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 +1483 -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-v5
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for text2sql-sft-v5
|
| 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-v5", 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/pcfkkc63)
|
| 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": 2.097365527654564e+17,
|
| 3 |
+
"train_loss": 0.2700612629453341,
|
| 4 |
+
"train_runtime": 2536.3753,
|
| 5 |
+
"train_samples": 7644,
|
| 6 |
+
"train_samples_per_second": 9.041,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 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": 2.097365527654564e+17,
|
| 3 |
+
"train_loss": 0.2700612629453341,
|
| 4 |
+
"train_runtime": 2536.3753,
|
| 5 |
+
"train_samples": 7644,
|
| 6 |
+
"train_samples_per_second": 9.041,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 180,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016666666666666666,
|
| 14 |
+
"grad_norm": 4.307253357056896,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.3486,
|
| 17 |
+
"num_tokens": 386694.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.03333333333333333,
|
| 22 |
+
"grad_norm": 4.360320258925879,
|
| 23 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 24 |
+
"loss": 1.355,
|
| 25 |
+
"num_tokens": 763332.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"grad_norm": 4.345332014222828,
|
| 31 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 32 |
+
"loss": 1.3444,
|
| 33 |
+
"num_tokens": 1139716.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.06666666666666667,
|
| 38 |
+
"grad_norm": 3.628391365691474,
|
| 39 |
+
"learning_rate": 5e-06,
|
| 40 |
+
"loss": 1.2589,
|
| 41 |
+
"num_tokens": 1538652.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.08333333333333333,
|
| 46 |
+
"grad_norm": 2.803675884185387,
|
| 47 |
+
"learning_rate": 6.666666666666667e-06,
|
| 48 |
+
"loss": 1.1789,
|
| 49 |
+
"num_tokens": 1906687.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.1,
|
| 54 |
+
"grad_norm": 1.6755164899194928,
|
| 55 |
+
"learning_rate": 8.333333333333334e-06,
|
| 56 |
+
"loss": 0.9559,
|
| 57 |
+
"num_tokens": 2291916.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11666666666666667,
|
| 62 |
+
"grad_norm": 1.6023439747170054,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.9039,
|
| 65 |
+
"num_tokens": 2681760.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.13333333333333333,
|
| 70 |
+
"grad_norm": 2.621524079150046,
|
| 71 |
+
"learning_rate": 9.999266547540887e-06,
|
| 72 |
+
"loss": 0.7046,
|
| 73 |
+
"num_tokens": 3083275.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"grad_norm": 1.8310985368282848,
|
| 79 |
+
"learning_rate": 9.997066429253546e-06,
|
| 80 |
+
"loss": 0.67,
|
| 81 |
+
"num_tokens": 3492333.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.16666666666666666,
|
| 86 |
+
"grad_norm": 1.588733471297654,
|
| 87 |
+
"learning_rate": 9.993400362330058e-06,
|
| 88 |
+
"loss": 0.5748,
|
| 89 |
+
"num_tokens": 3874036.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.18333333333333332,
|
| 94 |
+
"grad_norm": 0.8180449520265045,
|
| 95 |
+
"learning_rate": 9.988269541830775e-06,
|
| 96 |
+
"loss": 0.4871,
|
| 97 |
+
"num_tokens": 4288115.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.2,
|
| 102 |
+
"grad_norm": 0.752923941500878,
|
| 103 |
+
"learning_rate": 9.98167564029477e-06,
|
| 104 |
+
"loss": 0.4292,
|
| 105 |
+
"num_tokens": 4688262.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.21666666666666667,
|
| 110 |
+
"grad_norm": 0.372241919164793,
|
| 111 |
+
"learning_rate": 9.97362080719462e-06,
|
| 112 |
+
"loss": 0.4056,
|
| 113 |
+
"num_tokens": 5091722.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.23333333333333334,
|
| 118 |
+
"grad_norm": 0.33142327142903066,
|
| 119 |
+
"learning_rate": 9.96410766823572e-06,
|
| 120 |
+
"loss": 0.3793,
|
| 121 |
+
"num_tokens": 5471288.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25,
|
| 126 |
+
"grad_norm": 0.333034056817446,
|
| 127 |
+
"learning_rate": 9.95313932450037e-06,
|
| 128 |
+
"loss": 0.3692,
|
| 129 |
+
"num_tokens": 5889666.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.26666666666666666,
|
| 134 |
+
"grad_norm": 0.27138429604415093,
|
| 135 |
+
"learning_rate": 9.94071935143687e-06,
|
| 136 |
+
"loss": 0.3756,
|
| 137 |
+
"num_tokens": 6300311.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.2833333333333333,
|
| 142 |
+
"grad_norm": 0.25396556914093327,
|
| 143 |
+
"learning_rate": 9.926851797694012e-06,
|
| 144 |
+
"loss": 0.3632,
|
| 145 |
+
"num_tokens": 6715155.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.3,
|
| 150 |
+
"grad_norm": 0.2500253644023207,
|
| 151 |
+
"learning_rate": 9.911541183801312e-06,
|
| 152 |
+
"loss": 0.3374,
|
| 153 |
+
"num_tokens": 7135255.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.31666666666666665,
|
| 158 |
+
"grad_norm": 0.25089233453514137,
|
| 159 |
+
"learning_rate": 9.89479250069539e-06,
|
| 160 |
+
"loss": 0.321,
|
| 161 |
+
"num_tokens": 7508317.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.3333333333333333,
|
| 166 |
+
"grad_norm": 0.2482917013855084,
|
| 167 |
+
"learning_rate": 9.876611208093055e-06,
|
| 168 |
+
"loss": 0.3146,
|
| 169 |
+
"num_tokens": 7875185.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.35,
|
| 174 |
+
"grad_norm": 0.2170036674475473,
|
| 175 |
+
"learning_rate": 9.857003232711535e-06,
|
| 176 |
+
"loss": 0.3257,
|
| 177 |
+
"num_tokens": 8278743.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.36666666666666664,
|
| 182 |
+
"grad_norm": 0.21290870255144237,
|
| 183 |
+
"learning_rate": 9.835974966336504e-06,
|
| 184 |
+
"loss": 0.3043,
|
| 185 |
+
"num_tokens": 8653905.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.38333333333333336,
|
| 190 |
+
"grad_norm": 0.20612281123293255,
|
| 191 |
+
"learning_rate": 9.813533263738486e-06,
|
| 192 |
+
"loss": 0.3085,
|
| 193 |
+
"num_tokens": 9043909.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.4,
|
| 198 |
+
"grad_norm": 0.21450894869657447,
|
| 199 |
+
"learning_rate": 9.789685440438353e-06,
|
| 200 |
+
"loss": 0.3072,
|
| 201 |
+
"num_tokens": 9435837.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.4166666666666667,
|
| 206 |
+
"grad_norm": 0.20171788675549032,
|
| 207 |
+
"learning_rate": 9.764439270322612e-06,
|
| 208 |
+
"loss": 0.3075,
|
| 209 |
+
"num_tokens": 9830459.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.43333333333333335,
|
| 214 |
+
"grad_norm": 0.19965322014196185,
|
| 215 |
+
"learning_rate": 9.737802983109287e-06,
|
| 216 |
+
"loss": 0.307,
|
| 217 |
+
"num_tokens": 10213657.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.45,
|
| 222 |
+
"grad_norm": 0.1851962358951018,
|
| 223 |
+
"learning_rate": 9.709785261665205e-06,
|
| 224 |
+
"loss": 0.3011,
|
| 225 |
+
"num_tokens": 10635429.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4666666666666667,
|
| 230 |
+
"grad_norm": 0.18835954292626045,
|
| 231 |
+
"learning_rate": 9.680395239175563e-06,
|
| 232 |
+
"loss": 0.2958,
|
| 233 |
+
"num_tokens": 11041197.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.48333333333333334,
|
| 238 |
+
"grad_norm": 0.1810203496485964,
|
| 239 |
+
"learning_rate": 9.6496424961667e-06,
|
| 240 |
+
"loss": 0.289,
|
| 241 |
+
"num_tokens": 11456416.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5,
|
| 246 |
+
"grad_norm": 0.18244709386338018,
|
| 247 |
+
"learning_rate": 9.617537057383055e-06,
|
| 248 |
+
"loss": 0.2676,
|
| 249 |
+
"num_tokens": 11819187.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5166666666666667,
|
| 254 |
+
"grad_norm": 0.17564449531170986,
|
| 255 |
+
"learning_rate": 9.584089388519307e-06,
|
| 256 |
+
"loss": 0.2939,
|
| 257 |
+
"num_tokens": 12245580.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.5333333333333333,
|
| 262 |
+
"grad_norm": 0.17602330940765054,
|
| 263 |
+
"learning_rate": 9.549310392808782e-06,
|
| 264 |
+
"loss": 0.2908,
|
| 265 |
+
"num_tokens": 12656812.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.55,
|
| 270 |
+
"grad_norm": 0.17341734231138603,
|
| 271 |
+
"learning_rate": 9.51321140746922e-06,
|
| 272 |
+
"loss": 0.2693,
|
| 273 |
+
"num_tokens": 13051662.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5666666666666667,
|
| 278 |
+
"grad_norm": 0.17642947100637568,
|
| 279 |
+
"learning_rate": 9.475804200007104e-06,
|
| 280 |
+
"loss": 0.2844,
|
| 281 |
+
"num_tokens": 13460138.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5833333333333334,
|
| 286 |
+
"grad_norm": 0.18195529537136276,
|
| 287 |
+
"learning_rate": 9.437100964381674e-06,
|
| 288 |
+
"loss": 0.2562,
|
| 289 |
+
"num_tokens": 13839611.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6,
|
| 294 |
+
"grad_norm": 0.17156360193212303,
|
| 295 |
+
"learning_rate": 9.397114317029975e-06,
|
| 296 |
+
"loss": 0.2791,
|
| 297 |
+
"num_tokens": 14235849.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.6166666666666667,
|
| 302 |
+
"grad_norm": 0.16517378951073838,
|
| 303 |
+
"learning_rate": 9.355857292754152e-06,
|
| 304 |
+
"loss": 0.2574,
|
| 305 |
+
"num_tokens": 14628658.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.6333333333333333,
|
| 310 |
+
"grad_norm": 0.16623649868248883,
|
| 311 |
+
"learning_rate": 9.31334334047239e-06,
|
| 312 |
+
"loss": 0.258,
|
| 313 |
+
"num_tokens": 15022722.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.65,
|
| 318 |
+
"grad_norm": 0.16536066104473388,
|
| 319 |
+
"learning_rate": 9.269586318834841e-06,
|
| 320 |
+
"loss": 0.2621,
|
| 321 |
+
"num_tokens": 15412919.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.6666666666666666,
|
| 326 |
+
"grad_norm": 0.16136165971570182,
|
| 327 |
+
"learning_rate": 9.224600491706009e-06,
|
| 328 |
+
"loss": 0.2578,
|
| 329 |
+
"num_tokens": 15808067.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.6833333333333333,
|
| 334 |
+
"grad_norm": 0.16817050304190198,
|
| 335 |
+
"learning_rate": 9.178400523515013e-06,
|
| 336 |
+
"loss": 0.2551,
|
| 337 |
+
"num_tokens": 16216305.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7,
|
| 342 |
+
"grad_norm": 0.16231582842289252,
|
| 343 |
+
"learning_rate": 9.131001474475318e-06,
|
| 344 |
+
"loss": 0.2522,
|
| 345 |
+
"num_tokens": 16614956.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7166666666666667,
|
| 350 |
+
"grad_norm": 0.16568222727770732,
|
| 351 |
+
"learning_rate": 9.082418795675397e-06,
|
| 352 |
+
"loss": 0.2712,
|
| 353 |
+
"num_tokens": 17017704.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7333333333333333,
|
| 358 |
+
"grad_norm": 0.1655911348621601,
|
| 359 |
+
"learning_rate": 9.032668324042027e-06,
|
| 360 |
+
"loss": 0.251,
|
| 361 |
+
"num_tokens": 17417441.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.75,
|
| 366 |
+
"grad_norm": 0.1709011568135344,
|
| 367 |
+
"learning_rate": 8.981766277177764e-06,
|
| 368 |
+
"loss": 0.2613,
|
| 369 |
+
"num_tokens": 17836960.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.7666666666666667,
|
| 374 |
+
"grad_norm": 0.15724793095686002,
|
| 375 |
+
"learning_rate": 8.929729248074364e-06,
|
| 376 |
+
"loss": 0.2515,
|
| 377 |
+
"num_tokens": 18229148.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.7833333333333333,
|
| 382 |
+
"grad_norm": 0.1566336577784553,
|
| 383 |
+
"learning_rate": 8.87657419970381e-06,
|
| 384 |
+
"loss": 0.2386,
|
| 385 |
+
"num_tokens": 18629493.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.8,
|
| 390 |
+
"grad_norm": 0.156545141537549,
|
| 391 |
+
"learning_rate": 8.822318459488744e-06,
|
| 392 |
+
"loss": 0.2417,
|
| 393 |
+
"num_tokens": 19016532.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8166666666666667,
|
| 398 |
+
"grad_norm": 0.1682876261976619,
|
| 399 |
+
"learning_rate": 8.76697971365409e-06,
|
| 400 |
+
"loss": 0.25,
|
| 401 |
+
"num_tokens": 19420153.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8333333333333334,
|
| 406 |
+
"grad_norm": 0.15625972879253544,
|
| 407 |
+
"learning_rate": 8.71057600146172e-06,
|
| 408 |
+
"loss": 0.2477,
|
| 409 |
+
"num_tokens": 19799943.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.85,
|
| 414 |
+
"grad_norm": 0.15865902000624793,
|
| 415 |
+
"learning_rate": 8.65312570933004e-06,
|
| 416 |
+
"loss": 0.2535,
|
| 417 |
+
"num_tokens": 20211312.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.8666666666666667,
|
| 422 |
+
"grad_norm": 0.16243250536538423,
|
| 423 |
+
"learning_rate": 8.594647564840407e-06,
|
| 424 |
+
"loss": 0.2408,
|
| 425 |
+
"num_tokens": 20601752.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.8833333333333333,
|
| 430 |
+
"grad_norm": 0.16344681631488067,
|
| 431 |
+
"learning_rate": 8.535160630632312e-06,
|
| 432 |
+
"loss": 0.2571,
|
| 433 |
+
"num_tokens": 21018915.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9,
|
| 438 |
+
"grad_norm": 0.15878464256544747,
|
| 439 |
+
"learning_rate": 8.474684298189402e-06,
|
| 440 |
+
"loss": 0.2391,
|
| 441 |
+
"num_tokens": 21431176.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.9166666666666666,
|
| 446 |
+
"grad_norm": 0.16166754521090773,
|
| 447 |
+
"learning_rate": 8.413238281518225e-06,
|
| 448 |
+
"loss": 0.2349,
|
| 449 |
+
"num_tokens": 21813557.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9333333333333333,
|
| 454 |
+
"grad_norm": 0.1580424426734478,
|
| 455 |
+
"learning_rate": 8.350842610721908e-06,
|
| 456 |
+
"loss": 0.2374,
|
| 457 |
+
"num_tokens": 22194786.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.95,
|
| 462 |
+
"grad_norm": 0.16231313908249073,
|
| 463 |
+
"learning_rate": 8.287517625470754e-06,
|
| 464 |
+
"loss": 0.2255,
|
| 465 |
+
"num_tokens": 22567671.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.9666666666666667,
|
| 470 |
+
"grad_norm": 0.1557048649324866,
|
| 471 |
+
"learning_rate": 8.223283968371945e-06,
|
| 472 |
+
"loss": 0.2285,
|
| 473 |
+
"num_tokens": 22950599.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.9833333333333333,
|
| 478 |
+
"grad_norm": 0.1575134308288616,
|
| 479 |
+
"learning_rate": 8.158162578240479e-06,
|
| 480 |
+
"loss": 0.2322,
|
| 481 |
+
"num_tokens": 23343994.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.0,
|
| 486 |
+
"grad_norm": 0.1589382777080593,
|
| 487 |
+
"learning_rate": 8.09217468327358e-06,
|
| 488 |
+
"loss": 0.2304,
|
| 489 |
+
"num_tokens": 23741790.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.0166666666666666,
|
| 494 |
+
"grad_norm": 0.17102027510972934,
|
| 495 |
+
"learning_rate": 8.025341794130722e-06,
|
| 496 |
+
"loss": 0.2214,
|
| 497 |
+
"num_tokens": 24119088.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.0333333333333334,
|
| 502 |
+
"grad_norm": 0.15752410988362262,
|
| 503 |
+
"learning_rate": 7.957685696921637e-06,
|
| 504 |
+
"loss": 0.2346,
|
| 505 |
+
"num_tokens": 24525980.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.05,
|
| 510 |
+
"grad_norm": 0.16659406480726785,
|
| 511 |
+
"learning_rate": 7.889228446104492e-06,
|
| 512 |
+
"loss": 0.2215,
|
| 513 |
+
"num_tokens": 24923505.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0666666666666667,
|
| 518 |
+
"grad_norm": 0.17116959316903918,
|
| 519 |
+
"learning_rate": 7.8199923572966e-06,
|
| 520 |
+
"loss": 0.2417,
|
| 521 |
+
"num_tokens": 25357629.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.0833333333333333,
|
| 526 |
+
"grad_norm": 0.16260107516719483,
|
| 527 |
+
"learning_rate": 7.75e-06,
|
| 528 |
+
"loss": 0.2188,
|
| 529 |
+
"num_tokens": 25764560.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.1,
|
| 534 |
+
"grad_norm": 0.16804687462761858,
|
| 535 |
+
"learning_rate": 7.679274190244288e-06,
|
| 536 |
+
"loss": 0.2275,
|
| 537 |
+
"num_tokens": 26191304.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.1166666666666667,
|
| 542 |
+
"grad_norm": 0.16375887203042463,
|
| 543 |
+
"learning_rate": 7.607837983149057e-06,
|
| 544 |
+
"loss": 0.2138,
|
| 545 |
+
"num_tokens": 26571577.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.1333333333333333,
|
| 550 |
+
"grad_norm": 0.16023540725876087,
|
| 551 |
+
"learning_rate": 7.535714665408422e-06,
|
| 552 |
+
"loss": 0.2189,
|
| 553 |
+
"num_tokens": 26977355.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.15,
|
| 558 |
+
"grad_norm": 0.16856459027615175,
|
| 559 |
+
"learning_rate": 7.462927747700054e-06,
|
| 560 |
+
"loss": 0.2238,
|
| 561 |
+
"num_tokens": 27386485.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.1666666666666667,
|
| 566 |
+
"grad_norm": 0.15852201765248605,
|
| 567 |
+
"learning_rate": 7.389500957021192e-06,
|
| 568 |
+
"loss": 0.2232,
|
| 569 |
+
"num_tokens": 27796862.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1833333333333333,
|
| 574 |
+
"grad_norm": 0.1562037699869291,
|
| 575 |
+
"learning_rate": 7.31545822895414e-06,
|
| 576 |
+
"loss": 0.2062,
|
| 577 |
+
"num_tokens": 28173474.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.2,
|
| 582 |
+
"grad_norm": 0.16665718486974085,
|
| 583 |
+
"learning_rate": 7.240823699863777e-06,
|
| 584 |
+
"loss": 0.2063,
|
| 585 |
+
"num_tokens": 28525368.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.2166666666666668,
|
| 590 |
+
"grad_norm": 0.1583738566323773,
|
| 591 |
+
"learning_rate": 7.165621699029615e-06,
|
| 592 |
+
"loss": 0.2169,
|
| 593 |
+
"num_tokens": 28932221.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.2333333333333334,
|
| 598 |
+
"grad_norm": 0.15796778000095918,
|
| 599 |
+
"learning_rate": 7.0898767407149614e-06,
|
| 600 |
+
"loss": 0.2044,
|
| 601 |
+
"num_tokens": 29318980.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.25,
|
| 606 |
+
"grad_norm": 0.1536497599528125,
|
| 607 |
+
"learning_rate": 7.013613516175788e-06,
|
| 608 |
+
"loss": 0.1993,
|
| 609 |
+
"num_tokens": 29692583.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.2666666666666666,
|
| 614 |
+
"grad_norm": 0.1546218055415269,
|
| 615 |
+
"learning_rate": 6.93685688561191e-06,
|
| 616 |
+
"loss": 0.2051,
|
| 617 |
+
"num_tokens": 30070786.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.2833333333333332,
|
| 622 |
+
"grad_norm": 0.14705152616718795,
|
| 623 |
+
"learning_rate": 6.859631870063077e-06,
|
| 624 |
+
"loss": 0.2164,
|
| 625 |
+
"num_tokens": 30493521.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.3,
|
| 630 |
+
"grad_norm": 0.16343647621353785,
|
| 631 |
+
"learning_rate": 6.781963643252651e-06,
|
| 632 |
+
"loss": 0.2057,
|
| 633 |
+
"num_tokens": 30867731.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.3166666666666667,
|
| 638 |
+
"grad_norm": 0.16180013718977998,
|
| 639 |
+
"learning_rate": 6.703877523381495e-06,
|
| 640 |
+
"loss": 0.2151,
|
| 641 |
+
"num_tokens": 31278707.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.3333333333333333,
|
| 646 |
+
"grad_norm": 0.1554345859591716,
|
| 647 |
+
"learning_rate": 6.6253989648747845e-06,
|
| 648 |
+
"loss": 0.2204,
|
| 649 |
+
"num_tokens": 31686041.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.35,
|
| 654 |
+
"grad_norm": 0.158796010961646,
|
| 655 |
+
"learning_rate": 6.546553550084398e-06,
|
| 656 |
+
"loss": 0.2124,
|
| 657 |
+
"num_tokens": 32077613.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.3666666666666667,
|
| 662 |
+
"grad_norm": 0.15701623463042624,
|
| 663 |
+
"learning_rate": 6.46736698094961e-06,
|
| 664 |
+
"loss": 0.1948,
|
| 665 |
+
"num_tokens": 32436972.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.3833333333333333,
|
| 670 |
+
"grad_norm": 0.17232253970403388,
|
| 671 |
+
"learning_rate": 6.387865070618801e-06,
|
| 672 |
+
"loss": 0.2102,
|
| 673 |
+
"num_tokens": 32820896.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4,
|
| 678 |
+
"grad_norm": 0.15205370063709056,
|
| 679 |
+
"learning_rate": 6.308073735034923e-06,
|
| 680 |
+
"loss": 0.2145,
|
| 681 |
+
"num_tokens": 33232148.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4166666666666667,
|
| 686 |
+
"grad_norm": 0.16615604361419675,
|
| 687 |
+
"learning_rate": 6.228018984487443e-06,
|
| 688 |
+
"loss": 0.2097,
|
| 689 |
+
"num_tokens": 33617847.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.4333333333333333,
|
| 694 |
+
"grad_norm": 0.15608157931237884,
|
| 695 |
+
"learning_rate": 6.147726915133536e-06,
|
| 696 |
+
"loss": 0.2079,
|
| 697 |
+
"num_tokens": 34013743.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.45,
|
| 702 |
+
"grad_norm": 0.1533815994944839,
|
| 703 |
+
"learning_rate": 6.067223700491303e-06,
|
| 704 |
+
"loss": 0.2234,
|
| 705 |
+
"num_tokens": 34426281.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.4666666666666668,
|
| 710 |
+
"grad_norm": 0.16341622285747343,
|
| 711 |
+
"learning_rate": 5.986535582907739e-06,
|
| 712 |
+
"loss": 0.2082,
|
| 713 |
+
"num_tokens": 34820833.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.4833333333333334,
|
| 718 |
+
"grad_norm": 0.1501827141164398,
|
| 719 |
+
"learning_rate": 5.905688865004295e-06,
|
| 720 |
+
"loss": 0.2047,
|
| 721 |
+
"num_tokens": 35204582.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.5,
|
| 726 |
+
"grad_norm": 0.17073241665358838,
|
| 727 |
+
"learning_rate": 5.8247099011027745e-06,
|
| 728 |
+
"loss": 0.1981,
|
| 729 |
+
"num_tokens": 35593390.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5166666666666666,
|
| 734 |
+
"grad_norm": 0.155687295095261,
|
| 735 |
+
"learning_rate": 5.74362508863438e-06,
|
| 736 |
+
"loss": 0.2198,
|
| 737 |
+
"num_tokens": 36016331.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.5333333333333332,
|
| 742 |
+
"grad_norm": 0.16109998374651785,
|
| 743 |
+
"learning_rate": 5.662460859534714e-06,
|
| 744 |
+
"loss": 0.2023,
|
| 745 |
+
"num_tokens": 36413156.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.55,
|
| 750 |
+
"grad_norm": 0.16131117005573636,
|
| 751 |
+
"learning_rate": 5.581243671627522e-06,
|
| 752 |
+
"loss": 0.2171,
|
| 753 |
+
"num_tokens": 36798646.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.5666666666666667,
|
| 758 |
+
"grad_norm": 0.15364974978248802,
|
| 759 |
+
"learning_rate": 5.500000000000001e-06,
|
| 760 |
+
"loss": 0.2015,
|
| 761 |
+
"num_tokens": 37163989.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.5833333333333335,
|
| 766 |
+
"grad_norm": 0.15965272681106013,
|
| 767 |
+
"learning_rate": 5.418756328372477e-06,
|
| 768 |
+
"loss": 0.203,
|
| 769 |
+
"num_tokens": 37561194.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.6,
|
| 774 |
+
"grad_norm": 0.16238266195932857,
|
| 775 |
+
"learning_rate": 5.337539140465287e-06,
|
| 776 |
+
"loss": 0.2065,
|
| 777 |
+
"num_tokens": 37949527.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.6166666666666667,
|
| 782 |
+
"grad_norm": 0.15421187662404837,
|
| 783 |
+
"learning_rate": 5.256374911365621e-06,
|
| 784 |
+
"loss": 0.2006,
|
| 785 |
+
"num_tokens": 38339423.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.6333333333333333,
|
| 790 |
+
"grad_norm": 0.1425557076209861,
|
| 791 |
+
"learning_rate": 5.175290098897229e-06,
|
| 792 |
+
"loss": 0.2201,
|
| 793 |
+
"num_tokens": 38766377.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.65,
|
| 798 |
+
"grad_norm": 0.16173575303325918,
|
| 799 |
+
"learning_rate": 5.094311134995707e-06,
|
| 800 |
+
"loss": 0.2063,
|
| 801 |
+
"num_tokens": 39147856.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.6666666666666665,
|
| 806 |
+
"grad_norm": 0.15671341837921993,
|
| 807 |
+
"learning_rate": 5.013464417092263e-06,
|
| 808 |
+
"loss": 0.2123,
|
| 809 |
+
"num_tokens": 39566905.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.6833333333333333,
|
| 814 |
+
"grad_norm": 0.1466722022344314,
|
| 815 |
+
"learning_rate": 4.932776299508699e-06,
|
| 816 |
+
"loss": 0.2131,
|
| 817 |
+
"num_tokens": 39958103.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.7,
|
| 822 |
+
"grad_norm": 0.15459226194943745,
|
| 823 |
+
"learning_rate": 4.852273084866464e-06,
|
| 824 |
+
"loss": 0.2056,
|
| 825 |
+
"num_tokens": 40340633.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.7166666666666668,
|
| 830 |
+
"grad_norm": 0.15024633207597848,
|
| 831 |
+
"learning_rate": 4.771981015512559e-06,
|
| 832 |
+
"loss": 0.2032,
|
| 833 |
+
"num_tokens": 40751526.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.7333333333333334,
|
| 838 |
+
"grad_norm": 0.15035138034173598,
|
| 839 |
+
"learning_rate": 4.6919262649650775e-06,
|
| 840 |
+
"loss": 0.2089,
|
| 841 |
+
"num_tokens": 41164499.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.75,
|
| 846 |
+
"grad_norm": 0.15651786731510953,
|
| 847 |
+
"learning_rate": 4.6121349293812015e-06,
|
| 848 |
+
"loss": 0.1995,
|
| 849 |
+
"num_tokens": 41570804.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.7666666666666666,
|
| 854 |
+
"grad_norm": 0.15052460060489134,
|
| 855 |
+
"learning_rate": 4.532633019050392e-06,
|
| 856 |
+
"loss": 0.2014,
|
| 857 |
+
"num_tokens": 41958143.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.7833333333333332,
|
| 862 |
+
"grad_norm": 0.15701741784933038,
|
| 863 |
+
"learning_rate": 4.453446449915605e-06,
|
| 864 |
+
"loss": 0.1956,
|
| 865 |
+
"num_tokens": 42328835.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.8,
|
| 870 |
+
"grad_norm": 0.14940995875441748,
|
| 871 |
+
"learning_rate": 4.374601035125218e-06,
|
| 872 |
+
"loss": 0.2013,
|
| 873 |
+
"num_tokens": 42695932.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.8166666666666667,
|
| 878 |
+
"grad_norm": 0.14921621072385988,
|
| 879 |
+
"learning_rate": 4.296122476618507e-06,
|
| 880 |
+
"loss": 0.2106,
|
| 881 |
+
"num_tokens": 43099402.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.8333333333333335,
|
| 886 |
+
"grad_norm": 0.15120472210694338,
|
| 887 |
+
"learning_rate": 4.21803635674735e-06,
|
| 888 |
+
"loss": 0.2046,
|
| 889 |
+
"num_tokens": 43497618.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.85,
|
| 894 |
+
"grad_norm": 0.1537232334909544,
|
| 895 |
+
"learning_rate": 4.140368129936923e-06,
|
| 896 |
+
"loss": 0.2125,
|
| 897 |
+
"num_tokens": 43910914.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.8666666666666667,
|
| 902 |
+
"grad_norm": 0.14899934511970375,
|
| 903 |
+
"learning_rate": 4.0631431143880915e-06,
|
| 904 |
+
"loss": 0.2161,
|
| 905 |
+
"num_tokens": 44306362.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.8833333333333333,
|
| 910 |
+
"grad_norm": 0.14352426818162795,
|
| 911 |
+
"learning_rate": 3.986386483824212e-06,
|
| 912 |
+
"loss": 0.1881,
|
| 913 |
+
"num_tokens": 44690072.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.9,
|
| 918 |
+
"grad_norm": 0.14966797180869215,
|
| 919 |
+
"learning_rate": 3.91012325928504e-06,
|
| 920 |
+
"loss": 0.2139,
|
| 921 |
+
"num_tokens": 45097796.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.9166666666666665,
|
| 926 |
+
"grad_norm": 0.15059855985104126,
|
| 927 |
+
"learning_rate": 3.834378300970385e-06,
|
| 928 |
+
"loss": 0.2104,
|
| 929 |
+
"num_tokens": 45507999.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.9333333333333333,
|
| 934 |
+
"grad_norm": 0.145399379241378,
|
| 935 |
+
"learning_rate": 3.759176300136225e-06,
|
| 936 |
+
"loss": 0.206,
|
| 937 |
+
"num_tokens": 45893001.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.95,
|
| 942 |
+
"grad_norm": 0.15686955708392808,
|
| 943 |
+
"learning_rate": 3.684541771045862e-06,
|
| 944 |
+
"loss": 0.1925,
|
| 945 |
+
"num_tokens": 46266011.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.9666666666666668,
|
| 950 |
+
"grad_norm": 0.15173053989396762,
|
| 951 |
+
"learning_rate": 3.6104990429788102e-06,
|
| 952 |
+
"loss": 0.2025,
|
| 953 |
+
"num_tokens": 46654457.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.9833333333333334,
|
| 958 |
+
"grad_norm": 0.1437181537184728,
|
| 959 |
+
"learning_rate": 3.5370722522999468e-06,
|
| 960 |
+
"loss": 0.2052,
|
| 961 |
+
"num_tokens": 47068222.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.0,
|
| 966 |
+
"grad_norm": 0.15409940511826736,
|
| 967 |
+
"learning_rate": 3.4642853345915796e-06,
|
| 968 |
+
"loss": 0.2105,
|
| 969 |
+
"num_tokens": 47486208.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.0166666666666666,
|
| 974 |
+
"grad_norm": 0.15402414642751905,
|
| 975 |
+
"learning_rate": 3.392162016850945e-06,
|
| 976 |
+
"loss": 0.1735,
|
| 977 |
+
"num_tokens": 47861567.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.033333333333333,
|
| 982 |
+
"grad_norm": 0.15373305435044163,
|
| 983 |
+
"learning_rate": 3.3207258097557136e-06,
|
| 984 |
+
"loss": 0.196,
|
| 985 |
+
"num_tokens": 48258885.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.05,
|
| 990 |
+
"grad_norm": 0.14676915170123003,
|
| 991 |
+
"learning_rate": 3.2500000000000015e-06,
|
| 992 |
+
"loss": 0.1907,
|
| 993 |
+
"num_tokens": 48642658.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.066666666666667,
|
| 998 |
+
"grad_norm": 0.1440659388733191,
|
| 999 |
+
"learning_rate": 3.180007642703402e-06,
|
| 1000 |
+
"loss": 0.187,
|
| 1001 |
+
"num_tokens": 49052624.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.0833333333333335,
|
| 1006 |
+
"grad_norm": 0.14784811155267652,
|
| 1007 |
+
"learning_rate": 3.1107715538955107e-06,
|
| 1008 |
+
"loss": 0.1811,
|
| 1009 |
+
"num_tokens": 49459791.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.1,
|
| 1014 |
+
"grad_norm": 0.1539105789783882,
|
| 1015 |
+
"learning_rate": 3.042314303078364e-06,
|
| 1016 |
+
"loss": 0.1765,
|
| 1017 |
+
"num_tokens": 49827854.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.1166666666666667,
|
| 1022 |
+
"grad_norm": 0.1552411260071569,
|
| 1023 |
+
"learning_rate": 2.9746582058692803e-06,
|
| 1024 |
+
"loss": 0.2016,
|
| 1025 |
+
"num_tokens": 50245908.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.1333333333333333,
|
| 1030 |
+
"grad_norm": 0.15614255642839991,
|
| 1031 |
+
"learning_rate": 2.9078253167264225e-06,
|
| 1032 |
+
"loss": 0.1899,
|
| 1033 |
+
"num_tokens": 50630892.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.15,
|
| 1038 |
+
"grad_norm": 0.14811369323743206,
|
| 1039 |
+
"learning_rate": 2.841837421759521e-06,
|
| 1040 |
+
"loss": 0.1914,
|
| 1041 |
+
"num_tokens": 51034329.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.1666666666666665,
|
| 1046 |
+
"grad_norm": 0.1975445469271066,
|
| 1047 |
+
"learning_rate": 2.7767160316280583e-06,
|
| 1048 |
+
"loss": 0.1808,
|
| 1049 |
+
"num_tokens": 51424755.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.183333333333333,
|
| 1054 |
+
"grad_norm": 0.1451760497316787,
|
| 1055 |
+
"learning_rate": 2.712482374529247e-06,
|
| 1056 |
+
"loss": 0.2008,
|
| 1057 |
+
"num_tokens": 51824755.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.2,
|
| 1062 |
+
"grad_norm": 0.14733003430195793,
|
| 1063 |
+
"learning_rate": 2.6491573892780944e-06,
|
| 1064 |
+
"loss": 0.1949,
|
| 1065 |
+
"num_tokens": 52216263.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.216666666666667,
|
| 1070 |
+
"grad_norm": 0.14534251232717119,
|
| 1071 |
+
"learning_rate": 2.586761718481776e-06,
|
| 1072 |
+
"loss": 0.1834,
|
| 1073 |
+
"num_tokens": 52598901.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.2333333333333334,
|
| 1078 |
+
"grad_norm": 0.1496275777226439,
|
| 1079 |
+
"learning_rate": 2.5253157018105994e-06,
|
| 1080 |
+
"loss": 0.1905,
|
| 1081 |
+
"num_tokens": 52970634.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.25,
|
| 1086 |
+
"grad_norm": 0.14905373345924058,
|
| 1087 |
+
"learning_rate": 2.464839369367688e-06,
|
| 1088 |
+
"loss": 0.1911,
|
| 1089 |
+
"num_tokens": 53361046.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.2666666666666666,
|
| 1094 |
+
"grad_norm": 0.15115547136539223,
|
| 1095 |
+
"learning_rate": 2.405352435159595e-06,
|
| 1096 |
+
"loss": 0.1998,
|
| 1097 |
+
"num_tokens": 53778131.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.283333333333333,
|
| 1102 |
+
"grad_norm": 0.14476235639341437,
|
| 1103 |
+
"learning_rate": 2.34687429066996e-06,
|
| 1104 |
+
"loss": 0.1817,
|
| 1105 |
+
"num_tokens": 54168768.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.3,
|
| 1110 |
+
"grad_norm": 0.14725798416601737,
|
| 1111 |
+
"learning_rate": 2.28942399853828e-06,
|
| 1112 |
+
"loss": 0.1782,
|
| 1113 |
+
"num_tokens": 54548763.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.3166666666666664,
|
| 1118 |
+
"grad_norm": 0.14942987448940256,
|
| 1119 |
+
"learning_rate": 2.2330202863459123e-06,
|
| 1120 |
+
"loss": 0.1936,
|
| 1121 |
+
"num_tokens": 54983583.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.3333333333333335,
|
| 1126 |
+
"grad_norm": 0.15129686936588405,
|
| 1127 |
+
"learning_rate": 2.1776815405112567e-06,
|
| 1128 |
+
"loss": 0.1894,
|
| 1129 |
+
"num_tokens": 55390401.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.35,
|
| 1134 |
+
"grad_norm": 0.1451441459771395,
|
| 1135 |
+
"learning_rate": 2.12342580029619e-06,
|
| 1136 |
+
"loss": 0.1876,
|
| 1137 |
+
"num_tokens": 55790352.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.3666666666666667,
|
| 1142 |
+
"grad_norm": 0.1504932193926155,
|
| 1143 |
+
"learning_rate": 2.0702707519256365e-06,
|
| 1144 |
+
"loss": 0.1927,
|
| 1145 |
+
"num_tokens": 56198140.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.3833333333333333,
|
| 1150 |
+
"grad_norm": 0.1425074357758425,
|
| 1151 |
+
"learning_rate": 2.0182337228222366e-06,
|
| 1152 |
+
"loss": 0.1901,
|
| 1153 |
+
"num_tokens": 56586902.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.4,
|
| 1158 |
+
"grad_norm": 0.1523349986800055,
|
| 1159 |
+
"learning_rate": 1.9673316759579752e-06,
|
| 1160 |
+
"loss": 0.1901,
|
| 1161 |
+
"num_tokens": 56980540.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.4166666666666665,
|
| 1166 |
+
"grad_norm": 0.148279722484878,
|
| 1167 |
+
"learning_rate": 1.9175812043246034e-06,
|
| 1168 |
+
"loss": 0.1937,
|
| 1169 |
+
"num_tokens": 57379690.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.4333333333333336,
|
| 1174 |
+
"grad_norm": 0.14683043295079268,
|
| 1175 |
+
"learning_rate": 1.8689985255246834e-06,
|
| 1176 |
+
"loss": 0.1801,
|
| 1177 |
+
"num_tokens": 57759503.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.45,
|
| 1182 |
+
"grad_norm": 0.14410047957451386,
|
| 1183 |
+
"learning_rate": 1.821599476484987e-06,
|
| 1184 |
+
"loss": 0.1759,
|
| 1185 |
+
"num_tokens": 58137010.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.466666666666667,
|
| 1190 |
+
"grad_norm": 0.14626131914056648,
|
| 1191 |
+
"learning_rate": 1.7753995082939932e-06,
|
| 1192 |
+
"loss": 0.1996,
|
| 1193 |
+
"num_tokens": 58540304.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.4833333333333334,
|
| 1198 |
+
"grad_norm": 0.14663671779264556,
|
| 1199 |
+
"learning_rate": 1.7304136811651595e-06,
|
| 1200 |
+
"loss": 0.183,
|
| 1201 |
+
"num_tokens": 58940195.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.5,
|
| 1206 |
+
"grad_norm": 0.14829884847473565,
|
| 1207 |
+
"learning_rate": 1.6866566595276108e-06,
|
| 1208 |
+
"loss": 0.1909,
|
| 1209 |
+
"num_tokens": 59334134.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.5166666666666666,
|
| 1214 |
+
"grad_norm": 0.14666192308168516,
|
| 1215 |
+
"learning_rate": 1.6441427072458493e-06,
|
| 1216 |
+
"loss": 0.184,
|
| 1217 |
+
"num_tokens": 59715949.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.533333333333333,
|
| 1222 |
+
"grad_norm": 0.1481572245355778,
|
| 1223 |
+
"learning_rate": 1.602885682970026e-06,
|
| 1224 |
+
"loss": 0.1855,
|
| 1225 |
+
"num_tokens": 60116409.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 2.55,
|
| 1230 |
+
"grad_norm": 0.14392865327162538,
|
| 1231 |
+
"learning_rate": 1.5628990356183267e-06,
|
| 1232 |
+
"loss": 0.1866,
|
| 1233 |
+
"num_tokens": 60525002.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.5666666666666664,
|
| 1238 |
+
"grad_norm": 0.1461373431520025,
|
| 1239 |
+
"learning_rate": 1.5241957999928974e-06,
|
| 1240 |
+
"loss": 0.1878,
|
| 1241 |
+
"num_tokens": 60932270.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.5833333333333335,
|
| 1246 |
+
"grad_norm": 0.14672445166075807,
|
| 1247 |
+
"learning_rate": 1.48678859253078e-06,
|
| 1248 |
+
"loss": 0.1958,
|
| 1249 |
+
"num_tokens": 61334649.0,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.6,
|
| 1254 |
+
"grad_norm": 0.1520933383157152,
|
| 1255 |
+
"learning_rate": 1.4506896071912207e-06,
|
| 1256 |
+
"loss": 0.189,
|
| 1257 |
+
"num_tokens": 61734959.0,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.6166666666666667,
|
| 1262 |
+
"grad_norm": 0.1428209521559839,
|
| 1263 |
+
"learning_rate": 1.4159106114806943e-06,
|
| 1264 |
+
"loss": 0.184,
|
| 1265 |
+
"num_tokens": 62136249.0,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.6333333333333333,
|
| 1270 |
+
"grad_norm": 0.14550810004810277,
|
| 1271 |
+
"learning_rate": 1.3824629426169453e-06,
|
| 1272 |
+
"loss": 0.1955,
|
| 1273 |
+
"num_tokens": 62547232.0,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.65,
|
| 1278 |
+
"grad_norm": 0.1471795467648584,
|
| 1279 |
+
"learning_rate": 1.3503575038333012e-06,
|
| 1280 |
+
"loss": 0.1865,
|
| 1281 |
+
"num_tokens": 62925792.0,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 2.6666666666666665,
|
| 1286 |
+
"grad_norm": 0.14338365279795576,
|
| 1287 |
+
"learning_rate": 1.319604760824439e-06,
|
| 1288 |
+
"loss": 0.1934,
|
| 1289 |
+
"num_tokens": 63307635.0,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.6833333333333336,
|
| 1294 |
+
"grad_norm": 0.14628389297503275,
|
| 1295 |
+
"learning_rate": 1.290214738334796e-06,
|
| 1296 |
+
"loss": 0.1845,
|
| 1297 |
+
"num_tokens": 63682238.0,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.7,
|
| 1302 |
+
"grad_norm": 0.14038687556129809,
|
| 1303 |
+
"learning_rate": 1.2621970168907142e-06,
|
| 1304 |
+
"loss": 0.1817,
|
| 1305 |
+
"num_tokens": 64080742.0,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.716666666666667,
|
| 1310 |
+
"grad_norm": 0.1488881989185735,
|
| 1311 |
+
"learning_rate": 1.2355607296773896e-06,
|
| 1312 |
+
"loss": 0.1873,
|
| 1313 |
+
"num_tokens": 64470953.0,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.7333333333333334,
|
| 1318 |
+
"grad_norm": 0.14877894347532283,
|
| 1319 |
+
"learning_rate": 1.2103145595616483e-06,
|
| 1320 |
+
"loss": 0.1775,
|
| 1321 |
+
"num_tokens": 64841108.0,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.75,
|
| 1326 |
+
"grad_norm": 0.14123105169145264,
|
| 1327 |
+
"learning_rate": 1.1864667362615143e-06,
|
| 1328 |
+
"loss": 0.1873,
|
| 1329 |
+
"num_tokens": 65231331.0,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.7666666666666666,
|
| 1334 |
+
"grad_norm": 0.1450707618403656,
|
| 1335 |
+
"learning_rate": 1.164025033663497e-06,
|
| 1336 |
+
"loss": 0.1955,
|
| 1337 |
+
"num_tokens": 65618779.0,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.783333333333333,
|
| 1342 |
+
"grad_norm": 0.14187799392326958,
|
| 1343 |
+
"learning_rate": 1.1429967672884653e-06,
|
| 1344 |
+
"loss": 0.1739,
|
| 1345 |
+
"num_tokens": 65984834.0,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.8,
|
| 1350 |
+
"grad_norm": 0.14056724875916252,
|
| 1351 |
+
"learning_rate": 1.1233887919069461e-06,
|
| 1352 |
+
"loss": 0.1933,
|
| 1353 |
+
"num_tokens": 66393854.0,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.8166666666666664,
|
| 1358 |
+
"grad_norm": 0.14962757784279573,
|
| 1359 |
+
"learning_rate": 1.1052074993046102e-06,
|
| 1360 |
+
"loss": 0.1921,
|
| 1361 |
+
"num_tokens": 66790920.0,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.8333333333333335,
|
| 1366 |
+
"grad_norm": 0.14231360939136606,
|
| 1367 |
+
"learning_rate": 1.0884588161986893e-06,
|
| 1368 |
+
"loss": 0.1977,
|
| 1369 |
+
"num_tokens": 67209770.0,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.85,
|
| 1374 |
+
"grad_norm": 0.14850621871295716,
|
| 1375 |
+
"learning_rate": 1.073148202305988e-06,
|
| 1376 |
+
"loss": 0.1843,
|
| 1377 |
+
"num_tokens": 67598233.0,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 2.8666666666666667,
|
| 1382 |
+
"grad_norm": 0.14009685911878283,
|
| 1383 |
+
"learning_rate": 1.0592806485631326e-06,
|
| 1384 |
+
"loss": 0.1844,
|
| 1385 |
+
"num_tokens": 68012178.0,
|
| 1386 |
+
"step": 172
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.8833333333333333,
|
| 1390 |
+
"grad_norm": 0.14434460171184124,
|
| 1391 |
+
"learning_rate": 1.0468606754996326e-06,
|
| 1392 |
+
"loss": 0.1938,
|
| 1393 |
+
"num_tokens": 68425764.0,
|
| 1394 |
+
"step": 173
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 2.9,
|
| 1398 |
+
"grad_norm": 0.15620525484508824,
|
| 1399 |
+
"learning_rate": 1.0358923317642807e-06,
|
| 1400 |
+
"loss": 0.1945,
|
| 1401 |
+
"num_tokens": 68839975.0,
|
| 1402 |
+
"step": 174
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.9166666666666665,
|
| 1406 |
+
"grad_norm": 0.14119966117512753,
|
| 1407 |
+
"learning_rate": 1.026379192805382e-06,
|
| 1408 |
+
"loss": 0.1936,
|
| 1409 |
+
"num_tokens": 69246450.0,
|
| 1410 |
+
"step": 175
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.9333333333333336,
|
| 1414 |
+
"grad_norm": 0.14254063884129384,
|
| 1415 |
+
"learning_rate": 1.0183243597052312e-06,
|
| 1416 |
+
"loss": 0.1935,
|
| 1417 |
+
"num_tokens": 69641779.0,
|
| 1418 |
+
"step": 176
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.95,
|
| 1422 |
+
"grad_norm": 0.14492800400381445,
|
| 1423 |
+
"learning_rate": 1.0117304581692261e-06,
|
| 1424 |
+
"loss": 0.1826,
|
| 1425 |
+
"num_tokens": 70032641.0,
|
| 1426 |
+
"step": 177
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 2.966666666666667,
|
| 1430 |
+
"grad_norm": 0.13925574665371473,
|
| 1431 |
+
"learning_rate": 1.006599637669943e-06,
|
| 1432 |
+
"loss": 0.182,
|
| 1433 |
+
"num_tokens": 70438823.0,
|
| 1434 |
+
"step": 178
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.9833333333333334,
|
| 1438 |
+
"grad_norm": 0.1437065239067374,
|
| 1439 |
+
"learning_rate": 1.002933570746454e-06,
|
| 1440 |
+
"loss": 0.1843,
|
| 1441 |
+
"num_tokens": 70827059.0,
|
| 1442 |
+
"step": 179
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 3.0,
|
| 1446 |
+
"grad_norm": 0.14387233022808313,
|
| 1447 |
+
"learning_rate": 1.0007334524591145e-06,
|
| 1448 |
+
"loss": 0.1878,
|
| 1449 |
+
"num_tokens": 71219748.0,
|
| 1450 |
+
"step": 180
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 3.0,
|
| 1454 |
+
"step": 180,
|
| 1455 |
+
"total_flos": 2.097365527654564e+17,
|
| 1456 |
+
"train_loss": 0.2700612629453341,
|
| 1457 |
+
"train_runtime": 2536.3753,
|
| 1458 |
+
"train_samples_per_second": 9.041,
|
| 1459 |
+
"train_steps_per_second": 0.071
|
| 1460 |
+
}
|
| 1461 |
+
],
|
| 1462 |
+
"logging_steps": 1,
|
| 1463 |
+
"max_steps": 180,
|
| 1464 |
+
"num_input_tokens_seen": 0,
|
| 1465 |
+
"num_train_epochs": 3,
|
| 1466 |
+
"save_steps": 500,
|
| 1467 |
+
"stateful_callbacks": {
|
| 1468 |
+
"TrainerControl": {
|
| 1469 |
+
"args": {
|
| 1470 |
+
"should_epoch_stop": false,
|
| 1471 |
+
"should_evaluate": false,
|
| 1472 |
+
"should_log": false,
|
| 1473 |
+
"should_save": true,
|
| 1474 |
+
"should_training_stop": true
|
| 1475 |
+
},
|
| 1476 |
+
"attributes": {}
|
| 1477 |
+
}
|
| 1478 |
+
},
|
| 1479 |
+
"total_flos": 2.097365527654564e+17,
|
| 1480 |
+
"train_batch_size": 8,
|
| 1481 |
+
"trial_name": null,
|
| 1482 |
+
"trial_params": null
|
| 1483 |
+
}
|