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 +2297 -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-math-1.5B-Open-R1-Distill-eos-new
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-math-1.5B-Open-R1-Distill-eos-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-math-1.5B-Open-R1-Distill-eos-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/z662m0g8)
|
| 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": 1468598568615936.0,
|
| 3 |
+
"train_loss": 0.4715816771147933,
|
| 4 |
+
"train_runtime": 19678.9404,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.617,
|
| 7 |
+
"train_steps_per_second": 0.082
|
| 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": 1468598568615936.0,
|
| 3 |
+
"train_loss": 0.4715816771147933,
|
| 4 |
+
"train_runtime": 19678.9404,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.617,
|
| 7 |
+
"train_steps_per_second": 0.082
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2297 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1611,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00931098696461825,
|
| 14 |
+
"grad_norm": 16.336199791449793,
|
| 15 |
+
"learning_rate": 2.469135802469136e-06,
|
| 16 |
+
"loss": 1.9327,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0186219739292365,
|
| 21 |
+
"grad_norm": 9.22734324139331,
|
| 22 |
+
"learning_rate": 5.555555555555556e-06,
|
| 23 |
+
"loss": 1.6983,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.027932960893854747,
|
| 28 |
+
"grad_norm": 2.4572991614653783,
|
| 29 |
+
"learning_rate": 8.641975308641975e-06,
|
| 30 |
+
"loss": 1.1843,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.037243947858473,
|
| 35 |
+
"grad_norm": 0.8356668158228655,
|
| 36 |
+
"learning_rate": 1.1728395061728396e-05,
|
| 37 |
+
"loss": 0.9297,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04655493482309125,
|
| 42 |
+
"grad_norm": 0.4936127329444582,
|
| 43 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 44 |
+
"loss": 0.8284,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.055865921787709494,
|
| 49 |
+
"grad_norm": 0.3478722983428711,
|
| 50 |
+
"learning_rate": 1.7901234567901236e-05,
|
| 51 |
+
"loss": 0.7489,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06517690875232775,
|
| 56 |
+
"grad_norm": 0.25513496703130056,
|
| 57 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 58 |
+
"loss": 0.7016,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.074487895716946,
|
| 63 |
+
"grad_norm": 0.2403829000286689,
|
| 64 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 65 |
+
"loss": 0.673,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08379888268156424,
|
| 70 |
+
"grad_norm": 0.38912791976591726,
|
| 71 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 72 |
+
"loss": 0.6583,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0931098696461825,
|
| 77 |
+
"grad_norm": 0.1953193028806376,
|
| 78 |
+
"learning_rate": 3.0246913580246916e-05,
|
| 79 |
+
"loss": 0.6318,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10242085661080075,
|
| 84 |
+
"grad_norm": 0.17012378672445239,
|
| 85 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 86 |
+
"loss": 0.615,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11173184357541899,
|
| 91 |
+
"grad_norm": 0.19550839394534458,
|
| 92 |
+
"learning_rate": 3.6419753086419754e-05,
|
| 93 |
+
"loss": 0.6027,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12104283054003724,
|
| 98 |
+
"grad_norm": 0.1475381137651654,
|
| 99 |
+
"learning_rate": 3.950617283950617e-05,
|
| 100 |
+
"loss": 0.5917,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1303538175046555,
|
| 105 |
+
"grad_norm": 0.14017992287056805,
|
| 106 |
+
"learning_rate": 4.259259259259259e-05,
|
| 107 |
+
"loss": 0.5858,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.13966480446927373,
|
| 112 |
+
"grad_norm": 0.17019572604849684,
|
| 113 |
+
"learning_rate": 4.567901234567901e-05,
|
| 114 |
+
"loss": 0.5905,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.148975791433892,
|
| 119 |
+
"grad_norm": 0.17525567903422554,
|
| 120 |
+
"learning_rate": 4.876543209876544e-05,
|
| 121 |
+
"loss": 0.5734,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.15828677839851024,
|
| 126 |
+
"grad_norm": 0.14195461289074676,
|
| 127 |
+
"learning_rate": 4.999957311534635e-05,
|
| 128 |
+
"loss": 0.561,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.16759776536312848,
|
| 133 |
+
"grad_norm": 0.15882225996967175,
|
| 134 |
+
"learning_rate": 4.9996964434456464e-05,
|
| 135 |
+
"loss": 0.5562,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.17690875232774675,
|
| 140 |
+
"grad_norm": 0.15508701484518203,
|
| 141 |
+
"learning_rate": 4.999198450544716e-05,
|
| 142 |
+
"loss": 0.5615,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.186219739292365,
|
| 147 |
+
"grad_norm": 0.15282408576751363,
|
| 148 |
+
"learning_rate": 4.998463385321802e-05,
|
| 149 |
+
"loss": 0.5566,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.19553072625698323,
|
| 154 |
+
"grad_norm": 0.1441039498919609,
|
| 155 |
+
"learning_rate": 4.997491325255003e-05,
|
| 156 |
+
"loss": 0.5504,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2048417132216015,
|
| 161 |
+
"grad_norm": 0.1414977005402374,
|
| 162 |
+
"learning_rate": 4.9962823728023915e-05,
|
| 163 |
+
"loss": 0.5419,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.21415270018621974,
|
| 168 |
+
"grad_norm": 0.14874293035506805,
|
| 169 |
+
"learning_rate": 4.9948366553912146e-05,
|
| 170 |
+
"loss": 0.5307,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.22346368715083798,
|
| 175 |
+
"grad_norm": 0.16062863369880248,
|
| 176 |
+
"learning_rate": 4.99315432540446e-05,
|
| 177 |
+
"loss": 0.534,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.23277467411545624,
|
| 182 |
+
"grad_norm": 0.15097433303561048,
|
| 183 |
+
"learning_rate": 4.9912355601648e-05,
|
| 184 |
+
"loss": 0.5345,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.24208566108007448,
|
| 189 |
+
"grad_norm": 0.17442330409969137,
|
| 190 |
+
"learning_rate": 4.9890805619158954e-05,
|
| 191 |
+
"loss": 0.5375,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.25139664804469275,
|
| 196 |
+
"grad_norm": 0.21332022009684865,
|
| 197 |
+
"learning_rate": 4.9866895578010826e-05,
|
| 198 |
+
"loss": 0.5306,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.260707635009311,
|
| 203 |
+
"grad_norm": 0.1652894070341978,
|
| 204 |
+
"learning_rate": 4.9840627998394285e-05,
|
| 205 |
+
"loss": 0.5318,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.27001862197392923,
|
| 210 |
+
"grad_norm": 0.1637036108907819,
|
| 211 |
+
"learning_rate": 4.9812005648991715e-05,
|
| 212 |
+
"loss": 0.5324,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.27932960893854747,
|
| 217 |
+
"grad_norm": 0.2654815231921947,
|
| 218 |
+
"learning_rate": 4.978103154668534e-05,
|
| 219 |
+
"loss": 0.5382,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2886405959031657,
|
| 224 |
+
"grad_norm": 0.1647627509019107,
|
| 225 |
+
"learning_rate": 4.9747708956239245e-05,
|
| 226 |
+
"loss": 0.5217,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.297951582867784,
|
| 231 |
+
"grad_norm": 0.15907215366520921,
|
| 232 |
+
"learning_rate": 4.971204138995531e-05,
|
| 233 |
+
"loss": 0.5191,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.30726256983240224,
|
| 238 |
+
"grad_norm": 0.15147466492817646,
|
| 239 |
+
"learning_rate": 4.967403260730291e-05,
|
| 240 |
+
"loss": 0.5134,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3165735567970205,
|
| 245 |
+
"grad_norm": 0.1405938594476101,
|
| 246 |
+
"learning_rate": 4.963368661452277e-05,
|
| 247 |
+
"loss": 0.5195,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3258845437616387,
|
| 252 |
+
"grad_norm": 0.1595878244498165,
|
| 253 |
+
"learning_rate": 4.959100766420458e-05,
|
| 254 |
+
"loss": 0.5232,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.33519553072625696,
|
| 259 |
+
"grad_norm": 0.15951772828099983,
|
| 260 |
+
"learning_rate": 4.954600025483885e-05,
|
| 261 |
+
"loss": 0.5141,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.34450651769087526,
|
| 266 |
+
"grad_norm": 0.16382396726117066,
|
| 267 |
+
"learning_rate": 4.9498669130342686e-05,
|
| 268 |
+
"loss": 0.516,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3538175046554935,
|
| 273 |
+
"grad_norm": 0.17573565863431748,
|
| 274 |
+
"learning_rate": 4.944901927955983e-05,
|
| 275 |
+
"loss": 0.5161,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.36312849162011174,
|
| 280 |
+
"grad_norm": 0.1574125159399186,
|
| 281 |
+
"learning_rate": 4.939705593573477e-05,
|
| 282 |
+
"loss": 0.5185,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.37243947858473,
|
| 287 |
+
"grad_norm": 0.15370896499046016,
|
| 288 |
+
"learning_rate": 4.9342784575961175e-05,
|
| 289 |
+
"loss": 0.5082,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3817504655493482,
|
| 294 |
+
"grad_norm": 0.14999931215152523,
|
| 295 |
+
"learning_rate": 4.928621092060457e-05,
|
| 296 |
+
"loss": 0.5177,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.39106145251396646,
|
| 301 |
+
"grad_norm": 0.15559155877009215,
|
| 302 |
+
"learning_rate": 4.922734093269941e-05,
|
| 303 |
+
"loss": 0.5118,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.40037243947858475,
|
| 308 |
+
"grad_norm": 0.14927855222097725,
|
| 309 |
+
"learning_rate": 4.916618081732053e-05,
|
| 310 |
+
"loss": 0.5123,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.409683426443203,
|
| 315 |
+
"grad_norm": 0.17618505030960954,
|
| 316 |
+
"learning_rate": 4.9102737020929135e-05,
|
| 317 |
+
"loss": 0.5166,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.41899441340782123,
|
| 322 |
+
"grad_norm": 0.15485079003135388,
|
| 323 |
+
"learning_rate": 4.903701623069334e-05,
|
| 324 |
+
"loss": 0.5031,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.42830540037243947,
|
| 329 |
+
"grad_norm": 0.1516909848278948,
|
| 330 |
+
"learning_rate": 4.8969025373783266e-05,
|
| 331 |
+
"loss": 0.5025,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4376163873370577,
|
| 336 |
+
"grad_norm": 0.16374748063322728,
|
| 337 |
+
"learning_rate": 4.889877161664096e-05,
|
| 338 |
+
"loss": 0.5056,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.44692737430167595,
|
| 343 |
+
"grad_norm": 0.20591850992077587,
|
| 344 |
+
"learning_rate": 4.882626236422498e-05,
|
| 345 |
+
"loss": 0.5083,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.45623836126629425,
|
| 350 |
+
"grad_norm": 0.1556213381298468,
|
| 351 |
+
"learning_rate": 4.875150525922994e-05,
|
| 352 |
+
"loss": 0.5031,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4655493482309125,
|
| 357 |
+
"grad_norm": 0.16267277069927719,
|
| 358 |
+
"learning_rate": 4.8674508181280865e-05,
|
| 359 |
+
"loss": 0.5074,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4748603351955307,
|
| 364 |
+
"grad_norm": 0.15425490006295214,
|
| 365 |
+
"learning_rate": 4.8595279246102754e-05,
|
| 366 |
+
"loss": 0.4995,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.48417132216014896,
|
| 371 |
+
"grad_norm": 0.13465996416398995,
|
| 372 |
+
"learning_rate": 4.85138268046651e-05,
|
| 373 |
+
"loss": 0.5046,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4934823091247672,
|
| 378 |
+
"grad_norm": 0.17570069468472505,
|
| 379 |
+
"learning_rate": 4.843015944230166e-05,
|
| 380 |
+
"loss": 0.5042,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5027932960893855,
|
| 385 |
+
"grad_norm": 0.15339985049013902,
|
| 386 |
+
"learning_rate": 4.8344285977805594e-05,
|
| 387 |
+
"loss": 0.4972,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5121042830540037,
|
| 392 |
+
"grad_norm": 0.14216267176397104,
|
| 393 |
+
"learning_rate": 4.8256215462499866e-05,
|
| 394 |
+
"loss": 0.4977,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.521415270018622,
|
| 399 |
+
"grad_norm": 0.1442544392520683,
|
| 400 |
+
"learning_rate": 4.816595717928327e-05,
|
| 401 |
+
"loss": 0.5045,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5307262569832403,
|
| 406 |
+
"grad_norm": 0.14073656875745008,
|
| 407 |
+
"learning_rate": 4.807352064165195e-05,
|
| 408 |
+
"loss": 0.4899,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5400372439478585,
|
| 413 |
+
"grad_norm": 0.18295662717507738,
|
| 414 |
+
"learning_rate": 4.7978915592696644e-05,
|
| 415 |
+
"loss": 0.4968,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5493482309124768,
|
| 420 |
+
"grad_norm": 0.1804436580847151,
|
| 421 |
+
"learning_rate": 4.788215200407576e-05,
|
| 422 |
+
"loss": 0.4921,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5586592178770949,
|
| 427 |
+
"grad_norm": 0.14254600145362717,
|
| 428 |
+
"learning_rate": 4.7783240074964316e-05,
|
| 429 |
+
"loss": 0.4924,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5679702048417132,
|
| 434 |
+
"grad_norm": 0.1510375274736302,
|
| 435 |
+
"learning_rate": 4.76821902309789e-05,
|
| 436 |
+
"loss": 0.4969,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5772811918063314,
|
| 441 |
+
"grad_norm": 0.14322180938059342,
|
| 442 |
+
"learning_rate": 4.757901312307882e-05,
|
| 443 |
+
"loss": 0.4867,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5865921787709497,
|
| 448 |
+
"grad_norm": 0.15778761438406094,
|
| 449 |
+
"learning_rate": 4.747371962644344e-05,
|
| 450 |
+
"loss": 0.5062,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.595903165735568,
|
| 455 |
+
"grad_norm": 0.15689388105498725,
|
| 456 |
+
"learning_rate": 4.7366320839325864e-05,
|
| 457 |
+
"loss": 0.4992,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6052141527001862,
|
| 462 |
+
"grad_norm": 0.14383076831723837,
|
| 463 |
+
"learning_rate": 4.7256828081883205e-05,
|
| 464 |
+
"loss": 0.4989,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6145251396648045,
|
| 469 |
+
"grad_norm": 0.21080496453629785,
|
| 470 |
+
"learning_rate": 4.71452528949834e-05,
|
| 471 |
+
"loss": 0.4898,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6238361266294227,
|
| 476 |
+
"grad_norm": 0.14254271015618503,
|
| 477 |
+
"learning_rate": 4.7031607038988735e-05,
|
| 478 |
+
"loss": 0.4802,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.633147113594041,
|
| 483 |
+
"grad_norm": 0.15811041126836908,
|
| 484 |
+
"learning_rate": 4.691590249251627e-05,
|
| 485 |
+
"loss": 0.4907,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6424581005586593,
|
| 490 |
+
"grad_norm": 0.13753498439384687,
|
| 491 |
+
"learning_rate": 4.67981514511753e-05,
|
| 492 |
+
"loss": 0.494,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6517690875232774,
|
| 497 |
+
"grad_norm": 0.1381443189067191,
|
| 498 |
+
"learning_rate": 4.667836632628185e-05,
|
| 499 |
+
"loss": 0.4929,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6610800744878957,
|
| 504 |
+
"grad_norm": 0.14535188259873358,
|
| 505 |
+
"learning_rate": 4.655655974355051e-05,
|
| 506 |
+
"loss": 0.492,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6703910614525139,
|
| 511 |
+
"grad_norm": 0.16265320769415334,
|
| 512 |
+
"learning_rate": 4.643274454176365e-05,
|
| 513 |
+
"loss": 0.4854,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6797020484171322,
|
| 518 |
+
"grad_norm": 0.1426180701421254,
|
| 519 |
+
"learning_rate": 4.630693377141816e-05,
|
| 520 |
+
"loss": 0.4865,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6890130353817505,
|
| 525 |
+
"grad_norm": 0.1422570068389307,
|
| 526 |
+
"learning_rate": 4.6179140693349894e-05,
|
| 527 |
+
"loss": 0.4848,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6983240223463687,
|
| 532 |
+
"grad_norm": 0.14960885172487687,
|
| 533 |
+
"learning_rate": 4.6049378777335925e-05,
|
| 534 |
+
"loss": 0.478,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.707635009310987,
|
| 539 |
+
"grad_norm": 0.1686075463208643,
|
| 540 |
+
"learning_rate": 4.591766170067484e-05,
|
| 541 |
+
"loss": 0.4856,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7169459962756052,
|
| 546 |
+
"grad_norm": 0.1696479397319911,
|
| 547 |
+
"learning_rate": 4.578400334674503e-05,
|
| 548 |
+
"loss": 0.4738,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7262569832402235,
|
| 553 |
+
"grad_norm": 0.12636437658397243,
|
| 554 |
+
"learning_rate": 4.5648417803541405e-05,
|
| 555 |
+
"loss": 0.4861,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7355679702048417,
|
| 560 |
+
"grad_norm": 0.14823499403718474,
|
| 561 |
+
"learning_rate": 4.5510919362190465e-05,
|
| 562 |
+
"loss": 0.4874,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.74487895716946,
|
| 567 |
+
"grad_norm": 0.13876911181183,
|
| 568 |
+
"learning_rate": 4.5371522515443934e-05,
|
| 569 |
+
"loss": 0.481,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7541899441340782,
|
| 574 |
+
"grad_norm": 0.14555324320118293,
|
| 575 |
+
"learning_rate": 4.523024195615124e-05,
|
| 576 |
+
"loss": 0.4917,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7635009310986964,
|
| 581 |
+
"grad_norm": 0.1483421827835732,
|
| 582 |
+
"learning_rate": 4.508709257571081e-05,
|
| 583 |
+
"loss": 0.4818,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7728119180633147,
|
| 588 |
+
"grad_norm": 0.1419680809174011,
|
| 589 |
+
"learning_rate": 4.494208946250042e-05,
|
| 590 |
+
"loss": 0.4772,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7821229050279329,
|
| 595 |
+
"grad_norm": 0.16513221694643368,
|
| 596 |
+
"learning_rate": 4.4795247900286975e-05,
|
| 597 |
+
"loss": 0.4845,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7914338919925512,
|
| 602 |
+
"grad_norm": 0.14036938615466898,
|
| 603 |
+
"learning_rate": 4.46465833666154e-05,
|
| 604 |
+
"loss": 0.4904,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8007448789571695,
|
| 609 |
+
"grad_norm": 0.14632734868202635,
|
| 610 |
+
"learning_rate": 4.449611153117736e-05,
|
| 611 |
+
"loss": 0.4916,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8100558659217877,
|
| 616 |
+
"grad_norm": 0.20473257481525392,
|
| 617 |
+
"learning_rate": 4.4343848254159587e-05,
|
| 618 |
+
"loss": 0.4805,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.819366852886406,
|
| 623 |
+
"grad_norm": 0.12821369541497668,
|
| 624 |
+
"learning_rate": 4.418980958457217e-05,
|
| 625 |
+
"loss": 0.4778,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8286778398510242,
|
| 630 |
+
"grad_norm": 0.14169275068446857,
|
| 631 |
+
"learning_rate": 4.4034011758556957e-05,
|
| 632 |
+
"loss": 0.4824,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.8379888268156425,
|
| 637 |
+
"grad_norm": 0.13905298509358965,
|
| 638 |
+
"learning_rate": 4.387647119767619e-05,
|
| 639 |
+
"loss": 0.4879,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.8472998137802608,
|
| 644 |
+
"grad_norm": 0.14408464936999882,
|
| 645 |
+
"learning_rate": 4.3717204507181665e-05,
|
| 646 |
+
"loss": 0.4826,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8566108007448789,
|
| 651 |
+
"grad_norm": 0.1408096706025395,
|
| 652 |
+
"learning_rate": 4.355622847426443e-05,
|
| 653 |
+
"loss": 0.481,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.8659217877094972,
|
| 658 |
+
"grad_norm": 0.18158777593456274,
|
| 659 |
+
"learning_rate": 4.339356006628542e-05,
|
| 660 |
+
"loss": 0.4688,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8752327746741154,
|
| 665 |
+
"grad_norm": 0.12760922940847635,
|
| 666 |
+
"learning_rate": 4.322921642898701e-05,
|
| 667 |
+
"loss": 0.4802,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8845437616387337,
|
| 672 |
+
"grad_norm": 0.11771870402744473,
|
| 673 |
+
"learning_rate": 4.3063214884685835e-05,
|
| 674 |
+
"loss": 0.4856,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8938547486033519,
|
| 679 |
+
"grad_norm": 0.12319800101836006,
|
| 680 |
+
"learning_rate": 4.2895572930446895e-05,
|
| 681 |
+
"loss": 0.4864,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9031657355679702,
|
| 686 |
+
"grad_norm": 0.1266489948893168,
|
| 687 |
+
"learning_rate": 4.272630823623942e-05,
|
| 688 |
+
"loss": 0.4718,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9124767225325885,
|
| 693 |
+
"grad_norm": 0.1539105039445935,
|
| 694 |
+
"learning_rate": 4.255543864307431e-05,
|
| 695 |
+
"loss": 0.4852,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9217877094972067,
|
| 700 |
+
"grad_norm": 0.14332478118043573,
|
| 701 |
+
"learning_rate": 4.238298216112367e-05,
|
| 702 |
+
"loss": 0.4773,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.931098696461825,
|
| 707 |
+
"grad_norm": 0.12617484788483693,
|
| 708 |
+
"learning_rate": 4.220895696782251e-05,
|
| 709 |
+
"loss": 0.4727,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.9404096834264432,
|
| 714 |
+
"grad_norm": 0.1360094821692902,
|
| 715 |
+
"learning_rate": 4.2033381405952715e-05,
|
| 716 |
+
"loss": 0.4765,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.9497206703910615,
|
| 721 |
+
"grad_norm": 0.1283299871000522,
|
| 722 |
+
"learning_rate": 4.1856273981709757e-05,
|
| 723 |
+
"loss": 0.4785,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.9590316573556797,
|
| 728 |
+
"grad_norm": 0.1456300012973035,
|
| 729 |
+
"learning_rate": 4.167765336275201e-05,
|
| 730 |
+
"loss": 0.4836,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9683426443202979,
|
| 735 |
+
"grad_norm": 0.12631639520637056,
|
| 736 |
+
"learning_rate": 4.149753837623317e-05,
|
| 737 |
+
"loss": 0.4742,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9776536312849162,
|
| 742 |
+
"grad_norm": 0.12595076088478818,
|
| 743 |
+
"learning_rate": 4.1315948006817755e-05,
|
| 744 |
+
"loss": 0.4808,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9869646182495344,
|
| 749 |
+
"grad_norm": 0.12055722184602191,
|
| 750 |
+
"learning_rate": 4.113290139468015e-05,
|
| 751 |
+
"loss": 0.4725,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9962756052141527,
|
| 756 |
+
"grad_norm": 0.13737170916427302,
|
| 757 |
+
"learning_rate": 4.0948417833487104e-05,
|
| 758 |
+
"loss": 0.4771,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.005586592178771,
|
| 763 |
+
"grad_norm": 0.1402038369271413,
|
| 764 |
+
"learning_rate": 4.0762516768364164e-05,
|
| 765 |
+
"loss": 0.4531,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.0148975791433892,
|
| 770 |
+
"grad_norm": 0.1389386280489692,
|
| 771 |
+
"learning_rate": 4.0575217793846045e-05,
|
| 772 |
+
"loss": 0.4618,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.0242085661080074,
|
| 777 |
+
"grad_norm": 0.1301676008479176,
|
| 778 |
+
"learning_rate": 4.038654065181137e-05,
|
| 779 |
+
"loss": 0.4444,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0335195530726258,
|
| 784 |
+
"grad_norm": 0.12917021441633983,
|
| 785 |
+
"learning_rate": 4.0196505229401785e-05,
|
| 786 |
+
"loss": 0.4478,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.042830540037244,
|
| 791 |
+
"grad_norm": 0.12625994093795317,
|
| 792 |
+
"learning_rate": 4.0005131556925795e-05,
|
| 793 |
+
"loss": 0.447,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.0521415270018621,
|
| 798 |
+
"grad_norm": 0.1407545892773896,
|
| 799 |
+
"learning_rate": 3.98124398057475e-05,
|
| 800 |
+
"loss": 0.4511,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.0614525139664805,
|
| 805 |
+
"grad_norm": 0.1392139399442254,
|
| 806 |
+
"learning_rate": 3.961845028616052e-05,
|
| 807 |
+
"loss": 0.4581,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.0707635009310987,
|
| 812 |
+
"grad_norm": 0.11692992722859218,
|
| 813 |
+
"learning_rate": 3.9423183445247117e-05,
|
| 814 |
+
"loss": 0.4466,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.080074487895717,
|
| 819 |
+
"grad_norm": 0.11866718899104756,
|
| 820 |
+
"learning_rate": 3.9226659864723166e-05,
|
| 821 |
+
"loss": 0.4505,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.089385474860335,
|
| 826 |
+
"grad_norm": 0.1301769972288239,
|
| 827 |
+
"learning_rate": 3.902890025876867e-05,
|
| 828 |
+
"loss": 0.4568,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0986964618249535,
|
| 833 |
+
"grad_norm": 0.12988708729398774,
|
| 834 |
+
"learning_rate": 3.8829925471844434e-05,
|
| 835 |
+
"loss": 0.4486,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.1080074487895717,
|
| 840 |
+
"grad_norm": 0.14294084168875013,
|
| 841 |
+
"learning_rate": 3.8629756476495024e-05,
|
| 842 |
+
"loss": 0.4519,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.1173184357541899,
|
| 847 |
+
"grad_norm": 0.12461053171632061,
|
| 848 |
+
"learning_rate": 3.842841437113821e-05,
|
| 849 |
+
"loss": 0.4551,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.1266294227188083,
|
| 854 |
+
"grad_norm": 0.12220034734319962,
|
| 855 |
+
"learning_rate": 3.822592037784109e-05,
|
| 856 |
+
"loss": 0.4445,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.1359404096834265,
|
| 861 |
+
"grad_norm": 0.11924325065263018,
|
| 862 |
+
"learning_rate": 3.802229584008321e-05,
|
| 863 |
+
"loss": 0.4493,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.1452513966480447,
|
| 868 |
+
"grad_norm": 0.1549692686985166,
|
| 869 |
+
"learning_rate": 3.781756222050696e-05,
|
| 870 |
+
"loss": 0.4549,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.1545623836126628,
|
| 875 |
+
"grad_norm": 0.11567955790271696,
|
| 876 |
+
"learning_rate": 3.761174109865529e-05,
|
| 877 |
+
"loss": 0.4484,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1638733705772812,
|
| 882 |
+
"grad_norm": 0.11742160828357712,
|
| 883 |
+
"learning_rate": 3.7404854168697215e-05,
|
| 884 |
+
"loss": 0.4567,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1731843575418994,
|
| 889 |
+
"grad_norm": 0.12900092793504658,
|
| 890 |
+
"learning_rate": 3.719692323714109e-05,
|
| 891 |
+
"loss": 0.4352,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.1824953445065176,
|
| 896 |
+
"grad_norm": 0.14140700517521818,
|
| 897 |
+
"learning_rate": 3.6987970220536246e-05,
|
| 898 |
+
"loss": 0.4488,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.191806331471136,
|
| 903 |
+
"grad_norm": 0.1293764570562897,
|
| 904 |
+
"learning_rate": 3.677801714316283e-05,
|
| 905 |
+
"loss": 0.4512,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.2011173184357542,
|
| 910 |
+
"grad_norm": 0.1312966218053429,
|
| 911 |
+
"learning_rate": 3.6567086134710466e-05,
|
| 912 |
+
"loss": 0.4484,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.2104283054003724,
|
| 917 |
+
"grad_norm": 0.11960370887697533,
|
| 918 |
+
"learning_rate": 3.6355199427945634e-05,
|
| 919 |
+
"loss": 0.4499,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.2197392923649906,
|
| 924 |
+
"grad_norm": 0.12886802374746667,
|
| 925 |
+
"learning_rate": 3.6142379356368334e-05,
|
| 926 |
+
"loss": 0.4508,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.229050279329609,
|
| 931 |
+
"grad_norm": 0.12443137480159507,
|
| 932 |
+
"learning_rate": 3.5928648351858027e-05,
|
| 933 |
+
"loss": 0.4531,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.2383612662942272,
|
| 938 |
+
"grad_norm": 0.1235305037487046,
|
| 939 |
+
"learning_rate": 3.571402894230926e-05,
|
| 940 |
+
"loss": 0.4535,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.2476722532588453,
|
| 945 |
+
"grad_norm": 0.12201354012941291,
|
| 946 |
+
"learning_rate": 3.549854374925716e-05,
|
| 947 |
+
"loss": 0.4442,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.2569832402234637,
|
| 952 |
+
"grad_norm": 0.11281012174298978,
|
| 953 |
+
"learning_rate": 3.528221548549307e-05,
|
| 954 |
+
"loss": 0.4427,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.266294227188082,
|
| 959 |
+
"grad_norm": 0.12838733714308004,
|
| 960 |
+
"learning_rate": 3.506506695267052e-05,
|
| 961 |
+
"loss": 0.4529,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.2756052141527001,
|
| 966 |
+
"grad_norm": 0.15014600853193164,
|
| 967 |
+
"learning_rate": 3.4847121038901877e-05,
|
| 968 |
+
"loss": 0.4477,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.2849162011173183,
|
| 973 |
+
"grad_norm": 0.1302974794693121,
|
| 974 |
+
"learning_rate": 3.4628400716345896e-05,
|
| 975 |
+
"loss": 0.4426,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.2942271880819367,
|
| 980 |
+
"grad_norm": 0.14919901945518166,
|
| 981 |
+
"learning_rate": 3.440892903878634e-05,
|
| 982 |
+
"loss": 0.4548,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.303538175046555,
|
| 987 |
+
"grad_norm": 0.1440080046929404,
|
| 988 |
+
"learning_rate": 3.4188729139202065e-05,
|
| 989 |
+
"loss": 0.4468,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.3128491620111733,
|
| 994 |
+
"grad_norm": 0.13277438244879466,
|
| 995 |
+
"learning_rate": 3.396782422732874e-05,
|
| 996 |
+
"loss": 0.4477,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.3221601489757915,
|
| 1001 |
+
"grad_norm": 0.12813547908714812,
|
| 1002 |
+
"learning_rate": 3.374623758721246e-05,
|
| 1003 |
+
"loss": 0.443,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.3314711359404097,
|
| 1008 |
+
"grad_norm": 0.1142868678900171,
|
| 1009 |
+
"learning_rate": 3.352399257475553e-05,
|
| 1010 |
+
"loss": 0.4476,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.3407821229050279,
|
| 1015 |
+
"grad_norm": 0.12281619965751127,
|
| 1016 |
+
"learning_rate": 3.330111261525471e-05,
|
| 1017 |
+
"loss": 0.4509,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.3500931098696463,
|
| 1022 |
+
"grad_norm": 0.12546558627371193,
|
| 1023 |
+
"learning_rate": 3.307762120093208e-05,
|
| 1024 |
+
"loss": 0.4467,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.3594040968342644,
|
| 1029 |
+
"grad_norm": 0.12160846175906896,
|
| 1030 |
+
"learning_rate": 3.285354188845892e-05,
|
| 1031 |
+
"loss": 0.4559,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.3687150837988826,
|
| 1036 |
+
"grad_norm": 0.1327867446422573,
|
| 1037 |
+
"learning_rate": 3.262889829647276e-05,
|
| 1038 |
+
"loss": 0.4461,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.378026070763501,
|
| 1043 |
+
"grad_norm": 0.11851775176530409,
|
| 1044 |
+
"learning_rate": 3.2403714103087875e-05,
|
| 1045 |
+
"loss": 0.4376,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.3873370577281192,
|
| 1050 |
+
"grad_norm": 0.13354798789102165,
|
| 1051 |
+
"learning_rate": 3.217801304339959e-05,
|
| 1052 |
+
"loss": 0.4483,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.3966480446927374,
|
| 1057 |
+
"grad_norm": 0.1219907416413629,
|
| 1058 |
+
"learning_rate": 3.1951818906982474e-05,
|
| 1059 |
+
"loss": 0.4574,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.4059590316573556,
|
| 1064 |
+
"grad_norm": 0.1341034895178442,
|
| 1065 |
+
"learning_rate": 3.1725155535382905e-05,
|
| 1066 |
+
"loss": 0.4557,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.415270018621974,
|
| 1071 |
+
"grad_norm": 0.12347048681951657,
|
| 1072 |
+
"learning_rate": 3.1498046819606056e-05,
|
| 1073 |
+
"loss": 0.447,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.4245810055865922,
|
| 1078 |
+
"grad_norm": 0.11917886931538982,
|
| 1079 |
+
"learning_rate": 3.127051669759769e-05,
|
| 1080 |
+
"loss": 0.4454,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.4338919925512104,
|
| 1085 |
+
"grad_norm": 0.11857820273802168,
|
| 1086 |
+
"learning_rate": 3.1042589151721134e-05,
|
| 1087 |
+
"loss": 0.449,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.4432029795158288,
|
| 1092 |
+
"grad_norm": 0.11694287535715704,
|
| 1093 |
+
"learning_rate": 3.081428820622935e-05,
|
| 1094 |
+
"loss": 0.4384,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.452513966480447,
|
| 1099 |
+
"grad_norm": 0.1155522561144092,
|
| 1100 |
+
"learning_rate": 3.058563792473273e-05,
|
| 1101 |
+
"loss": 0.4391,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.4618249534450651,
|
| 1106 |
+
"grad_norm": 0.12724124843039097,
|
| 1107 |
+
"learning_rate": 3.0356662407662768e-05,
|
| 1108 |
+
"loss": 0.4464,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.4711359404096833,
|
| 1113 |
+
"grad_norm": 0.12271179738453024,
|
| 1114 |
+
"learning_rate": 3.0127385789731766e-05,
|
| 1115 |
+
"loss": 0.447,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.4804469273743017,
|
| 1120 |
+
"grad_norm": 0.13153662517383716,
|
| 1121 |
+
"learning_rate": 2.9897832237388977e-05,
|
| 1122 |
+
"loss": 0.4522,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.48975791433892,
|
| 1127 |
+
"grad_norm": 0.13079604733987632,
|
| 1128 |
+
"learning_rate": 2.9668025946273353e-05,
|
| 1129 |
+
"loss": 0.4466,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.499068901303538,
|
| 1134 |
+
"grad_norm": 0.12483287404044502,
|
| 1135 |
+
"learning_rate": 2.943799113866329e-05,
|
| 1136 |
+
"loss": 0.4535,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.5083798882681565,
|
| 1141 |
+
"grad_norm": 0.16043696471672628,
|
| 1142 |
+
"learning_rate": 2.9207752060923526e-05,
|
| 1143 |
+
"loss": 0.4451,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.5176908752327747,
|
| 1148 |
+
"grad_norm": 0.1237851353311521,
|
| 1149 |
+
"learning_rate": 2.8977332980949468e-05,
|
| 1150 |
+
"loss": 0.4311,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.5270018621973929,
|
| 1155 |
+
"grad_norm": 0.11667518885636707,
|
| 1156 |
+
"learning_rate": 2.874675818560933e-05,
|
| 1157 |
+
"loss": 0.439,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.536312849162011,
|
| 1162 |
+
"grad_norm": 0.1165443133197676,
|
| 1163 |
+
"learning_rate": 2.851605197818416e-05,
|
| 1164 |
+
"loss": 0.4533,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.5456238361266295,
|
| 1169 |
+
"grad_norm": 0.11852825430527979,
|
| 1170 |
+
"learning_rate": 2.828523867580628e-05,
|
| 1171 |
+
"loss": 0.4478,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.5549348230912476,
|
| 1176 |
+
"grad_norm": 0.11263242835984934,
|
| 1177 |
+
"learning_rate": 2.80543426068961e-05,
|
| 1178 |
+
"loss": 0.4413,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.564245810055866,
|
| 1183 |
+
"grad_norm": 0.11792947875462449,
|
| 1184 |
+
"learning_rate": 2.7823388108597904e-05,
|
| 1185 |
+
"loss": 0.4419,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.5735567970204842,
|
| 1190 |
+
"grad_norm": 0.11536152090272359,
|
| 1191 |
+
"learning_rate": 2.75923995242146e-05,
|
| 1192 |
+
"loss": 0.4441,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.5828677839851024,
|
| 1197 |
+
"grad_norm": 0.11948166926439772,
|
| 1198 |
+
"learning_rate": 2.7361401200641883e-05,
|
| 1199 |
+
"loss": 0.4481,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.5921787709497206,
|
| 1204 |
+
"grad_norm": 0.13523357634130967,
|
| 1205 |
+
"learning_rate": 2.7130417485801968e-05,
|
| 1206 |
+
"loss": 0.446,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6014897579143388,
|
| 1211 |
+
"grad_norm": 0.12128750858126454,
|
| 1212 |
+
"learning_rate": 2.6899472726077275e-05,
|
| 1213 |
+
"loss": 0.4425,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6108007448789572,
|
| 1218 |
+
"grad_norm": 0.11455173358368062,
|
| 1219 |
+
"learning_rate": 2.6668591263744246e-05,
|
| 1220 |
+
"loss": 0.4441,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.6201117318435754,
|
| 1225 |
+
"grad_norm": 0.13042675513137278,
|
| 1226 |
+
"learning_rate": 2.6437797434407574e-05,
|
| 1227 |
+
"loss": 0.4398,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.6294227188081938,
|
| 1232 |
+
"grad_norm": 0.12385390445885733,
|
| 1233 |
+
"learning_rate": 2.620711556443516e-05,
|
| 1234 |
+
"loss": 0.4511,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.638733705772812,
|
| 1239 |
+
"grad_norm": 0.11517915674628858,
|
| 1240 |
+
"learning_rate": 2.5976569968394083e-05,
|
| 1241 |
+
"loss": 0.4443,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.6480446927374302,
|
| 1246 |
+
"grad_norm": 0.10395291968134747,
|
| 1247 |
+
"learning_rate": 2.574618494648771e-05,
|
| 1248 |
+
"loss": 0.4442,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.6573556797020483,
|
| 1253 |
+
"grad_norm": 0.11431662054546529,
|
| 1254 |
+
"learning_rate": 2.5515984781994417e-05,
|
| 1255 |
+
"loss": 0.4433,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.6666666666666665,
|
| 1260 |
+
"grad_norm": 0.11997395296814937,
|
| 1261 |
+
"learning_rate": 2.528599373870804e-05,
|
| 1262 |
+
"loss": 0.4412,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.675977653631285,
|
| 1267 |
+
"grad_norm": 0.11251548912326118,
|
| 1268 |
+
"learning_rate": 2.5056236058380422e-05,
|
| 1269 |
+
"loss": 0.4341,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.6852886405959033,
|
| 1274 |
+
"grad_norm": 0.12200163922402081,
|
| 1275 |
+
"learning_rate": 2.4826735958166238e-05,
|
| 1276 |
+
"loss": 0.4391,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.6945996275605215,
|
| 1281 |
+
"grad_norm": 0.12515447326859908,
|
| 1282 |
+
"learning_rate": 2.4597517628070434e-05,
|
| 1283 |
+
"loss": 0.4335,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.7039106145251397,
|
| 1288 |
+
"grad_norm": 0.11900007427268738,
|
| 1289 |
+
"learning_rate": 2.4368605228398534e-05,
|
| 1290 |
+
"loss": 0.4442,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.7132216014897579,
|
| 1295 |
+
"grad_norm": 0.10327616314867456,
|
| 1296 |
+
"learning_rate": 2.4140022887210074e-05,
|
| 1297 |
+
"loss": 0.442,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.722532588454376,
|
| 1302 |
+
"grad_norm": 0.11195530093482621,
|
| 1303 |
+
"learning_rate": 2.391179469777543e-05,
|
| 1304 |
+
"loss": 0.4335,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.7318435754189943,
|
| 1309 |
+
"grad_norm": 0.10733741642428904,
|
| 1310 |
+
"learning_rate": 2.3683944716036316e-05,
|
| 1311 |
+
"loss": 0.4379,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.7411545623836127,
|
| 1316 |
+
"grad_norm": 0.10722035609207795,
|
| 1317 |
+
"learning_rate": 2.345649695807019e-05,
|
| 1318 |
+
"loss": 0.4367,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.750465549348231,
|
| 1323 |
+
"grad_norm": 0.11022965957105299,
|
| 1324 |
+
"learning_rate": 2.322947539755892e-05,
|
| 1325 |
+
"loss": 0.4433,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.7597765363128492,
|
| 1330 |
+
"grad_norm": 0.11737086019377437,
|
| 1331 |
+
"learning_rate": 2.3002903963261884e-05,
|
| 1332 |
+
"loss": 0.4403,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.7690875232774674,
|
| 1337 |
+
"grad_norm": 0.10855004430890172,
|
| 1338 |
+
"learning_rate": 2.2776806536493774e-05,
|
| 1339 |
+
"loss": 0.4391,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.7783985102420856,
|
| 1344 |
+
"grad_norm": 0.11126097809718666,
|
| 1345 |
+
"learning_rate": 2.2551206948607466e-05,
|
| 1346 |
+
"loss": 0.4344,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.7877094972067038,
|
| 1351 |
+
"grad_norm": 0.11482383919676267,
|
| 1352 |
+
"learning_rate": 2.2326128978482103e-05,
|
| 1353 |
+
"loss": 0.4369,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.7970204841713222,
|
| 1358 |
+
"grad_norm": 0.10817387409350918,
|
| 1359 |
+
"learning_rate": 2.2101596350016756e-05,
|
| 1360 |
+
"loss": 0.4384,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8063314711359404,
|
| 1365 |
+
"grad_norm": 0.10278656697485476,
|
| 1366 |
+
"learning_rate": 2.1877632729629803e-05,
|
| 1367 |
+
"loss": 0.4363,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.8156424581005588,
|
| 1372 |
+
"grad_norm": 0.10003238891948513,
|
| 1373 |
+
"learning_rate": 2.16542617237645e-05,
|
| 1374 |
+
"loss": 0.4386,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.824953445065177,
|
| 1379 |
+
"grad_norm": 0.12056952514610235,
|
| 1380 |
+
"learning_rate": 2.1431506876400694e-05,
|
| 1381 |
+
"loss": 0.4324,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.8342644320297952,
|
| 1386 |
+
"grad_norm": 0.11514887779350329,
|
| 1387 |
+
"learning_rate": 2.1209391666573265e-05,
|
| 1388 |
+
"loss": 0.4431,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.8435754189944134,
|
| 1393 |
+
"grad_norm": 0.11972084038390686,
|
| 1394 |
+
"learning_rate": 2.0987939505897393e-05,
|
| 1395 |
+
"loss": 0.4452,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.8528864059590315,
|
| 1400 |
+
"grad_norm": 0.11700688868223293,
|
| 1401 |
+
"learning_rate": 2.076717373610083e-05,
|
| 1402 |
+
"loss": 0.4423,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.86219739292365,
|
| 1407 |
+
"grad_norm": 0.111956011270972,
|
| 1408 |
+
"learning_rate": 2.054711762656369e-05,
|
| 1409 |
+
"loss": 0.4377,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.8715083798882681,
|
| 1414 |
+
"grad_norm": 0.10113399321289508,
|
| 1415 |
+
"learning_rate": 2.032779437186572e-05,
|
| 1416 |
+
"loss": 0.4386,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.8808193668528865,
|
| 1421 |
+
"grad_norm": 0.1058333563087994,
|
| 1422 |
+
"learning_rate": 2.010922708934157e-05,
|
| 1423 |
+
"loss": 0.4317,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.8901303538175047,
|
| 1428 |
+
"grad_norm": 0.10370579219821685,
|
| 1429 |
+
"learning_rate": 1.9891438816644114e-05,
|
| 1430 |
+
"loss": 0.4349,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.899441340782123,
|
| 1435 |
+
"grad_norm": 0.1206689535928644,
|
| 1436 |
+
"learning_rate": 1.967445250931627e-05,
|
| 1437 |
+
"loss": 0.4365,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.908752327746741,
|
| 1442 |
+
"grad_norm": 0.1202510464984422,
|
| 1443 |
+
"learning_rate": 1.945829103837133e-05,
|
| 1444 |
+
"loss": 0.4479,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.9180633147113593,
|
| 1449 |
+
"grad_norm": 0.10822437459168585,
|
| 1450 |
+
"learning_rate": 1.9242977187882383e-05,
|
| 1451 |
+
"loss": 0.4438,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.9273743016759777,
|
| 1456 |
+
"grad_norm": 0.11150240856764543,
|
| 1457 |
+
"learning_rate": 1.902853365258072e-05,
|
| 1458 |
+
"loss": 0.4366,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.9366852886405959,
|
| 1463 |
+
"grad_norm": 0.10570123944866744,
|
| 1464 |
+
"learning_rate": 1.8814983035463794e-05,
|
| 1465 |
+
"loss": 0.4433,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.9459962756052143,
|
| 1470 |
+
"grad_norm": 0.10602330715260787,
|
| 1471 |
+
"learning_rate": 1.86023478454128e-05,
|
| 1472 |
+
"loss": 0.4388,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.9553072625698324,
|
| 1477 |
+
"grad_norm": 0.10899590289579546,
|
| 1478 |
+
"learning_rate": 1.8390650494820107e-05,
|
| 1479 |
+
"loss": 0.4362,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.9646182495344506,
|
| 1484 |
+
"grad_norm": 0.11765129534980089,
|
| 1485 |
+
"learning_rate": 1.8179913297226993e-05,
|
| 1486 |
+
"loss": 0.4408,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.9739292364990688,
|
| 1491 |
+
"grad_norm": 0.11030605011675014,
|
| 1492 |
+
"learning_rate": 1.7970158464971714e-05,
|
| 1493 |
+
"loss": 0.4467,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.983240223463687,
|
| 1498 |
+
"grad_norm": 0.10612432103217494,
|
| 1499 |
+
"learning_rate": 1.7761408106848217e-05,
|
| 1500 |
+
"loss": 0.4346,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.9925512104283054,
|
| 1505 |
+
"grad_norm": 0.10754649072396187,
|
| 1506 |
+
"learning_rate": 1.7553684225775867e-05,
|
| 1507 |
+
"loss": 0.429,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.001862197392924,
|
| 1512 |
+
"grad_norm": 0.10691719626323028,
|
| 1513 |
+
"learning_rate": 1.734700871648024e-05,
|
| 1514 |
+
"loss": 0.4264,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.011173184357542,
|
| 1519 |
+
"grad_norm": 0.11506657646587219,
|
| 1520 |
+
"learning_rate": 1.7141403363185325e-05,
|
| 1521 |
+
"loss": 0.4226,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.02048417132216,
|
| 1526 |
+
"grad_norm": 0.10752371863340741,
|
| 1527 |
+
"learning_rate": 1.6936889837317466e-05,
|
| 1528 |
+
"loss": 0.421,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.0297951582867784,
|
| 1533 |
+
"grad_norm": 0.10258005127471478,
|
| 1534 |
+
"learning_rate": 1.6733489695221056e-05,
|
| 1535 |
+
"loss": 0.4148,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.0391061452513966,
|
| 1540 |
+
"grad_norm": 0.10283082864546561,
|
| 1541 |
+
"learning_rate": 1.6531224375886507e-05,
|
| 1542 |
+
"loss": 0.4202,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.0484171322160147,
|
| 1547 |
+
"grad_norm": 0.10708122228606631,
|
| 1548 |
+
"learning_rate": 1.6330115198690462e-05,
|
| 1549 |
+
"loss": 0.4287,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.0577281191806334,
|
| 1554 |
+
"grad_norm": 0.10210619581682416,
|
| 1555 |
+
"learning_rate": 1.6130183361148672e-05,
|
| 1556 |
+
"loss": 0.4212,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.0670391061452515,
|
| 1561 |
+
"grad_norm": 0.09909955572450115,
|
| 1562 |
+
"learning_rate": 1.593144993668175e-05,
|
| 1563 |
+
"loss": 0.4128,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.0763500931098697,
|
| 1568 |
+
"grad_norm": 0.09903027868569465,
|
| 1569 |
+
"learning_rate": 1.5733935872393924e-05,
|
| 1570 |
+
"loss": 0.4102,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.085661080074488,
|
| 1575 |
+
"grad_norm": 0.11465913565196915,
|
| 1576 |
+
"learning_rate": 1.5537661986865187e-05,
|
| 1577 |
+
"loss": 0.4196,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.094972067039106,
|
| 1582 |
+
"grad_norm": 0.10431445935320442,
|
| 1583 |
+
"learning_rate": 1.5342648967956935e-05,
|
| 1584 |
+
"loss": 0.4211,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.1042830540037243,
|
| 1589 |
+
"grad_norm": 0.10867828847006396,
|
| 1590 |
+
"learning_rate": 1.5148917370631389e-05,
|
| 1591 |
+
"loss": 0.4273,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.1135940409683425,
|
| 1596 |
+
"grad_norm": 0.10564151475662023,
|
| 1597 |
+
"learning_rate": 1.4956487614785076e-05,
|
| 1598 |
+
"loss": 0.4177,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.122905027932961,
|
| 1603 |
+
"grad_norm": 0.10252126454298957,
|
| 1604 |
+
"learning_rate": 1.47653799830965e-05,
|
| 1605 |
+
"loss": 0.4256,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.1322160148975793,
|
| 1610 |
+
"grad_norm": 0.10583448098931744,
|
| 1611 |
+
"learning_rate": 1.4575614618888248e-05,
|
| 1612 |
+
"loss": 0.4162,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.1415270018621975,
|
| 1617 |
+
"grad_norm": 0.11129869429457806,
|
| 1618 |
+
"learning_rate": 1.438721152400388e-05,
|
| 1619 |
+
"loss": 0.4214,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.1508379888268156,
|
| 1624 |
+
"grad_norm": 0.10661908698656541,
|
| 1625 |
+
"learning_rate": 1.4200190556699653e-05,
|
| 1626 |
+
"loss": 0.4171,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.160148975791434,
|
| 1631 |
+
"grad_norm": 0.10172941781846247,
|
| 1632 |
+
"learning_rate": 1.4014571429551348e-05,
|
| 1633 |
+
"loss": 0.4198,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.169459962756052,
|
| 1638 |
+
"grad_norm": 0.10129345871926003,
|
| 1639 |
+
"learning_rate": 1.3830373707376623e-05,
|
| 1640 |
+
"loss": 0.4207,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.17877094972067,
|
| 1645 |
+
"grad_norm": 0.1039002300974548,
|
| 1646 |
+
"learning_rate": 1.364761680517269e-05,
|
| 1647 |
+
"loss": 0.414,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.188081936685289,
|
| 1652 |
+
"grad_norm": 0.09557941393888705,
|
| 1653 |
+
"learning_rate": 1.3466319986070008e-05,
|
| 1654 |
+
"loss": 0.419,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.197392923649907,
|
| 1659 |
+
"grad_norm": 0.10379899436807119,
|
| 1660 |
+
"learning_rate": 1.3286502359301862e-05,
|
| 1661 |
+
"loss": 0.423,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.206703910614525,
|
| 1666 |
+
"grad_norm": 0.09519170293308159,
|
| 1667 |
+
"learning_rate": 1.3108182878190156e-05,
|
| 1668 |
+
"loss": 0.4071,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.2160148975791434,
|
| 1673 |
+
"grad_norm": 0.09880897724698645,
|
| 1674 |
+
"learning_rate": 1.2931380338147745e-05,
|
| 1675 |
+
"loss": 0.4137,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.2253258845437616,
|
| 1680 |
+
"grad_norm": 0.10001625336759871,
|
| 1681 |
+
"learning_rate": 1.2756113374697301e-05,
|
| 1682 |
+
"loss": 0.4141,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.2346368715083798,
|
| 1687 |
+
"grad_norm": 0.0996637237587361,
|
| 1688 |
+
"learning_rate": 1.2582400461507055e-05,
|
| 1689 |
+
"loss": 0.4203,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.243947858472998,
|
| 1694 |
+
"grad_norm": 0.10454993690871738,
|
| 1695 |
+
"learning_rate": 1.2410259908443657e-05,
|
| 1696 |
+
"loss": 0.4102,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.2532588454376166,
|
| 1701 |
+
"grad_norm": 0.1003379879509651,
|
| 1702 |
+
"learning_rate": 1.2239709859642236e-05,
|
| 1703 |
+
"loss": 0.4223,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.2625698324022347,
|
| 1708 |
+
"grad_norm": 0.09802095097599599,
|
| 1709 |
+
"learning_rate": 1.2070768291593964e-05,
|
| 1710 |
+
"loss": 0.4151,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.271880819366853,
|
| 1715 |
+
"grad_norm": 0.09783634576245234,
|
| 1716 |
+
"learning_rate": 1.1903453011251281e-05,
|
| 1717 |
+
"loss": 0.4171,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.281191806331471,
|
| 1722 |
+
"grad_norm": 0.10651764573200316,
|
| 1723 |
+
"learning_rate": 1.1737781654150954e-05,
|
| 1724 |
+
"loss": 0.4171,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.2905027932960893,
|
| 1729 |
+
"grad_norm": 0.10998450255021262,
|
| 1730 |
+
"learning_rate": 1.1573771682555298e-05,
|
| 1731 |
+
"loss": 0.4212,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.2998137802607075,
|
| 1736 |
+
"grad_norm": 0.09653384858037176,
|
| 1737 |
+
"learning_rate": 1.1411440383611559e-05,
|
| 1738 |
+
"loss": 0.4149,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.3091247672253257,
|
| 1743 |
+
"grad_norm": 0.10197498165183494,
|
| 1744 |
+
"learning_rate": 1.1250804867529793e-05,
|
| 1745 |
+
"loss": 0.4174,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.3184357541899443,
|
| 1750 |
+
"grad_norm": 0.10064617044586674,
|
| 1751 |
+
"learning_rate": 1.1091882065779429e-05,
|
| 1752 |
+
"loss": 0.4142,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.3277467411545625,
|
| 1757 |
+
"grad_norm": 0.09997648870136769,
|
| 1758 |
+
"learning_rate": 1.093468872930462e-05,
|
| 1759 |
+
"loss": 0.4248,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.3370577281191807,
|
| 1764 |
+
"grad_norm": 0.10126015276405256,
|
| 1765 |
+
"learning_rate": 1.0779241426758628e-05,
|
| 1766 |
+
"loss": 0.4187,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.346368715083799,
|
| 1771 |
+
"grad_norm": 0.10248882729986777,
|
| 1772 |
+
"learning_rate": 1.0625556542757494e-05,
|
| 1773 |
+
"loss": 0.4256,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.355679702048417,
|
| 1778 |
+
"grad_norm": 0.09629566154715391,
|
| 1779 |
+
"learning_rate": 1.0473650276152972e-05,
|
| 1780 |
+
"loss": 0.4215,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.364990689013035,
|
| 1785 |
+
"grad_norm": 0.09893527097271672,
|
| 1786 |
+
"learning_rate": 1.0323538638325184e-05,
|
| 1787 |
+
"loss": 0.4188,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.3743016759776534,
|
| 1792 |
+
"grad_norm": 0.09302606623894093,
|
| 1793 |
+
"learning_rate": 1.0175237451494946e-05,
|
| 1794 |
+
"loss": 0.4145,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.383612662942272,
|
| 1799 |
+
"grad_norm": 0.10187238212320712,
|
| 1800 |
+
"learning_rate": 1.0028762347056049e-05,
|
| 1801 |
+
"loss": 0.4087,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.39292364990689,
|
| 1806 |
+
"grad_norm": 0.09943852275889314,
|
| 1807 |
+
"learning_rate": 9.88412876392769e-06,
|
| 1808 |
+
"loss": 0.4234,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.4022346368715084,
|
| 1813 |
+
"grad_norm": 0.09579290986291013,
|
| 1814 |
+
"learning_rate": 9.741351946927141e-06,
|
| 1815 |
+
"loss": 0.4209,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.4115456238361266,
|
| 1820 |
+
"grad_norm": 0.10121357816296453,
|
| 1821 |
+
"learning_rate": 9.600446945162908e-06,
|
| 1822 |
+
"loss": 0.4221,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.4208566108007448,
|
| 1827 |
+
"grad_norm": 0.09927071713182525,
|
| 1828 |
+
"learning_rate": 9.461428610448502e-06,
|
| 1829 |
+
"loss": 0.4227,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.430167597765363,
|
| 1834 |
+
"grad_norm": 0.10159715499322029,
|
| 1835 |
+
"learning_rate": 9.324311595737025e-06,
|
| 1836 |
+
"loss": 0.4169,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.439478584729981,
|
| 1841 |
+
"grad_norm": 0.10043193606766965,
|
| 1842 |
+
"learning_rate": 9.189110353576703e-06,
|
| 1843 |
+
"loss": 0.4117,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.4487895716945998,
|
| 1848 |
+
"grad_norm": 0.09912578603874618,
|
| 1849 |
+
"learning_rate": 9.055839134587527e-06,
|
| 1850 |
+
"loss": 0.4151,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.458100558659218,
|
| 1855 |
+
"grad_norm": 0.09297775914893847,
|
| 1856 |
+
"learning_rate": 8.92451198595921e-06,
|
| 1857 |
+
"loss": 0.4099,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.467411545623836,
|
| 1862 |
+
"grad_norm": 0.09984530224126298,
|
| 1863 |
+
"learning_rate": 8.795142749970564e-06,
|
| 1864 |
+
"loss": 0.4123,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.4767225325884543,
|
| 1869 |
+
"grad_norm": 0.09120975321788215,
|
| 1870 |
+
"learning_rate": 8.667745062530503e-06,
|
| 1871 |
+
"loss": 0.4143,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.4860335195530725,
|
| 1876 |
+
"grad_norm": 0.09774167066305631,
|
| 1877 |
+
"learning_rate": 8.542332351740727e-06,
|
| 1878 |
+
"loss": 0.4189,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.4953445065176907,
|
| 1883 |
+
"grad_norm": 0.09827792678481405,
|
| 1884 |
+
"learning_rate": 8.418917836480417e-06,
|
| 1885 |
+
"loss": 0.4194,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.504655493482309,
|
| 1890 |
+
"grad_norm": 0.09390126470923525,
|
| 1891 |
+
"learning_rate": 8.297514525012894e-06,
|
| 1892 |
+
"loss": 0.422,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.5139664804469275,
|
| 1897 |
+
"grad_norm": 0.09346706560041741,
|
| 1898 |
+
"learning_rate": 8.178135213614499e-06,
|
| 1899 |
+
"loss": 0.4198,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.5232774674115457,
|
| 1904 |
+
"grad_norm": 0.09400692518566071,
|
| 1905 |
+
"learning_rate": 8.060792485225877e-06,
|
| 1906 |
+
"loss": 0.4153,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.532588454376164,
|
| 1911 |
+
"grad_norm": 0.09935167204099171,
|
| 1912 |
+
"learning_rate": 7.945498708125612e-06,
|
| 1913 |
+
"loss": 0.419,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.541899441340782,
|
| 1918 |
+
"grad_norm": 0.09255945749166977,
|
| 1919 |
+
"learning_rate": 7.832266034626668e-06,
|
| 1920 |
+
"loss": 0.4077,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.5512104283054002,
|
| 1925 |
+
"grad_norm": 0.09429134332541908,
|
| 1926 |
+
"learning_rate": 7.721106399795427e-06,
|
| 1927 |
+
"loss": 0.4111,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.560521415270019,
|
| 1932 |
+
"grad_norm": 0.09593431408689819,
|
| 1933 |
+
"learning_rate": 7.612031520193731e-06,
|
| 1934 |
+
"loss": 0.4144,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.5698324022346366,
|
| 1939 |
+
"grad_norm": 0.10216201759504691,
|
| 1940 |
+
"learning_rate": 7.505052892643915e-06,
|
| 1941 |
+
"loss": 0.4147,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.5791433891992552,
|
| 1946 |
+
"grad_norm": 0.09195284463580435,
|
| 1947 |
+
"learning_rate": 7.4001817930170036e-06,
|
| 1948 |
+
"loss": 0.42,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.5884543761638734,
|
| 1953 |
+
"grad_norm": 0.09617799061198681,
|
| 1954 |
+
"learning_rate": 7.297429275044194e-06,
|
| 1955 |
+
"loss": 0.4093,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.5977653631284916,
|
| 1960 |
+
"grad_norm": 0.10099179291339958,
|
| 1961 |
+
"learning_rate": 7.196806169151786e-06,
|
| 1962 |
+
"loss": 0.4233,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.60707635009311,
|
| 1967 |
+
"grad_norm": 0.09641311151569762,
|
| 1968 |
+
"learning_rate": 7.098323081319576e-06,
|
| 1969 |
+
"loss": 0.4155,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.616387337057728,
|
| 1974 |
+
"grad_norm": 0.09465528720326888,
|
| 1975 |
+
"learning_rate": 7.001990391963011e-06,
|
| 1976 |
+
"loss": 0.4179,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.6256983240223466,
|
| 1981 |
+
"grad_norm": 0.09927128319879645,
|
| 1982 |
+
"learning_rate": 6.907818254839017e-06,
|
| 1983 |
+
"loss": 0.4203,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.635009310986965,
|
| 1988 |
+
"grad_norm": 0.09942785015352072,
|
| 1989 |
+
"learning_rate": 6.815816595975771e-06,
|
| 1990 |
+
"loss": 0.4216,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.644320297951583,
|
| 1995 |
+
"grad_norm": 0.1002604796284761,
|
| 1996 |
+
"learning_rate": 6.725995112626489e-06,
|
| 1997 |
+
"loss": 0.4214,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.653631284916201,
|
| 2002 |
+
"grad_norm": 0.09509870809273925,
|
| 2003 |
+
"learning_rate": 6.638363272247286e-06,
|
| 2004 |
+
"loss": 0.4149,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.6629422718808193,
|
| 2009 |
+
"grad_norm": 0.10038637331627898,
|
| 2010 |
+
"learning_rate": 6.552930311499275e-06,
|
| 2011 |
+
"loss": 0.4243,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.6722532588454375,
|
| 2016 |
+
"grad_norm": 0.09849966019071536,
|
| 2017 |
+
"learning_rate": 6.469705235275016e-06,
|
| 2018 |
+
"loss": 0.423,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.6815642458100557,
|
| 2023 |
+
"grad_norm": 0.09583945495890936,
|
| 2024 |
+
"learning_rate": 6.388696815749346e-06,
|
| 2025 |
+
"loss": 0.4297,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.6908752327746743,
|
| 2030 |
+
"grad_norm": 0.09818740944151227,
|
| 2031 |
+
"learning_rate": 6.309913591454788e-06,
|
| 2032 |
+
"loss": 0.4175,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.7001862197392925,
|
| 2037 |
+
"grad_norm": 0.09297545599110695,
|
| 2038 |
+
"learning_rate": 6.233363866381562e-06,
|
| 2039 |
+
"loss": 0.4151,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.7094972067039107,
|
| 2044 |
+
"grad_norm": 0.09347294049524463,
|
| 2045 |
+
"learning_rate": 6.159055709102293e-06,
|
| 2046 |
+
"loss": 0.4211,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.718808193668529,
|
| 2051 |
+
"grad_norm": 0.09063495788855541,
|
| 2052 |
+
"learning_rate": 6.086996951921601e-06,
|
| 2053 |
+
"loss": 0.4169,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.728119180633147,
|
| 2058 |
+
"grad_norm": 0.09576157520224456,
|
| 2059 |
+
"learning_rate": 6.017195190050504e-06,
|
| 2060 |
+
"loss": 0.4178,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.7374301675977653,
|
| 2065 |
+
"grad_norm": 0.09821892447570103,
|
| 2066 |
+
"learning_rate": 5.949657780805906e-06,
|
| 2067 |
+
"loss": 0.4196,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.7467411545623834,
|
| 2072 |
+
"grad_norm": 0.09403307674636713,
|
| 2073 |
+
"learning_rate": 5.88439184283509e-06,
|
| 2074 |
+
"loss": 0.4191,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.756052141527002,
|
| 2079 |
+
"grad_norm": 0.09844473844449389,
|
| 2080 |
+
"learning_rate": 5.821404255365381e-06,
|
| 2081 |
+
"loss": 0.4167,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.7653631284916202,
|
| 2086 |
+
"grad_norm": 0.1049290391027304,
|
| 2087 |
+
"learning_rate": 5.7607016574790845e-06,
|
| 2088 |
+
"loss": 0.4158,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.7746741154562384,
|
| 2093 |
+
"grad_norm": 0.09142057289478683,
|
| 2094 |
+
"learning_rate": 5.702290447413681e-06,
|
| 2095 |
+
"loss": 0.4195,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.7839851024208566,
|
| 2100 |
+
"grad_norm": 0.09437947535885335,
|
| 2101 |
+
"learning_rate": 5.646176781887437e-06,
|
| 2102 |
+
"loss": 0.422,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.793296089385475,
|
| 2107 |
+
"grad_norm": 0.09658988683610302,
|
| 2108 |
+
"learning_rate": 5.592366575450494e-06,
|
| 2109 |
+
"loss": 0.4132,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.802607076350093,
|
| 2114 |
+
"grad_norm": 0.10021332194018327,
|
| 2115 |
+
"learning_rate": 5.5408654998614055e-06,
|
| 2116 |
+
"loss": 0.4285,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.811918063314711,
|
| 2121 |
+
"grad_norm": 0.09395338001674504,
|
| 2122 |
+
"learning_rate": 5.491678983489372e-06,
|
| 2123 |
+
"loss": 0.4056,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.82122905027933,
|
| 2128 |
+
"grad_norm": 0.10069367341531493,
|
| 2129 |
+
"learning_rate": 5.4448122107420415e-06,
|
| 2130 |
+
"loss": 0.4289,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.830540037243948,
|
| 2135 |
+
"grad_norm": 0.0977726987894797,
|
| 2136 |
+
"learning_rate": 5.40027012151906e-06,
|
| 2137 |
+
"loss": 0.4178,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.839851024208566,
|
| 2142 |
+
"grad_norm": 0.09024612259420411,
|
| 2143 |
+
"learning_rate": 5.3580574106914015e-06,
|
| 2144 |
+
"loss": 0.4118,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.8491620111731844,
|
| 2149 |
+
"grad_norm": 0.09342541886916174,
|
| 2150 |
+
"learning_rate": 5.318178527606511e-06,
|
| 2151 |
+
"loss": 0.4205,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.8584729981378025,
|
| 2156 |
+
"grad_norm": 0.09438754600698024,
|
| 2157 |
+
"learning_rate": 5.2806376756193194e-06,
|
| 2158 |
+
"loss": 0.4129,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.8677839851024207,
|
| 2163 |
+
"grad_norm": 0.09314142674041269,
|
| 2164 |
+
"learning_rate": 5.245438811649216e-06,
|
| 2165 |
+
"loss": 0.4174,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.877094972067039,
|
| 2170 |
+
"grad_norm": 0.09920083405177257,
|
| 2171 |
+
"learning_rate": 5.212585645762963e-06,
|
| 2172 |
+
"loss": 0.413,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.8864059590316575,
|
| 2177 |
+
"grad_norm": 0.10054514046549108,
|
| 2178 |
+
"learning_rate": 5.182081640783647e-06,
|
| 2179 |
+
"loss": 0.4201,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.8957169459962757,
|
| 2184 |
+
"grad_norm": 0.09375029466655158,
|
| 2185 |
+
"learning_rate": 5.153930011925686e-06,
|
| 2186 |
+
"loss": 0.4117,
|
| 2187 |
+
"step": 1555
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.905027932960894,
|
| 2191 |
+
"grad_norm": 0.1187162272510011,
|
| 2192 |
+
"learning_rate": 5.128133726455941e-06,
|
| 2193 |
+
"loss": 0.4147,
|
| 2194 |
+
"step": 1560
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.914338919925512,
|
| 2198 |
+
"grad_norm": 0.09097957682917539,
|
| 2199 |
+
"learning_rate": 5.104695503380948e-06,
|
| 2200 |
+
"loss": 0.406,
|
| 2201 |
+
"step": 1565
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.9236499068901303,
|
| 2205 |
+
"grad_norm": 0.08917608409363194,
|
| 2206 |
+
"learning_rate": 5.083617813160338e-06,
|
| 2207 |
+
"loss": 0.4139,
|
| 2208 |
+
"step": 1570
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.9329608938547485,
|
| 2212 |
+
"grad_norm": 0.09357577576462056,
|
| 2213 |
+
"learning_rate": 5.064902877446432e-06,
|
| 2214 |
+
"loss": 0.4198,
|
| 2215 |
+
"step": 1575
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.9422718808193666,
|
| 2219 |
+
"grad_norm": 0.09162535893385207,
|
| 2220 |
+
"learning_rate": 5.048552668850077e-06,
|
| 2221 |
+
"loss": 0.4211,
|
| 2222 |
+
"step": 1580
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.9515828677839853,
|
| 2226 |
+
"grad_norm": 0.09497386963890858,
|
| 2227 |
+
"learning_rate": 5.034568910732737e-06,
|
| 2228 |
+
"loss": 0.4143,
|
| 2229 |
+
"step": 1585
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.9608938547486034,
|
| 2233 |
+
"grad_norm": 0.09474281729138122,
|
| 2234 |
+
"learning_rate": 5.022953077024818e-06,
|
| 2235 |
+
"loss": 0.4194,
|
| 2236 |
+
"step": 1590
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.9702048417132216,
|
| 2240 |
+
"grad_norm": 0.09634825165067597,
|
| 2241 |
+
"learning_rate": 5.0137063920703455e-06,
|
| 2242 |
+
"loss": 0.4142,
|
| 2243 |
+
"step": 1595
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.97951582867784,
|
| 2247 |
+
"grad_norm": 0.09441014556129712,
|
| 2248 |
+
"learning_rate": 5.0068298304978894e-06,
|
| 2249 |
+
"loss": 0.4174,
|
| 2250 |
+
"step": 1600
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.988826815642458,
|
| 2254 |
+
"grad_norm": 0.09449692277995367,
|
| 2255 |
+
"learning_rate": 5.002324117117843e-06,
|
| 2256 |
+
"loss": 0.4177,
|
| 2257 |
+
"step": 1605
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.998137802607076,
|
| 2261 |
+
"grad_norm": 0.09204215488513472,
|
| 2262 |
+
"learning_rate": 5.000189726846031e-06,
|
| 2263 |
+
"loss": 0.4193,
|
| 2264 |
+
"step": 1610
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 3.0,
|
| 2268 |
+
"step": 1611,
|
| 2269 |
+
"total_flos": 1468598568615936.0,
|
| 2270 |
+
"train_loss": 0.4715816771147933,
|
| 2271 |
+
"train_runtime": 19678.9404,
|
| 2272 |
+
"train_samples_per_second": 2.617,
|
| 2273 |
+
"train_steps_per_second": 0.082
|
| 2274 |
+
}
|
| 2275 |
+
],
|
| 2276 |
+
"logging_steps": 5,
|
| 2277 |
+
"max_steps": 1611,
|
| 2278 |
+
"num_input_tokens_seen": 0,
|
| 2279 |
+
"num_train_epochs": 3,
|
| 2280 |
+
"save_steps": 100,
|
| 2281 |
+
"stateful_callbacks": {
|
| 2282 |
+
"TrainerControl": {
|
| 2283 |
+
"args": {
|
| 2284 |
+
"should_epoch_stop": false,
|
| 2285 |
+
"should_evaluate": false,
|
| 2286 |
+
"should_log": false,
|
| 2287 |
+
"should_save": true,
|
| 2288 |
+
"should_training_stop": true
|
| 2289 |
+
},
|
| 2290 |
+
"attributes": {}
|
| 2291 |
+
}
|
| 2292 |
+
},
|
| 2293 |
+
"total_flos": 1468598568615936.0,
|
| 2294 |
+
"train_batch_size": 4,
|
| 2295 |
+
"trial_name": null,
|
| 2296 |
+
"trial_params": null
|
| 2297 |
+
}
|