Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +1520 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Open-R1-Distill-eos-epic-new
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Open-R1-Distill-eos-epic-new
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-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="flyingbugs/Qwen2.5-1.5B-Open-R1-Distill-eos-epic-new", 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/jjh233/huggingface/runs/sk5qkneu)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.54.0
|
| 39 |
+
- Pytorch: 2.7.1
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
+
- Tokenizers: 0.21.2
|
| 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": 962656789856256.0,
|
| 3 |
+
"train_loss": 0.5030564876329718,
|
| 4 |
+
"train_runtime": 14725.7023,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.293,
|
| 7 |
+
"train_steps_per_second": 0.072
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.54.0"
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 962656789856256.0,
|
| 3 |
+
"train_loss": 0.5030564876329718,
|
| 4 |
+
"train_runtime": 14725.7023,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.293,
|
| 7 |
+
"train_steps_per_second": 0.072
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1520 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1056,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.014204545454545454,
|
| 14 |
+
"grad_norm": 16.233426918647123,
|
| 15 |
+
"learning_rate": 3.7735849056603773e-06,
|
| 16 |
+
"loss": 1.9367,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.028409090909090908,
|
| 21 |
+
"grad_norm": 3.700378147836118,
|
| 22 |
+
"learning_rate": 8.49056603773585e-06,
|
| 23 |
+
"loss": 1.5623,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04261363636363636,
|
| 28 |
+
"grad_norm": 1.411828049687858,
|
| 29 |
+
"learning_rate": 1.320754716981132e-05,
|
| 30 |
+
"loss": 1.0659,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.056818181818181816,
|
| 35 |
+
"grad_norm": 0.5502005679393165,
|
| 36 |
+
"learning_rate": 1.7924528301886792e-05,
|
| 37 |
+
"loss": 0.876,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.07102272727272728,
|
| 42 |
+
"grad_norm": 0.39964518009977995,
|
| 43 |
+
"learning_rate": 2.2641509433962265e-05,
|
| 44 |
+
"loss": 0.7709,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08522727272727272,
|
| 49 |
+
"grad_norm": 0.2819938310171901,
|
| 50 |
+
"learning_rate": 2.7358490566037738e-05,
|
| 51 |
+
"loss": 0.7212,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09943181818181818,
|
| 56 |
+
"grad_norm": 0.22596397421278658,
|
| 57 |
+
"learning_rate": 3.207547169811321e-05,
|
| 58 |
+
"loss": 0.6941,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11363636363636363,
|
| 63 |
+
"grad_norm": 0.19821070636934998,
|
| 64 |
+
"learning_rate": 3.679245283018868e-05,
|
| 65 |
+
"loss": 0.6626,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1278409090909091,
|
| 70 |
+
"grad_norm": 0.1776825768871472,
|
| 71 |
+
"learning_rate": 4.150943396226415e-05,
|
| 72 |
+
"loss": 0.6458,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14204545454545456,
|
| 77 |
+
"grad_norm": 0.15959969460809642,
|
| 78 |
+
"learning_rate": 4.6226415094339625e-05,
|
| 79 |
+
"loss": 0.6317,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15625,
|
| 84 |
+
"grad_norm": 0.16520239332693426,
|
| 85 |
+
"learning_rate": 4.999988963025308e-05,
|
| 86 |
+
"loss": 0.6111,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.17045454545454544,
|
| 91 |
+
"grad_norm": 0.14604811373242252,
|
| 92 |
+
"learning_rate": 4.999602680280325e-05,
|
| 93 |
+
"loss": 0.6049,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1846590909090909,
|
| 98 |
+
"grad_norm": 0.153405093129135,
|
| 99 |
+
"learning_rate": 4.998664657075762e-05,
|
| 100 |
+
"loss": 0.5878,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.19886363636363635,
|
| 105 |
+
"grad_norm": 0.13290633271306487,
|
| 106 |
+
"learning_rate": 4.9971751234724005e-05,
|
| 107 |
+
"loss": 0.5872,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.21306818181818182,
|
| 112 |
+
"grad_norm": 0.14464611604457972,
|
| 113 |
+
"learning_rate": 4.995134444795177e-05,
|
| 114 |
+
"loss": 0.5809,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.22727272727272727,
|
| 119 |
+
"grad_norm": 0.1539967921458611,
|
| 120 |
+
"learning_rate": 4.992543121543581e-05,
|
| 121 |
+
"loss": 0.5687,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.24147727272727273,
|
| 126 |
+
"grad_norm": 0.1872261556450498,
|
| 127 |
+
"learning_rate": 4.9894017892689e-05,
|
| 128 |
+
"loss": 0.5736,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2556818181818182,
|
| 133 |
+
"grad_norm": 0.1461192468496281,
|
| 134 |
+
"learning_rate": 4.985711218418346e-05,
|
| 135 |
+
"loss": 0.5729,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.26988636363636365,
|
| 140 |
+
"grad_norm": 0.15510991989675932,
|
| 141 |
+
"learning_rate": 4.981472314146093e-05,
|
| 142 |
+
"loss": 0.5651,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2840909090909091,
|
| 147 |
+
"grad_norm": 0.15383826812713372,
|
| 148 |
+
"learning_rate": 4.976686116091281e-05,
|
| 149 |
+
"loss": 0.5669,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.29829545454545453,
|
| 154 |
+
"grad_norm": 0.12937769599328974,
|
| 155 |
+
"learning_rate": 4.971353798123026e-05,
|
| 156 |
+
"loss": 0.5608,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3125,
|
| 161 |
+
"grad_norm": 0.14866942632641453,
|
| 162 |
+
"learning_rate": 4.965476668052522e-05,
|
| 163 |
+
"loss": 0.5547,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.32670454545454547,
|
| 168 |
+
"grad_norm": 0.15767211601593334,
|
| 169 |
+
"learning_rate": 4.959056167312283e-05,
|
| 170 |
+
"loss": 0.5572,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3409090909090909,
|
| 175 |
+
"grad_norm": 0.16235663995148145,
|
| 176 |
+
"learning_rate": 4.952093870602615e-05,
|
| 177 |
+
"loss": 0.5613,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.35511363636363635,
|
| 182 |
+
"grad_norm": 0.15329109428934323,
|
| 183 |
+
"learning_rate": 4.944591485505405e-05,
|
| 184 |
+
"loss": 0.5515,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3693181818181818,
|
| 189 |
+
"grad_norm": 0.16475626406284527,
|
| 190 |
+
"learning_rate": 4.93655085206531e-05,
|
| 191 |
+
"loss": 0.5538,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3835227272727273,
|
| 196 |
+
"grad_norm": 0.17396494811540575,
|
| 197 |
+
"learning_rate": 4.92797394233848e-05,
|
| 198 |
+
"loss": 0.5455,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3977272727272727,
|
| 203 |
+
"grad_norm": 0.1684931659310488,
|
| 204 |
+
"learning_rate": 4.918862859908871e-05,
|
| 205 |
+
"loss": 0.5439,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4119318181818182,
|
| 210 |
+
"grad_norm": 0.15970431189153267,
|
| 211 |
+
"learning_rate": 4.909219839372333e-05,
|
| 212 |
+
"loss": 0.5431,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.42613636363636365,
|
| 217 |
+
"grad_norm": 0.1333165751370488,
|
| 218 |
+
"learning_rate": 4.8990472457885386e-05,
|
| 219 |
+
"loss": 0.5367,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.4403409090909091,
|
| 224 |
+
"grad_norm": 0.15417885622445218,
|
| 225 |
+
"learning_rate": 4.8883475741009324e-05,
|
| 226 |
+
"loss": 0.5381,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.45454545454545453,
|
| 231 |
+
"grad_norm": 0.1416173613974234,
|
| 232 |
+
"learning_rate": 4.877123448524815e-05,
|
| 233 |
+
"loss": 0.5356,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.46875,
|
| 238 |
+
"grad_norm": 0.13087882893136601,
|
| 239 |
+
"learning_rate": 4.865377621903726e-05,
|
| 240 |
+
"loss": 0.5288,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.48295454545454547,
|
| 245 |
+
"grad_norm": 0.14764636629826566,
|
| 246 |
+
"learning_rate": 4.853112975034276e-05,
|
| 247 |
+
"loss": 0.5347,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4971590909090909,
|
| 252 |
+
"grad_norm": 0.16758747023050016,
|
| 253 |
+
"learning_rate": 4.840332515959601e-05,
|
| 254 |
+
"loss": 0.5372,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.5113636363636364,
|
| 259 |
+
"grad_norm": 0.18224306322957698,
|
| 260 |
+
"learning_rate": 4.827039379231604e-05,
|
| 261 |
+
"loss": 0.5275,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5255681818181818,
|
| 266 |
+
"grad_norm": 0.1662865774101808,
|
| 267 |
+
"learning_rate": 4.813236825142173e-05,
|
| 268 |
+
"loss": 0.5408,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5397727272727273,
|
| 273 |
+
"grad_norm": 0.17763881404547607,
|
| 274 |
+
"learning_rate": 4.798928238923555e-05,
|
| 275 |
+
"loss": 0.5289,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5539772727272727,
|
| 280 |
+
"grad_norm": 0.16091215915603133,
|
| 281 |
+
"learning_rate": 4.7841171299180906e-05,
|
| 282 |
+
"loss": 0.5397,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5681818181818182,
|
| 287 |
+
"grad_norm": 0.1404358353075446,
|
| 288 |
+
"learning_rate": 4.768807130717508e-05,
|
| 289 |
+
"loss": 0.5256,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5823863636363636,
|
| 294 |
+
"grad_norm": 0.166459644318507,
|
| 295 |
+
"learning_rate": 4.753001996271991e-05,
|
| 296 |
+
"loss": 0.5235,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5965909090909091,
|
| 301 |
+
"grad_norm": 0.13606607208723026,
|
| 302 |
+
"learning_rate": 4.73670560296923e-05,
|
| 303 |
+
"loss": 0.5291,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6107954545454546,
|
| 308 |
+
"grad_norm": 0.1370837785726949,
|
| 309 |
+
"learning_rate": 4.7199219476837034e-05,
|
| 310 |
+
"loss": 0.5254,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.625,
|
| 315 |
+
"grad_norm": 0.130041325528082,
|
| 316 |
+
"learning_rate": 4.702655146796385e-05,
|
| 317 |
+
"loss": 0.5281,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6392045454545454,
|
| 322 |
+
"grad_norm": 0.13838008337473828,
|
| 323 |
+
"learning_rate": 4.684909435185169e-05,
|
| 324 |
+
"loss": 0.5163,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6534090909090909,
|
| 329 |
+
"grad_norm": 0.1249145523375738,
|
| 330 |
+
"learning_rate": 4.6666891651862096e-05,
|
| 331 |
+
"loss": 0.5164,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6676136363636364,
|
| 336 |
+
"grad_norm": 0.11918127255464575,
|
| 337 |
+
"learning_rate": 4.6479988055264654e-05,
|
| 338 |
+
"loss": 0.5156,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6818181818181818,
|
| 343 |
+
"grad_norm": 0.13410033100059227,
|
| 344 |
+
"learning_rate": 4.628842940227693e-05,
|
| 345 |
+
"loss": 0.5267,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6960227272727273,
|
| 350 |
+
"grad_norm": 0.14513137581304156,
|
| 351 |
+
"learning_rate": 4.609226267482162e-05,
|
| 352 |
+
"loss": 0.516,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.7102272727272727,
|
| 357 |
+
"grad_norm": 0.17472387433508568,
|
| 358 |
+
"learning_rate": 4.589153598500372e-05,
|
| 359 |
+
"loss": 0.5103,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.7244318181818182,
|
| 364 |
+
"grad_norm": 0.13807513906855917,
|
| 365 |
+
"learning_rate": 4.568629856331049e-05,
|
| 366 |
+
"loss": 0.5111,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.7386363636363636,
|
| 371 |
+
"grad_norm": 0.1606554123531758,
|
| 372 |
+
"learning_rate": 4.547660074653713e-05,
|
| 373 |
+
"loss": 0.5106,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7528409090909091,
|
| 378 |
+
"grad_norm": 0.13512067917257073,
|
| 379 |
+
"learning_rate": 4.526249396544107e-05,
|
| 380 |
+
"loss": 0.52,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7670454545454546,
|
| 385 |
+
"grad_norm": 0.12966854507444983,
|
| 386 |
+
"learning_rate": 4.504403073212805e-05,
|
| 387 |
+
"loss": 0.5137,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.78125,
|
| 392 |
+
"grad_norm": 0.14417839979685987,
|
| 393 |
+
"learning_rate": 4.482126462717289e-05,
|
| 394 |
+
"loss": 0.5131,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7954545454545454,
|
| 399 |
+
"grad_norm": 0.14967027976448785,
|
| 400 |
+
"learning_rate": 4.45942502864783e-05,
|
| 401 |
+
"loss": 0.5164,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8096590909090909,
|
| 406 |
+
"grad_norm": 0.13862324342167873,
|
| 407 |
+
"learning_rate": 4.436304338787472e-05,
|
| 408 |
+
"loss": 0.5083,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.8238636363636364,
|
| 413 |
+
"grad_norm": 0.1285629705362091,
|
| 414 |
+
"learning_rate": 4.4127700637464834e-05,
|
| 415 |
+
"loss": 0.5196,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.8380681818181818,
|
| 420 |
+
"grad_norm": 0.12976169635746898,
|
| 421 |
+
"learning_rate": 4.388827975571561e-05,
|
| 422 |
+
"loss": 0.5125,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8522727272727273,
|
| 427 |
+
"grad_norm": 0.14210550405367858,
|
| 428 |
+
"learning_rate": 4.364483946330182e-05,
|
| 429 |
+
"loss": 0.5051,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8664772727272727,
|
| 434 |
+
"grad_norm": 0.16907430743029442,
|
| 435 |
+
"learning_rate": 4.3397439466704074e-05,
|
| 436 |
+
"loss": 0.5135,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8806818181818182,
|
| 441 |
+
"grad_norm": 0.16584741007419773,
|
| 442 |
+
"learning_rate": 4.314614044356517e-05,
|
| 443 |
+
"loss": 0.5104,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8948863636363636,
|
| 448 |
+
"grad_norm": 0.15722645631531904,
|
| 449 |
+
"learning_rate": 4.289100402780813e-05,
|
| 450 |
+
"loss": 0.5044,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.9090909090909091,
|
| 455 |
+
"grad_norm": 0.13402395269180703,
|
| 456 |
+
"learning_rate": 4.2632092794519926e-05,
|
| 457 |
+
"loss": 0.5126,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.9232954545454546,
|
| 462 |
+
"grad_norm": 0.12897493665476578,
|
| 463 |
+
"learning_rate": 4.236947024460409e-05,
|
| 464 |
+
"loss": 0.5073,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9375,
|
| 469 |
+
"grad_norm": 0.12307110209575203,
|
| 470 |
+
"learning_rate": 4.2103200789206496e-05,
|
| 471 |
+
"loss": 0.5064,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.9517045454545454,
|
| 476 |
+
"grad_norm": 0.13103687604123465,
|
| 477 |
+
"learning_rate": 4.1833349733917774e-05,
|
| 478 |
+
"loss": 0.5018,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9659090909090909,
|
| 483 |
+
"grad_norm": 0.1441008725503634,
|
| 484 |
+
"learning_rate": 4.155998326275636e-05,
|
| 485 |
+
"loss": 0.5016,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9801136363636364,
|
| 490 |
+
"grad_norm": 0.14676840920070153,
|
| 491 |
+
"learning_rate": 4.128316842193612e-05,
|
| 492 |
+
"loss": 0.5017,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9943181818181818,
|
| 497 |
+
"grad_norm": 0.1299772490214553,
|
| 498 |
+
"learning_rate": 4.100297310342252e-05,
|
| 499 |
+
"loss": 0.5084,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.0085227272727273,
|
| 504 |
+
"grad_norm": 0.11841362182036683,
|
| 505 |
+
"learning_rate": 4.071946602828136e-05,
|
| 506 |
+
"loss": 0.484,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.0227272727272727,
|
| 511 |
+
"grad_norm": 0.1320677520863094,
|
| 512 |
+
"learning_rate": 4.043271672982416e-05,
|
| 513 |
+
"loss": 0.4757,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0369318181818181,
|
| 518 |
+
"grad_norm": 0.1525515212145726,
|
| 519 |
+
"learning_rate": 4.014279553655429e-05,
|
| 520 |
+
"loss": 0.4712,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0511363636363635,
|
| 525 |
+
"grad_norm": 0.12388717475970465,
|
| 526 |
+
"learning_rate": 3.984977355491816e-05,
|
| 527 |
+
"loss": 0.4741,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0653409090909092,
|
| 532 |
+
"grad_norm": 0.12285428485981521,
|
| 533 |
+
"learning_rate": 3.9553722651865525e-05,
|
| 534 |
+
"loss": 0.4805,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0795454545454546,
|
| 539 |
+
"grad_norm": 0.14068486142094294,
|
| 540 |
+
"learning_rate": 3.925471543722334e-05,
|
| 541 |
+
"loss": 0.476,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.09375,
|
| 546 |
+
"grad_norm": 0.11956188719769793,
|
| 547 |
+
"learning_rate": 3.895282524588736e-05,
|
| 548 |
+
"loss": 0.4744,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.1079545454545454,
|
| 553 |
+
"grad_norm": 0.12566341647227572,
|
| 554 |
+
"learning_rate": 3.8648126119835895e-05,
|
| 555 |
+
"loss": 0.4728,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.1221590909090908,
|
| 560 |
+
"grad_norm": 0.11910968307671285,
|
| 561 |
+
"learning_rate": 3.834069278997025e-05,
|
| 562 |
+
"loss": 0.4672,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.1363636363636362,
|
| 567 |
+
"grad_norm": 0.1357524801191257,
|
| 568 |
+
"learning_rate": 3.803060065778607e-05,
|
| 569 |
+
"loss": 0.4765,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1505681818181819,
|
| 574 |
+
"grad_norm": 0.12366787866403461,
|
| 575 |
+
"learning_rate": 3.77179257768803e-05,
|
| 576 |
+
"loss": 0.4769,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1647727272727273,
|
| 581 |
+
"grad_norm": 0.1322634035357931,
|
| 582 |
+
"learning_rate": 3.740274483429815e-05,
|
| 583 |
+
"loss": 0.4808,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1789772727272727,
|
| 588 |
+
"grad_norm": 0.13258784372135785,
|
| 589 |
+
"learning_rate": 3.708513513172481e-05,
|
| 590 |
+
"loss": 0.4763,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.1931818181818181,
|
| 595 |
+
"grad_norm": 0.1356892941793857,
|
| 596 |
+
"learning_rate": 3.67651745665262e-05,
|
| 597 |
+
"loss": 0.4772,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.2073863636363638,
|
| 602 |
+
"grad_norm": 0.12523099567966772,
|
| 603 |
+
"learning_rate": 3.644294161264394e-05,
|
| 604 |
+
"loss": 0.4691,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.2215909090909092,
|
| 609 |
+
"grad_norm": 0.12166675336360953,
|
| 610 |
+
"learning_rate": 3.611851530134856e-05,
|
| 611 |
+
"loss": 0.4763,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.2357954545454546,
|
| 616 |
+
"grad_norm": 0.11908896334134955,
|
| 617 |
+
"learning_rate": 3.579197520185628e-05,
|
| 618 |
+
"loss": 0.4772,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.25,
|
| 623 |
+
"grad_norm": 0.1273632443581102,
|
| 624 |
+
"learning_rate": 3.546340140181376e-05,
|
| 625 |
+
"loss": 0.4887,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.2642045454545454,
|
| 630 |
+
"grad_norm": 0.11548733790030413,
|
| 631 |
+
"learning_rate": 3.5132874487655685e-05,
|
| 632 |
+
"loss": 0.4688,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2784090909090908,
|
| 637 |
+
"grad_norm": 0.1251859404517232,
|
| 638 |
+
"learning_rate": 3.480047552484001e-05,
|
| 639 |
+
"loss": 0.4695,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.2926136363636362,
|
| 644 |
+
"grad_norm": 0.11622578447126647,
|
| 645 |
+
"learning_rate": 3.4466286037965786e-05,
|
| 646 |
+
"loss": 0.476,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.3068181818181819,
|
| 651 |
+
"grad_norm": 0.12517918383447438,
|
| 652 |
+
"learning_rate": 3.4130387990778286e-05,
|
| 653 |
+
"loss": 0.4805,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.3210227272727273,
|
| 658 |
+
"grad_norm": 0.12611864483533994,
|
| 659 |
+
"learning_rate": 3.379286376606651e-05,
|
| 660 |
+
"loss": 0.4754,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.3352272727272727,
|
| 665 |
+
"grad_norm": 0.13719373565556317,
|
| 666 |
+
"learning_rate": 3.3453796145457835e-05,
|
| 667 |
+
"loss": 0.4659,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.3494318181818181,
|
| 672 |
+
"grad_norm": 0.11875949906730647,
|
| 673 |
+
"learning_rate": 3.311326828911494e-05,
|
| 674 |
+
"loss": 0.4769,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.3636363636363638,
|
| 679 |
+
"grad_norm": 0.13353175627047656,
|
| 680 |
+
"learning_rate": 3.277136371533981e-05,
|
| 681 |
+
"loss": 0.4759,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.3778409090909092,
|
| 686 |
+
"grad_norm": 0.1417715943995476,
|
| 687 |
+
"learning_rate": 3.2428166280089885e-05,
|
| 688 |
+
"loss": 0.4744,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.3920454545454546,
|
| 693 |
+
"grad_norm": 0.14007028648406247,
|
| 694 |
+
"learning_rate": 3.20837601564115e-05,
|
| 695 |
+
"loss": 0.4734,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.40625,
|
| 700 |
+
"grad_norm": 0.12629456979175258,
|
| 701 |
+
"learning_rate": 3.173822981379548e-05,
|
| 702 |
+
"loss": 0.4724,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.4204545454545454,
|
| 707 |
+
"grad_norm": 0.12349607254647936,
|
| 708 |
+
"learning_rate": 3.1391659997460064e-05,
|
| 709 |
+
"loss": 0.4713,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.4346590909090908,
|
| 714 |
+
"grad_norm": 0.11464965836513225,
|
| 715 |
+
"learning_rate": 3.104413570756612e-05,
|
| 716 |
+
"loss": 0.4708,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.4488636363636362,
|
| 721 |
+
"grad_norm": 0.1208312662969904,
|
| 722 |
+
"learning_rate": 3.069574217836993e-05,
|
| 723 |
+
"loss": 0.4803,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.4630681818181819,
|
| 728 |
+
"grad_norm": 0.10698876943855158,
|
| 729 |
+
"learning_rate": 3.0346564857318567e-05,
|
| 730 |
+
"loss": 0.4633,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.4772727272727273,
|
| 735 |
+
"grad_norm": 0.11384636090749484,
|
| 736 |
+
"learning_rate": 2.9996689384092874e-05,
|
| 737 |
+
"loss": 0.4699,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.4914772727272727,
|
| 742 |
+
"grad_norm": 0.11145569232907346,
|
| 743 |
+
"learning_rate": 2.964620156960342e-05,
|
| 744 |
+
"loss": 0.4744,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5056818181818183,
|
| 749 |
+
"grad_norm": 0.13346919699354048,
|
| 750 |
+
"learning_rate": 2.929518737494437e-05,
|
| 751 |
+
"loss": 0.4747,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.5198863636363638,
|
| 756 |
+
"grad_norm": 0.11742663104280518,
|
| 757 |
+
"learning_rate": 2.8943732890310577e-05,
|
| 758 |
+
"loss": 0.4713,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.5340909090909092,
|
| 763 |
+
"grad_norm": 0.12233693509061423,
|
| 764 |
+
"learning_rate": 2.859192431388298e-05,
|
| 765 |
+
"loss": 0.4747,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.5482954545454546,
|
| 770 |
+
"grad_norm": 0.11567941988020804,
|
| 771 |
+
"learning_rate": 2.8239847930687522e-05,
|
| 772 |
+
"loss": 0.4776,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.5625,
|
| 777 |
+
"grad_norm": 0.12718334961619032,
|
| 778 |
+
"learning_rate": 2.788759009143279e-05,
|
| 779 |
+
"loss": 0.4686,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.5767045454545454,
|
| 784 |
+
"grad_norm": 0.10446651216785705,
|
| 785 |
+
"learning_rate": 2.753523719133152e-05,
|
| 786 |
+
"loss": 0.4712,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.5909090909090908,
|
| 791 |
+
"grad_norm": 0.11060336379300346,
|
| 792 |
+
"learning_rate": 2.7182875648911177e-05,
|
| 793 |
+
"loss": 0.4739,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.6051136363636362,
|
| 798 |
+
"grad_norm": 0.11390898204723482,
|
| 799 |
+
"learning_rate": 2.683059188481887e-05,
|
| 800 |
+
"loss": 0.4638,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.6193181818181817,
|
| 805 |
+
"grad_norm": 0.11190601188366513,
|
| 806 |
+
"learning_rate": 2.647847230062567e-05,
|
| 807 |
+
"loss": 0.4711,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.6335227272727273,
|
| 812 |
+
"grad_norm": 0.11305263482331018,
|
| 813 |
+
"learning_rate": 2.6126603257635733e-05,
|
| 814 |
+
"loss": 0.4691,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.6477272727272727,
|
| 819 |
+
"grad_norm": 0.1265534565322895,
|
| 820 |
+
"learning_rate": 2.5775071055705075e-05,
|
| 821 |
+
"loss": 0.4791,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.6619318181818183,
|
| 826 |
+
"grad_norm": 0.11028857191690714,
|
| 827 |
+
"learning_rate": 2.5423961912075712e-05,
|
| 828 |
+
"loss": 0.4741,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.6761363636363638,
|
| 833 |
+
"grad_norm": 0.11709279310297076,
|
| 834 |
+
"learning_rate": 2.5073361940229773e-05,
|
| 835 |
+
"loss": 0.4627,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.6903409090909092,
|
| 840 |
+
"grad_norm": 0.12689675181012736,
|
| 841 |
+
"learning_rate": 2.4723357128769286e-05,
|
| 842 |
+
"loss": 0.4716,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.7045454545454546,
|
| 847 |
+
"grad_norm": 0.12232567128887789,
|
| 848 |
+
"learning_rate": 2.4374033320326506e-05,
|
| 849 |
+
"loss": 0.4718,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.71875,
|
| 854 |
+
"grad_norm": 0.11216636447930772,
|
| 855 |
+
"learning_rate": 2.4025476190509938e-05,
|
| 856 |
+
"loss": 0.4703,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.7329545454545454,
|
| 861 |
+
"grad_norm": 0.11075120188097681,
|
| 862 |
+
"learning_rate": 2.3677771226891564e-05,
|
| 863 |
+
"loss": 0.4749,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.7471590909090908,
|
| 868 |
+
"grad_norm": 0.1296834181423037,
|
| 869 |
+
"learning_rate": 2.3331003708039932e-05,
|
| 870 |
+
"loss": 0.4756,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.7613636363636362,
|
| 875 |
+
"grad_norm": 0.10873440353655982,
|
| 876 |
+
"learning_rate": 2.2985258682604706e-05,
|
| 877 |
+
"loss": 0.4753,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.7755681818181817,
|
| 882 |
+
"grad_norm": 0.11054731896051188,
|
| 883 |
+
"learning_rate": 2.264062094845749e-05,
|
| 884 |
+
"loss": 0.4681,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.7897727272727273,
|
| 889 |
+
"grad_norm": 0.1077785017076799,
|
| 890 |
+
"learning_rate": 2.229717503189418e-05,
|
| 891 |
+
"loss": 0.4667,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.8039772727272727,
|
| 896 |
+
"grad_norm": 0.12146741261267094,
|
| 897 |
+
"learning_rate": 2.195500516690398e-05,
|
| 898 |
+
"loss": 0.4667,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.8181818181818183,
|
| 903 |
+
"grad_norm": 0.11013296161652279,
|
| 904 |
+
"learning_rate": 2.1614195274510002e-05,
|
| 905 |
+
"loss": 0.4692,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.8323863636363638,
|
| 910 |
+
"grad_norm": 0.1122431509566975,
|
| 911 |
+
"learning_rate": 2.1274828942186743e-05,
|
| 912 |
+
"loss": 0.4761,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.8465909090909092,
|
| 917 |
+
"grad_norm": 0.11152245824612014,
|
| 918 |
+
"learning_rate": 2.09369894033593e-05,
|
| 919 |
+
"loss": 0.4611,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.8607954545454546,
|
| 924 |
+
"grad_norm": 0.10540289603858785,
|
| 925 |
+
"learning_rate": 2.0600759516989397e-05,
|
| 926 |
+
"loss": 0.4659,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.875,
|
| 931 |
+
"grad_norm": 0.12268974044452592,
|
| 932 |
+
"learning_rate": 2.026622174725336e-05,
|
| 933 |
+
"loss": 0.4659,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.8892045454545454,
|
| 938 |
+
"grad_norm": 0.11217674945544069,
|
| 939 |
+
"learning_rate": 1.9933458143316748e-05,
|
| 940 |
+
"loss": 0.4683,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.9034090909090908,
|
| 945 |
+
"grad_norm": 0.11593305886838406,
|
| 946 |
+
"learning_rate": 1.9602550319210967e-05,
|
| 947 |
+
"loss": 0.4655,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.9176136363636362,
|
| 952 |
+
"grad_norm": 0.11394452786176468,
|
| 953 |
+
"learning_rate": 1.9273579433816452e-05,
|
| 954 |
+
"loss": 0.4634,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.9318181818181817,
|
| 959 |
+
"grad_norm": 0.12344588418657035,
|
| 960 |
+
"learning_rate": 1.894662617095753e-05,
|
| 961 |
+
"loss": 0.4605,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.9460227272727273,
|
| 966 |
+
"grad_norm": 0.10588427958742584,
|
| 967 |
+
"learning_rate": 1.8621770719613862e-05,
|
| 968 |
+
"loss": 0.4636,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.9602272727272727,
|
| 973 |
+
"grad_norm": 0.10548340772355062,
|
| 974 |
+
"learning_rate": 1.829909275425309e-05,
|
| 975 |
+
"loss": 0.4694,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.9744318181818183,
|
| 980 |
+
"grad_norm": 0.10424071348650422,
|
| 981 |
+
"learning_rate": 1.7978671415289878e-05,
|
| 982 |
+
"loss": 0.4705,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.9886363636363638,
|
| 987 |
+
"grad_norm": 0.1105427740992237,
|
| 988 |
+
"learning_rate": 1.7660585289675758e-05,
|
| 989 |
+
"loss": 0.4631,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.002840909090909,
|
| 994 |
+
"grad_norm": 0.12132401905710084,
|
| 995 |
+
"learning_rate": 1.7344912391624826e-05,
|
| 996 |
+
"loss": 0.4573,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.0170454545454546,
|
| 1001 |
+
"grad_norm": 0.11150850216312608,
|
| 1002 |
+
"learning_rate": 1.7031730143479873e-05,
|
| 1003 |
+
"loss": 0.4495,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.03125,
|
| 1008 |
+
"grad_norm": 0.1062932021752816,
|
| 1009 |
+
"learning_rate": 1.672111535672367e-05,
|
| 1010 |
+
"loss": 0.4361,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.0454545454545454,
|
| 1015 |
+
"grad_norm": 0.10247863399966832,
|
| 1016 |
+
"learning_rate": 1.64131442131401e-05,
|
| 1017 |
+
"loss": 0.4437,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.059659090909091,
|
| 1022 |
+
"grad_norm": 0.10677014234090489,
|
| 1023 |
+
"learning_rate": 1.6107892246129692e-05,
|
| 1024 |
+
"loss": 0.4434,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.0738636363636362,
|
| 1029 |
+
"grad_norm": 0.10650883791134519,
|
| 1030 |
+
"learning_rate": 1.5805434322184224e-05,
|
| 1031 |
+
"loss": 0.4445,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.0880681818181817,
|
| 1036 |
+
"grad_norm": 0.10387373586373833,
|
| 1037 |
+
"learning_rate": 1.550584462252487e-05,
|
| 1038 |
+
"loss": 0.4509,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.102272727272727,
|
| 1043 |
+
"grad_norm": 0.1030086032533747,
|
| 1044 |
+
"learning_rate": 1.520919662490839e-05,
|
| 1045 |
+
"loss": 0.4438,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.116477272727273,
|
| 1050 |
+
"grad_norm": 0.10277657855159573,
|
| 1051 |
+
"learning_rate": 1.4915563085605922e-05,
|
| 1052 |
+
"loss": 0.4391,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.1306818181818183,
|
| 1057 |
+
"grad_norm": 0.09814581198724093,
|
| 1058 |
+
"learning_rate": 1.4625016021558654e-05,
|
| 1059 |
+
"loss": 0.4458,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.1448863636363638,
|
| 1064 |
+
"grad_norm": 0.11056576999353432,
|
| 1065 |
+
"learning_rate": 1.4337626692714862e-05,
|
| 1066 |
+
"loss": 0.4496,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.159090909090909,
|
| 1071 |
+
"grad_norm": 0.09890533126932854,
|
| 1072 |
+
"learning_rate": 1.4053465584552613e-05,
|
| 1073 |
+
"loss": 0.4395,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.1732954545454546,
|
| 1078 |
+
"grad_norm": 0.10516851231359878,
|
| 1079 |
+
"learning_rate": 1.3772602390792397e-05,
|
| 1080 |
+
"loss": 0.442,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.1875,
|
| 1085 |
+
"grad_norm": 0.10009393657351306,
|
| 1086 |
+
"learning_rate": 1.3495105996303959e-05,
|
| 1087 |
+
"loss": 0.4384,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.2017045454545454,
|
| 1092 |
+
"grad_norm": 0.0998627875200131,
|
| 1093 |
+
"learning_rate": 1.3221044460211496e-05,
|
| 1094 |
+
"loss": 0.4436,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.215909090909091,
|
| 1099 |
+
"grad_norm": 0.09883322341572116,
|
| 1100 |
+
"learning_rate": 1.2950484999201407e-05,
|
| 1101 |
+
"loss": 0.4508,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.2301136363636362,
|
| 1106 |
+
"grad_norm": 0.09827162855077891,
|
| 1107 |
+
"learning_rate": 1.2683493971036633e-05,
|
| 1108 |
+
"loss": 0.4394,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.2443181818181817,
|
| 1113 |
+
"grad_norm": 0.1028260573381402,
|
| 1114 |
+
"learning_rate": 1.2420136858281663e-05,
|
| 1115 |
+
"loss": 0.4442,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.2585227272727275,
|
| 1120 |
+
"grad_norm": 0.10185969414875563,
|
| 1121 |
+
"learning_rate": 1.2160478252242191e-05,
|
| 1122 |
+
"loss": 0.4522,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.2727272727272725,
|
| 1127 |
+
"grad_norm": 0.09897503980351197,
|
| 1128 |
+
"learning_rate": 1.1904581837123386e-05,
|
| 1129 |
+
"loss": 0.4395,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.2869318181818183,
|
| 1134 |
+
"grad_norm": 0.10179604173619207,
|
| 1135 |
+
"learning_rate": 1.1652510374410607e-05,
|
| 1136 |
+
"loss": 0.4476,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.3011363636363638,
|
| 1141 |
+
"grad_norm": 0.10087044008989485,
|
| 1142 |
+
"learning_rate": 1.1404325687476435e-05,
|
| 1143 |
+
"loss": 0.455,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.315340909090909,
|
| 1148 |
+
"grad_norm": 0.09796524933029822,
|
| 1149 |
+
"learning_rate": 1.1160088646417834e-05,
|
| 1150 |
+
"loss": 0.441,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.3295454545454546,
|
| 1155 |
+
"grad_norm": 0.10278194962659604,
|
| 1156 |
+
"learning_rate": 1.0919859153127004e-05,
|
| 1157 |
+
"loss": 0.4415,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.34375,
|
| 1162 |
+
"grad_norm": 0.10008666177717428,
|
| 1163 |
+
"learning_rate": 1.0683696126599816e-05,
|
| 1164 |
+
"loss": 0.4504,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.3579545454545454,
|
| 1169 |
+
"grad_norm": 0.10127145328521546,
|
| 1170 |
+
"learning_rate": 1.045165748848525e-05,
|
| 1171 |
+
"loss": 0.4432,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.372159090909091,
|
| 1176 |
+
"grad_norm": 0.09465727719419995,
|
| 1177 |
+
"learning_rate": 1.0223800148879456e-05,
|
| 1178 |
+
"loss": 0.4406,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.3863636363636362,
|
| 1183 |
+
"grad_norm": 0.10223238212578617,
|
| 1184 |
+
"learning_rate": 1.0000179992367925e-05,
|
| 1185 |
+
"loss": 0.4417,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.4005681818181817,
|
| 1190 |
+
"grad_norm": 0.10542315681224666,
|
| 1191 |
+
"learning_rate": 9.780851864319119e-06,
|
| 1192 |
+
"loss": 0.4447,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.4147727272727275,
|
| 1197 |
+
"grad_norm": 0.0963765340314958,
|
| 1198 |
+
"learning_rate": 9.565869557433065e-06,
|
| 1199 |
+
"loss": 0.4412,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.4289772727272725,
|
| 1204 |
+
"grad_norm": 0.10046217850351946,
|
| 1205 |
+
"learning_rate": 9.35528579854809e-06,
|
| 1206 |
+
"loss": 0.4484,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.4431818181818183,
|
| 1211 |
+
"grad_norm": 0.10147180197503058,
|
| 1212 |
+
"learning_rate": 9.149152235708938e-06,
|
| 1213 |
+
"loss": 0.4397,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.4573863636363638,
|
| 1218 |
+
"grad_norm": 0.11146703090708097,
|
| 1219 |
+
"learning_rate": 8.947519425499546e-06,
|
| 1220 |
+
"loss": 0.4457,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.471590909090909,
|
| 1225 |
+
"grad_norm": 0.0945703122512324,
|
| 1226 |
+
"learning_rate": 8.750436820643412e-06,
|
| 1227 |
+
"loss": 0.4392,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.4857954545454546,
|
| 1232 |
+
"grad_norm": 0.09908284212508756,
|
| 1233 |
+
"learning_rate": 8.557952757874824e-06,
|
| 1234 |
+
"loss": 0.442,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.5,
|
| 1239 |
+
"grad_norm": 0.09395206380523909,
|
| 1240 |
+
"learning_rate": 8.370114446083686e-06,
|
| 1241 |
+
"loss": 0.4354,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.5142045454545454,
|
| 1246 |
+
"grad_norm": 0.1005576468311754,
|
| 1247 |
+
"learning_rate": 8.186967954736992e-06,
|
| 1248 |
+
"loss": 0.4533,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.528409090909091,
|
| 1253 |
+
"grad_norm": 0.1020807372597039,
|
| 1254 |
+
"learning_rate": 8.008558202579839e-06,
|
| 1255 |
+
"loss": 0.443,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.5426136363636362,
|
| 1260 |
+
"grad_norm": 0.09991703967673085,
|
| 1261 |
+
"learning_rate": 7.834928946618499e-06,
|
| 1262 |
+
"loss": 0.4475,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.5568181818181817,
|
| 1267 |
+
"grad_norm": 0.10275386995373673,
|
| 1268 |
+
"learning_rate": 7.666122771388617e-06,
|
| 1269 |
+
"loss": 0.4484,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.5710227272727275,
|
| 1274 |
+
"grad_norm": 0.10616220162227955,
|
| 1275 |
+
"learning_rate": 7.502181078510801e-06,
|
| 1276 |
+
"loss": 0.441,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.5852272727272725,
|
| 1281 |
+
"grad_norm": 0.09678868754399234,
|
| 1282 |
+
"learning_rate": 7.343144076536432e-06,
|
| 1283 |
+
"loss": 0.4345,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.5994318181818183,
|
| 1288 |
+
"grad_norm": 0.09985443664593775,
|
| 1289 |
+
"learning_rate": 7.189050771086084e-06,
|
| 1290 |
+
"loss": 0.4432,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.6136363636363638,
|
| 1295 |
+
"grad_norm": 0.09670777253001571,
|
| 1296 |
+
"learning_rate": 7.039938955282907e-06,
|
| 1297 |
+
"loss": 0.4417,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.627840909090909,
|
| 1302 |
+
"grad_norm": 0.09783216540452833,
|
| 1303 |
+
"learning_rate": 6.895845200483489e-06,
|
| 1304 |
+
"loss": 0.4424,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.6420454545454546,
|
| 1309 |
+
"grad_norm": 0.09147945018928255,
|
| 1310 |
+
"learning_rate": 6.756804847308286e-06,
|
| 1311 |
+
"loss": 0.4434,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.65625,
|
| 1316 |
+
"grad_norm": 0.09802106237190225,
|
| 1317 |
+
"learning_rate": 6.622851996973932e-06,
|
| 1318 |
+
"loss": 0.4407,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.6704545454545454,
|
| 1323 |
+
"grad_norm": 0.09462692879617098,
|
| 1324 |
+
"learning_rate": 6.49401950292956e-06,
|
| 1325 |
+
"loss": 0.4433,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.684659090909091,
|
| 1330 |
+
"grad_norm": 0.09624748034407322,
|
| 1331 |
+
"learning_rate": 6.3703389627990844e-06,
|
| 1332 |
+
"loss": 0.4387,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.6988636363636362,
|
| 1337 |
+
"grad_norm": 0.09543251734275723,
|
| 1338 |
+
"learning_rate": 6.2518407106315695e-06,
|
| 1339 |
+
"loss": 0.4363,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.7130681818181817,
|
| 1344 |
+
"grad_norm": 0.09883095226273896,
|
| 1345 |
+
"learning_rate": 6.138553809461422e-06,
|
| 1346 |
+
"loss": 0.4386,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.7272727272727275,
|
| 1351 |
+
"grad_norm": 0.09756625437555602,
|
| 1352 |
+
"learning_rate": 6.030506044180375e-06,
|
| 1353 |
+
"loss": 0.4459,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.7414772727272725,
|
| 1358 |
+
"grad_norm": 0.09607808880251172,
|
| 1359 |
+
"learning_rate": 5.92772391472293e-06,
|
| 1360 |
+
"loss": 0.4359,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.7556818181818183,
|
| 1365 |
+
"grad_norm": 0.09216704090541984,
|
| 1366 |
+
"learning_rate": 5.830232629566935e-06,
|
| 1367 |
+
"loss": 0.45,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.7698863636363638,
|
| 1372 |
+
"grad_norm": 0.09291163689146356,
|
| 1373 |
+
"learning_rate": 5.738056099550936e-06,
|
| 1374 |
+
"loss": 0.4363,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.784090909090909,
|
| 1379 |
+
"grad_norm": 0.09345711945306576,
|
| 1380 |
+
"learning_rate": 5.6512169320097665e-06,
|
| 1381 |
+
"loss": 0.4497,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.7982954545454546,
|
| 1386 |
+
"grad_norm": 0.09335066659653964,
|
| 1387 |
+
"learning_rate": 5.569736425229844e-06,
|
| 1388 |
+
"loss": 0.4411,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.8125,
|
| 1393 |
+
"grad_norm": 0.09732221176443216,
|
| 1394 |
+
"learning_rate": 5.493634563225524e-06,
|
| 1395 |
+
"loss": 0.4453,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.8267045454545454,
|
| 1400 |
+
"grad_norm": 0.0954814046395625,
|
| 1401 |
+
"learning_rate": 5.422930010837793e-06,
|
| 1402 |
+
"loss": 0.4433,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.840909090909091,
|
| 1407 |
+
"grad_norm": 0.09445562287163194,
|
| 1408 |
+
"learning_rate": 5.357640109156516e-06,
|
| 1409 |
+
"loss": 0.4396,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.8551136363636362,
|
| 1414 |
+
"grad_norm": 0.09370114782801439,
|
| 1415 |
+
"learning_rate": 5.297780871267323e-06,
|
| 1416 |
+
"loss": 0.441,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.8693181818181817,
|
| 1421 |
+
"grad_norm": 0.09116071509216306,
|
| 1422 |
+
"learning_rate": 5.243366978324231e-06,
|
| 1423 |
+
"loss": 0.4422,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.8835227272727275,
|
| 1428 |
+
"grad_norm": 0.09885237977800734,
|
| 1429 |
+
"learning_rate": 5.1944117759489156e-06,
|
| 1430 |
+
"loss": 0.4404,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.8977272727272725,
|
| 1435 |
+
"grad_norm": 0.09995837383801799,
|
| 1436 |
+
"learning_rate": 5.1509272709575616e-06,
|
| 1437 |
+
"loss": 0.4456,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.9119318181818183,
|
| 1442 |
+
"grad_norm": 0.09596178401038803,
|
| 1443 |
+
"learning_rate": 5.112924128416038e-06,
|
| 1444 |
+
"loss": 0.4404,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.9261363636363638,
|
| 1449 |
+
"grad_norm": 0.09406970508523729,
|
| 1450 |
+
"learning_rate": 5.080411669024179e-06,
|
| 1451 |
+
"loss": 0.4391,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.940340909090909,
|
| 1456 |
+
"grad_norm": 0.0951093143907049,
|
| 1457 |
+
"learning_rate": 5.0533978668297775e-06,
|
| 1458 |
+
"loss": 0.4483,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.9545454545454546,
|
| 1463 |
+
"grad_norm": 0.09615998973664797,
|
| 1464 |
+
"learning_rate": 5.031889347272857e-06,
|
| 1465 |
+
"loss": 0.4408,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.96875,
|
| 1470 |
+
"grad_norm": 0.09428736632782057,
|
| 1471 |
+
"learning_rate": 5.015891385560713e-06,
|
| 1472 |
+
"loss": 0.4432,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.9829545454545454,
|
| 1477 |
+
"grad_norm": 0.09338757409389373,
|
| 1478 |
+
"learning_rate": 5.005407905374099e-06,
|
| 1479 |
+
"loss": 0.4372,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.997159090909091,
|
| 1484 |
+
"grad_norm": 0.09934638872755362,
|
| 1485 |
+
"learning_rate": 5.0004414779049116e-06,
|
| 1486 |
+
"loss": 0.4421,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.0,
|
| 1491 |
+
"step": 1056,
|
| 1492 |
+
"total_flos": 962656789856256.0,
|
| 1493 |
+
"train_loss": 0.5030564876329718,
|
| 1494 |
+
"train_runtime": 14725.7023,
|
| 1495 |
+
"train_samples_per_second": 2.293,
|
| 1496 |
+
"train_steps_per_second": 0.072
|
| 1497 |
+
}
|
| 1498 |
+
],
|
| 1499 |
+
"logging_steps": 5,
|
| 1500 |
+
"max_steps": 1056,
|
| 1501 |
+
"num_input_tokens_seen": 0,
|
| 1502 |
+
"num_train_epochs": 3,
|
| 1503 |
+
"save_steps": 100,
|
| 1504 |
+
"stateful_callbacks": {
|
| 1505 |
+
"TrainerControl": {
|
| 1506 |
+
"args": {
|
| 1507 |
+
"should_epoch_stop": false,
|
| 1508 |
+
"should_evaluate": false,
|
| 1509 |
+
"should_log": false,
|
| 1510 |
+
"should_save": true,
|
| 1511 |
+
"should_training_stop": true
|
| 1512 |
+
},
|
| 1513 |
+
"attributes": {}
|
| 1514 |
+
}
|
| 1515 |
+
},
|
| 1516 |
+
"total_flos": 962656789856256.0,
|
| 1517 |
+
"train_batch_size": 4,
|
| 1518 |
+
"trial_name": null,
|
| 1519 |
+
"trial_params": null
|
| 1520 |
+
}
|