+
"step": 154,
|
| 1247 |
+
"total_flos": 6.182777521931551e+18,
|
| 1248 |
+
"train_loss": 0.45148222612870204,
|
| 1249 |
+
"train_runtime": 6331.7497,
|
| 1250 |
+
"train_samples_per_second": 10.918,
|
| 1251 |
+
"train_steps_per_second": 0.024
|
| 1252 |
+
}
|
| 1253 |
+
],
|
| 1254 |
+
"logging_steps": 1,
|
| 1255 |
+
"max_steps": 154,
|
| 1256 |
+
"num_input_tokens_seen": 0,
|
| 1257 |
+
"num_train_epochs": 1,
|
| 1258 |
+
"save_steps": 8,
|
| 1259 |
+
"stateful_callbacks": {
|
| 1260 |
+
"TrainerControl": {
|
| 1261 |
+
"args": {
|
| 1262 |
+
"should_epoch_stop": false,
|
| 1263 |
+
"should_evaluate": false,
|
| 1264 |
+
"should_log": false,
|
| 1265 |
+
"should_save": true,
|
| 1266 |
+
"should_training_stop": true
|
| 1267 |
+
},
|
| 1268 |
+
"attributes": {}
|
| 1269 |
+
}
|
| 1270 |
+
},
|
| 1271 |
+
"total_flos": 6.182777521931551e+18,
|
| 1272 |
+
"train_batch_size": 16,
|
| 1273 |
+
"trial_name": null,
|
| 1274 |
+
"trial_params": null
|
| 1275 |
+
}
|