Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +14 -0
- train_results.json +8 -0
- trainer_state.json +1683 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-7B-Open-R1-Distill-Italian
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-7B-Open-R1-Distill-Italian
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="bezir/Qwen2.5-7B-Open-R1-Distill-Italian", 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/bezirglasgow/huggingface/runs/a4k6nluk)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.3.2
|
| 41 |
+
- Tokenizers: 0.21.0
|
| 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 Gallouédec},
|
| 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": 1074983740637184.0,
|
| 3 |
+
"train_loss": 0.49954891321022377,
|
| 4 |
+
"train_runtime": 168401.8035,
|
| 5 |
+
"train_samples": 104697,
|
| 6 |
+
"train_samples_per_second": 0.78,
|
| 7 |
+
"train_steps_per_second": 0.006
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.49.0"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1074983740637184.0,
|
| 3 |
+
"train_loss": 0.49954891321022377,
|
| 4 |
+
"train_runtime": 168401.8035,
|
| 5 |
+
"train_samples": 104697,
|
| 6 |
+
"train_samples_per_second": 0.78,
|
| 7 |
+
"train_steps_per_second": 0.006
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1683 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9973216459702945,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1026,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.009739469198928659,
|
| 13 |
+
"grad_norm": 5.16649192443276,
|
| 14 |
+
"learning_rate": 4.854368932038835e-07,
|
| 15 |
+
"loss": 0.956,
|
| 16 |
+
"mean_token_accuracy": 0.7770209729671478,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019478938397857318,
|
| 21 |
+
"grad_norm": 4.487616874759018,
|
| 22 |
+
"learning_rate": 9.70873786407767e-07,
|
| 23 |
+
"loss": 0.9595,
|
| 24 |
+
"mean_token_accuracy": 0.774706457555294,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.029218407596785977,
|
| 29 |
+
"grad_norm": 1.9918521253065147,
|
| 30 |
+
"learning_rate": 1.4563106796116506e-06,
|
| 31 |
+
"loss": 0.9087,
|
| 32 |
+
"mean_token_accuracy": 0.7794785097241401,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.038957876795714635,
|
| 37 |
+
"grad_norm": 2.140741610293528,
|
| 38 |
+
"learning_rate": 1.941747572815534e-06,
|
| 39 |
+
"loss": 0.8516,
|
| 40 |
+
"mean_token_accuracy": 0.7845764443278312,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.048697345994643294,
|
| 45 |
+
"grad_norm": 1.577104941303547,
|
| 46 |
+
"learning_rate": 2.427184466019418e-06,
|
| 47 |
+
"loss": 0.7835,
|
| 48 |
+
"mean_token_accuracy": 0.795551997423172,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05843681519357195,
|
| 53 |
+
"grad_norm": 0.9851513931833208,
|
| 54 |
+
"learning_rate": 2.912621359223301e-06,
|
| 55 |
+
"loss": 0.7536,
|
| 56 |
+
"mean_token_accuracy": 0.801626966893673,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0681762843925006,
|
| 61 |
+
"grad_norm": 0.7665830684245213,
|
| 62 |
+
"learning_rate": 3.398058252427185e-06,
|
| 63 |
+
"loss": 0.7207,
|
| 64 |
+
"mean_token_accuracy": 0.8073863789439202,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07791575359142927,
|
| 69 |
+
"grad_norm": 0.6623786102965908,
|
| 70 |
+
"learning_rate": 3.883495145631068e-06,
|
| 71 |
+
"loss": 0.6976,
|
| 72 |
+
"mean_token_accuracy": 0.8124146014451981,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08765522279035792,
|
| 77 |
+
"grad_norm": 0.5409465013517523,
|
| 78 |
+
"learning_rate": 4.368932038834952e-06,
|
| 79 |
+
"loss": 0.6791,
|
| 80 |
+
"mean_token_accuracy": 0.8153241157531739,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.09739469198928659,
|
| 85 |
+
"grad_norm": 0.533911697336328,
|
| 86 |
+
"learning_rate": 4.854368932038836e-06,
|
| 87 |
+
"loss": 0.6494,
|
| 88 |
+
"mean_token_accuracy": 0.8212776482105255,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.10713416118821524,
|
| 93 |
+
"grad_norm": 0.46335668910229383,
|
| 94 |
+
"learning_rate": 5.3398058252427185e-06,
|
| 95 |
+
"loss": 0.6374,
|
| 96 |
+
"mean_token_accuracy": 0.8242872759699822,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1168736303871439,
|
| 101 |
+
"grad_norm": 0.48547854119926936,
|
| 102 |
+
"learning_rate": 5.825242718446602e-06,
|
| 103 |
+
"loss": 0.6321,
|
| 104 |
+
"mean_token_accuracy": 0.8252887204289436,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.12661309958607256,
|
| 109 |
+
"grad_norm": 0.4864652293922326,
|
| 110 |
+
"learning_rate": 6.310679611650487e-06,
|
| 111 |
+
"loss": 0.6246,
|
| 112 |
+
"mean_token_accuracy": 0.8261281028389931,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.1363525687850012,
|
| 117 |
+
"grad_norm": 0.48690138801181443,
|
| 118 |
+
"learning_rate": 6.79611650485437e-06,
|
| 119 |
+
"loss": 0.6168,
|
| 120 |
+
"mean_token_accuracy": 0.8278339207172394,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.14609203798392986,
|
| 125 |
+
"grad_norm": 0.4337713878880355,
|
| 126 |
+
"learning_rate": 7.2815533980582534e-06,
|
| 127 |
+
"loss": 0.5925,
|
| 128 |
+
"mean_token_accuracy": 0.8333460614085197,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15583150718285854,
|
| 133 |
+
"grad_norm": 0.45660620623082415,
|
| 134 |
+
"learning_rate": 7.766990291262136e-06,
|
| 135 |
+
"loss": 0.5973,
|
| 136 |
+
"mean_token_accuracy": 0.8320671111345291,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.1655709763817872,
|
| 141 |
+
"grad_norm": 0.4424374164027964,
|
| 142 |
+
"learning_rate": 8.25242718446602e-06,
|
| 143 |
+
"loss": 0.5873,
|
| 144 |
+
"mean_token_accuracy": 0.8338468298316002,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.17531044558071585,
|
| 149 |
+
"grad_norm": 0.4949541791856808,
|
| 150 |
+
"learning_rate": 8.737864077669904e-06,
|
| 151 |
+
"loss": 0.5846,
|
| 152 |
+
"mean_token_accuracy": 0.8346328064799309,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1850499147796445,
|
| 157 |
+
"grad_norm": 0.44716595203588544,
|
| 158 |
+
"learning_rate": 9.223300970873788e-06,
|
| 159 |
+
"loss": 0.574,
|
| 160 |
+
"mean_token_accuracy": 0.8365551233291626,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.19478938397857318,
|
| 165 |
+
"grad_norm": 0.40922461158607365,
|
| 166 |
+
"learning_rate": 9.708737864077671e-06,
|
| 167 |
+
"loss": 0.5745,
|
| 168 |
+
"mean_token_accuracy": 0.8366570115089417,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.20452885317750183,
|
| 173 |
+
"grad_norm": 0.5016773528604923,
|
| 174 |
+
"learning_rate": 9.99988415036596e-06,
|
| 175 |
+
"loss": 0.5649,
|
| 176 |
+
"mean_token_accuracy": 0.8382768034934998,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.21426832237643048,
|
| 181 |
+
"grad_norm": 0.5010899629730204,
|
| 182 |
+
"learning_rate": 9.99858090363555e-06,
|
| 183 |
+
"loss": 0.569,
|
| 184 |
+
"mean_token_accuracy": 0.8377967774868011,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22400779157535913,
|
| 189 |
+
"grad_norm": 0.5010895934649102,
|
| 190 |
+
"learning_rate": 9.995829976834402e-06,
|
| 191 |
+
"loss": 0.5654,
|
| 192 |
+
"mean_token_accuracy": 0.8383171066641808,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.2337472607742878,
|
| 197 |
+
"grad_norm": 0.5864787846174829,
|
| 198 |
+
"learning_rate": 9.99163216668102e-06,
|
| 199 |
+
"loss": 0.5703,
|
| 200 |
+
"mean_token_accuracy": 0.8369988009333611,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.24348672997321646,
|
| 205 |
+
"grad_norm": 0.5502383423638442,
|
| 206 |
+
"learning_rate": 9.985988688937684e-06,
|
| 207 |
+
"loss": 0.5632,
|
| 208 |
+
"mean_token_accuracy": 0.8387595832347869,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.2532261991721451,
|
| 213 |
+
"grad_norm": 0.4838385873501471,
|
| 214 |
+
"learning_rate": 9.978901178058333e-06,
|
| 215 |
+
"loss": 0.5472,
|
| 216 |
+
"mean_token_accuracy": 0.8424718379974365,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.26296566837107377,
|
| 221 |
+
"grad_norm": 0.5371306966614764,
|
| 222 |
+
"learning_rate": 9.970371686715205e-06,
|
| 223 |
+
"loss": 0.5431,
|
| 224 |
+
"mean_token_accuracy": 0.8432716697454452,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.2727051375700024,
|
| 229 |
+
"grad_norm": 0.5584506793424302,
|
| 230 |
+
"learning_rate": 9.960402685204347e-06,
|
| 231 |
+
"loss": 0.5516,
|
| 232 |
+
"mean_token_accuracy": 0.8408507108688354,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2824446067689311,
|
| 237 |
+
"grad_norm": 0.5467853450677332,
|
| 238 |
+
"learning_rate": 9.948997060730161e-06,
|
| 239 |
+
"loss": 0.5464,
|
| 240 |
+
"mean_token_accuracy": 0.8424971371889114,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2921840759678597,
|
| 245 |
+
"grad_norm": 0.48818575924287444,
|
| 246 |
+
"learning_rate": 9.936158116569231e-06,
|
| 247 |
+
"loss": 0.5489,
|
| 248 |
+
"mean_token_accuracy": 0.8420207649469376,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.30192354516678843,
|
| 253 |
+
"grad_norm": 0.46723378629583207,
|
| 254 |
+
"learning_rate": 9.921889571113629e-06,
|
| 255 |
+
"loss": 0.5462,
|
| 256 |
+
"mean_token_accuracy": 0.8419363871216774,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.3116630143657171,
|
| 261 |
+
"grad_norm": 0.561719955013033,
|
| 262 |
+
"learning_rate": 9.906195556793996e-06,
|
| 263 |
+
"loss": 0.546,
|
| 264 |
+
"mean_token_accuracy": 0.8423524782061577,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.32140248356464574,
|
| 269 |
+
"grad_norm": 0.625160714021079,
|
| 270 |
+
"learning_rate": 9.889080618882719e-06,
|
| 271 |
+
"loss": 0.5335,
|
| 272 |
+
"mean_token_accuracy": 0.8451830595731735,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.3311419527635744,
|
| 277 |
+
"grad_norm": 0.5878540451317104,
|
| 278 |
+
"learning_rate": 9.870549714177538e-06,
|
| 279 |
+
"loss": 0.5463,
|
| 280 |
+
"mean_token_accuracy": 0.8417419150471688,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.34088142196250304,
|
| 285 |
+
"grad_norm": 0.6154889939045929,
|
| 286 |
+
"learning_rate": 9.850608209565967e-06,
|
| 287 |
+
"loss": 0.5327,
|
| 288 |
+
"mean_token_accuracy": 0.8450453072786331,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3506208911614317,
|
| 293 |
+
"grad_norm": 0.4329465610848603,
|
| 294 |
+
"learning_rate": 9.829261880470941e-06,
|
| 295 |
+
"loss": 0.5392,
|
| 296 |
+
"mean_token_accuracy": 0.8434989348053932,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.36036036036036034,
|
| 301 |
+
"grad_norm": 0.5971707984256834,
|
| 302 |
+
"learning_rate": 9.806516909178161e-06,
|
| 303 |
+
"loss": 0.5324,
|
| 304 |
+
"mean_token_accuracy": 0.84499292075634,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.370099829559289,
|
| 309 |
+
"grad_norm": 0.44190322710346147,
|
| 310 |
+
"learning_rate": 9.78237988304557e-06,
|
| 311 |
+
"loss": 0.5332,
|
| 312 |
+
"mean_token_accuracy": 0.845010556280613,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.3798392987582177,
|
| 317 |
+
"grad_norm": 0.4258724885095506,
|
| 318 |
+
"learning_rate": 9.756857792595555e-06,
|
| 319 |
+
"loss": 0.5319,
|
| 320 |
+
"mean_token_accuracy": 0.845000034570694,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.38957876795714635,
|
| 325 |
+
"grad_norm": 0.4729261486427116,
|
| 326 |
+
"learning_rate": 9.729958029490353e-06,
|
| 327 |
+
"loss": 0.5336,
|
| 328 |
+
"mean_token_accuracy": 0.8447421163320541,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.399318237156075,
|
| 333 |
+
"grad_norm": 0.4528083565277609,
|
| 334 |
+
"learning_rate": 9.701688384391296e-06,
|
| 335 |
+
"loss": 0.5347,
|
| 336 |
+
"mean_token_accuracy": 0.8443498685956001,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.40905770635500366,
|
| 341 |
+
"grad_norm": 0.5259149339810829,
|
| 342 |
+
"learning_rate": 9.672057044702492e-06,
|
| 343 |
+
"loss": 0.5199,
|
| 344 |
+
"mean_token_accuracy": 0.848120279610157,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4187971755539323,
|
| 349 |
+
"grad_norm": 0.46836949308672154,
|
| 350 |
+
"learning_rate": 9.641072592199599e-06,
|
| 351 |
+
"loss": 0.5219,
|
| 352 |
+
"mean_token_accuracy": 0.8473641723394394,
|
| 353 |
+
"step": 215
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.42853664475286096,
|
| 357 |
+
"grad_norm": 0.5302502163183013,
|
| 358 |
+
"learning_rate": 9.608744000544392e-06,
|
| 359 |
+
"loss": 0.5174,
|
| 360 |
+
"mean_token_accuracy": 0.8485160410404206,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.4382761139517896,
|
| 365 |
+
"grad_norm": 0.51343914785562,
|
| 366 |
+
"learning_rate": 9.575080632685832e-06,
|
| 367 |
+
"loss": 0.5239,
|
| 368 |
+
"mean_token_accuracy": 0.846913392841816,
|
| 369 |
+
"step": 225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.44801558315071827,
|
| 373 |
+
"grad_norm": 0.5925559680424145,
|
| 374 |
+
"learning_rate": 9.54009223814837e-06,
|
| 375 |
+
"loss": 0.5277,
|
| 376 |
+
"mean_token_accuracy": 0.8454070091247559,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.4577550523496469,
|
| 381 |
+
"grad_norm": 0.426110283810703,
|
| 382 |
+
"learning_rate": 9.503788950208324e-06,
|
| 383 |
+
"loss": 0.5215,
|
| 384 |
+
"mean_token_accuracy": 0.8473676040768623,
|
| 385 |
+
"step": 235
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.4674945215485756,
|
| 389 |
+
"grad_norm": 0.5303378941560718,
|
| 390 |
+
"learning_rate": 9.466181282959083e-06,
|
| 391 |
+
"loss": 0.5282,
|
| 392 |
+
"mean_token_accuracy": 0.8465007901191711,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.4772339907475043,
|
| 397 |
+
"grad_norm": 0.4965315113021109,
|
| 398 |
+
"learning_rate": 9.427280128266049e-06,
|
| 399 |
+
"loss": 0.5179,
|
| 400 |
+
"mean_token_accuracy": 0.8484022691845894,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.48697345994643293,
|
| 405 |
+
"grad_norm": 0.44982624201366644,
|
| 406 |
+
"learning_rate": 9.387096752612144e-06,
|
| 407 |
+
"loss": 0.5224,
|
| 408 |
+
"mean_token_accuracy": 0.8463509559631348,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4967129291453616,
|
| 413 |
+
"grad_norm": 0.4623459721033935,
|
| 414 |
+
"learning_rate": 9.345642793834825e-06,
|
| 415 |
+
"loss": 0.5271,
|
| 416 |
+
"mean_token_accuracy": 0.8463737353682518,
|
| 417 |
+
"step": 255
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.5064523983442902,
|
| 421 |
+
"grad_norm": 0.5825923961149249,
|
| 422 |
+
"learning_rate": 9.302930257755579e-06,
|
| 423 |
+
"loss": 0.53,
|
| 424 |
+
"mean_token_accuracy": 0.8450088694691658,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.5161918675432189,
|
| 429 |
+
"grad_norm": 0.45940800329264964,
|
| 430 |
+
"learning_rate": 9.258971514702789e-06,
|
| 431 |
+
"loss": 0.507,
|
| 432 |
+
"mean_token_accuracy": 0.8508246764540672,
|
| 433 |
+
"step": 265
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.5259313367421475,
|
| 437 |
+
"grad_norm": 0.4465364801256697,
|
| 438 |
+
"learning_rate": 9.213779295929082e-06,
|
| 439 |
+
"loss": 0.5087,
|
| 440 |
+
"mean_token_accuracy": 0.8500014141201973,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.5356708059410762,
|
| 445 |
+
"grad_norm": 0.4686695606038613,
|
| 446 |
+
"learning_rate": 9.167366689924116e-06,
|
| 447 |
+
"loss": 0.5163,
|
| 448 |
+
"mean_token_accuracy": 0.8484609499573708,
|
| 449 |
+
"step": 275
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.5454102751400048,
|
| 453 |
+
"grad_norm": 0.5572145736502692,
|
| 454 |
+
"learning_rate": 9.119747138623925e-06,
|
| 455 |
+
"loss": 0.5221,
|
| 456 |
+
"mean_token_accuracy": 0.8470426678657532,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5551497443389335,
|
| 461 |
+
"grad_norm": 0.4765827682250088,
|
| 462 |
+
"learning_rate": 9.070934433517872e-06,
|
| 463 |
+
"loss": 0.5068,
|
| 464 |
+
"mean_token_accuracy": 0.8509115263819694,
|
| 465 |
+
"step": 285
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5648892135378621,
|
| 469 |
+
"grad_norm": 0.49934327207360063,
|
| 470 |
+
"learning_rate": 9.020942711654404e-06,
|
| 471 |
+
"loss": 0.5106,
|
| 472 |
+
"mean_token_accuracy": 0.8498208403587342,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.5746286827367908,
|
| 477 |
+
"grad_norm": 0.5101324493724546,
|
| 478 |
+
"learning_rate": 8.969786451546691e-06,
|
| 479 |
+
"loss": 0.5123,
|
| 480 |
+
"mean_token_accuracy": 0.8496938437223435,
|
| 481 |
+
"step": 295
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.5843681519357194,
|
| 485 |
+
"grad_norm": 0.5089021103596151,
|
| 486 |
+
"learning_rate": 8.917480468979387e-06,
|
| 487 |
+
"loss": 0.5128,
|
| 488 |
+
"mean_token_accuracy": 0.8487787261605263,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.5941076211346482,
|
| 493 |
+
"grad_norm": 0.5501775930667125,
|
| 494 |
+
"learning_rate": 8.864039912717713e-06,
|
| 495 |
+
"loss": 0.5123,
|
| 496 |
+
"mean_token_accuracy": 0.849444879591465,
|
| 497 |
+
"step": 305
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.6038470903335769,
|
| 501 |
+
"grad_norm": 0.41563520519489466,
|
| 502 |
+
"learning_rate": 8.809480260120096e-06,
|
| 503 |
+
"loss": 0.5048,
|
| 504 |
+
"mean_token_accuracy": 0.8513683333992959,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.6135865595325055,
|
| 509 |
+
"grad_norm": 0.4999791105897695,
|
| 510 |
+
"learning_rate": 8.753817312655642e-06,
|
| 511 |
+
"loss": 0.514,
|
| 512 |
+
"mean_token_accuracy": 0.8484693005681038,
|
| 513 |
+
"step": 315
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6233260287314342,
|
| 517 |
+
"grad_norm": 0.48088239973601826,
|
| 518 |
+
"learning_rate": 8.697067191327748e-06,
|
| 519 |
+
"loss": 0.5114,
|
| 520 |
+
"mean_token_accuracy": 0.8495015501976013,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6330654979303628,
|
| 525 |
+
"grad_norm": 0.4440141428026334,
|
| 526 |
+
"learning_rate": 8.639246332005163e-06,
|
| 527 |
+
"loss": 0.5064,
|
| 528 |
+
"mean_token_accuracy": 0.8507678374648094,
|
| 529 |
+
"step": 325
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.6428049671292915,
|
| 533 |
+
"grad_norm": 0.5288324873519791,
|
| 534 |
+
"learning_rate": 8.580371480661857e-06,
|
| 535 |
+
"loss": 0.5024,
|
| 536 |
+
"mean_token_accuracy": 0.8514497712254524,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6525444363282201,
|
| 541 |
+
"grad_norm": 0.4563934748637001,
|
| 542 |
+
"learning_rate": 8.520459688527091e-06,
|
| 543 |
+
"loss": 0.5108,
|
| 544 |
+
"mean_token_accuracy": 0.849525935947895,
|
| 545 |
+
"step": 335
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.6622839055271488,
|
| 549 |
+
"grad_norm": 0.4756063591717307,
|
| 550 |
+
"learning_rate": 8.459528307147066e-06,
|
| 551 |
+
"loss": 0.51,
|
| 552 |
+
"mean_token_accuracy": 0.8501726359128952,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.6720233747260774,
|
| 557 |
+
"grad_norm": 0.5732019741491505,
|
| 558 |
+
"learning_rate": 8.397594983359591e-06,
|
| 559 |
+
"loss": 0.5062,
|
| 560 |
+
"mean_token_accuracy": 0.850397090613842,
|
| 561 |
+
"step": 345
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.6817628439250061,
|
| 565 |
+
"grad_norm": 0.5267653966986828,
|
| 566 |
+
"learning_rate": 8.334677654183254e-06,
|
| 567 |
+
"loss": 0.5065,
|
| 568 |
+
"mean_token_accuracy": 0.8505988359451294,
|
| 569 |
+
"step": 350
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.6915023131239347,
|
| 573 |
+
"grad_norm": 0.4796149747636043,
|
| 574 |
+
"learning_rate": 8.27079454162252e-06,
|
| 575 |
+
"loss": 0.5028,
|
| 576 |
+
"mean_token_accuracy": 0.851087860763073,
|
| 577 |
+
"step": 355
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7012417823228634,
|
| 581 |
+
"grad_norm": 0.4809967856664383,
|
| 582 |
+
"learning_rate": 8.205964147390313e-06,
|
| 583 |
+
"loss": 0.5084,
|
| 584 |
+
"mean_token_accuracy": 0.8496400877833367,
|
| 585 |
+
"step": 360
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.710981251521792,
|
| 589 |
+
"grad_norm": 0.4348534092140185,
|
| 590 |
+
"learning_rate": 8.140205247549583e-06,
|
| 591 |
+
"loss": 0.4983,
|
| 592 |
+
"mean_token_accuracy": 0.8522587567567825,
|
| 593 |
+
"step": 365
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.7207207207207207,
|
| 597 |
+
"grad_norm": 0.4799630529257426,
|
| 598 |
+
"learning_rate": 8.073536887075417e-06,
|
| 599 |
+
"loss": 0.5119,
|
| 600 |
+
"mean_token_accuracy": 0.8493492469191551,
|
| 601 |
+
"step": 370
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.7304601899196493,
|
| 605 |
+
"grad_norm": 0.5305052950944196,
|
| 606 |
+
"learning_rate": 8.005978374339264e-06,
|
| 607 |
+
"loss": 0.4946,
|
| 608 |
+
"mean_token_accuracy": 0.8531364649534225,
|
| 609 |
+
"step": 375
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.740199659118578,
|
| 613 |
+
"grad_norm": 0.46401531374429855,
|
| 614 |
+
"learning_rate": 7.937549275516882e-06,
|
| 615 |
+
"loss": 0.493,
|
| 616 |
+
"mean_token_accuracy": 0.8535278528928757,
|
| 617 |
+
"step": 380
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.7499391283175066,
|
| 621 |
+
"grad_norm": 0.46753323308197925,
|
| 622 |
+
"learning_rate": 7.868269408921614e-06,
|
| 623 |
+
"loss": 0.504,
|
| 624 |
+
"mean_token_accuracy": 0.8511819407343865,
|
| 625 |
+
"step": 385
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7596785975164354,
|
| 629 |
+
"grad_norm": 0.43897436674183826,
|
| 630 |
+
"learning_rate": 7.798158839264645e-06,
|
| 631 |
+
"loss": 0.4983,
|
| 632 |
+
"mean_token_accuracy": 0.8521765768527985,
|
| 633 |
+
"step": 390
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7694180667153641,
|
| 637 |
+
"grad_norm": 0.4030095081507055,
|
| 638 |
+
"learning_rate": 7.7272378718439e-06,
|
| 639 |
+
"loss": 0.5092,
|
| 640 |
+
"mean_token_accuracy": 0.8500049978494644,
|
| 641 |
+
"step": 395
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.7791575359142927,
|
| 645 |
+
"grad_norm": 0.393465790048579,
|
| 646 |
+
"learning_rate": 7.655527046663254e-06,
|
| 647 |
+
"loss": 0.5022,
|
| 648 |
+
"mean_token_accuracy": 0.8510702222585678,
|
| 649 |
+
"step": 400
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7888970051132214,
|
| 653 |
+
"grad_norm": 0.49269595855244275,
|
| 654 |
+
"learning_rate": 7.5830471324837765e-06,
|
| 655 |
+
"loss": 0.4945,
|
| 656 |
+
"mean_token_accuracy": 0.8529314771294594,
|
| 657 |
+
"step": 405
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.79863647431215,
|
| 661 |
+
"grad_norm": 0.4729001525106615,
|
| 662 |
+
"learning_rate": 7.5098191208087144e-06,
|
| 663 |
+
"loss": 0.5,
|
| 664 |
+
"mean_token_accuracy": 0.8525989070534706,
|
| 665 |
+
"step": 410
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.8083759435110787,
|
| 669 |
+
"grad_norm": 0.44720074409020516,
|
| 670 |
+
"learning_rate": 7.4358642198039835e-06,
|
| 671 |
+
"loss": 0.4946,
|
| 672 |
+
"mean_token_accuracy": 0.8530281245708465,
|
| 673 |
+
"step": 415
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.8181154127100073,
|
| 677 |
+
"grad_norm": 0.4192773521625985,
|
| 678 |
+
"learning_rate": 7.36120384815588e-06,
|
| 679 |
+
"loss": 0.4927,
|
| 680 |
+
"mean_token_accuracy": 0.8539465010166168,
|
| 681 |
+
"step": 420
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.827854881908936,
|
| 685 |
+
"grad_norm": 0.41037683317185314,
|
| 686 |
+
"learning_rate": 7.285859628867851e-06,
|
| 687 |
+
"loss": 0.4952,
|
| 688 |
+
"mean_token_accuracy": 0.8532393842935562,
|
| 689 |
+
"step": 425
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8375943511078646,
|
| 693 |
+
"grad_norm": 0.4536782151813187,
|
| 694 |
+
"learning_rate": 7.209853382998077e-06,
|
| 695 |
+
"loss": 0.4983,
|
| 696 |
+
"mean_token_accuracy": 0.8528945103287697,
|
| 697 |
+
"step": 430
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8473338203067933,
|
| 701 |
+
"grad_norm": 0.4895833290473578,
|
| 702 |
+
"learning_rate": 7.133207123339689e-06,
|
| 703 |
+
"loss": 0.4939,
|
| 704 |
+
"mean_token_accuracy": 0.853129243850708,
|
| 705 |
+
"step": 435
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8570732895057219,
|
| 709 |
+
"grad_norm": 0.4771689532642086,
|
| 710 |
+
"learning_rate": 7.055943048045476e-06,
|
| 711 |
+
"loss": 0.5002,
|
| 712 |
+
"mean_token_accuracy": 0.8518661975860595,
|
| 713 |
+
"step": 440
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.8668127587046506,
|
| 717 |
+
"grad_norm": 0.4439177979495324,
|
| 718 |
+
"learning_rate": 6.978083534198878e-06,
|
| 719 |
+
"loss": 0.4977,
|
| 720 |
+
"mean_token_accuracy": 0.8526063248515129,
|
| 721 |
+
"step": 445
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.8765522279035792,
|
| 725 |
+
"grad_norm": 0.45795986197220584,
|
| 726 |
+
"learning_rate": 6.899651131333194e-06,
|
| 727 |
+
"loss": 0.4876,
|
| 728 |
+
"mean_token_accuracy": 0.8546572834253311,
|
| 729 |
+
"step": 450
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.8862916971025079,
|
| 733 |
+
"grad_norm": 0.38084088770564956,
|
| 734 |
+
"learning_rate": 6.82066855490081e-06,
|
| 735 |
+
"loss": 0.5009,
|
| 736 |
+
"mean_token_accuracy": 0.851148933172226,
|
| 737 |
+
"step": 455
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.8960311663014365,
|
| 741 |
+
"grad_norm": 0.4552737931829716,
|
| 742 |
+
"learning_rate": 6.741158679694403e-06,
|
| 743 |
+
"loss": 0.4968,
|
| 744 |
+
"mean_token_accuracy": 0.8524380102753639,
|
| 745 |
+
"step": 460
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9057706355003652,
|
| 749 |
+
"grad_norm": 0.38831398930391275,
|
| 750 |
+
"learning_rate": 6.661144533221974e-06,
|
| 751 |
+
"loss": 0.4897,
|
| 752 |
+
"mean_token_accuracy": 0.8537176489830017,
|
| 753 |
+
"step": 465
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.9155101046992938,
|
| 757 |
+
"grad_norm": 0.42794585960634596,
|
| 758 |
+
"learning_rate": 6.58064928903767e-06,
|
| 759 |
+
"loss": 0.4942,
|
| 760 |
+
"mean_token_accuracy": 0.8529506504535675,
|
| 761 |
+
"step": 470
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9252495738982226,
|
| 765 |
+
"grad_norm": 0.42890975667323755,
|
| 766 |
+
"learning_rate": 6.499696260030297e-06,
|
| 767 |
+
"loss": 0.5064,
|
| 768 |
+
"mean_token_accuracy": 0.8502799227833748,
|
| 769 |
+
"step": 475
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.9349890430971513,
|
| 773 |
+
"grad_norm": 0.4478332747744812,
|
| 774 |
+
"learning_rate": 6.418308891671484e-06,
|
| 775 |
+
"loss": 0.4855,
|
| 776 |
+
"mean_token_accuracy": 0.8555838361382484,
|
| 777 |
+
"step": 480
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.9447285122960799,
|
| 781 |
+
"grad_norm": 0.435211802978247,
|
| 782 |
+
"learning_rate": 6.336510755225447e-06,
|
| 783 |
+
"loss": 0.4835,
|
| 784 |
+
"mean_token_accuracy": 0.8558964654803276,
|
| 785 |
+
"step": 485
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.9544679814950086,
|
| 789 |
+
"grad_norm": 0.4462726381437146,
|
| 790 |
+
"learning_rate": 6.25432554092232e-06,
|
| 791 |
+
"loss": 0.4898,
|
| 792 |
+
"mean_token_accuracy": 0.8544702440500259,
|
| 793 |
+
"step": 490
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.9642074506939372,
|
| 797 |
+
"grad_norm": 0.44503915866443544,
|
| 798 |
+
"learning_rate": 6.171777051097037e-06,
|
| 799 |
+
"loss": 0.4858,
|
| 800 |
+
"mean_token_accuracy": 0.8554443955421448,
|
| 801 |
+
"step": 495
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9739469198928659,
|
| 805 |
+
"grad_norm": 0.47966098493432496,
|
| 806 |
+
"learning_rate": 6.088889193295738e-06,
|
| 807 |
+
"loss": 0.4929,
|
| 808 |
+
"mean_token_accuracy": 0.8535514727234841,
|
| 809 |
+
"step": 500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.9836863890917945,
|
| 813 |
+
"grad_norm": 0.5437585793823457,
|
| 814 |
+
"learning_rate": 6.005685973351708e-06,
|
| 815 |
+
"loss": 0.4931,
|
| 816 |
+
"mean_token_accuracy": 0.8531181156635285,
|
| 817 |
+
"step": 505
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.9934258582907232,
|
| 821 |
+
"grad_norm": 0.4124694681433172,
|
| 822 |
+
"learning_rate": 5.922191488432857e-06,
|
| 823 |
+
"loss": 0.4917,
|
| 824 |
+
"mean_token_accuracy": 0.8535135626792908,
|
| 825 |
+
"step": 510
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.0019478938397857,
|
| 829 |
+
"grad_norm": 0.803029283965446,
|
| 830 |
+
"learning_rate": 5.838429920062734e-06,
|
| 831 |
+
"loss": 0.4727,
|
| 832 |
+
"mean_token_accuracy": 0.8567549926894051,
|
| 833 |
+
"step": 515
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.0116873630387144,
|
| 837 |
+
"grad_norm": 0.3927635667112885,
|
| 838 |
+
"learning_rate": 5.754425527117118e-06,
|
| 839 |
+
"loss": 0.4479,
|
| 840 |
+
"mean_token_accuracy": 0.864441742002964,
|
| 841 |
+
"step": 520
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.021426832237643,
|
| 845 |
+
"grad_norm": 0.45928387456979786,
|
| 846 |
+
"learning_rate": 5.670202638798213e-06,
|
| 847 |
+
"loss": 0.4598,
|
| 848 |
+
"mean_token_accuracy": 0.8615871027112008,
|
| 849 |
+
"step": 525
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.0311663014365717,
|
| 853 |
+
"grad_norm": 0.517389580126703,
|
| 854 |
+
"learning_rate": 5.585785647588458e-06,
|
| 855 |
+
"loss": 0.4572,
|
| 856 |
+
"mean_token_accuracy": 0.8620010375976562,
|
| 857 |
+
"step": 530
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0409057706355003,
|
| 861 |
+
"grad_norm": 0.37886924917283415,
|
| 862 |
+
"learning_rate": 5.501199002186024e-06,
|
| 863 |
+
"loss": 0.455,
|
| 864 |
+
"mean_token_accuracy": 0.8625968441367149,
|
| 865 |
+
"step": 535
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.050645239834429,
|
| 869 |
+
"grad_norm": 0.39773153996958316,
|
| 870 |
+
"learning_rate": 5.416467200424032e-06,
|
| 871 |
+
"loss": 0.45,
|
| 872 |
+
"mean_token_accuracy": 0.8637859463691712,
|
| 873 |
+
"step": 540
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.0603847090333576,
|
| 877 |
+
"grad_norm": 0.40508395528042257,
|
| 878 |
+
"learning_rate": 5.33161478217552e-06,
|
| 879 |
+
"loss": 0.4516,
|
| 880 |
+
"mean_token_accuracy": 0.8634377360343933,
|
| 881 |
+
"step": 545
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.0701241782322863,
|
| 885 |
+
"grad_norm": 0.37429603209812456,
|
| 886 |
+
"learning_rate": 5.246666322246267e-06,
|
| 887 |
+
"loss": 0.4445,
|
| 888 |
+
"mean_token_accuracy": 0.8651037693023682,
|
| 889 |
+
"step": 550
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.079863647431215,
|
| 893 |
+
"grad_norm": 0.47125189912053295,
|
| 894 |
+
"learning_rate": 5.1616464232574635e-06,
|
| 895 |
+
"loss": 0.4626,
|
| 896 |
+
"mean_token_accuracy": 0.8602706581354141,
|
| 897 |
+
"step": 555
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.0896031166301436,
|
| 901 |
+
"grad_norm": 0.435383825468146,
|
| 902 |
+
"learning_rate": 5.076579708520355e-06,
|
| 903 |
+
"loss": 0.4497,
|
| 904 |
+
"mean_token_accuracy": 0.8635805040597916,
|
| 905 |
+
"step": 560
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.0993425858290724,
|
| 909 |
+
"grad_norm": 0.412421290706311,
|
| 910 |
+
"learning_rate": 4.991490814904888e-06,
|
| 911 |
+
"loss": 0.4378,
|
| 912 |
+
"mean_token_accuracy": 0.8668369174003601,
|
| 913 |
+
"step": 565
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.109082055028001,
|
| 917 |
+
"grad_norm": 0.41209358309681204,
|
| 918 |
+
"learning_rate": 4.906404385704402e-06,
|
| 919 |
+
"loss": 0.4525,
|
| 920 |
+
"mean_token_accuracy": 0.8637306377291679,
|
| 921 |
+
"step": 570
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.1188215242269297,
|
| 925 |
+
"grad_norm": 0.3821281290056491,
|
| 926 |
+
"learning_rate": 4.82134506349851e-06,
|
| 927 |
+
"loss": 0.4564,
|
| 928 |
+
"mean_token_accuracy": 0.8625956058502198,
|
| 929 |
+
"step": 575
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.1285609934258582,
|
| 933 |
+
"grad_norm": 0.34980242368851916,
|
| 934 |
+
"learning_rate": 4.736337483016138e-06,
|
| 935 |
+
"loss": 0.4513,
|
| 936 |
+
"mean_token_accuracy": 0.8634121060371399,
|
| 937 |
+
"step": 580
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.138300462624787,
|
| 941 |
+
"grad_norm": 0.39297932611221925,
|
| 942 |
+
"learning_rate": 4.651406264000871e-06,
|
| 943 |
+
"loss": 0.4512,
|
| 944 |
+
"mean_token_accuracy": 0.8632175624370575,
|
| 945 |
+
"step": 585
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.1480399318237156,
|
| 949 |
+
"grad_norm": 0.4317512663581136,
|
| 950 |
+
"learning_rate": 4.5665760040806174e-06,
|
| 951 |
+
"loss": 0.4558,
|
| 952 |
+
"mean_token_accuracy": 0.8621700823307037,
|
| 953 |
+
"step": 590
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.1577794010226443,
|
| 957 |
+
"grad_norm": 0.4166519413744608,
|
| 958 |
+
"learning_rate": 4.481871271643698e-06,
|
| 959 |
+
"loss": 0.4543,
|
| 960 |
+
"mean_token_accuracy": 0.8628953084349632,
|
| 961 |
+
"step": 595
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.1675188702215729,
|
| 965 |
+
"grad_norm": 0.3817664896689048,
|
| 966 |
+
"learning_rate": 4.397316598723385e-06,
|
| 967 |
+
"loss": 0.4599,
|
| 968 |
+
"mean_token_accuracy": 0.8614401906728745,
|
| 969 |
+
"step": 600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.1772583394205016,
|
| 973 |
+
"grad_norm": 0.39223028227054235,
|
| 974 |
+
"learning_rate": 4.312936473892984e-06,
|
| 975 |
+
"loss": 0.4559,
|
| 976 |
+
"mean_token_accuracy": 0.8621881052851676,
|
| 977 |
+
"step": 605
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.1869978086194302,
|
| 981 |
+
"grad_norm": 0.39870192645434044,
|
| 982 |
+
"learning_rate": 4.228755335173488e-06,
|
| 983 |
+
"loss": 0.4554,
|
| 984 |
+
"mean_token_accuracy": 0.8622724115848541,
|
| 985 |
+
"step": 610
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.196737277818359,
|
| 989 |
+
"grad_norm": 0.3968827579618214,
|
| 990 |
+
"learning_rate": 4.1447975629559e-06,
|
| 991 |
+
"loss": 0.4496,
|
| 992 |
+
"mean_token_accuracy": 0.8639340966939926,
|
| 993 |
+
"step": 615
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.2064767470172875,
|
| 997 |
+
"grad_norm": 0.3525974840125754,
|
| 998 |
+
"learning_rate": 4.061087472940204e-06,
|
| 999 |
+
"loss": 0.4468,
|
| 1000 |
+
"mean_token_accuracy": 0.8643500834703446,
|
| 1001 |
+
"step": 620
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.2162162162162162,
|
| 1005 |
+
"grad_norm": 0.34784808537613615,
|
| 1006 |
+
"learning_rate": 3.977649309093113e-06,
|
| 1007 |
+
"loss": 0.4463,
|
| 1008 |
+
"mean_token_accuracy": 0.8645710095763206,
|
| 1009 |
+
"step": 625
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.225955685415145,
|
| 1013 |
+
"grad_norm": 0.3588527258157974,
|
| 1014 |
+
"learning_rate": 3.89450723662657e-06,
|
| 1015 |
+
"loss": 0.4517,
|
| 1016 |
+
"mean_token_accuracy": 0.863483439385891,
|
| 1017 |
+
"step": 630
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.2356951546140735,
|
| 1021 |
+
"grad_norm": 0.495886348965792,
|
| 1022 |
+
"learning_rate": 3.8116853349990574e-06,
|
| 1023 |
+
"loss": 0.4507,
|
| 1024 |
+
"mean_token_accuracy": 0.8636451244354248,
|
| 1025 |
+
"step": 635
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.245434623813002,
|
| 1029 |
+
"grad_norm": 0.3842625748309975,
|
| 1030 |
+
"learning_rate": 3.729207590941753e-06,
|
| 1031 |
+
"loss": 0.4377,
|
| 1032 |
+
"mean_token_accuracy": 0.8670691177248955,
|
| 1033 |
+
"step": 640
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.2551740930119308,
|
| 1037 |
+
"grad_norm": 0.4426936471853252,
|
| 1038 |
+
"learning_rate": 3.647097891511536e-06,
|
| 1039 |
+
"loss": 0.4495,
|
| 1040 |
+
"mean_token_accuracy": 0.8640359625220299,
|
| 1041 |
+
"step": 645
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.2649135622108596,
|
| 1045 |
+
"grad_norm": 0.3707914127374137,
|
| 1046 |
+
"learning_rate": 3.565380017172854e-06,
|
| 1047 |
+
"loss": 0.4397,
|
| 1048 |
+
"mean_token_accuracy": 0.8666136890649796,
|
| 1049 |
+
"step": 650
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.2746530314097881,
|
| 1053 |
+
"grad_norm": 0.35267532874755536,
|
| 1054 |
+
"learning_rate": 3.4840776349104755e-06,
|
| 1055 |
+
"loss": 0.4539,
|
| 1056 |
+
"mean_token_accuracy": 0.8626947477459908,
|
| 1057 |
+
"step": 655
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.284392500608717,
|
| 1061 |
+
"grad_norm": 0.3749743227529099,
|
| 1062 |
+
"learning_rate": 3.4032142913750956e-06,
|
| 1063 |
+
"loss": 0.4497,
|
| 1064 |
+
"mean_token_accuracy": 0.8637418314814568,
|
| 1065 |
+
"step": 660
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.2941319698076454,
|
| 1069 |
+
"grad_norm": 0.37600006002277636,
|
| 1070 |
+
"learning_rate": 3.322813406063794e-06,
|
| 1071 |
+
"loss": 0.4559,
|
| 1072 |
+
"mean_token_accuracy": 0.8622224271297455,
|
| 1073 |
+
"step": 665
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.3038714390065742,
|
| 1077 |
+
"grad_norm": 0.4005804398308692,
|
| 1078 |
+
"learning_rate": 3.242898264537331e-06,
|
| 1079 |
+
"loss": 0.4521,
|
| 1080 |
+
"mean_token_accuracy": 0.8632362619042396,
|
| 1081 |
+
"step": 670
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3136109082055027,
|
| 1085 |
+
"grad_norm": 0.38630202996272256,
|
| 1086 |
+
"learning_rate": 3.1634920116762175e-06,
|
| 1087 |
+
"loss": 0.4499,
|
| 1088 |
+
"mean_token_accuracy": 0.8635998621582985,
|
| 1089 |
+
"step": 675
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.3233503774044315,
|
| 1093 |
+
"grad_norm": 0.36180685239531096,
|
| 1094 |
+
"learning_rate": 3.0846176449775363e-06,
|
| 1095 |
+
"loss": 0.4508,
|
| 1096 |
+
"mean_token_accuracy": 0.8636634424328804,
|
| 1097 |
+
"step": 680
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.33308984660336,
|
| 1101 |
+
"grad_norm": 0.3357931590954893,
|
| 1102 |
+
"learning_rate": 3.0062980078944515e-06,
|
| 1103 |
+
"loss": 0.4379,
|
| 1104 |
+
"mean_token_accuracy": 0.8665053129196167,
|
| 1105 |
+
"step": 685
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.3428293158022888,
|
| 1109 |
+
"grad_norm": 0.35662293115272325,
|
| 1110 |
+
"learning_rate": 2.9285557832203328e-06,
|
| 1111 |
+
"loss": 0.4458,
|
| 1112 |
+
"mean_token_accuracy": 0.8648849859833717,
|
| 1113 |
+
"step": 690
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.3525687850012174,
|
| 1117 |
+
"grad_norm": 0.35254913645932934,
|
| 1118 |
+
"learning_rate": 2.851413486519388e-06,
|
| 1119 |
+
"loss": 0.4413,
|
| 1120 |
+
"mean_token_accuracy": 0.8654858738183975,
|
| 1121 |
+
"step": 695
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.3623082542001461,
|
| 1125 |
+
"grad_norm": 0.3448432687225989,
|
| 1126 |
+
"learning_rate": 2.774893459605766e-06,
|
| 1127 |
+
"loss": 0.4431,
|
| 1128 |
+
"mean_token_accuracy": 0.86555365473032,
|
| 1129 |
+
"step": 700
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.3720477233990747,
|
| 1133 |
+
"grad_norm": 0.35405617501926967,
|
| 1134 |
+
"learning_rate": 2.69901786407295e-06,
|
| 1135 |
+
"loss": 0.444,
|
| 1136 |
+
"mean_token_accuracy": 0.8651208564639091,
|
| 1137 |
+
"step": 705
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.3817871925980034,
|
| 1141 |
+
"grad_norm": 0.36859590132072323,
|
| 1142 |
+
"learning_rate": 2.6238086748753587e-06,
|
| 1143 |
+
"loss": 0.456,
|
| 1144 |
+
"mean_token_accuracy": 0.8627100110054016,
|
| 1145 |
+
"step": 710
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.3915266617969322,
|
| 1149 |
+
"grad_norm": 0.35246470987862855,
|
| 1150 |
+
"learning_rate": 2.5492876739639912e-06,
|
| 1151 |
+
"loss": 0.4533,
|
| 1152 |
+
"mean_token_accuracy": 0.8628792524337768,
|
| 1153 |
+
"step": 715
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 1.4012661309958607,
|
| 1157 |
+
"grad_norm": 0.36351033252725057,
|
| 1158 |
+
"learning_rate": 2.475476443977996e-06,
|
| 1159 |
+
"loss": 0.4469,
|
| 1160 |
+
"mean_token_accuracy": 0.8642540082335473,
|
| 1161 |
+
"step": 720
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.4110056001947893,
|
| 1165 |
+
"grad_norm": 0.35938233389923585,
|
| 1166 |
+
"learning_rate": 2.40239636199393e-06,
|
| 1167 |
+
"loss": 0.4451,
|
| 1168 |
+
"mean_token_accuracy": 0.8650069192051888,
|
| 1169 |
+
"step": 725
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.420745069393718,
|
| 1173 |
+
"grad_norm": 0.3673326064574297,
|
| 1174 |
+
"learning_rate": 2.3300685933345656e-06,
|
| 1175 |
+
"loss": 0.4485,
|
| 1176 |
+
"mean_token_accuracy": 0.8642319470643998,
|
| 1177 |
+
"step": 730
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.4304845385926468,
|
| 1181 |
+
"grad_norm": 0.37166399663475924,
|
| 1182 |
+
"learning_rate": 2.2585140854390432e-06,
|
| 1183 |
+
"loss": 0.4496,
|
| 1184 |
+
"mean_token_accuracy": 0.8641144469380379,
|
| 1185 |
+
"step": 735
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.4402240077915753,
|
| 1189 |
+
"grad_norm": 0.34969080725493995,
|
| 1190 |
+
"learning_rate": 2.187753561796097e-06,
|
| 1191 |
+
"loss": 0.449,
|
| 1192 |
+
"mean_token_accuracy": 0.8638374775648117,
|
| 1193 |
+
"step": 740
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.449963476990504,
|
| 1197 |
+
"grad_norm": 0.33346605175419364,
|
| 1198 |
+
"learning_rate": 2.117807515942163e-06,
|
| 1199 |
+
"loss": 0.4487,
|
| 1200 |
+
"mean_token_accuracy": 0.8639461770653725,
|
| 1201 |
+
"step": 745
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.4597029461894326,
|
| 1205 |
+
"grad_norm": 0.3402282068550279,
|
| 1206 |
+
"learning_rate": 2.0486962055260744e-06,
|
| 1207 |
+
"loss": 0.4381,
|
| 1208 |
+
"mean_token_accuracy": 0.8668898791074753,
|
| 1209 |
+
"step": 750
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.4694424153883614,
|
| 1213 |
+
"grad_norm": 0.3454615445905308,
|
| 1214 |
+
"learning_rate": 1.9804396464420798e-06,
|
| 1215 |
+
"loss": 0.4407,
|
| 1216 |
+
"mean_token_accuracy": 0.8662415385246277,
|
| 1217 |
+
"step": 755
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.47918188458729,
|
| 1221 |
+
"grad_norm": 0.3815154168732918,
|
| 1222 |
+
"learning_rate": 1.9130576070328695e-06,
|
| 1223 |
+
"loss": 0.4502,
|
| 1224 |
+
"mean_token_accuracy": 0.863922019302845,
|
| 1225 |
+
"step": 760
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.4889213537862187,
|
| 1229 |
+
"grad_norm": 0.35782414062256107,
|
| 1230 |
+
"learning_rate": 1.8465696023643115e-06,
|
| 1231 |
+
"loss": 0.4484,
|
| 1232 |
+
"mean_token_accuracy": 0.8640252217650414,
|
| 1233 |
+
"step": 765
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.4986608229851472,
|
| 1237 |
+
"grad_norm": 0.34966179386580715,
|
| 1238 |
+
"learning_rate": 1.7809948885735295e-06,
|
| 1239 |
+
"loss": 0.4476,
|
| 1240 |
+
"mean_token_accuracy": 0.8640663206577301,
|
| 1241 |
+
"step": 770
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.508400292184076,
|
| 1245 |
+
"grad_norm": 0.3283826370466805,
|
| 1246 |
+
"learning_rate": 1.7163524572919748e-06,
|
| 1247 |
+
"loss": 0.4535,
|
| 1248 |
+
"mean_token_accuracy": 0.8629004299640656,
|
| 1249 |
+
"step": 775
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5181397613830048,
|
| 1253 |
+
"grad_norm": 0.3309412101835561,
|
| 1254 |
+
"learning_rate": 1.6526610301451028e-06,
|
| 1255 |
+
"loss": 0.4374,
|
| 1256 |
+
"mean_token_accuracy": 0.8666589662432671,
|
| 1257 |
+
"step": 780
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.5278792305819333,
|
| 1261 |
+
"grad_norm": 0.35820157894670385,
|
| 1262 |
+
"learning_rate": 1.5899390533302538e-06,
|
| 1263 |
+
"loss": 0.4387,
|
| 1264 |
+
"mean_token_accuracy": 0.8667290091514588,
|
| 1265 |
+
"step": 785
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 1.5376186997808619,
|
| 1269 |
+
"grad_norm": 0.34472450626785944,
|
| 1270 |
+
"learning_rate": 1.5282046922742876e-06,
|
| 1271 |
+
"loss": 0.4502,
|
| 1272 |
+
"mean_token_accuracy": 0.8635128363966942,
|
| 1273 |
+
"step": 790
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.5473581689797906,
|
| 1277 |
+
"grad_norm": 0.31690650065908227,
|
| 1278 |
+
"learning_rate": 1.4674758263725614e-06,
|
| 1279 |
+
"loss": 0.4461,
|
| 1280 |
+
"mean_token_accuracy": 0.8644041374325753,
|
| 1281 |
+
"step": 795
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.5570976381787194,
|
| 1285 |
+
"grad_norm": 0.3261992242400567,
|
| 1286 |
+
"learning_rate": 1.4077700438107183e-06,
|
| 1287 |
+
"loss": 0.445,
|
| 1288 |
+
"mean_token_accuracy": 0.8651425749063492,
|
| 1289 |
+
"step": 800
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.566837107377648,
|
| 1293 |
+
"grad_norm": 0.37132210271715693,
|
| 1294 |
+
"learning_rate": 1.3491046364708294e-06,
|
| 1295 |
+
"loss": 0.445,
|
| 1296 |
+
"mean_token_accuracy": 0.8648254871368408,
|
| 1297 |
+
"step": 805
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.5765765765765765,
|
| 1301 |
+
"grad_norm": 0.34739884194127096,
|
| 1302 |
+
"learning_rate": 1.2914965949233572e-06,
|
| 1303 |
+
"loss": 0.4474,
|
| 1304 |
+
"mean_token_accuracy": 0.8643729150295257,
|
| 1305 |
+
"step": 810
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5863160457755052,
|
| 1309 |
+
"grad_norm": 0.3092847696386134,
|
| 1310 |
+
"learning_rate": 1.2349626035063705e-06,
|
| 1311 |
+
"loss": 0.4389,
|
| 1312 |
+
"mean_token_accuracy": 0.8666358023881913,
|
| 1313 |
+
"step": 815
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.596055514974434,
|
| 1317 |
+
"grad_norm": 0.33368514787450476,
|
| 1318 |
+
"learning_rate": 1.1795190354934587e-06,
|
| 1319 |
+
"loss": 0.4635,
|
| 1320 |
+
"mean_token_accuracy": 0.8606240957975387,
|
| 1321 |
+
"step": 820
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.6057949841733625,
|
| 1325 |
+
"grad_norm": 0.3355701607651583,
|
| 1326 |
+
"learning_rate": 1.1251819483517334e-06,
|
| 1327 |
+
"loss": 0.4469,
|
| 1328 |
+
"mean_token_accuracy": 0.8647612199187279,
|
| 1329 |
+
"step": 825
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.615534453372291,
|
| 1333 |
+
"grad_norm": 0.3215469441235877,
|
| 1334 |
+
"learning_rate": 1.0719670790912928e-06,
|
| 1335 |
+
"loss": 0.4479,
|
| 1336 |
+
"mean_token_accuracy": 0.8641064539551735,
|
| 1337 |
+
"step": 830
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.6252739225712198,
|
| 1341 |
+
"grad_norm": 0.3331920310980409,
|
| 1342 |
+
"learning_rate": 1.019889839707498e-06,
|
| 1343 |
+
"loss": 0.447,
|
| 1344 |
+
"mean_token_accuracy": 0.8645351231098175,
|
| 1345 |
+
"step": 835
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.6350133917701486,
|
| 1349 |
+
"grad_norm": 0.3311460501397384,
|
| 1350 |
+
"learning_rate": 9.689653127173743e-07,
|
| 1351 |
+
"loss": 0.4548,
|
| 1352 |
+
"mean_token_accuracy": 0.8624306350946427,
|
| 1353 |
+
"step": 840
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.6447528609690771,
|
| 1357 |
+
"grad_norm": 0.3387701231769685,
|
| 1358 |
+
"learning_rate": 9.192082467914465e-07,
|
| 1359 |
+
"loss": 0.444,
|
| 1360 |
+
"mean_token_accuracy": 0.8649628892540931,
|
| 1361 |
+
"step": 845
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.654492330168006,
|
| 1365 |
+
"grad_norm": 0.33969198086970775,
|
| 1366 |
+
"learning_rate": 8.706330524822548e-07,
|
| 1367 |
+
"loss": 0.4413,
|
| 1368 |
+
"mean_token_accuracy": 0.865912164747715,
|
| 1369 |
+
"step": 850
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.6642317993669344,
|
| 1373 |
+
"grad_norm": 0.32626435288941413,
|
| 1374 |
+
"learning_rate": 8.232537980507848e-07,
|
| 1375 |
+
"loss": 0.4454,
|
| 1376 |
+
"mean_token_accuracy": 0.8650734156370163,
|
| 1377 |
+
"step": 855
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.6739712685658632,
|
| 1381 |
+
"grad_norm": 0.32534723430048623,
|
| 1382 |
+
"learning_rate": 7.770842053920585e-07,
|
| 1383 |
+
"loss": 0.4424,
|
| 1384 |
+
"mean_token_accuracy": 0.8653772249817848,
|
| 1385 |
+
"step": 860
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.683710737764792,
|
| 1389 |
+
"grad_norm": 0.33973250353406415,
|
| 1390 |
+
"learning_rate": 7.321376460610136e-07,
|
| 1391 |
+
"loss": 0.4398,
|
| 1392 |
+
"mean_token_accuracy": 0.865781269967556,
|
| 1393 |
+
"step": 865
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.6934502069637205,
|
| 1397 |
+
"grad_norm": 0.31477206750092435,
|
| 1398 |
+
"learning_rate": 6.884271373998608e-07,
|
| 1399 |
+
"loss": 0.4402,
|
| 1400 |
+
"mean_token_accuracy": 0.8660067468881607,
|
| 1401 |
+
"step": 870
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.703189676162649,
|
| 1405 |
+
"grad_norm": 0.3537664329765484,
|
| 1406 |
+
"learning_rate": 6.459653387680248e-07,
|
| 1407 |
+
"loss": 0.4426,
|
| 1408 |
+
"mean_token_accuracy": 0.8656087100505829,
|
| 1409 |
+
"step": 875
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.7129291453615778,
|
| 1413 |
+
"grad_norm": 0.32858889216418335,
|
| 1414 |
+
"learning_rate": 6.047645478757635e-07,
|
| 1415 |
+
"loss": 0.4367,
|
| 1416 |
+
"mean_token_accuracy": 0.8670719146728516,
|
| 1417 |
+
"step": 880
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7226686145605066,
|
| 1421 |
+
"grad_norm": 0.32864732265316704,
|
| 1422 |
+
"learning_rate": 5.648366972225222e-07,
|
| 1423 |
+
"loss": 0.4527,
|
| 1424 |
+
"mean_token_accuracy": 0.8630405649542808,
|
| 1425 |
+
"step": 885
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.7324080837594351,
|
| 1429 |
+
"grad_norm": 0.3173505795175411,
|
| 1430 |
+
"learning_rate": 5.261933506410722e-07,
|
| 1431 |
+
"loss": 0.4401,
|
| 1432 |
+
"mean_token_accuracy": 0.8665132194757461,
|
| 1433 |
+
"step": 890
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 1.7421475529583637,
|
| 1437 |
+
"grad_norm": 0.36040952773775503,
|
| 1438 |
+
"learning_rate": 4.888456999484098e-07,
|
| 1439 |
+
"loss": 0.4465,
|
| 1440 |
+
"mean_token_accuracy": 0.8646954327821732,
|
| 1441 |
+
"step": 895
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.7518870221572924,
|
| 1445 |
+
"grad_norm": 0.31604383070212816,
|
| 1446 |
+
"learning_rate": 4.528045617044019e-07,
|
| 1447 |
+
"loss": 0.443,
|
| 1448 |
+
"mean_token_accuracy": 0.8652036920189857,
|
| 1449 |
+
"step": 900
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.7616264913562212,
|
| 1453 |
+
"grad_norm": 0.31389323834734445,
|
| 1454 |
+
"learning_rate": 4.180803740791156e-07,
|
| 1455 |
+
"loss": 0.4426,
|
| 1456 |
+
"mean_token_accuracy": 0.8656812936067582,
|
| 1457 |
+
"step": 905
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.7713659605551497,
|
| 1461 |
+
"grad_norm": 0.3097110381509705,
|
| 1462 |
+
"learning_rate": 3.846831938297324e-07,
|
| 1463 |
+
"loss": 0.4468,
|
| 1464 |
+
"mean_token_accuracy": 0.8643257409334183,
|
| 1465 |
+
"step": 910
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.7811054297540783,
|
| 1469 |
+
"grad_norm": 0.31179540512244613,
|
| 1470 |
+
"learning_rate": 3.5262269338792623e-07,
|
| 1471 |
+
"loss": 0.4447,
|
| 1472 |
+
"mean_token_accuracy": 0.8651932507753373,
|
| 1473 |
+
"step": 915
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.790844898953007,
|
| 1477 |
+
"grad_norm": 0.33502042463366694,
|
| 1478 |
+
"learning_rate": 3.219081580585548e-07,
|
| 1479 |
+
"loss": 0.4508,
|
| 1480 |
+
"mean_token_accuracy": 0.863429008424282,
|
| 1481 |
+
"step": 920
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.8005843681519358,
|
| 1485 |
+
"grad_norm": 0.3164739894198197,
|
| 1486 |
+
"learning_rate": 2.9254848333046817e-07,
|
| 1487 |
+
"loss": 0.4528,
|
| 1488 |
+
"mean_token_accuracy": 0.8630515649914742,
|
| 1489 |
+
"step": 925
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 1.8103238373508643,
|
| 1493 |
+
"grad_norm": 0.3030075688047627,
|
| 1494 |
+
"learning_rate": 2.645521723002037e-07,
|
| 1495 |
+
"loss": 0.4507,
|
| 1496 |
+
"mean_token_accuracy": 0.8635053560137749,
|
| 1497 |
+
"step": 930
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.8200633065497929,
|
| 1501 |
+
"grad_norm": 0.3371646202292577,
|
| 1502 |
+
"learning_rate": 2.3792733320934348e-07,
|
| 1503 |
+
"loss": 0.4441,
|
| 1504 |
+
"mean_token_accuracy": 0.8654543533921242,
|
| 1505 |
+
"step": 935
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.8298027757487216,
|
| 1509 |
+
"grad_norm": 0.3074575906934633,
|
| 1510 |
+
"learning_rate": 2.12681677096217e-07,
|
| 1511 |
+
"loss": 0.4351,
|
| 1512 |
+
"mean_token_accuracy": 0.8675669968128205,
|
| 1513 |
+
"step": 940
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.8395422449476504,
|
| 1517 |
+
"grad_norm": 0.30631898093344184,
|
| 1518 |
+
"learning_rate": 1.888225155626433e-07,
|
| 1519 |
+
"loss": 0.444,
|
| 1520 |
+
"mean_token_accuracy": 0.8653656959533691,
|
| 1521 |
+
"step": 945
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.8492817141465792,
|
| 1525 |
+
"grad_norm": 0.2958594503607962,
|
| 1526 |
+
"learning_rate": 1.6635675865635859e-07,
|
| 1527 |
+
"loss": 0.4568,
|
| 1528 |
+
"mean_token_accuracy": 0.8619549512863159,
|
| 1529 |
+
"step": 950
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.8590211833455077,
|
| 1533 |
+
"grad_norm": 0.31258753396965294,
|
| 1534 |
+
"learning_rate": 1.4529091286973994e-07,
|
| 1535 |
+
"loss": 0.444,
|
| 1536 |
+
"mean_token_accuracy": 0.8656645834445953,
|
| 1537 |
+
"step": 955
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.8687606525444362,
|
| 1541 |
+
"grad_norm": 0.30999125345039114,
|
| 1542 |
+
"learning_rate": 1.2563107925540774e-07,
|
| 1543 |
+
"loss": 0.4444,
|
| 1544 |
+
"mean_token_accuracy": 0.8654705569148063,
|
| 1545 |
+
"step": 960
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.878500121743365,
|
| 1549 |
+
"grad_norm": 0.3160340098992061,
|
| 1550 |
+
"learning_rate": 1.0738295165924783e-07,
|
| 1551 |
+
"loss": 0.4459,
|
| 1552 |
+
"mean_token_accuracy": 0.8648449763655662,
|
| 1553 |
+
"step": 965
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.8882395909422938,
|
| 1557 |
+
"grad_norm": 0.3187758679651324,
|
| 1558 |
+
"learning_rate": 9.055181507137245e-08,
|
| 1559 |
+
"loss": 0.444,
|
| 1560 |
+
"mean_token_accuracy": 0.8654528453946113,
|
| 1561 |
+
"step": 970
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.8979790601412223,
|
| 1565 |
+
"grad_norm": 0.33617665839091787,
|
| 1566 |
+
"learning_rate": 7.514254409549005e-08,
|
| 1567 |
+
"loss": 0.4481,
|
| 1568 |
+
"mean_token_accuracy": 0.8641701668500901,
|
| 1569 |
+
"step": 975
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.9077185293401508,
|
| 1573 |
+
"grad_norm": 0.31232672260705024,
|
| 1574 |
+
"learning_rate": 6.115960153712963e-08,
|
| 1575 |
+
"loss": 0.4414,
|
| 1576 |
+
"mean_token_accuracy": 0.8660656422376632,
|
| 1577 |
+
"step": 980
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.9174579985390796,
|
| 1581 |
+
"grad_norm": 0.303119007372895,
|
| 1582 |
+
"learning_rate": 4.860703711113246e-08,
|
| 1583 |
+
"loss": 0.4362,
|
| 1584 |
+
"mean_token_accuracy": 0.8676238685846329,
|
| 1585 |
+
"step": 985
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9271974677380084,
|
| 1589 |
+
"grad_norm": 0.30341116951092534,
|
| 1590 |
+
"learning_rate": 3.748848626878132e-08,
|
| 1591 |
+
"loss": 0.4508,
|
| 1592 |
+
"mean_token_accuracy": 0.8636912703514099,
|
| 1593 |
+
"step": 990
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.936936936936937,
|
| 1597 |
+
"grad_norm": 0.31515978754450974,
|
| 1598 |
+
"learning_rate": 2.7807169144906108e-08,
|
| 1599 |
+
"loss": 0.4528,
|
| 1600 |
+
"mean_token_accuracy": 0.8630853027105332,
|
| 1601 |
+
"step": 995
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 1.9466764061358655,
|
| 1605 |
+
"grad_norm": 0.30748596132213357,
|
| 1606 |
+
"learning_rate": 1.9565889625275945e-08,
|
| 1607 |
+
"loss": 0.4558,
|
| 1608 |
+
"mean_token_accuracy": 0.8628044292330742,
|
| 1609 |
+
"step": 1000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 1.9564158753347942,
|
| 1613 |
+
"grad_norm": 0.30248992557073057,
|
| 1614 |
+
"learning_rate": 1.2767034534540978e-08,
|
| 1615 |
+
"loss": 0.4467,
|
| 1616 |
+
"mean_token_accuracy": 0.86439578384161,
|
| 1617 |
+
"step": 1005
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.966155344533723,
|
| 1621 |
+
"grad_norm": 0.3256862744869616,
|
| 1622 |
+
"learning_rate": 7.412572944965335e-09,
|
| 1623 |
+
"loss": 0.4548,
|
| 1624 |
+
"mean_token_accuracy": 0.8625592529773712,
|
| 1625 |
+
"step": 1010
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.9758948137326515,
|
| 1629 |
+
"grad_norm": 0.3147340514506444,
|
| 1630 |
+
"learning_rate": 3.5040556061483043e-09,
|
| 1631 |
+
"loss": 0.4422,
|
| 1632 |
+
"mean_token_accuracy": 0.8657747611403466,
|
| 1633 |
+
"step": 1015
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.98563428293158,
|
| 1637 |
+
"grad_norm": 0.32764257560082577,
|
| 1638 |
+
"learning_rate": 1.0426144958985974e-09,
|
| 1639 |
+
"loss": 0.4419,
|
| 1640 |
+
"mean_token_accuracy": 0.8660721600055694,
|
| 1641 |
+
"step": 1020
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.9953737521305088,
|
| 1645 |
+
"grad_norm": 0.3098108021812636,
|
| 1646 |
+
"learning_rate": 2.8962492393258546e-11,
|
| 1647 |
+
"loss": 0.4452,
|
| 1648 |
+
"mean_token_accuracy": 0.8650736406445503,
|
| 1649 |
+
"step": 1025
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.9973216459702945,
|
| 1653 |
+
"mean_token_accuracy": 0.8681519404053688,
|
| 1654 |
+
"step": 1026,
|
| 1655 |
+
"total_flos": 1074983740637184.0,
|
| 1656 |
+
"train_loss": 0.49954891321022377,
|
| 1657 |
+
"train_runtime": 168401.8035,
|
| 1658 |
+
"train_samples_per_second": 0.78,
|
| 1659 |
+
"train_steps_per_second": 0.006
|
| 1660 |
+
}
|
| 1661 |
+
],
|
| 1662 |
+
"logging_steps": 5,
|
| 1663 |
+
"max_steps": 1026,
|
| 1664 |
+
"num_input_tokens_seen": 0,
|
| 1665 |
+
"num_train_epochs": 2,
|
| 1666 |
+
"save_steps": 50,
|
| 1667 |
+
"stateful_callbacks": {
|
| 1668 |
+
"TrainerControl": {
|
| 1669 |
+
"args": {
|
| 1670 |
+
"should_epoch_stop": false,
|
| 1671 |
+
"should_evaluate": false,
|
| 1672 |
+
"should_log": false,
|
| 1673 |
+
"should_save": true,
|
| 1674 |
+
"should_training_stop": true
|
| 1675 |
+
},
|
| 1676 |
+
"attributes": {}
|
| 1677 |
+
}
|
| 1678 |
+
},
|
| 1679 |
+
"total_flos": 1074983740637184.0,
|
| 1680 |
+
"train_batch_size": 2,
|
| 1681 |
+
"trial_name": null,
|
| 1682 |
+
"trial_params": null
|
| 1683 |
+
}
|