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 +1411 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: text2sql-sft-v9
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for text2sql-sft-v9
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-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="genies-llm/text2sql-sft-v9", 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/genies-rnd/text2sql-sft/runs/v732vvn5)
|
| 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: 2.6.0
|
| 40 |
+
- Datasets: 4.0.0
|
| 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": 2.276376686268252e+17,
|
| 3 |
+
"train_loss": 0.25581319124726526,
|
| 4 |
+
"train_runtime": 2707.0199,
|
| 5 |
+
"train_samples": 7285,
|
| 6 |
+
"train_samples_per_second": 8.073,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 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": 1.1,
|
| 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": 2.276376686268252e+17,
|
| 3 |
+
"train_loss": 0.25581319124726526,
|
| 4 |
+
"train_runtime": 2707.0199,
|
| 5 |
+
"train_samples": 7285,
|
| 6 |
+
"train_samples_per_second": 8.073,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1411 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 171,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.017543859649122806,
|
| 14 |
+
"grad_norm": 3.77577782421705,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.1733,
|
| 17 |
+
"num_tokens": 427344.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.03508771929824561,
|
| 22 |
+
"grad_norm": 3.7130563556909215,
|
| 23 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 24 |
+
"loss": 1.164,
|
| 25 |
+
"num_tokens": 866449.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05263157894736842,
|
| 30 |
+
"grad_norm": 3.970572390407664,
|
| 31 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 32 |
+
"loss": 1.2254,
|
| 33 |
+
"num_tokens": 1268563.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.07017543859649122,
|
| 38 |
+
"grad_norm": 3.512030300056592,
|
| 39 |
+
"learning_rate": 5e-06,
|
| 40 |
+
"loss": 1.2077,
|
| 41 |
+
"num_tokens": 1669265.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.08771929824561403,
|
| 46 |
+
"grad_norm": 2.37795690695823,
|
| 47 |
+
"learning_rate": 6.666666666666667e-06,
|
| 48 |
+
"loss": 1.0413,
|
| 49 |
+
"num_tokens": 2093363.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.10526315789473684,
|
| 54 |
+
"grad_norm": 1.525864968420599,
|
| 55 |
+
"learning_rate": 8.333333333333334e-06,
|
| 56 |
+
"loss": 0.874,
|
| 57 |
+
"num_tokens": 2505147.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12280701754385964,
|
| 62 |
+
"grad_norm": 1.4347947716935,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.8159,
|
| 65 |
+
"num_tokens": 2931742.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.14035087719298245,
|
| 70 |
+
"grad_norm": 2.6084462153475063,
|
| 71 |
+
"learning_rate": 9.999184354855868e-06,
|
| 72 |
+
"loss": 0.6802,
|
| 73 |
+
"num_tokens": 3316057.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15789473684210525,
|
| 78 |
+
"grad_norm": 1.5740859932252258,
|
| 79 |
+
"learning_rate": 9.996737715102133e-06,
|
| 80 |
+
"loss": 0.6019,
|
| 81 |
+
"num_tokens": 3761399.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.17543859649122806,
|
| 86 |
+
"grad_norm": 1.5450933348615719,
|
| 87 |
+
"learning_rate": 9.99266096766761e-06,
|
| 88 |
+
"loss": 0.5439,
|
| 89 |
+
"num_tokens": 4179394.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.19298245614035087,
|
| 94 |
+
"grad_norm": 0.9018401685238229,
|
| 95 |
+
"learning_rate": 9.98695559040975e-06,
|
| 96 |
+
"loss": 0.4438,
|
| 97 |
+
"num_tokens": 4600345.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.21052631578947367,
|
| 102 |
+
"grad_norm": 0.5196800459649759,
|
| 103 |
+
"learning_rate": 9.979623651578881e-06,
|
| 104 |
+
"loss": 0.395,
|
| 105 |
+
"num_tokens": 4980610.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.22807017543859648,
|
| 110 |
+
"grad_norm": 0.4799071601752034,
|
| 111 |
+
"learning_rate": 9.970667809068476e-06,
|
| 112 |
+
"loss": 0.3892,
|
| 113 |
+
"num_tokens": 5395359.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.24561403508771928,
|
| 118 |
+
"grad_norm": 0.31207959270885294,
|
| 119 |
+
"learning_rate": 9.960091309451626e-06,
|
| 120 |
+
"loss": 0.3808,
|
| 121 |
+
"num_tokens": 5805663.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2631578947368421,
|
| 126 |
+
"grad_norm": 0.31760448278346387,
|
| 127 |
+
"learning_rate": 9.947897986804131e-06,
|
| 128 |
+
"loss": 0.3708,
|
| 129 |
+
"num_tokens": 6201438.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2807017543859649,
|
| 134 |
+
"grad_norm": 0.3009817279323404,
|
| 135 |
+
"learning_rate": 9.93409226131462e-06,
|
| 136 |
+
"loss": 0.3557,
|
| 137 |
+
"num_tokens": 6614132.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.2982456140350877,
|
| 142 |
+
"grad_norm": 0.2599822684525422,
|
| 143 |
+
"learning_rate": 9.91867913768218e-06,
|
| 144 |
+
"loss": 0.3284,
|
| 145 |
+
"num_tokens": 7030814.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.3157894736842105,
|
| 150 |
+
"grad_norm": 0.24197734921107386,
|
| 151 |
+
"learning_rate": 9.901664203302126e-06,
|
| 152 |
+
"loss": 0.3272,
|
| 153 |
+
"num_tokens": 7453748.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.3333333333333333,
|
| 158 |
+
"grad_norm": 0.2741912470593866,
|
| 159 |
+
"learning_rate": 9.883053626240503e-06,
|
| 160 |
+
"loss": 0.3181,
|
| 161 |
+
"num_tokens": 7874681.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.3508771929824561,
|
| 166 |
+
"grad_norm": 0.21560866373997145,
|
| 167 |
+
"learning_rate": 9.862854152998112e-06,
|
| 168 |
+
"loss": 0.3102,
|
| 169 |
+
"num_tokens": 8349009.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3684210526315789,
|
| 174 |
+
"grad_norm": 0.203790119667157,
|
| 175 |
+
"learning_rate": 9.841073106064852e-06,
|
| 176 |
+
"loss": 0.3038,
|
| 177 |
+
"num_tokens": 8779295.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.38596491228070173,
|
| 182 |
+
"grad_norm": 0.21543607735771148,
|
| 183 |
+
"learning_rate": 9.81771838126524e-06,
|
| 184 |
+
"loss": 0.3039,
|
| 185 |
+
"num_tokens": 9155380.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.40350877192982454,
|
| 190 |
+
"grad_norm": 0.19448461940928388,
|
| 191 |
+
"learning_rate": 9.792798444896107e-06,
|
| 192 |
+
"loss": 0.2923,
|
| 193 |
+
"num_tokens": 9572881.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.42105263157894735,
|
| 198 |
+
"grad_norm": 0.20104199677846465,
|
| 199 |
+
"learning_rate": 9.766322330657499e-06,
|
| 200 |
+
"loss": 0.3004,
|
| 201 |
+
"num_tokens": 9972480.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.43859649122807015,
|
| 206 |
+
"grad_norm": 0.19715422132031898,
|
| 207 |
+
"learning_rate": 9.738299636377863e-06,
|
| 208 |
+
"loss": 0.291,
|
| 209 |
+
"num_tokens": 10406948.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.45614035087719296,
|
| 214 |
+
"grad_norm": 0.19192801250536232,
|
| 215 |
+
"learning_rate": 9.70874052053476e-06,
|
| 216 |
+
"loss": 0.289,
|
| 217 |
+
"num_tokens": 10821942.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.47368421052631576,
|
| 222 |
+
"grad_norm": 0.18616122639207905,
|
| 223 |
+
"learning_rate": 9.677655698572326e-06,
|
| 224 |
+
"loss": 0.2622,
|
| 225 |
+
"num_tokens": 11234170.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.49122807017543857,
|
| 230 |
+
"grad_norm": 0.192192334546507,
|
| 231 |
+
"learning_rate": 9.645056439016827e-06,
|
| 232 |
+
"loss": 0.275,
|
| 233 |
+
"num_tokens": 11627308.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5087719298245614,
|
| 238 |
+
"grad_norm": 0.18829460979027127,
|
| 239 |
+
"learning_rate": 9.610954559391704e-06,
|
| 240 |
+
"loss": 0.2754,
|
| 241 |
+
"num_tokens": 12022656.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5263157894736842,
|
| 246 |
+
"grad_norm": 0.17300283701775698,
|
| 247 |
+
"learning_rate": 9.57536242193364e-06,
|
| 248 |
+
"loss": 0.2692,
|
| 249 |
+
"num_tokens": 12444405.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.543859649122807,
|
| 254 |
+
"grad_norm": 0.17695771762278176,
|
| 255 |
+
"learning_rate": 9.538292929111114e-06,
|
| 256 |
+
"loss": 0.2734,
|
| 257 |
+
"num_tokens": 12837998.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.5614035087719298,
|
| 262 |
+
"grad_norm": 0.16869993658358656,
|
| 263 |
+
"learning_rate": 9.499759518947156e-06,
|
| 264 |
+
"loss": 0.2657,
|
| 265 |
+
"num_tokens": 13261798.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.5789473684210527,
|
| 270 |
+
"grad_norm": 0.15857386041778282,
|
| 271 |
+
"learning_rate": 9.459776160147941e-06,
|
| 272 |
+
"loss": 0.2559,
|
| 273 |
+
"num_tokens": 13717762.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5964912280701754,
|
| 278 |
+
"grad_norm": 0.16181853610382824,
|
| 279 |
+
"learning_rate": 9.418357347038999e-06,
|
| 280 |
+
"loss": 0.2427,
|
| 281 |
+
"num_tokens": 14142042.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6140350877192983,
|
| 286 |
+
"grad_norm": 0.16729961186553155,
|
| 287 |
+
"learning_rate": 9.375518094310904e-06,
|
| 288 |
+
"loss": 0.2546,
|
| 289 |
+
"num_tokens": 14543269.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.631578947368421,
|
| 294 |
+
"grad_norm": 0.16125107833920507,
|
| 295 |
+
"learning_rate": 9.331273931576306e-06,
|
| 296 |
+
"loss": 0.2455,
|
| 297 |
+
"num_tokens": 14941779.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.6491228070175439,
|
| 302 |
+
"grad_norm": 0.1651336881757046,
|
| 303 |
+
"learning_rate": 9.285640897740316e-06,
|
| 304 |
+
"loss": 0.2479,
|
| 305 |
+
"num_tokens": 15378768.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.6666666666666666,
|
| 310 |
+
"grad_norm": 0.16309612539485216,
|
| 311 |
+
"learning_rate": 9.238635535186247e-06,
|
| 312 |
+
"loss": 0.2524,
|
| 313 |
+
"num_tokens": 15784254.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.6842105263157895,
|
| 318 |
+
"grad_norm": 0.1613815194130245,
|
| 319 |
+
"learning_rate": 9.19027488377886e-06,
|
| 320 |
+
"loss": 0.252,
|
| 321 |
+
"num_tokens": 16187575.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.7017543859649122,
|
| 326 |
+
"grad_norm": 0.15494556090577644,
|
| 327 |
+
"learning_rate": 9.140576474687263e-06,
|
| 328 |
+
"loss": 0.2397,
|
| 329 |
+
"num_tokens": 16592627.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.7192982456140351,
|
| 334 |
+
"grad_norm": 0.15730027265317648,
|
| 335 |
+
"learning_rate": 9.0895583240297e-06,
|
| 336 |
+
"loss": 0.2396,
|
| 337 |
+
"num_tokens": 17019496.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7368421052631579,
|
| 342 |
+
"grad_norm": 0.15536856311696803,
|
| 343 |
+
"learning_rate": 9.037238926342544e-06,
|
| 344 |
+
"loss": 0.2388,
|
| 345 |
+
"num_tokens": 17448731.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7543859649122807,
|
| 350 |
+
"grad_norm": 0.16373703052589486,
|
| 351 |
+
"learning_rate": 8.983637247875872e-06,
|
| 352 |
+
"loss": 0.2447,
|
| 353 |
+
"num_tokens": 17852418.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7719298245614035,
|
| 358 |
+
"grad_norm": 0.1564039931823383,
|
| 359 |
+
"learning_rate": 8.92877271971802e-06,
|
| 360 |
+
"loss": 0.2317,
|
| 361 |
+
"num_tokens": 18284414.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.7894736842105263,
|
| 366 |
+
"grad_norm": 0.15673969833275106,
|
| 367 |
+
"learning_rate": 8.872665230751644e-06,
|
| 368 |
+
"loss": 0.2445,
|
| 369 |
+
"num_tokens": 18700575.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.8070175438596491,
|
| 374 |
+
"grad_norm": 0.16227301290569535,
|
| 375 |
+
"learning_rate": 8.815335120443822e-06,
|
| 376 |
+
"loss": 0.2369,
|
| 377 |
+
"num_tokens": 19112507.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.8245614035087719,
|
| 382 |
+
"grad_norm": 0.16192875727409162,
|
| 383 |
+
"learning_rate": 8.756803171472817e-06,
|
| 384 |
+
"loss": 0.2488,
|
| 385 |
+
"num_tokens": 19497572.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.8421052631578947,
|
| 390 |
+
"grad_norm": 0.14878902875215574,
|
| 391 |
+
"learning_rate": 8.69709060219416e-06,
|
| 392 |
+
"loss": 0.221,
|
| 393 |
+
"num_tokens": 19887057.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8596491228070176,
|
| 398 |
+
"grad_norm": 0.168304643511618,
|
| 399 |
+
"learning_rate": 8.636219058948823e-06,
|
| 400 |
+
"loss": 0.2338,
|
| 401 |
+
"num_tokens": 20294327.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8771929824561403,
|
| 406 |
+
"grad_norm": 0.14440251287899045,
|
| 407 |
+
"learning_rate": 8.574210608216206e-06,
|
| 408 |
+
"loss": 0.2165,
|
| 409 |
+
"num_tokens": 20731445.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.8947368421052632,
|
| 414 |
+
"grad_norm": 0.14573622062248015,
|
| 415 |
+
"learning_rate": 8.511087728614863e-06,
|
| 416 |
+
"loss": 0.2291,
|
| 417 |
+
"num_tokens": 21165129.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.9122807017543859,
|
| 422 |
+
"grad_norm": 0.15767251624934578,
|
| 423 |
+
"learning_rate": 8.446873302753783e-06,
|
| 424 |
+
"loss": 0.2231,
|
| 425 |
+
"num_tokens": 21564437.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.9298245614035088,
|
| 430 |
+
"grad_norm": 0.14330856767528197,
|
| 431 |
+
"learning_rate": 8.381590608937251e-06,
|
| 432 |
+
"loss": 0.2274,
|
| 433 |
+
"num_tokens": 22012280.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9473684210526315,
|
| 438 |
+
"grad_norm": 0.1524166655671973,
|
| 439 |
+
"learning_rate": 8.315263312726248e-06,
|
| 440 |
+
"loss": 0.2131,
|
| 441 |
+
"num_tokens": 22396001.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.9649122807017544,
|
| 446 |
+
"grad_norm": 0.15336585183985868,
|
| 447 |
+
"learning_rate": 8.247915458359473e-06,
|
| 448 |
+
"loss": 0.2195,
|
| 449 |
+
"num_tokens": 22793769.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9824561403508771,
|
| 454 |
+
"grad_norm": 0.1588593078419976,
|
| 455 |
+
"learning_rate": 8.179571460037096e-06,
|
| 456 |
+
"loss": 0.2345,
|
| 457 |
+
"num_tokens": 23201717.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0,
|
| 462 |
+
"grad_norm": 0.14666483129173052,
|
| 463 |
+
"learning_rate": 8.110256093070393e-06,
|
| 464 |
+
"loss": 0.2346,
|
| 465 |
+
"num_tokens": 23647950.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.0175438596491229,
|
| 470 |
+
"grad_norm": 0.15418874889368148,
|
| 471 |
+
"learning_rate": 8.039994484900463e-06,
|
| 472 |
+
"loss": 0.2268,
|
| 473 |
+
"num_tokens": 24100529.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.0350877192982457,
|
| 478 |
+
"grad_norm": 0.14747387727593939,
|
| 479 |
+
"learning_rate": 7.968812105989316e-06,
|
| 480 |
+
"loss": 0.2155,
|
| 481 |
+
"num_tokens": 24540892.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.0526315789473684,
|
| 486 |
+
"grad_norm": 0.154346076339797,
|
| 487 |
+
"learning_rate": 7.896734760586599e-06,
|
| 488 |
+
"loss": 0.2057,
|
| 489 |
+
"num_tokens": 24956824.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.0701754385964912,
|
| 494 |
+
"grad_norm": 0.14685651214148715,
|
| 495 |
+
"learning_rate": 7.82378857737533e-06,
|
| 496 |
+
"loss": 0.2036,
|
| 497 |
+
"num_tokens": 25384518.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.087719298245614,
|
| 502 |
+
"grad_norm": 0.16326674348993506,
|
| 503 |
+
"learning_rate": 7.75e-06,
|
| 504 |
+
"loss": 0.2001,
|
| 505 |
+
"num_tokens": 25771807.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1052631578947367,
|
| 510 |
+
"grad_norm": 0.147771119836904,
|
| 511 |
+
"learning_rate": 7.675395777480538e-06,
|
| 512 |
+
"loss": 0.1996,
|
| 513 |
+
"num_tokens": 26177417.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.1228070175438596,
|
| 518 |
+
"grad_norm": 0.14003657083220583,
|
| 519 |
+
"learning_rate": 7.600002954515532e-06,
|
| 520 |
+
"loss": 0.2072,
|
| 521 |
+
"num_tokens": 26622325.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.1403508771929824,
|
| 526 |
+
"grad_norm": 0.15332767124685198,
|
| 527 |
+
"learning_rate": 7.523848861678297e-06,
|
| 528 |
+
"loss": 0.2065,
|
| 529 |
+
"num_tokens": 27045078.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.1578947368421053,
|
| 534 |
+
"grad_norm": 0.15183433287347486,
|
| 535 |
+
"learning_rate": 7.446961105509289e-06,
|
| 536 |
+
"loss": 0.2032,
|
| 537 |
+
"num_tokens": 27438828.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.1754385964912282,
|
| 542 |
+
"grad_norm": 0.14554656331938712,
|
| 543 |
+
"learning_rate": 7.36936755850849e-06,
|
| 544 |
+
"loss": 0.2054,
|
| 545 |
+
"num_tokens": 27854689.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.1929824561403508,
|
| 550 |
+
"grad_norm": 0.1537836129829156,
|
| 551 |
+
"learning_rate": 7.2910963490313815e-06,
|
| 552 |
+
"loss": 0.1949,
|
| 553 |
+
"num_tokens": 28233580.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.2105263157894737,
|
| 558 |
+
"grad_norm": 0.14572761360447276,
|
| 559 |
+
"learning_rate": 7.212175851092154e-06,
|
| 560 |
+
"loss": 0.1958,
|
| 561 |
+
"num_tokens": 28641897.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2280701754385965,
|
| 566 |
+
"grad_norm": 0.13708384426430809,
|
| 567 |
+
"learning_rate": 7.132634674077884e-06,
|
| 568 |
+
"loss": 0.2021,
|
| 569 |
+
"num_tokens": 29084929.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.2456140350877192,
|
| 574 |
+
"grad_norm": 0.1486755044006831,
|
| 575 |
+
"learning_rate": 7.052501652377368e-06,
|
| 576 |
+
"loss": 0.2044,
|
| 577 |
+
"num_tokens": 29482516.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.263157894736842,
|
| 582 |
+
"grad_norm": 0.14957101767673275,
|
| 583 |
+
"learning_rate": 6.971805834928399e-06,
|
| 584 |
+
"loss": 0.2048,
|
| 585 |
+
"num_tokens": 29899136.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.280701754385965,
|
| 590 |
+
"grad_norm": 0.1486401064457622,
|
| 591 |
+
"learning_rate": 6.890576474687264e-06,
|
| 592 |
+
"loss": 0.2068,
|
| 593 |
+
"num_tokens": 30317666.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.2982456140350878,
|
| 598 |
+
"grad_norm": 0.15958496167902586,
|
| 599 |
+
"learning_rate": 6.808843018024296e-06,
|
| 600 |
+
"loss": 0.1986,
|
| 601 |
+
"num_tokens": 30734034.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.3157894736842106,
|
| 606 |
+
"grad_norm": 0.1383546863269268,
|
| 607 |
+
"learning_rate": 6.726635094049291e-06,
|
| 608 |
+
"loss": 0.199,
|
| 609 |
+
"num_tokens": 31155917.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.3333333333333333,
|
| 614 |
+
"grad_norm": 0.14368049999314014,
|
| 615 |
+
"learning_rate": 6.643982503870693e-06,
|
| 616 |
+
"loss": 0.2032,
|
| 617 |
+
"num_tokens": 31573757.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.3508771929824561,
|
| 622 |
+
"grad_norm": 0.13900291410105262,
|
| 623 |
+
"learning_rate": 6.560915209792424e-06,
|
| 624 |
+
"loss": 0.2016,
|
| 625 |
+
"num_tokens": 32010739.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.368421052631579,
|
| 630 |
+
"grad_norm": 0.13844326865953724,
|
| 631 |
+
"learning_rate": 6.477463324452286e-06,
|
| 632 |
+
"loss": 0.1925,
|
| 633 |
+
"num_tokens": 32424467.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.3859649122807016,
|
| 638 |
+
"grad_norm": 0.1433757292045691,
|
| 639 |
+
"learning_rate": 6.393657099905854e-06,
|
| 640 |
+
"loss": 0.2008,
|
| 641 |
+
"num_tokens": 32834770.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.4035087719298245,
|
| 646 |
+
"grad_norm": 0.14196299072627255,
|
| 647 |
+
"learning_rate": 6.309526916659843e-06,
|
| 648 |
+
"loss": 0.1924,
|
| 649 |
+
"num_tokens": 33255872.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.4210526315789473,
|
| 654 |
+
"grad_norm": 0.13753823275156205,
|
| 655 |
+
"learning_rate": 6.225103272658889e-06,
|
| 656 |
+
"loss": 0.2034,
|
| 657 |
+
"num_tokens": 33706927.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.4385964912280702,
|
| 662 |
+
"grad_norm": 0.1384289808314504,
|
| 663 |
+
"learning_rate": 6.140416772229785e-06,
|
| 664 |
+
"loss": 0.1917,
|
| 665 |
+
"num_tokens": 34112601.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.456140350877193,
|
| 670 |
+
"grad_norm": 0.14627667997521285,
|
| 671 |
+
"learning_rate": 6.0554981149871276e-06,
|
| 672 |
+
"loss": 0.2063,
|
| 673 |
+
"num_tokens": 34517104.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4736842105263157,
|
| 678 |
+
"grad_norm": 0.1558573666402862,
|
| 679 |
+
"learning_rate": 5.970378084704441e-06,
|
| 680 |
+
"loss": 0.1994,
|
| 681 |
+
"num_tokens": 34897309.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4912280701754386,
|
| 686 |
+
"grad_norm": 0.1417112898190135,
|
| 687 |
+
"learning_rate": 5.88508753815478e-06,
|
| 688 |
+
"loss": 0.1881,
|
| 689 |
+
"num_tokens": 35307793.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.5087719298245614,
|
| 694 |
+
"grad_norm": 0.1385582692497573,
|
| 695 |
+
"learning_rate": 5.799657393924869e-06,
|
| 696 |
+
"loss": 0.198,
|
| 697 |
+
"num_tokens": 35741435.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.526315789473684,
|
| 702 |
+
"grad_norm": 0.15662493183414183,
|
| 703 |
+
"learning_rate": 5.714118621206843e-06,
|
| 704 |
+
"loss": 0.1909,
|
| 705 |
+
"num_tokens": 36110154.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.543859649122807,
|
| 710 |
+
"grad_norm": 0.14798100623872662,
|
| 711 |
+
"learning_rate": 5.6285022285716325e-06,
|
| 712 |
+
"loss": 0.2063,
|
| 713 |
+
"num_tokens": 36508508.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.5614035087719298,
|
| 718 |
+
"grad_norm": 0.13949297838603725,
|
| 719 |
+
"learning_rate": 5.542839252728096e-06,
|
| 720 |
+
"loss": 0.2056,
|
| 721 |
+
"num_tokens": 36962199.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.5789473684210527,
|
| 726 |
+
"grad_norm": 0.1388395627421214,
|
| 727 |
+
"learning_rate": 5.457160747271906e-06,
|
| 728 |
+
"loss": 0.1977,
|
| 729 |
+
"num_tokens": 37416119.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5964912280701755,
|
| 734 |
+
"grad_norm": 0.13753404705909872,
|
| 735 |
+
"learning_rate": 5.371497771428368e-06,
|
| 736 |
+
"loss": 0.1988,
|
| 737 |
+
"num_tokens": 37844052.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6140350877192984,
|
| 742 |
+
"grad_norm": 0.13813649436163167,
|
| 743 |
+
"learning_rate": 5.2858813787931605e-06,
|
| 744 |
+
"loss": 0.193,
|
| 745 |
+
"num_tokens": 38281149.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.631578947368421,
|
| 750 |
+
"grad_norm": 0.13735934501319846,
|
| 751 |
+
"learning_rate": 5.2003426060751324e-06,
|
| 752 |
+
"loss": 0.1948,
|
| 753 |
+
"num_tokens": 38696776.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.6491228070175439,
|
| 758 |
+
"grad_norm": 0.14464652766257102,
|
| 759 |
+
"learning_rate": 5.114912461845223e-06,
|
| 760 |
+
"loss": 0.1954,
|
| 761 |
+
"num_tokens": 39118421.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.6666666666666665,
|
| 766 |
+
"grad_norm": 0.1441541884884212,
|
| 767 |
+
"learning_rate": 5.02962191529556e-06,
|
| 768 |
+
"loss": 0.1969,
|
| 769 |
+
"num_tokens": 39531921.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.6842105263157894,
|
| 774 |
+
"grad_norm": 0.14549147633711634,
|
| 775 |
+
"learning_rate": 4.944501885012875e-06,
|
| 776 |
+
"loss": 0.1987,
|
| 777 |
+
"num_tokens": 39942510.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.7017543859649122,
|
| 782 |
+
"grad_norm": 0.14239386063143547,
|
| 783 |
+
"learning_rate": 4.859583227770218e-06,
|
| 784 |
+
"loss": 0.1942,
|
| 785 |
+
"num_tokens": 40349157.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.719298245614035,
|
| 790 |
+
"grad_norm": 0.14101938277964904,
|
| 791 |
+
"learning_rate": 4.774896727341113e-06,
|
| 792 |
+
"loss": 0.1896,
|
| 793 |
+
"num_tokens": 40755487.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.736842105263158,
|
| 798 |
+
"grad_norm": 0.1513563377956916,
|
| 799 |
+
"learning_rate": 4.6904730833401575e-06,
|
| 800 |
+
"loss": 0.1741,
|
| 801 |
+
"num_tokens": 41109588.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7543859649122808,
|
| 806 |
+
"grad_norm": 0.14171664584567437,
|
| 807 |
+
"learning_rate": 4.606342900094147e-06,
|
| 808 |
+
"loss": 0.1978,
|
| 809 |
+
"num_tokens": 41549463.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.7719298245614035,
|
| 814 |
+
"grad_norm": 0.1403769471140474,
|
| 815 |
+
"learning_rate": 4.5225366755477165e-06,
|
| 816 |
+
"loss": 0.2018,
|
| 817 |
+
"num_tokens": 41986009.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.7894736842105263,
|
| 822 |
+
"grad_norm": 0.14588775725754724,
|
| 823 |
+
"learning_rate": 4.439084790207577e-06,
|
| 824 |
+
"loss": 0.1991,
|
| 825 |
+
"num_tokens": 42393517.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.807017543859649,
|
| 830 |
+
"grad_norm": 0.14195463960673751,
|
| 831 |
+
"learning_rate": 4.35601749612931e-06,
|
| 832 |
+
"loss": 0.1954,
|
| 833 |
+
"num_tokens": 42788971.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.8245614035087718,
|
| 838 |
+
"grad_norm": 0.14486517700153345,
|
| 839 |
+
"learning_rate": 4.273364905950711e-06,
|
| 840 |
+
"loss": 0.2001,
|
| 841 |
+
"num_tokens": 43200059.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.8421052631578947,
|
| 846 |
+
"grad_norm": 0.14536497153998434,
|
| 847 |
+
"learning_rate": 4.191156981975704e-06,
|
| 848 |
+
"loss": 0.1881,
|
| 849 |
+
"num_tokens": 43591515.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.8596491228070176,
|
| 854 |
+
"grad_norm": 0.1483672348465985,
|
| 855 |
+
"learning_rate": 4.109423525312738e-06,
|
| 856 |
+
"loss": 0.1936,
|
| 857 |
+
"num_tokens": 43989015.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.8771929824561404,
|
| 862 |
+
"grad_norm": 0.14387471159557752,
|
| 863 |
+
"learning_rate": 4.028194165071603e-06,
|
| 864 |
+
"loss": 0.1959,
|
| 865 |
+
"num_tokens": 44390867.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.8947368421052633,
|
| 870 |
+
"grad_norm": 0.14319263387686854,
|
| 871 |
+
"learning_rate": 3.9474983476226335e-06,
|
| 872 |
+
"loss": 0.2026,
|
| 873 |
+
"num_tokens": 44814288.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.912280701754386,
|
| 878 |
+
"grad_norm": 0.13718763298366718,
|
| 879 |
+
"learning_rate": 3.867365325922116e-06,
|
| 880 |
+
"loss": 0.1919,
|
| 881 |
+
"num_tokens": 45232685.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.9298245614035088,
|
| 886 |
+
"grad_norm": 0.13661747990592807,
|
| 887 |
+
"learning_rate": 3.7878241489078473e-06,
|
| 888 |
+
"loss": 0.192,
|
| 889 |
+
"num_tokens": 45633905.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.9473684210526314,
|
| 894 |
+
"grad_norm": 0.13757723840377134,
|
| 895 |
+
"learning_rate": 3.7089036509686216e-06,
|
| 896 |
+
"loss": 0.196,
|
| 897 |
+
"num_tokens": 46052270.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.9649122807017543,
|
| 902 |
+
"grad_norm": 0.14009156799615108,
|
| 903 |
+
"learning_rate": 3.630632441491512e-06,
|
| 904 |
+
"loss": 0.1945,
|
| 905 |
+
"num_tokens": 46479271.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.9824561403508771,
|
| 910 |
+
"grad_norm": 0.1392559652525668,
|
| 911 |
+
"learning_rate": 3.5530388944907124e-06,
|
| 912 |
+
"loss": 0.1985,
|
| 913 |
+
"num_tokens": 46884227.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.0,
|
| 918 |
+
"grad_norm": 0.13976428969132587,
|
| 919 |
+
"learning_rate": 3.476151138321705e-06,
|
| 920 |
+
"loss": 0.1995,
|
| 921 |
+
"num_tokens": 47297644.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.017543859649123,
|
| 926 |
+
"grad_norm": 0.1378198428541279,
|
| 927 |
+
"learning_rate": 3.3999970454844688e-06,
|
| 928 |
+
"loss": 0.1724,
|
| 929 |
+
"num_tokens": 47688068.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.0350877192982457,
|
| 934 |
+
"grad_norm": 0.134440422974191,
|
| 935 |
+
"learning_rate": 3.3246042225194626e-06,
|
| 936 |
+
"loss": 0.1796,
|
| 937 |
+
"num_tokens": 48092477.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.0526315789473686,
|
| 942 |
+
"grad_norm": 0.13660484419562605,
|
| 943 |
+
"learning_rate": 3.2500000000000015e-06,
|
| 944 |
+
"loss": 0.1763,
|
| 945 |
+
"num_tokens": 48476841.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.0701754385964914,
|
| 950 |
+
"grad_norm": 0.14109474340650238,
|
| 951 |
+
"learning_rate": 3.176211422624672e-06,
|
| 952 |
+
"loss": 0.1778,
|
| 953 |
+
"num_tokens": 48854905.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.087719298245614,
|
| 958 |
+
"grad_norm": 0.13774654351946805,
|
| 959 |
+
"learning_rate": 3.103265239413401e-06,
|
| 960 |
+
"loss": 0.1793,
|
| 961 |
+
"num_tokens": 49295065.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.1052631578947367,
|
| 966 |
+
"grad_norm": 0.14705463035874308,
|
| 967 |
+
"learning_rate": 3.0311878940106864e-06,
|
| 968 |
+
"loss": 0.1885,
|
| 969 |
+
"num_tokens": 49711843.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.1228070175438596,
|
| 974 |
+
"grad_norm": 0.13965440849358451,
|
| 975 |
+
"learning_rate": 2.9600055150995397e-06,
|
| 976 |
+
"loss": 0.1804,
|
| 977 |
+
"num_tokens": 50121373.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1403508771929824,
|
| 982 |
+
"grad_norm": 0.1431354792667028,
|
| 983 |
+
"learning_rate": 2.889743906929609e-06,
|
| 984 |
+
"loss": 0.1761,
|
| 985 |
+
"num_tokens": 50524660.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.1578947368421053,
|
| 990 |
+
"grad_norm": 0.13549946577694855,
|
| 991 |
+
"learning_rate": 2.820428539962905e-06,
|
| 992 |
+
"loss": 0.1756,
|
| 993 |
+
"num_tokens": 50952097.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.175438596491228,
|
| 998 |
+
"grad_norm": 0.13874042982824947,
|
| 999 |
+
"learning_rate": 2.7520845416405285e-06,
|
| 1000 |
+
"loss": 0.1787,
|
| 1001 |
+
"num_tokens": 51357662.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.192982456140351,
|
| 1006 |
+
"grad_norm": 0.13352052067268536,
|
| 1007 |
+
"learning_rate": 2.6847366872737535e-06,
|
| 1008 |
+
"loss": 0.1786,
|
| 1009 |
+
"num_tokens": 51772391.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.2105263157894735,
|
| 1014 |
+
"grad_norm": 0.13750830287403998,
|
| 1015 |
+
"learning_rate": 2.618409391062751e-06,
|
| 1016 |
+
"loss": 0.1827,
|
| 1017 |
+
"num_tokens": 52198396.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.2280701754385963,
|
| 1022 |
+
"grad_norm": 0.14077287411728898,
|
| 1023 |
+
"learning_rate": 2.5531266972462176e-06,
|
| 1024 |
+
"loss": 0.1786,
|
| 1025 |
+
"num_tokens": 52585564.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.245614035087719,
|
| 1030 |
+
"grad_norm": 0.13893984896019573,
|
| 1031 |
+
"learning_rate": 2.4889122713851397e-06,
|
| 1032 |
+
"loss": 0.1788,
|
| 1033 |
+
"num_tokens": 52997398.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.263157894736842,
|
| 1038 |
+
"grad_norm": 0.13788162656378736,
|
| 1039 |
+
"learning_rate": 2.425789391783796e-06,
|
| 1040 |
+
"loss": 0.1878,
|
| 1041 |
+
"num_tokens": 53407933.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.280701754385965,
|
| 1046 |
+
"grad_norm": 0.13629331805149528,
|
| 1047 |
+
"learning_rate": 2.36378094105118e-06,
|
| 1048 |
+
"loss": 0.1836,
|
| 1049 |
+
"num_tokens": 53817667.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.2982456140350878,
|
| 1054 |
+
"grad_norm": 0.145846640939152,
|
| 1055 |
+
"learning_rate": 2.302909397805841e-06,
|
| 1056 |
+
"loss": 0.1761,
|
| 1057 |
+
"num_tokens": 54208139.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.3157894736842106,
|
| 1062 |
+
"grad_norm": 0.1415158735561498,
|
| 1063 |
+
"learning_rate": 2.2431968285271843e-06,
|
| 1064 |
+
"loss": 0.1861,
|
| 1065 |
+
"num_tokens": 54616138.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.3333333333333335,
|
| 1070 |
+
"grad_norm": 0.1399694993181749,
|
| 1071 |
+
"learning_rate": 2.1846648795561777e-06,
|
| 1072 |
+
"loss": 0.18,
|
| 1073 |
+
"num_tokens": 55028264.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.3508771929824563,
|
| 1078 |
+
"grad_norm": 0.1340221566625987,
|
| 1079 |
+
"learning_rate": 2.1273347692483574e-06,
|
| 1080 |
+
"loss": 0.1818,
|
| 1081 |
+
"num_tokens": 55474995.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.3684210526315788,
|
| 1086 |
+
"grad_norm": 0.13728502667314055,
|
| 1087 |
+
"learning_rate": 2.071227280281982e-06,
|
| 1088 |
+
"loss": 0.1697,
|
| 1089 |
+
"num_tokens": 55872252.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.3859649122807016,
|
| 1094 |
+
"grad_norm": 0.13569940106251407,
|
| 1095 |
+
"learning_rate": 2.016362752124129e-06,
|
| 1096 |
+
"loss": 0.1799,
|
| 1097 |
+
"num_tokens": 56295990.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.4035087719298245,
|
| 1102 |
+
"grad_norm": 0.1433225385861297,
|
| 1103 |
+
"learning_rate": 1.9627610736574575e-06,
|
| 1104 |
+
"loss": 0.1744,
|
| 1105 |
+
"num_tokens": 56700633.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.4210526315789473,
|
| 1110 |
+
"grad_norm": 0.13712140562366157,
|
| 1111 |
+
"learning_rate": 1.9104416759703017e-06,
|
| 1112 |
+
"loss": 0.1772,
|
| 1113 |
+
"num_tokens": 57123351.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.43859649122807,
|
| 1118 |
+
"grad_norm": 0.14064914274676912,
|
| 1119 |
+
"learning_rate": 1.8594235253127373e-06,
|
| 1120 |
+
"loss": 0.1794,
|
| 1121 |
+
"num_tokens": 57541451.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.456140350877193,
|
| 1126 |
+
"grad_norm": 0.15170132064659694,
|
| 1127 |
+
"learning_rate": 1.8097251162211405e-06,
|
| 1128 |
+
"loss": 0.1831,
|
| 1129 |
+
"num_tokens": 57962223.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.473684210526316,
|
| 1134 |
+
"grad_norm": 0.13964776563103484,
|
| 1135 |
+
"learning_rate": 1.7613644648137543e-06,
|
| 1136 |
+
"loss": 0.1756,
|
| 1137 |
+
"num_tokens": 58375881.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.4912280701754383,
|
| 1142 |
+
"grad_norm": 0.13507579048092097,
|
| 1143 |
+
"learning_rate": 1.7143591022596846e-06,
|
| 1144 |
+
"loss": 0.1821,
|
| 1145 |
+
"num_tokens": 58796929.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.5087719298245617,
|
| 1150 |
+
"grad_norm": 0.13875107577532086,
|
| 1151 |
+
"learning_rate": 1.6687260684236943e-06,
|
| 1152 |
+
"loss": 0.1773,
|
| 1153 |
+
"num_tokens": 59207995.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.526315789473684,
|
| 1158 |
+
"grad_norm": 0.14061593378122658,
|
| 1159 |
+
"learning_rate": 1.6244819056890975e-06,
|
| 1160 |
+
"loss": 0.1716,
|
| 1161 |
+
"num_tokens": 59582578.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.543859649122807,
|
| 1166 |
+
"grad_norm": 0.12901477335373565,
|
| 1167 |
+
"learning_rate": 1.5816426529610035e-06,
|
| 1168 |
+
"loss": 0.1764,
|
| 1169 |
+
"num_tokens": 60014351.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.56140350877193,
|
| 1174 |
+
"grad_norm": 0.13513262564013573,
|
| 1175 |
+
"learning_rate": 1.5402238398520614e-06,
|
| 1176 |
+
"loss": 0.1742,
|
| 1177 |
+
"num_tokens": 60428513.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.5789473684210527,
|
| 1182 |
+
"grad_norm": 0.12744611421871882,
|
| 1183 |
+
"learning_rate": 1.5002404810528452e-06,
|
| 1184 |
+
"loss": 0.1798,
|
| 1185 |
+
"num_tokens": 60870775.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.5964912280701755,
|
| 1190 |
+
"grad_norm": 0.1281932184087842,
|
| 1191 |
+
"learning_rate": 1.4617070708888882e-06,
|
| 1192 |
+
"loss": 0.1788,
|
| 1193 |
+
"num_tokens": 61333167.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.6140350877192984,
|
| 1198 |
+
"grad_norm": 0.13398144271039164,
|
| 1199 |
+
"learning_rate": 1.4246375780663613e-06,
|
| 1200 |
+
"loss": 0.1792,
|
| 1201 |
+
"num_tokens": 61737623.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.6315789473684212,
|
| 1206 |
+
"grad_norm": 0.13540743049220252,
|
| 1207 |
+
"learning_rate": 1.389045440608296e-06,
|
| 1208 |
+
"loss": 0.1755,
|
| 1209 |
+
"num_tokens": 62143293.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.6491228070175437,
|
| 1214 |
+
"grad_norm": 0.13564465493581726,
|
| 1215 |
+
"learning_rate": 1.354943560983175e-06,
|
| 1216 |
+
"loss": 0.1735,
|
| 1217 |
+
"num_tokens": 62558499.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.6666666666666665,
|
| 1222 |
+
"grad_norm": 0.12805186009140426,
|
| 1223 |
+
"learning_rate": 1.3223443014276738e-06,
|
| 1224 |
+
"loss": 0.1736,
|
| 1225 |
+
"num_tokens": 63004628.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 2.6842105263157894,
|
| 1230 |
+
"grad_norm": 0.1328569132316143,
|
| 1231 |
+
"learning_rate": 1.2912594794652406e-06,
|
| 1232 |
+
"loss": 0.1642,
|
| 1233 |
+
"num_tokens": 63387346.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.7017543859649122,
|
| 1238 |
+
"grad_norm": 0.1325321320124978,
|
| 1239 |
+
"learning_rate": 1.2617003636221394e-06,
|
| 1240 |
+
"loss": 0.169,
|
| 1241 |
+
"num_tokens": 63804970.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.719298245614035,
|
| 1246 |
+
"grad_norm": 0.13540714382771668,
|
| 1247 |
+
"learning_rate": 1.2336776693425028e-06,
|
| 1248 |
+
"loss": 0.1744,
|
| 1249 |
+
"num_tokens": 64196162.0,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.736842105263158,
|
| 1254 |
+
"grad_norm": 0.14020781213013872,
|
| 1255 |
+
"learning_rate": 1.2072015551038933e-06,
|
| 1256 |
+
"loss": 0.1811,
|
| 1257 |
+
"num_tokens": 64585657.0,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.754385964912281,
|
| 1262 |
+
"grad_norm": 0.14012421310202808,
|
| 1263 |
+
"learning_rate": 1.1822816187347625e-06,
|
| 1264 |
+
"loss": 0.1882,
|
| 1265 |
+
"num_tokens": 64990929.0,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.7719298245614032,
|
| 1270 |
+
"grad_norm": 0.13359559789919473,
|
| 1271 |
+
"learning_rate": 1.1589268939351499e-06,
|
| 1272 |
+
"loss": 0.1644,
|
| 1273 |
+
"num_tokens": 65419394.0,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.7894736842105265,
|
| 1278 |
+
"grad_norm": 0.1293973137684263,
|
| 1279 |
+
"learning_rate": 1.1371458470018896e-06,
|
| 1280 |
+
"loss": 0.1686,
|
| 1281 |
+
"num_tokens": 65848256.0,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 2.807017543859649,
|
| 1286 |
+
"grad_norm": 0.12796590503255867,
|
| 1287 |
+
"learning_rate": 1.1169463737594995e-06,
|
| 1288 |
+
"loss": 0.173,
|
| 1289 |
+
"num_tokens": 66276026.0,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.824561403508772,
|
| 1294 |
+
"grad_norm": 0.1386629969970847,
|
| 1295 |
+
"learning_rate": 1.0983357966978747e-06,
|
| 1296 |
+
"loss": 0.1698,
|
| 1297 |
+
"num_tokens": 66662640.0,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.8421052631578947,
|
| 1302 |
+
"grad_norm": 0.1312256058443758,
|
| 1303 |
+
"learning_rate": 1.0813208623178199e-06,
|
| 1304 |
+
"loss": 0.1831,
|
| 1305 |
+
"num_tokens": 67101128.0,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.8596491228070176,
|
| 1310 |
+
"grad_norm": 0.13566699518356568,
|
| 1311 |
+
"learning_rate": 1.0659077386853817e-06,
|
| 1312 |
+
"loss": 0.1918,
|
| 1313 |
+
"num_tokens": 67527335.0,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.8771929824561404,
|
| 1318 |
+
"grad_norm": 0.13207372833151468,
|
| 1319 |
+
"learning_rate": 1.0521020131958692e-06,
|
| 1320 |
+
"loss": 0.18,
|
| 1321 |
+
"num_tokens": 67953220.0,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.8947368421052633,
|
| 1326 |
+
"grad_norm": 0.1351068484295404,
|
| 1327 |
+
"learning_rate": 1.0399086905483752e-06,
|
| 1328 |
+
"loss": 0.1796,
|
| 1329 |
+
"num_tokens": 68401961.0,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.912280701754386,
|
| 1334 |
+
"grad_norm": 0.13512574709033598,
|
| 1335 |
+
"learning_rate": 1.0293321909315242e-06,
|
| 1336 |
+
"loss": 0.1742,
|
| 1337 |
+
"num_tokens": 68815465.0,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.9298245614035086,
|
| 1342 |
+
"grad_norm": 0.13483699443340522,
|
| 1343 |
+
"learning_rate": 1.0203763484211196e-06,
|
| 1344 |
+
"loss": 0.1778,
|
| 1345 |
+
"num_tokens": 69255767.0,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.9473684210526314,
|
| 1350 |
+
"grad_norm": 0.13142810366700336,
|
| 1351 |
+
"learning_rate": 1.0130444095902514e-06,
|
| 1352 |
+
"loss": 0.1842,
|
| 1353 |
+
"num_tokens": 69678619.0,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.9649122807017543,
|
| 1358 |
+
"grad_norm": 0.13693412077884642,
|
| 1359 |
+
"learning_rate": 1.0073390323323897e-06,
|
| 1360 |
+
"loss": 0.177,
|
| 1361 |
+
"num_tokens": 70098414.0,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.982456140350877,
|
| 1366 |
+
"grad_norm": 0.1320466096940847,
|
| 1367 |
+
"learning_rate": 1.0032622848978689e-06,
|
| 1368 |
+
"loss": 0.168,
|
| 1369 |
+
"num_tokens": 70513950.0,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.0,
|
| 1374 |
+
"grad_norm": 0.1365255306036787,
|
| 1375 |
+
"learning_rate": 1.000815645144134e-06,
|
| 1376 |
+
"loss": 0.1794,
|
| 1377 |
+
"num_tokens": 70937090.0,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 3.0,
|
| 1382 |
+
"step": 171,
|
| 1383 |
+
"total_flos": 2.276376686268252e+17,
|
| 1384 |
+
"train_loss": 0.25581319124726526,
|
| 1385 |
+
"train_runtime": 2707.0199,
|
| 1386 |
+
"train_samples_per_second": 8.073,
|
| 1387 |
+
"train_steps_per_second": 0.063
|
| 1388 |
+
}
|
| 1389 |
+
],
|
| 1390 |
+
"logging_steps": 1,
|
| 1391 |
+
"max_steps": 171,
|
| 1392 |
+
"num_input_tokens_seen": 0,
|
| 1393 |
+
"num_train_epochs": 3,
|
| 1394 |
+
"save_steps": 500,
|
| 1395 |
+
"stateful_callbacks": {
|
| 1396 |
+
"TrainerControl": {
|
| 1397 |
+
"args": {
|
| 1398 |
+
"should_epoch_stop": false,
|
| 1399 |
+
"should_evaluate": false,
|
| 1400 |
+
"should_log": false,
|
| 1401 |
+
"should_save": true,
|
| 1402 |
+
"should_training_stop": true
|
| 1403 |
+
},
|
| 1404 |
+
"attributes": {}
|
| 1405 |
+
}
|
| 1406 |
+
},
|
| 1407 |
+
"total_flos": 2.276376686268252e+17,
|
| 1408 |
+
"train_batch_size": 8,
|
| 1409 |
+
"trial_name": null,
|
| 1410 |
+
"trial_params": null
|
| 1411 |
+
}
|