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-v6
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for text2sql-sft-v6
|
| 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-v6", 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/9v6qppxc)
|
| 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": 2.3168881532705178e+17,
|
| 3 |
+
"train_loss": 0.25350178002614027,
|
| 4 |
+
"train_runtime": 2712.8956,
|
| 5 |
+
"train_samples": 7296,
|
| 6 |
+
"train_samples_per_second": 8.068,
|
| 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": 2.3168881532705178e+17,
|
| 3 |
+
"train_loss": 0.25350178002614027,
|
| 4 |
+
"train_runtime": 2712.8956,
|
| 5 |
+
"train_samples": 7296,
|
| 6 |
+
"train_samples_per_second": 8.068,
|
| 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": 3.9338779838849725,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.2337,
|
| 17 |
+
"num_tokens": 415561.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.03508771929824561,
|
| 22 |
+
"grad_norm": 4.061961880981431,
|
| 23 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 24 |
+
"loss": 1.2551,
|
| 25 |
+
"num_tokens": 811930.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05263157894736842,
|
| 30 |
+
"grad_norm": 4.126747331618448,
|
| 31 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 32 |
+
"loss": 1.2772,
|
| 33 |
+
"num_tokens": 1198366.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.07017543859649122,
|
| 38 |
+
"grad_norm": 3.410910565563502,
|
| 39 |
+
"learning_rate": 5e-06,
|
| 40 |
+
"loss": 1.1776,
|
| 41 |
+
"num_tokens": 1608933.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.08771929824561403,
|
| 46 |
+
"grad_norm": 2.233718748318594,
|
| 47 |
+
"learning_rate": 6.666666666666667e-06,
|
| 48 |
+
"loss": 0.9942,
|
| 49 |
+
"num_tokens": 2068099.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.10526315789473684,
|
| 54 |
+
"grad_norm": 1.470021030676499,
|
| 55 |
+
"learning_rate": 8.333333333333334e-06,
|
| 56 |
+
"loss": 0.8448,
|
| 57 |
+
"num_tokens": 2506575.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12280701754385964,
|
| 62 |
+
"grad_norm": 1.4565364805839704,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.8213,
|
| 65 |
+
"num_tokens": 2932014.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.14035087719298245,
|
| 70 |
+
"grad_norm": 2.3516845691230217,
|
| 71 |
+
"learning_rate": 9.999184354855868e-06,
|
| 72 |
+
"loss": 0.6275,
|
| 73 |
+
"num_tokens": 3370254.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15789473684210525,
|
| 78 |
+
"grad_norm": 1.8135724347288096,
|
| 79 |
+
"learning_rate": 9.996737715102133e-06,
|
| 80 |
+
"loss": 0.5931,
|
| 81 |
+
"num_tokens": 3782161.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.17543859649122806,
|
| 86 |
+
"grad_norm": 1.4106997469551075,
|
| 87 |
+
"learning_rate": 9.99266096766761e-06,
|
| 88 |
+
"loss": 0.4933,
|
| 89 |
+
"num_tokens": 4211970.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.19298245614035087,
|
| 94 |
+
"grad_norm": 0.8131031118317348,
|
| 95 |
+
"learning_rate": 9.98695559040975e-06,
|
| 96 |
+
"loss": 0.4229,
|
| 97 |
+
"num_tokens": 4613367.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.21052631578947367,
|
| 102 |
+
"grad_norm": 0.7764134903704204,
|
| 103 |
+
"learning_rate": 9.979623651578881e-06,
|
| 104 |
+
"loss": 0.3888,
|
| 105 |
+
"num_tokens": 5012484.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.22807017543859648,
|
| 110 |
+
"grad_norm": 0.37508885186302826,
|
| 111 |
+
"learning_rate": 9.970667809068476e-06,
|
| 112 |
+
"loss": 0.3783,
|
| 113 |
+
"num_tokens": 5420781.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.24561403508771928,
|
| 118 |
+
"grad_norm": 0.3209831897748014,
|
| 119 |
+
"learning_rate": 9.960091309451626e-06,
|
| 120 |
+
"loss": 0.3308,
|
| 121 |
+
"num_tokens": 5823019.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2631578947368421,
|
| 126 |
+
"grad_norm": 0.2796386507143645,
|
| 127 |
+
"learning_rate": 9.947897986804131e-06,
|
| 128 |
+
"loss": 0.3456,
|
| 129 |
+
"num_tokens": 6241736.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2807017543859649,
|
| 134 |
+
"grad_norm": 0.25191330470494944,
|
| 135 |
+
"learning_rate": 9.93409226131462e-06,
|
| 136 |
+
"loss": 0.3172,
|
| 137 |
+
"num_tokens": 6680804.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.2982456140350877,
|
| 142 |
+
"grad_norm": 0.2415593584049499,
|
| 143 |
+
"learning_rate": 9.91867913768218e-06,
|
| 144 |
+
"loss": 0.3253,
|
| 145 |
+
"num_tokens": 7107939.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.3157894736842105,
|
| 150 |
+
"grad_norm": 0.3003770654260172,
|
| 151 |
+
"learning_rate": 9.901664203302126e-06,
|
| 152 |
+
"loss": 0.3213,
|
| 153 |
+
"num_tokens": 7524281.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.3333333333333333,
|
| 158 |
+
"grad_norm": 0.3539478460817712,
|
| 159 |
+
"learning_rate": 9.883053626240503e-06,
|
| 160 |
+
"loss": 0.2966,
|
| 161 |
+
"num_tokens": 7939796.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.3508771929824561,
|
| 166 |
+
"grad_norm": 0.2280690675113219,
|
| 167 |
+
"learning_rate": 9.862854152998112e-06,
|
| 168 |
+
"loss": 0.3043,
|
| 169 |
+
"num_tokens": 8366406.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3684210526315789,
|
| 174 |
+
"grad_norm": 0.21683554455375648,
|
| 175 |
+
"learning_rate": 9.841073106064852e-06,
|
| 176 |
+
"loss": 0.3057,
|
| 177 |
+
"num_tokens": 8772526.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.38596491228070173,
|
| 182 |
+
"grad_norm": 0.19203110899204243,
|
| 183 |
+
"learning_rate": 9.81771838126524e-06,
|
| 184 |
+
"loss": 0.2899,
|
| 185 |
+
"num_tokens": 9193705.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.40350877192982454,
|
| 190 |
+
"grad_norm": 0.21290762042544037,
|
| 191 |
+
"learning_rate": 9.792798444896107e-06,
|
| 192 |
+
"loss": 0.3073,
|
| 193 |
+
"num_tokens": 9641419.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.42105263157894735,
|
| 198 |
+
"grad_norm": 0.1917960836643891,
|
| 199 |
+
"learning_rate": 9.766322330657499e-06,
|
| 200 |
+
"loss": 0.2921,
|
| 201 |
+
"num_tokens": 10041552.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.43859649122807015,
|
| 206 |
+
"grad_norm": 0.18577210434865676,
|
| 207 |
+
"learning_rate": 9.738299636377863e-06,
|
| 208 |
+
"loss": 0.28,
|
| 209 |
+
"num_tokens": 10476244.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.45614035087719296,
|
| 214 |
+
"grad_norm": 0.18309063662126532,
|
| 215 |
+
"learning_rate": 9.70874052053476e-06,
|
| 216 |
+
"loss": 0.2785,
|
| 217 |
+
"num_tokens": 10863935.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.47368421052631576,
|
| 222 |
+
"grad_norm": 0.18434080604136077,
|
| 223 |
+
"learning_rate": 9.677655698572326e-06,
|
| 224 |
+
"loss": 0.2661,
|
| 225 |
+
"num_tokens": 11259192.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.49122807017543857,
|
| 230 |
+
"grad_norm": 0.16956692098933204,
|
| 231 |
+
"learning_rate": 9.645056439016827e-06,
|
| 232 |
+
"loss": 0.273,
|
| 233 |
+
"num_tokens": 11708724.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5087719298245614,
|
| 238 |
+
"grad_norm": 0.16434051233500432,
|
| 239 |
+
"learning_rate": 9.610954559391704e-06,
|
| 240 |
+
"loss": 0.2667,
|
| 241 |
+
"num_tokens": 12137403.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5263157894736842,
|
| 246 |
+
"grad_norm": 0.17669427582556774,
|
| 247 |
+
"learning_rate": 9.57536242193364e-06,
|
| 248 |
+
"loss": 0.2584,
|
| 249 |
+
"num_tokens": 12543239.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.543859649122807,
|
| 254 |
+
"grad_norm": 0.1652310917436867,
|
| 255 |
+
"learning_rate": 9.538292929111114e-06,
|
| 256 |
+
"loss": 0.2569,
|
| 257 |
+
"num_tokens": 12940013.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.5614035087719298,
|
| 262 |
+
"grad_norm": 0.15646296852545927,
|
| 263 |
+
"learning_rate": 9.499759518947156e-06,
|
| 264 |
+
"loss": 0.2607,
|
| 265 |
+
"num_tokens": 13409215.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.5789473684210527,
|
| 270 |
+
"grad_norm": 0.16249861759922887,
|
| 271 |
+
"learning_rate": 9.459776160147941e-06,
|
| 272 |
+
"loss": 0.2461,
|
| 273 |
+
"num_tokens": 13806115.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5964912280701754,
|
| 278 |
+
"grad_norm": 0.15613005334949157,
|
| 279 |
+
"learning_rate": 9.418357347038999e-06,
|
| 280 |
+
"loss": 0.2493,
|
| 281 |
+
"num_tokens": 14248072.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6140350877192983,
|
| 286 |
+
"grad_norm": 0.16063917924130028,
|
| 287 |
+
"learning_rate": 9.375518094310904e-06,
|
| 288 |
+
"loss": 0.255,
|
| 289 |
+
"num_tokens": 14680852.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.631578947368421,
|
| 294 |
+
"grad_norm": 0.15840497254274827,
|
| 295 |
+
"learning_rate": 9.331273931576306e-06,
|
| 296 |
+
"loss": 0.2459,
|
| 297 |
+
"num_tokens": 15109781.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.6491228070175439,
|
| 302 |
+
"grad_norm": 0.1549313386657812,
|
| 303 |
+
"learning_rate": 9.285640897740316e-06,
|
| 304 |
+
"loss": 0.2461,
|
| 305 |
+
"num_tokens": 15556489.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.6666666666666666,
|
| 310 |
+
"grad_norm": 0.15967707273841447,
|
| 311 |
+
"learning_rate": 9.238635535186247e-06,
|
| 312 |
+
"loss": 0.2358,
|
| 313 |
+
"num_tokens": 15975315.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.6842105263157895,
|
| 318 |
+
"grad_norm": 0.1664153879515682,
|
| 319 |
+
"learning_rate": 9.19027488377886e-06,
|
| 320 |
+
"loss": 0.2453,
|
| 321 |
+
"num_tokens": 16366263.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.7017543859649122,
|
| 326 |
+
"grad_norm": 0.16085937077964602,
|
| 327 |
+
"learning_rate": 9.140576474687263e-06,
|
| 328 |
+
"loss": 0.2339,
|
| 329 |
+
"num_tokens": 16780696.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.7192982456140351,
|
| 334 |
+
"grad_norm": 0.1525506357194124,
|
| 335 |
+
"learning_rate": 9.0895583240297e-06,
|
| 336 |
+
"loss": 0.2454,
|
| 337 |
+
"num_tokens": 17226365.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7368421052631579,
|
| 342 |
+
"grad_norm": 0.15414442592489289,
|
| 343 |
+
"learning_rate": 9.037238926342544e-06,
|
| 344 |
+
"loss": 0.2315,
|
| 345 |
+
"num_tokens": 17651462.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7543859649122807,
|
| 350 |
+
"grad_norm": 0.160113618784668,
|
| 351 |
+
"learning_rate": 8.983637247875872e-06,
|
| 352 |
+
"loss": 0.24,
|
| 353 |
+
"num_tokens": 18064676.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7719298245614035,
|
| 358 |
+
"grad_norm": 0.1592020616116995,
|
| 359 |
+
"learning_rate": 8.92877271971802e-06,
|
| 360 |
+
"loss": 0.236,
|
| 361 |
+
"num_tokens": 18474727.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.7894736842105263,
|
| 366 |
+
"grad_norm": 0.15245337800135356,
|
| 367 |
+
"learning_rate": 8.872665230751644e-06,
|
| 368 |
+
"loss": 0.2405,
|
| 369 |
+
"num_tokens": 18902046.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.8070175438596491,
|
| 374 |
+
"grad_norm": 0.20723449258057428,
|
| 375 |
+
"learning_rate": 8.815335120443822e-06,
|
| 376 |
+
"loss": 0.224,
|
| 377 |
+
"num_tokens": 19319711.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.8245614035087719,
|
| 382 |
+
"grad_norm": 0.1474862726874557,
|
| 383 |
+
"learning_rate": 8.756803171472817e-06,
|
| 384 |
+
"loss": 0.2412,
|
| 385 |
+
"num_tokens": 19757131.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.8421052631578947,
|
| 390 |
+
"grad_norm": 0.15052042969864995,
|
| 391 |
+
"learning_rate": 8.69709060219416e-06,
|
| 392 |
+
"loss": 0.2327,
|
| 393 |
+
"num_tokens": 20194869.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8596491228070176,
|
| 398 |
+
"grad_norm": 0.15385476085770403,
|
| 399 |
+
"learning_rate": 8.636219058948823e-06,
|
| 400 |
+
"loss": 0.2266,
|
| 401 |
+
"num_tokens": 20597224.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8771929824561403,
|
| 406 |
+
"grad_norm": 0.15228109362462297,
|
| 407 |
+
"learning_rate": 8.574210608216206e-06,
|
| 408 |
+
"loss": 0.239,
|
| 409 |
+
"num_tokens": 21031895.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.8947368421052632,
|
| 414 |
+
"grad_norm": 0.14813164351615135,
|
| 415 |
+
"learning_rate": 8.511087728614863e-06,
|
| 416 |
+
"loss": 0.2271,
|
| 417 |
+
"num_tokens": 21445108.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.9122807017543859,
|
| 422 |
+
"grad_norm": 0.14876791381975332,
|
| 423 |
+
"learning_rate": 8.446873302753783e-06,
|
| 424 |
+
"loss": 0.2277,
|
| 425 |
+
"num_tokens": 21886020.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.9298245614035088,
|
| 430 |
+
"grad_norm": 0.14949287901477407,
|
| 431 |
+
"learning_rate": 8.381590608937251e-06,
|
| 432 |
+
"loss": 0.2395,
|
| 433 |
+
"num_tokens": 22300331.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9473684210526315,
|
| 438 |
+
"grad_norm": 0.1413875737037552,
|
| 439 |
+
"learning_rate": 8.315263312726248e-06,
|
| 440 |
+
"loss": 0.2321,
|
| 441 |
+
"num_tokens": 22731352.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.9649122807017544,
|
| 446 |
+
"grad_norm": 0.14923397563157811,
|
| 447 |
+
"learning_rate": 8.247915458359473e-06,
|
| 448 |
+
"loss": 0.2169,
|
| 449 |
+
"num_tokens": 23159887.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9824561403508771,
|
| 454 |
+
"grad_norm": 0.15363902325932008,
|
| 455 |
+
"learning_rate": 8.179571460037096e-06,
|
| 456 |
+
"loss": 0.2357,
|
| 457 |
+
"num_tokens": 23618660.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0,
|
| 462 |
+
"grad_norm": 0.14687085036662337,
|
| 463 |
+
"learning_rate": 8.110256093070393e-06,
|
| 464 |
+
"loss": 0.2334,
|
| 465 |
+
"num_tokens": 24039673.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.0175438596491229,
|
| 470 |
+
"grad_norm": 0.1476041876990848,
|
| 471 |
+
"learning_rate": 8.039994484900463e-06,
|
| 472 |
+
"loss": 0.2011,
|
| 473 |
+
"num_tokens": 24434236.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.0350877192982457,
|
| 478 |
+
"grad_norm": 0.1419449695352204,
|
| 479 |
+
"learning_rate": 7.968812105989316e-06,
|
| 480 |
+
"loss": 0.2114,
|
| 481 |
+
"num_tokens": 24853504.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.0526315789473684,
|
| 486 |
+
"grad_norm": 0.15337353318491537,
|
| 487 |
+
"learning_rate": 7.896734760586599e-06,
|
| 488 |
+
"loss": 0.2052,
|
| 489 |
+
"num_tokens": 25255898.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.0701754385964912,
|
| 494 |
+
"grad_norm": 0.14113455068915454,
|
| 495 |
+
"learning_rate": 7.82378857737533e-06,
|
| 496 |
+
"loss": 0.2098,
|
| 497 |
+
"num_tokens": 25667644.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.087719298245614,
|
| 502 |
+
"grad_norm": 0.14898616979585055,
|
| 503 |
+
"learning_rate": 7.75e-06,
|
| 504 |
+
"loss": 0.2041,
|
| 505 |
+
"num_tokens": 26083880.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1052631578947367,
|
| 510 |
+
"grad_norm": 0.15200676955309492,
|
| 511 |
+
"learning_rate": 7.675395777480538e-06,
|
| 512 |
+
"loss": 0.1911,
|
| 513 |
+
"num_tokens": 26465737.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.1228070175438596,
|
| 518 |
+
"grad_norm": 0.15217717203165435,
|
| 519 |
+
"learning_rate": 7.600002954515532e-06,
|
| 520 |
+
"loss": 0.2113,
|
| 521 |
+
"num_tokens": 26905038.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.1403508771929824,
|
| 526 |
+
"grad_norm": 0.1392806691058708,
|
| 527 |
+
"learning_rate": 7.523848861678297e-06,
|
| 528 |
+
"loss": 0.1981,
|
| 529 |
+
"num_tokens": 27327803.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.1578947368421053,
|
| 534 |
+
"grad_norm": 0.14823210297550762,
|
| 535 |
+
"learning_rate": 7.446961105509289e-06,
|
| 536 |
+
"loss": 0.199,
|
| 537 |
+
"num_tokens": 27743615.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.1754385964912282,
|
| 542 |
+
"grad_norm": 0.15025342094871685,
|
| 543 |
+
"learning_rate": 7.36936755850849e-06,
|
| 544 |
+
"loss": 0.2035,
|
| 545 |
+
"num_tokens": 28159990.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.1929824561403508,
|
| 550 |
+
"grad_norm": 0.1424694767142918,
|
| 551 |
+
"learning_rate": 7.2910963490313815e-06,
|
| 552 |
+
"loss": 0.1997,
|
| 553 |
+
"num_tokens": 28556831.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.2105263157894737,
|
| 558 |
+
"grad_norm": 0.14322092181407153,
|
| 559 |
+
"learning_rate": 7.212175851092154e-06,
|
| 560 |
+
"loss": 0.1961,
|
| 561 |
+
"num_tokens": 28995194.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2280701754385965,
|
| 566 |
+
"grad_norm": 0.1526511754370368,
|
| 567 |
+
"learning_rate": 7.132634674077884e-06,
|
| 568 |
+
"loss": 0.1921,
|
| 569 |
+
"num_tokens": 29410916.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.2456140350877192,
|
| 574 |
+
"grad_norm": 0.139735447301268,
|
| 575 |
+
"learning_rate": 7.052501652377368e-06,
|
| 576 |
+
"loss": 0.2063,
|
| 577 |
+
"num_tokens": 29913120.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.263157894736842,
|
| 582 |
+
"grad_norm": 0.14344116097027,
|
| 583 |
+
"learning_rate": 6.971805834928399e-06,
|
| 584 |
+
"loss": 0.2027,
|
| 585 |
+
"num_tokens": 30351179.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.280701754385965,
|
| 590 |
+
"grad_norm": 0.1426174151835526,
|
| 591 |
+
"learning_rate": 6.890576474687264e-06,
|
| 592 |
+
"loss": 0.2064,
|
| 593 |
+
"num_tokens": 30791604.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.2982456140350878,
|
| 598 |
+
"grad_norm": 0.14994921794042249,
|
| 599 |
+
"learning_rate": 6.808843018024296e-06,
|
| 600 |
+
"loss": 0.2065,
|
| 601 |
+
"num_tokens": 31261315.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.3157894736842106,
|
| 606 |
+
"grad_norm": 0.15092392748993957,
|
| 607 |
+
"learning_rate": 6.726635094049291e-06,
|
| 608 |
+
"loss": 0.1908,
|
| 609 |
+
"num_tokens": 31659426.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.3333333333333333,
|
| 614 |
+
"grad_norm": 0.14611148416178402,
|
| 615 |
+
"learning_rate": 6.643982503870693e-06,
|
| 616 |
+
"loss": 0.2051,
|
| 617 |
+
"num_tokens": 32057379.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.3508771929824561,
|
| 622 |
+
"grad_norm": 0.1427497694651295,
|
| 623 |
+
"learning_rate": 6.560915209792424e-06,
|
| 624 |
+
"loss": 0.1992,
|
| 625 |
+
"num_tokens": 32476948.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.368421052631579,
|
| 630 |
+
"grad_norm": 0.14625754427445514,
|
| 631 |
+
"learning_rate": 6.477463324452286e-06,
|
| 632 |
+
"loss": 0.1966,
|
| 633 |
+
"num_tokens": 32880627.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.3859649122807016,
|
| 638 |
+
"grad_norm": 0.14428604329114683,
|
| 639 |
+
"learning_rate": 6.393657099905854e-06,
|
| 640 |
+
"loss": 0.2,
|
| 641 |
+
"num_tokens": 33298268.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.4035087719298245,
|
| 646 |
+
"grad_norm": 0.14115165460163148,
|
| 647 |
+
"learning_rate": 6.309526916659843e-06,
|
| 648 |
+
"loss": 0.1961,
|
| 649 |
+
"num_tokens": 33735278.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.4210526315789473,
|
| 654 |
+
"grad_norm": 0.14007382911380342,
|
| 655 |
+
"learning_rate": 6.225103272658889e-06,
|
| 656 |
+
"loss": 0.199,
|
| 657 |
+
"num_tokens": 34180174.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.4385964912280702,
|
| 662 |
+
"grad_norm": 0.1464893959125568,
|
| 663 |
+
"learning_rate": 6.140416772229785e-06,
|
| 664 |
+
"loss": 0.1996,
|
| 665 |
+
"num_tokens": 34600325.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.456140350877193,
|
| 670 |
+
"grad_norm": 0.14708924135818197,
|
| 671 |
+
"learning_rate": 6.0554981149871276e-06,
|
| 672 |
+
"loss": 0.1978,
|
| 673 |
+
"num_tokens": 35028867.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4736842105263157,
|
| 678 |
+
"grad_norm": 0.15137327410210355,
|
| 679 |
+
"learning_rate": 5.970378084704441e-06,
|
| 680 |
+
"loss": 0.1971,
|
| 681 |
+
"num_tokens": 35465932.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4912280701754386,
|
| 686 |
+
"grad_norm": 0.14187565136169733,
|
| 687 |
+
"learning_rate": 5.88508753815478e-06,
|
| 688 |
+
"loss": 0.1922,
|
| 689 |
+
"num_tokens": 35857083.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.5087719298245614,
|
| 694 |
+
"grad_norm": 0.14750567085422958,
|
| 695 |
+
"learning_rate": 5.799657393924869e-06,
|
| 696 |
+
"loss": 0.1886,
|
| 697 |
+
"num_tokens": 36243816.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.526315789473684,
|
| 702 |
+
"grad_norm": 0.13584876516210329,
|
| 703 |
+
"learning_rate": 5.714118621206843e-06,
|
| 704 |
+
"loss": 0.1949,
|
| 705 |
+
"num_tokens": 36682515.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.543859649122807,
|
| 710 |
+
"grad_norm": 0.13138592337104565,
|
| 711 |
+
"learning_rate": 5.6285022285716325e-06,
|
| 712 |
+
"loss": 0.1848,
|
| 713 |
+
"num_tokens": 37108482.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.5614035087719298,
|
| 718 |
+
"grad_norm": 0.14022318239136972,
|
| 719 |
+
"learning_rate": 5.542839252728096e-06,
|
| 720 |
+
"loss": 0.1986,
|
| 721 |
+
"num_tokens": 37546779.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.5789473684210527,
|
| 726 |
+
"grad_norm": 0.14886854943483496,
|
| 727 |
+
"learning_rate": 5.457160747271906e-06,
|
| 728 |
+
"loss": 0.2025,
|
| 729 |
+
"num_tokens": 37965357.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5964912280701755,
|
| 734 |
+
"grad_norm": 0.14038303393485826,
|
| 735 |
+
"learning_rate": 5.371497771428368e-06,
|
| 736 |
+
"loss": 0.1975,
|
| 737 |
+
"num_tokens": 38406113.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6140350877192984,
|
| 742 |
+
"grad_norm": 0.14458491708947513,
|
| 743 |
+
"learning_rate": 5.2858813787931605e-06,
|
| 744 |
+
"loss": 0.1872,
|
| 745 |
+
"num_tokens": 38800413.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.631578947368421,
|
| 750 |
+
"grad_norm": 0.1480350806263145,
|
| 751 |
+
"learning_rate": 5.2003426060751324e-06,
|
| 752 |
+
"loss": 0.1968,
|
| 753 |
+
"num_tokens": 39200782.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.6491228070175439,
|
| 758 |
+
"grad_norm": 0.13730868120439885,
|
| 759 |
+
"learning_rate": 5.114912461845223e-06,
|
| 760 |
+
"loss": 0.2098,
|
| 761 |
+
"num_tokens": 39666940.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.6666666666666665,
|
| 766 |
+
"grad_norm": 0.13357583490843425,
|
| 767 |
+
"learning_rate": 5.02962191529556e-06,
|
| 768 |
+
"loss": 0.2005,
|
| 769 |
+
"num_tokens": 40103554.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.6842105263157894,
|
| 774 |
+
"grad_norm": 0.13277577033293314,
|
| 775 |
+
"learning_rate": 4.944501885012875e-06,
|
| 776 |
+
"loss": 0.1894,
|
| 777 |
+
"num_tokens": 40523764.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.7017543859649122,
|
| 782 |
+
"grad_norm": 0.1445531104714593,
|
| 783 |
+
"learning_rate": 4.859583227770218e-06,
|
| 784 |
+
"loss": 0.1966,
|
| 785 |
+
"num_tokens": 40923093.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.719298245614035,
|
| 790 |
+
"grad_norm": 0.1346892995124459,
|
| 791 |
+
"learning_rate": 4.774896727341113e-06,
|
| 792 |
+
"loss": 0.2085,
|
| 793 |
+
"num_tokens": 41388977.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.736842105263158,
|
| 798 |
+
"grad_norm": 0.13950660376280916,
|
| 799 |
+
"learning_rate": 4.6904730833401575e-06,
|
| 800 |
+
"loss": 0.1993,
|
| 801 |
+
"num_tokens": 41804049.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7543859649122808,
|
| 806 |
+
"grad_norm": 0.13419027046897863,
|
| 807 |
+
"learning_rate": 4.606342900094147e-06,
|
| 808 |
+
"loss": 0.197,
|
| 809 |
+
"num_tokens": 42212384.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.7719298245614035,
|
| 814 |
+
"grad_norm": 0.13471704895191902,
|
| 815 |
+
"learning_rate": 4.5225366755477165e-06,
|
| 816 |
+
"loss": 0.1991,
|
| 817 |
+
"num_tokens": 42626890.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.7894736842105263,
|
| 822 |
+
"grad_norm": 0.1370431857295371,
|
| 823 |
+
"learning_rate": 4.439084790207577e-06,
|
| 824 |
+
"loss": 0.181,
|
| 825 |
+
"num_tokens": 43045185.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.807017543859649,
|
| 830 |
+
"grad_norm": 0.13585245130540036,
|
| 831 |
+
"learning_rate": 4.35601749612931e-06,
|
| 832 |
+
"loss": 0.1926,
|
| 833 |
+
"num_tokens": 43469318.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.8245614035087718,
|
| 838 |
+
"grad_norm": 0.14177193142263728,
|
| 839 |
+
"learning_rate": 4.273364905950711e-06,
|
| 840 |
+
"loss": 0.1883,
|
| 841 |
+
"num_tokens": 43860735.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.8421052631578947,
|
| 846 |
+
"grad_norm": 0.13934124481189936,
|
| 847 |
+
"learning_rate": 4.191156981975704e-06,
|
| 848 |
+
"loss": 0.186,
|
| 849 |
+
"num_tokens": 44259177.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.8596491228070176,
|
| 854 |
+
"grad_norm": 0.13757581593440663,
|
| 855 |
+
"learning_rate": 4.109423525312738e-06,
|
| 856 |
+
"loss": 0.1813,
|
| 857 |
+
"num_tokens": 44652826.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.8771929824561404,
|
| 862 |
+
"grad_norm": 0.12994085331633362,
|
| 863 |
+
"learning_rate": 4.028194165071603e-06,
|
| 864 |
+
"loss": 0.2007,
|
| 865 |
+
"num_tokens": 45110456.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.8947368421052633,
|
| 870 |
+
"grad_norm": 0.1315821088883057,
|
| 871 |
+
"learning_rate": 3.9474983476226335e-06,
|
| 872 |
+
"loss": 0.1984,
|
| 873 |
+
"num_tokens": 45561128.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.912280701754386,
|
| 878 |
+
"grad_norm": 0.13466926193354203,
|
| 879 |
+
"learning_rate": 3.867365325922116e-06,
|
| 880 |
+
"loss": 0.195,
|
| 881 |
+
"num_tokens": 45999442.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.9298245614035088,
|
| 886 |
+
"grad_norm": 0.1407044279595099,
|
| 887 |
+
"learning_rate": 3.7878241489078473e-06,
|
| 888 |
+
"loss": 0.1957,
|
| 889 |
+
"num_tokens": 46405471.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.9473684210526314,
|
| 894 |
+
"grad_norm": 0.13869286010098864,
|
| 895 |
+
"learning_rate": 3.7089036509686216e-06,
|
| 896 |
+
"loss": 0.2096,
|
| 897 |
+
"num_tokens": 46837446.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.9649122807017543,
|
| 902 |
+
"grad_norm": 0.13744222256799704,
|
| 903 |
+
"learning_rate": 3.630632441491512e-06,
|
| 904 |
+
"loss": 0.1874,
|
| 905 |
+
"num_tokens": 47238683.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.9824561403508771,
|
| 910 |
+
"grad_norm": 0.13584540109090137,
|
| 911 |
+
"learning_rate": 3.5530388944907124e-06,
|
| 912 |
+
"loss": 0.1944,
|
| 913 |
+
"num_tokens": 47661310.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.0,
|
| 918 |
+
"grad_norm": 0.14078927259649465,
|
| 919 |
+
"learning_rate": 3.476151138321705e-06,
|
| 920 |
+
"loss": 0.1893,
|
| 921 |
+
"num_tokens": 48079346.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.017543859649123,
|
| 926 |
+
"grad_norm": 0.14801647762626233,
|
| 927 |
+
"learning_rate": 3.3999970454844688e-06,
|
| 928 |
+
"loss": 0.1833,
|
| 929 |
+
"num_tokens": 48481444.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.0350877192982457,
|
| 934 |
+
"grad_norm": 0.14207211024797958,
|
| 935 |
+
"learning_rate": 3.3246042225194626e-06,
|
| 936 |
+
"loss": 0.1972,
|
| 937 |
+
"num_tokens": 48904379.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.0526315789473686,
|
| 942 |
+
"grad_norm": 0.13459996651406178,
|
| 943 |
+
"learning_rate": 3.2500000000000015e-06,
|
| 944 |
+
"loss": 0.1734,
|
| 945 |
+
"num_tokens": 49314280.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.0701754385964914,
|
| 950 |
+
"grad_norm": 0.13420885166445595,
|
| 951 |
+
"learning_rate": 3.176211422624672e-06,
|
| 952 |
+
"loss": 0.1748,
|
| 953 |
+
"num_tokens": 49720807.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.087719298245614,
|
| 958 |
+
"grad_norm": 0.1396854400821284,
|
| 959 |
+
"learning_rate": 3.103265239413401e-06,
|
| 960 |
+
"loss": 0.1781,
|
| 961 |
+
"num_tokens": 50151950.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.1052631578947367,
|
| 966 |
+
"grad_norm": 0.14321980578287785,
|
| 967 |
+
"learning_rate": 3.0311878940106864e-06,
|
| 968 |
+
"loss": 0.182,
|
| 969 |
+
"num_tokens": 50574817.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.1228070175438596,
|
| 974 |
+
"grad_norm": 0.1402669344348115,
|
| 975 |
+
"learning_rate": 2.9600055150995397e-06,
|
| 976 |
+
"loss": 0.1804,
|
| 977 |
+
"num_tokens": 50991178.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1403508771929824,
|
| 982 |
+
"grad_norm": 0.14268249286817555,
|
| 983 |
+
"learning_rate": 2.889743906929609e-06,
|
| 984 |
+
"loss": 0.1701,
|
| 985 |
+
"num_tokens": 51370437.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.1578947368421053,
|
| 990 |
+
"grad_norm": 0.13769468594260603,
|
| 991 |
+
"learning_rate": 2.820428539962905e-06,
|
| 992 |
+
"loss": 0.1803,
|
| 993 |
+
"num_tokens": 51807382.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.175438596491228,
|
| 998 |
+
"grad_norm": 0.1418977810735795,
|
| 999 |
+
"learning_rate": 2.7520845416405285e-06,
|
| 1000 |
+
"loss": 0.1867,
|
| 1001 |
+
"num_tokens": 52214420.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.192982456140351,
|
| 1006 |
+
"grad_norm": 0.1357482680971467,
|
| 1007 |
+
"learning_rate": 2.6847366872737535e-06,
|
| 1008 |
+
"loss": 0.1855,
|
| 1009 |
+
"num_tokens": 52648228.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.2105263157894735,
|
| 1014 |
+
"grad_norm": 0.13758984714319883,
|
| 1015 |
+
"learning_rate": 2.618409391062751e-06,
|
| 1016 |
+
"loss": 0.1928,
|
| 1017 |
+
"num_tokens": 53085345.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.2280701754385963,
|
| 1022 |
+
"grad_norm": 0.13835249455110674,
|
| 1023 |
+
"learning_rate": 2.5531266972462176e-06,
|
| 1024 |
+
"loss": 0.1753,
|
| 1025 |
+
"num_tokens": 53493140.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.245614035087719,
|
| 1030 |
+
"grad_norm": 0.13785872746102823,
|
| 1031 |
+
"learning_rate": 2.4889122713851397e-06,
|
| 1032 |
+
"loss": 0.1734,
|
| 1033 |
+
"num_tokens": 53922832.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.263157894736842,
|
| 1038 |
+
"grad_norm": 0.1369141853241696,
|
| 1039 |
+
"learning_rate": 2.425789391783796e-06,
|
| 1040 |
+
"loss": 0.1771,
|
| 1041 |
+
"num_tokens": 54319035.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.280701754385965,
|
| 1046 |
+
"grad_norm": 0.13274261857238875,
|
| 1047 |
+
"learning_rate": 2.36378094105118e-06,
|
| 1048 |
+
"loss": 0.1759,
|
| 1049 |
+
"num_tokens": 54754161.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.2982456140350878,
|
| 1054 |
+
"grad_norm": 0.13374187150373806,
|
| 1055 |
+
"learning_rate": 2.302909397805841e-06,
|
| 1056 |
+
"loss": 0.1757,
|
| 1057 |
+
"num_tokens": 55177972.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.3157894736842106,
|
| 1062 |
+
"grad_norm": 0.14056010545232225,
|
| 1063 |
+
"learning_rate": 2.2431968285271843e-06,
|
| 1064 |
+
"loss": 0.1762,
|
| 1065 |
+
"num_tokens": 55567532.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.3333333333333335,
|
| 1070 |
+
"grad_norm": 0.14440093167538778,
|
| 1071 |
+
"learning_rate": 2.1846648795561777e-06,
|
| 1072 |
+
"loss": 0.1789,
|
| 1073 |
+
"num_tokens": 55997257.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.3508771929824563,
|
| 1078 |
+
"grad_norm": 0.13209921359488944,
|
| 1079 |
+
"learning_rate": 2.1273347692483574e-06,
|
| 1080 |
+
"loss": 0.1683,
|
| 1081 |
+
"num_tokens": 56435780.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.3684210526315788,
|
| 1086 |
+
"grad_norm": 0.13075669290172312,
|
| 1087 |
+
"learning_rate": 2.071227280281982e-06,
|
| 1088 |
+
"loss": 0.1766,
|
| 1089 |
+
"num_tokens": 56880449.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.3859649122807016,
|
| 1094 |
+
"grad_norm": 0.15520159951824955,
|
| 1095 |
+
"learning_rate": 2.016362752124129e-06,
|
| 1096 |
+
"loss": 0.1766,
|
| 1097 |
+
"num_tokens": 57298925.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.4035087719298245,
|
| 1102 |
+
"grad_norm": 0.13674994090087955,
|
| 1103 |
+
"learning_rate": 1.9627610736574575e-06,
|
| 1104 |
+
"loss": 0.1689,
|
| 1105 |
+
"num_tokens": 57702294.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.4210526315789473,
|
| 1110 |
+
"grad_norm": 0.13321588166669115,
|
| 1111 |
+
"learning_rate": 1.9104416759703017e-06,
|
| 1112 |
+
"loss": 0.1758,
|
| 1113 |
+
"num_tokens": 58154418.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.43859649122807,
|
| 1118 |
+
"grad_norm": 0.13632315461262803,
|
| 1119 |
+
"learning_rate": 1.8594235253127373e-06,
|
| 1120 |
+
"loss": 0.1767,
|
| 1121 |
+
"num_tokens": 58579683.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.456140350877193,
|
| 1126 |
+
"grad_norm": 0.1288153252214618,
|
| 1127 |
+
"learning_rate": 1.8097251162211405e-06,
|
| 1128 |
+
"loss": 0.1811,
|
| 1129 |
+
"num_tokens": 59051562.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.473684210526316,
|
| 1134 |
+
"grad_norm": 0.12987465966750822,
|
| 1135 |
+
"learning_rate": 1.7613644648137543e-06,
|
| 1136 |
+
"loss": 0.1774,
|
| 1137 |
+
"num_tokens": 59501698.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.4912280701754383,
|
| 1142 |
+
"grad_norm": 0.1374425426257984,
|
| 1143 |
+
"learning_rate": 1.7143591022596846e-06,
|
| 1144 |
+
"loss": 0.1944,
|
| 1145 |
+
"num_tokens": 59955592.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.5087719298245617,
|
| 1150 |
+
"grad_norm": 0.13531966438989285,
|
| 1151 |
+
"learning_rate": 1.6687260684236943e-06,
|
| 1152 |
+
"loss": 0.1805,
|
| 1153 |
+
"num_tokens": 60381274.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.526315789473684,
|
| 1158 |
+
"grad_norm": 0.134925096600037,
|
| 1159 |
+
"learning_rate": 1.6244819056890975e-06,
|
| 1160 |
+
"loss": 0.171,
|
| 1161 |
+
"num_tokens": 60788438.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.543859649122807,
|
| 1166 |
+
"grad_norm": 0.1407719819848176,
|
| 1167 |
+
"learning_rate": 1.5816426529610035e-06,
|
| 1168 |
+
"loss": 0.1714,
|
| 1169 |
+
"num_tokens": 61184551.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.56140350877193,
|
| 1174 |
+
"grad_norm": 0.1359063010745857,
|
| 1175 |
+
"learning_rate": 1.5402238398520614e-06,
|
| 1176 |
+
"loss": 0.1758,
|
| 1177 |
+
"num_tokens": 61619839.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.5789473684210527,
|
| 1182 |
+
"grad_norm": 0.13246835060504009,
|
| 1183 |
+
"learning_rate": 1.5002404810528452e-06,
|
| 1184 |
+
"loss": 0.1739,
|
| 1185 |
+
"num_tokens": 62045889.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.5964912280701755,
|
| 1190 |
+
"grad_norm": 0.13964950522945552,
|
| 1191 |
+
"learning_rate": 1.4617070708888882e-06,
|
| 1192 |
+
"loss": 0.1718,
|
| 1193 |
+
"num_tokens": 62437900.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.6140350877192984,
|
| 1198 |
+
"grad_norm": 0.13372294299780066,
|
| 1199 |
+
"learning_rate": 1.4246375780663613e-06,
|
| 1200 |
+
"loss": 0.1661,
|
| 1201 |
+
"num_tokens": 62843119.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.6315789473684212,
|
| 1206 |
+
"grad_norm": 0.13805400712254826,
|
| 1207 |
+
"learning_rate": 1.389045440608296e-06,
|
| 1208 |
+
"loss": 0.1828,
|
| 1209 |
+
"num_tokens": 63262284.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.6491228070175437,
|
| 1214 |
+
"grad_norm": 0.13808339180910903,
|
| 1215 |
+
"learning_rate": 1.354943560983175e-06,
|
| 1216 |
+
"loss": 0.1803,
|
| 1217 |
+
"num_tokens": 63701914.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.6666666666666665,
|
| 1222 |
+
"grad_norm": 0.13165183261262675,
|
| 1223 |
+
"learning_rate": 1.3223443014276738e-06,
|
| 1224 |
+
"loss": 0.1774,
|
| 1225 |
+
"num_tokens": 64149759.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 2.6842105263157894,
|
| 1230 |
+
"grad_norm": 0.1319243140393186,
|
| 1231 |
+
"learning_rate": 1.2912594794652406e-06,
|
| 1232 |
+
"loss": 0.1799,
|
| 1233 |
+
"num_tokens": 64602514.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.7017543859649122,
|
| 1238 |
+
"grad_norm": 0.13538494698388223,
|
| 1239 |
+
"learning_rate": 1.2617003636221394e-06,
|
| 1240 |
+
"loss": 0.1694,
|
| 1241 |
+
"num_tokens": 64992832.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.719298245614035,
|
| 1246 |
+
"grad_norm": 0.13498616412912304,
|
| 1247 |
+
"learning_rate": 1.2336776693425028e-06,
|
| 1248 |
+
"loss": 0.1707,
|
| 1249 |
+
"num_tokens": 65389001.0,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.736842105263158,
|
| 1254 |
+
"grad_norm": 0.12924445948277097,
|
| 1255 |
+
"learning_rate": 1.2072015551038933e-06,
|
| 1256 |
+
"loss": 0.1692,
|
| 1257 |
+
"num_tokens": 65842297.0,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.754385964912281,
|
| 1262 |
+
"grad_norm": 0.13206490698518994,
|
| 1263 |
+
"learning_rate": 1.1822816187347625e-06,
|
| 1264 |
+
"loss": 0.1719,
|
| 1265 |
+
"num_tokens": 66254756.0,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.7719298245614032,
|
| 1270 |
+
"grad_norm": 0.13946311479316087,
|
| 1271 |
+
"learning_rate": 1.1589268939351499e-06,
|
| 1272 |
+
"loss": 0.1824,
|
| 1273 |
+
"num_tokens": 66653349.0,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.7894736842105265,
|
| 1278 |
+
"grad_norm": 0.12958606648427337,
|
| 1279 |
+
"learning_rate": 1.1371458470018896e-06,
|
| 1280 |
+
"loss": 0.1758,
|
| 1281 |
+
"num_tokens": 67089072.0,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 2.807017543859649,
|
| 1286 |
+
"grad_norm": 0.12836201287391627,
|
| 1287 |
+
"learning_rate": 1.1169463737594995e-06,
|
| 1288 |
+
"loss": 0.1725,
|
| 1289 |
+
"num_tokens": 67530318.0,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.824561403508772,
|
| 1294 |
+
"grad_norm": 0.1312877766550337,
|
| 1295 |
+
"learning_rate": 1.0983357966978747e-06,
|
| 1296 |
+
"loss": 0.17,
|
| 1297 |
+
"num_tokens": 67943670.0,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.8421052631578947,
|
| 1302 |
+
"grad_norm": 0.1292736067143446,
|
| 1303 |
+
"learning_rate": 1.0813208623178199e-06,
|
| 1304 |
+
"loss": 0.1759,
|
| 1305 |
+
"num_tokens": 68380170.0,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.8596491228070176,
|
| 1310 |
+
"grad_norm": 0.13227684289793154,
|
| 1311 |
+
"learning_rate": 1.0659077386853817e-06,
|
| 1312 |
+
"loss": 0.1719,
|
| 1313 |
+
"num_tokens": 68808114.0,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.8771929824561404,
|
| 1318 |
+
"grad_norm": 0.13694616326909123,
|
| 1319 |
+
"learning_rate": 1.0521020131958692e-06,
|
| 1320 |
+
"loss": 0.168,
|
| 1321 |
+
"num_tokens": 69191512.0,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.8947368421052633,
|
| 1326 |
+
"grad_norm": 0.135480809490847,
|
| 1327 |
+
"learning_rate": 1.0399086905483752e-06,
|
| 1328 |
+
"loss": 0.1659,
|
| 1329 |
+
"num_tokens": 69582710.0,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.912280701754386,
|
| 1334 |
+
"grad_norm": 0.13656650923592858,
|
| 1335 |
+
"learning_rate": 1.0293321909315242e-06,
|
| 1336 |
+
"loss": 0.1764,
|
| 1337 |
+
"num_tokens": 69995390.0,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.9298245614035086,
|
| 1342 |
+
"grad_norm": 0.13037307085567856,
|
| 1343 |
+
"learning_rate": 1.0203763484211196e-06,
|
| 1344 |
+
"loss": 0.1737,
|
| 1345 |
+
"num_tokens": 70418613.0,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.9473684210526314,
|
| 1350 |
+
"grad_norm": 0.13386161162103719,
|
| 1351 |
+
"learning_rate": 1.0130444095902514e-06,
|
| 1352 |
+
"loss": 0.1731,
|
| 1353 |
+
"num_tokens": 70848952.0,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.9649122807017543,
|
| 1358 |
+
"grad_norm": 0.13477603098195323,
|
| 1359 |
+
"learning_rate": 1.0073390323323897e-06,
|
| 1360 |
+
"loss": 0.1859,
|
| 1361 |
+
"num_tokens": 71284648.0,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.982456140350877,
|
| 1366 |
+
"grad_norm": 0.13335006132129937,
|
| 1367 |
+
"learning_rate": 1.0032622848978689e-06,
|
| 1368 |
+
"loss": 0.1727,
|
| 1369 |
+
"num_tokens": 71712021.0,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.0,
|
| 1374 |
+
"grad_norm": 0.13952787638079295,
|
| 1375 |
+
"learning_rate": 1.000815645144134e-06,
|
| 1376 |
+
"loss": 0.1803,
|
| 1377 |
+
"num_tokens": 72119019.0,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 3.0,
|
| 1382 |
+
"step": 171,
|
| 1383 |
+
"total_flos": 2.3168881532705178e+17,
|
| 1384 |
+
"train_loss": 0.25350178002614027,
|
| 1385 |
+
"train_runtime": 2712.8956,
|
| 1386 |
+
"train_samples_per_second": 8.068,
|
| 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": 2.3168881532705178e+17,
|
| 1408 |
+
"train_batch_size": 8,
|
| 1409 |
+
"trial_name": null,
|
| 1410 |
+
"trial_params": null
|
| 1411 |
+
}
|