Model save
Browse files- README.md +57 -0
- all_results.json +8 -0
- generation_config.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1540 -0
README.md
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
model_name: Qwen7B-EP2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
licence: license
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Qwen7B-EP2
|
| 12 |
+
|
| 13 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 14 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
+
|
| 16 |
+
## Quick start
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import pipeline
|
| 20 |
+
|
| 21 |
+
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?"
|
| 22 |
+
generator = pipeline("text-generation", model="ZMC2019/Qwen7B-EP2", device="cuda")
|
| 23 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 24 |
+
print(output["generated_text"])
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
## Training procedure
|
| 28 |
+
|
| 29 |
+
[<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/randomresearch/sparsity/runs/fsqf8i8n)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
This model was trained with SFT.
|
| 33 |
+
|
| 34 |
+
### Framework versions
|
| 35 |
+
|
| 36 |
+
- TRL: 0.16.0.dev0
|
| 37 |
+
- Transformers: 4.49.0
|
| 38 |
+
- Pytorch: 2.5.1
|
| 39 |
+
- Datasets: 3.5.0
|
| 40 |
+
- Tokenizers: 0.21.1
|
| 41 |
+
|
| 42 |
+
## Citations
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
Cite TRL as:
|
| 47 |
+
|
| 48 |
+
```bibtex
|
| 49 |
+
@misc{vonwerra2022trl,
|
| 50 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 51 |
+
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},
|
| 52 |
+
year = 2020,
|
| 53 |
+
journal = {GitHub repository},
|
| 54 |
+
publisher = {GitHub},
|
| 55 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 56 |
+
}
|
| 57 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 9.192833840127672e+17,
|
| 3 |
+
"train_loss": 0.17092923446448186,
|
| 4 |
+
"train_runtime": 41238.1916,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.416,
|
| 7 |
+
"train_steps_per_second": 0.026
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.49.0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 9.192833840127672e+17,
|
| 3 |
+
"train_loss": 0.17092923446448186,
|
| 4 |
+
"train_runtime": 41238.1916,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.416,
|
| 7 |
+
"train_steps_per_second": 0.026
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.999534233814625,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1073,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004657661853749418,
|
| 13 |
+
"grad_norm": 0.4898898763392053,
|
| 14 |
+
"learning_rate": 1.3814146295083454e-05,
|
| 15 |
+
"loss": 0.2136,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009315323707498836,
|
| 20 |
+
"grad_norm": 0.30738158613581057,
|
| 21 |
+
"learning_rate": 1.3749473325537183e-05,
|
| 22 |
+
"loss": 0.2136,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013972985561248253,
|
| 27 |
+
"grad_norm": 0.3003735412620342,
|
| 28 |
+
"learning_rate": 1.3684800355990914e-05,
|
| 29 |
+
"loss": 0.2106,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018630647414997672,
|
| 34 |
+
"grad_norm": 0.2829346467316103,
|
| 35 |
+
"learning_rate": 1.3620127386444643e-05,
|
| 36 |
+
"loss": 0.2119,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02328830926874709,
|
| 41 |
+
"grad_norm": 0.2663704136751027,
|
| 42 |
+
"learning_rate": 1.3555454416898371e-05,
|
| 43 |
+
"loss": 0.2061,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.027945971122496506,
|
| 48 |
+
"grad_norm": 0.27394556988751145,
|
| 49 |
+
"learning_rate": 1.34907814473521e-05,
|
| 50 |
+
"loss": 0.2082,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.032603632976245925,
|
| 55 |
+
"grad_norm": 0.2902960250334669,
|
| 56 |
+
"learning_rate": 1.342610847780583e-05,
|
| 57 |
+
"loss": 0.2111,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.037261294829995344,
|
| 62 |
+
"grad_norm": 0.28344160120346346,
|
| 63 |
+
"learning_rate": 1.336143550825956e-05,
|
| 64 |
+
"loss": 0.2097,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04191895668374476,
|
| 69 |
+
"grad_norm": 0.27851995467853674,
|
| 70 |
+
"learning_rate": 1.3296762538713289e-05,
|
| 71 |
+
"loss": 0.2016,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04657661853749418,
|
| 76 |
+
"grad_norm": 0.27273102311702296,
|
| 77 |
+
"learning_rate": 1.3232089569167018e-05,
|
| 78 |
+
"loss": 0.2049,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05123428039124359,
|
| 83 |
+
"grad_norm": 0.26628353235058055,
|
| 84 |
+
"learning_rate": 1.3167416599620746e-05,
|
| 85 |
+
"loss": 0.2045,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05589194224499301,
|
| 90 |
+
"grad_norm": 0.27569927041474046,
|
| 91 |
+
"learning_rate": 1.3102743630074475e-05,
|
| 92 |
+
"loss": 0.2064,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06054960409874243,
|
| 97 |
+
"grad_norm": 0.2686606023580276,
|
| 98 |
+
"learning_rate": 1.3038070660528204e-05,
|
| 99 |
+
"loss": 0.2038,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06520726595249185,
|
| 104 |
+
"grad_norm": 0.26109094018402645,
|
| 105 |
+
"learning_rate": 1.2973397690981933e-05,
|
| 106 |
+
"loss": 0.1956,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06986492780624126,
|
| 111 |
+
"grad_norm": 0.2641336722833559,
|
| 112 |
+
"learning_rate": 1.2908724721435662e-05,
|
| 113 |
+
"loss": 0.1991,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07452258965999069,
|
| 118 |
+
"grad_norm": 0.2758157412328419,
|
| 119 |
+
"learning_rate": 1.2844051751889391e-05,
|
| 120 |
+
"loss": 0.2041,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0791802515137401,
|
| 125 |
+
"grad_norm": 0.2644334180100764,
|
| 126 |
+
"learning_rate": 1.277937878234312e-05,
|
| 127 |
+
"loss": 0.1966,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08383791336748952,
|
| 132 |
+
"grad_norm": 0.27815334897512417,
|
| 133 |
+
"learning_rate": 1.2714705812796849e-05,
|
| 134 |
+
"loss": 0.2016,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08849557522123894,
|
| 139 |
+
"grad_norm": 0.27597274674830136,
|
| 140 |
+
"learning_rate": 1.265003284325058e-05,
|
| 141 |
+
"loss": 0.1991,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09315323707498836,
|
| 146 |
+
"grad_norm": 0.287243548410707,
|
| 147 |
+
"learning_rate": 1.2585359873704308e-05,
|
| 148 |
+
"loss": 0.1985,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09781089892873777,
|
| 153 |
+
"grad_norm": 0.27239660838008967,
|
| 154 |
+
"learning_rate": 1.2520686904158037e-05,
|
| 155 |
+
"loss": 0.1992,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10246856078248719,
|
| 160 |
+
"grad_norm": 0.2638215362187855,
|
| 161 |
+
"learning_rate": 1.2456013934611766e-05,
|
| 162 |
+
"loss": 0.1955,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10712622263623661,
|
| 167 |
+
"grad_norm": 0.2728798276130817,
|
| 168 |
+
"learning_rate": 1.2391340965065495e-05,
|
| 169 |
+
"loss": 0.1964,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11178388448998602,
|
| 174 |
+
"grad_norm": 0.2820044360306929,
|
| 175 |
+
"learning_rate": 1.2326667995519225e-05,
|
| 176 |
+
"loss": 0.2014,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11644154634373545,
|
| 181 |
+
"grad_norm": 0.2647841505206279,
|
| 182 |
+
"learning_rate": 1.2261995025972954e-05,
|
| 183 |
+
"loss": 0.1968,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12109920819748486,
|
| 188 |
+
"grad_norm": 0.27673471471676736,
|
| 189 |
+
"learning_rate": 1.2197322056426683e-05,
|
| 190 |
+
"loss": 0.1909,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1257568700512343,
|
| 195 |
+
"grad_norm": 0.28180912840315686,
|
| 196 |
+
"learning_rate": 1.2132649086880412e-05,
|
| 197 |
+
"loss": 0.1954,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1304145319049837,
|
| 202 |
+
"grad_norm": 0.2736818512163929,
|
| 203 |
+
"learning_rate": 1.2067976117334141e-05,
|
| 204 |
+
"loss": 0.1964,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1350721937587331,
|
| 209 |
+
"grad_norm": 0.2839435152252633,
|
| 210 |
+
"learning_rate": 1.2003303147787872e-05,
|
| 211 |
+
"loss": 0.1988,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13972985561248252,
|
| 216 |
+
"grad_norm": 0.2921732101625134,
|
| 217 |
+
"learning_rate": 1.19386301782416e-05,
|
| 218 |
+
"loss": 0.198,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14438751746623196,
|
| 223 |
+
"grad_norm": 0.27512193018407655,
|
| 224 |
+
"learning_rate": 1.187395720869533e-05,
|
| 225 |
+
"loss": 0.1891,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14904517931998137,
|
| 230 |
+
"grad_norm": 0.2792499314366877,
|
| 231 |
+
"learning_rate": 1.1809284239149058e-05,
|
| 232 |
+
"loss": 0.1902,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1537028411737308,
|
| 237 |
+
"grad_norm": 0.26757397271285654,
|
| 238 |
+
"learning_rate": 1.1744611269602787e-05,
|
| 239 |
+
"loss": 0.1946,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1583605030274802,
|
| 244 |
+
"grad_norm": 0.28991583056580006,
|
| 245 |
+
"learning_rate": 1.1679938300056518e-05,
|
| 246 |
+
"loss": 0.1916,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1630181648812296,
|
| 251 |
+
"grad_norm": 0.27237661265377583,
|
| 252 |
+
"learning_rate": 1.1615265330510247e-05,
|
| 253 |
+
"loss": 0.1956,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16767582673497905,
|
| 258 |
+
"grad_norm": 0.2732388141630142,
|
| 259 |
+
"learning_rate": 1.1550592360963975e-05,
|
| 260 |
+
"loss": 0.1905,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17233348858872846,
|
| 265 |
+
"grad_norm": 0.2844631040084945,
|
| 266 |
+
"learning_rate": 1.1485919391417704e-05,
|
| 267 |
+
"loss": 0.1915,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17699115044247787,
|
| 272 |
+
"grad_norm": 0.2701931339672014,
|
| 273 |
+
"learning_rate": 1.1421246421871433e-05,
|
| 274 |
+
"loss": 0.1857,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18164881229622729,
|
| 279 |
+
"grad_norm": 0.28012425319201967,
|
| 280 |
+
"learning_rate": 1.1356573452325162e-05,
|
| 281 |
+
"loss": 0.1912,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18630647414997673,
|
| 286 |
+
"grad_norm": 0.2621061718354639,
|
| 287 |
+
"learning_rate": 1.1291900482778891e-05,
|
| 288 |
+
"loss": 0.1833,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.19096413600372614,
|
| 293 |
+
"grad_norm": 0.2760400495539924,
|
| 294 |
+
"learning_rate": 1.122722751323262e-05,
|
| 295 |
+
"loss": 0.1892,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19562179785747555,
|
| 300 |
+
"grad_norm": 0.26636742780061357,
|
| 301 |
+
"learning_rate": 1.1162554543686349e-05,
|
| 302 |
+
"loss": 0.1865,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20027945971122496,
|
| 307 |
+
"grad_norm": 0.31125133254546505,
|
| 308 |
+
"learning_rate": 1.1097881574140078e-05,
|
| 309 |
+
"loss": 0.1873,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20493712156497437,
|
| 314 |
+
"grad_norm": 0.2688780855128172,
|
| 315 |
+
"learning_rate": 1.1033208604593806e-05,
|
| 316 |
+
"loss": 0.1859,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2095947834187238,
|
| 321 |
+
"grad_norm": 0.2693646481515354,
|
| 322 |
+
"learning_rate": 1.0968535635047537e-05,
|
| 323 |
+
"loss": 0.1894,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21425244527247322,
|
| 328 |
+
"grad_norm": 0.28079052289539963,
|
| 329 |
+
"learning_rate": 1.0903862665501266e-05,
|
| 330 |
+
"loss": 0.1893,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21891010712622264,
|
| 335 |
+
"grad_norm": 0.27013814274453324,
|
| 336 |
+
"learning_rate": 1.0839189695954995e-05,
|
| 337 |
+
"loss": 0.1839,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22356776897997205,
|
| 342 |
+
"grad_norm": 0.269308134266216,
|
| 343 |
+
"learning_rate": 1.0774516726408724e-05,
|
| 344 |
+
"loss": 0.1832,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22822543083372146,
|
| 349 |
+
"grad_norm": 0.25987395698645904,
|
| 350 |
+
"learning_rate": 1.0709843756862453e-05,
|
| 351 |
+
"loss": 0.1806,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2328830926874709,
|
| 356 |
+
"grad_norm": 0.25989005139940363,
|
| 357 |
+
"learning_rate": 1.0645170787316183e-05,
|
| 358 |
+
"loss": 0.1845,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2375407545412203,
|
| 363 |
+
"grad_norm": 0.28768279357194804,
|
| 364 |
+
"learning_rate": 1.0580497817769912e-05,
|
| 365 |
+
"loss": 0.1837,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24219841639496972,
|
| 370 |
+
"grad_norm": 0.2897791509924734,
|
| 371 |
+
"learning_rate": 1.0515824848223641e-05,
|
| 372 |
+
"loss": 0.1843,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24685607824871914,
|
| 377 |
+
"grad_norm": 0.28979828443977984,
|
| 378 |
+
"learning_rate": 1.045115187867737e-05,
|
| 379 |
+
"loss": 0.1799,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2515137401024686,
|
| 384 |
+
"grad_norm": 0.2739040687522917,
|
| 385 |
+
"learning_rate": 1.0386478909131099e-05,
|
| 386 |
+
"loss": 0.1772,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.25617140195621796,
|
| 391 |
+
"grad_norm": 0.2890741342392963,
|
| 392 |
+
"learning_rate": 1.032180593958483e-05,
|
| 393 |
+
"loss": 0.1898,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2608290638099674,
|
| 398 |
+
"grad_norm": 0.2747509835907636,
|
| 399 |
+
"learning_rate": 1.0257132970038558e-05,
|
| 400 |
+
"loss": 0.1766,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.26548672566371684,
|
| 405 |
+
"grad_norm": 0.27733781470827146,
|
| 406 |
+
"learning_rate": 1.0192460000492287e-05,
|
| 407 |
+
"loss": 0.1784,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2701443875174662,
|
| 412 |
+
"grad_norm": 0.2776581600424973,
|
| 413 |
+
"learning_rate": 1.0127787030946016e-05,
|
| 414 |
+
"loss": 0.1783,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.27480204937121566,
|
| 419 |
+
"grad_norm": 0.27029507409106857,
|
| 420 |
+
"learning_rate": 1.0063114061399745e-05,
|
| 421 |
+
"loss": 0.178,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27945971122496505,
|
| 426 |
+
"grad_norm": 0.29948763382660526,
|
| 427 |
+
"learning_rate": 9.998441091853475e-06,
|
| 428 |
+
"loss": 0.1956,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2841173730787145,
|
| 433 |
+
"grad_norm": 0.2692368615689735,
|
| 434 |
+
"learning_rate": 9.933768122307204e-06,
|
| 435 |
+
"loss": 0.1916,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2887750349324639,
|
| 440 |
+
"grad_norm": 0.28882532117108234,
|
| 441 |
+
"learning_rate": 9.869095152760933e-06,
|
| 442 |
+
"loss": 0.18,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2934326967862133,
|
| 447 |
+
"grad_norm": 0.2697705799841791,
|
| 448 |
+
"learning_rate": 9.804422183214662e-06,
|
| 449 |
+
"loss": 0.1818,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.29809035863996275,
|
| 454 |
+
"grad_norm": 0.2710934907314508,
|
| 455 |
+
"learning_rate": 9.739749213668391e-06,
|
| 456 |
+
"loss": 0.1795,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.30274802049371213,
|
| 461 |
+
"grad_norm": 0.2812918620602142,
|
| 462 |
+
"learning_rate": 9.67507624412212e-06,
|
| 463 |
+
"loss": 0.1761,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3074056823474616,
|
| 468 |
+
"grad_norm": 0.28980918452292975,
|
| 469 |
+
"learning_rate": 9.610403274575849e-06,
|
| 470 |
+
"loss": 0.1733,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.312063344201211,
|
| 475 |
+
"grad_norm": 0.2850328800925296,
|
| 476 |
+
"learning_rate": 9.545730305029578e-06,
|
| 477 |
+
"loss": 0.1757,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3167210060549604,
|
| 482 |
+
"grad_norm": 0.2717999778810994,
|
| 483 |
+
"learning_rate": 9.481057335483306e-06,
|
| 484 |
+
"loss": 0.1804,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.32137866790870984,
|
| 489 |
+
"grad_norm": 0.2560784991693304,
|
| 490 |
+
"learning_rate": 9.416384365937035e-06,
|
| 491 |
+
"loss": 0.1697,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3260363297624592,
|
| 496 |
+
"grad_norm": 0.26722744730572845,
|
| 497 |
+
"learning_rate": 9.351711396390764e-06,
|
| 498 |
+
"loss": 0.1702,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.33069399161620866,
|
| 503 |
+
"grad_norm": 0.2821288703896537,
|
| 504 |
+
"learning_rate": 9.287038426844495e-06,
|
| 505 |
+
"loss": 0.1695,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3353516534699581,
|
| 510 |
+
"grad_norm": 0.2741963334942978,
|
| 511 |
+
"learning_rate": 9.222365457298224e-06,
|
| 512 |
+
"loss": 0.1703,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3400093153237075,
|
| 517 |
+
"grad_norm": 0.26771221973733034,
|
| 518 |
+
"learning_rate": 9.157692487751953e-06,
|
| 519 |
+
"loss": 0.1708,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3446669771774569,
|
| 524 |
+
"grad_norm": 0.2799829020254886,
|
| 525 |
+
"learning_rate": 9.093019518205682e-06,
|
| 526 |
+
"loss": 0.176,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3493246390312063,
|
| 531 |
+
"grad_norm": 0.27899662489213484,
|
| 532 |
+
"learning_rate": 9.02834654865941e-06,
|
| 533 |
+
"loss": 0.1733,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35398230088495575,
|
| 538 |
+
"grad_norm": 0.29451880914284095,
|
| 539 |
+
"learning_rate": 8.963673579113141e-06,
|
| 540 |
+
"loss": 0.1641,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3586399627387052,
|
| 545 |
+
"grad_norm": 0.2548290052895923,
|
| 546 |
+
"learning_rate": 8.89900060956687e-06,
|
| 547 |
+
"loss": 0.1652,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36329762459245457,
|
| 552 |
+
"grad_norm": 0.2782998276983566,
|
| 553 |
+
"learning_rate": 8.834327640020599e-06,
|
| 554 |
+
"loss": 0.1736,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.367955286446204,
|
| 559 |
+
"grad_norm": 0.3108837807460626,
|
| 560 |
+
"learning_rate": 8.769654670474328e-06,
|
| 561 |
+
"loss": 0.1666,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.37261294829995345,
|
| 566 |
+
"grad_norm": 0.2597747591243422,
|
| 567 |
+
"learning_rate": 8.704981700928057e-06,
|
| 568 |
+
"loss": 0.1653,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.37727061015370283,
|
| 573 |
+
"grad_norm": 0.26914952065737996,
|
| 574 |
+
"learning_rate": 8.640308731381787e-06,
|
| 575 |
+
"loss": 0.1672,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3819282720074523,
|
| 580 |
+
"grad_norm": 0.2732409152801453,
|
| 581 |
+
"learning_rate": 8.575635761835516e-06,
|
| 582 |
+
"loss": 0.1662,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.38658593386120166,
|
| 587 |
+
"grad_norm": 0.2743043246649274,
|
| 588 |
+
"learning_rate": 8.510962792289245e-06,
|
| 589 |
+
"loss": 0.1657,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3912435957149511,
|
| 594 |
+
"grad_norm": 0.25669123853699566,
|
| 595 |
+
"learning_rate": 8.446289822742974e-06,
|
| 596 |
+
"loss": 0.1618,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39590125756870054,
|
| 601 |
+
"grad_norm": 0.2575953744135377,
|
| 602 |
+
"learning_rate": 8.381616853196703e-06,
|
| 603 |
+
"loss": 0.1673,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4005589194224499,
|
| 608 |
+
"grad_norm": 0.277605285139537,
|
| 609 |
+
"learning_rate": 8.316943883650433e-06,
|
| 610 |
+
"loss": 0.1659,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.40521658127619936,
|
| 615 |
+
"grad_norm": 0.2564386597519866,
|
| 616 |
+
"learning_rate": 8.252270914104162e-06,
|
| 617 |
+
"loss": 0.1651,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.40987424312994875,
|
| 622 |
+
"grad_norm": 0.26934757965420686,
|
| 623 |
+
"learning_rate": 8.187597944557891e-06,
|
| 624 |
+
"loss": 0.1667,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4145319049836982,
|
| 629 |
+
"grad_norm": 0.2572104011525305,
|
| 630 |
+
"learning_rate": 8.12292497501162e-06,
|
| 631 |
+
"loss": 0.1621,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4191895668374476,
|
| 636 |
+
"grad_norm": 0.2733590889138333,
|
| 637 |
+
"learning_rate": 8.058252005465349e-06,
|
| 638 |
+
"loss": 0.1651,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.423847228691197,
|
| 643 |
+
"grad_norm": 0.27856343837637626,
|
| 644 |
+
"learning_rate": 7.993579035919078e-06,
|
| 645 |
+
"loss": 0.1695,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42850489054494645,
|
| 650 |
+
"grad_norm": 0.2602976128013146,
|
| 651 |
+
"learning_rate": 7.928906066372807e-06,
|
| 652 |
+
"loss": 0.1644,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.43316255239869583,
|
| 657 |
+
"grad_norm": 0.2636316936812981,
|
| 658 |
+
"learning_rate": 7.864233096826535e-06,
|
| 659 |
+
"loss": 0.165,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.43782021425244527,
|
| 664 |
+
"grad_norm": 0.2674553223546519,
|
| 665 |
+
"learning_rate": 7.799560127280264e-06,
|
| 666 |
+
"loss": 0.1665,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4424778761061947,
|
| 671 |
+
"grad_norm": 0.2795005672444373,
|
| 672 |
+
"learning_rate": 7.734887157733993e-06,
|
| 673 |
+
"loss": 0.1677,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4471355379599441,
|
| 678 |
+
"grad_norm": 0.2642634409457942,
|
| 679 |
+
"learning_rate": 7.670214188187722e-06,
|
| 680 |
+
"loss": 0.1639,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.45179319981369354,
|
| 685 |
+
"grad_norm": 0.27874468479656006,
|
| 686 |
+
"learning_rate": 7.6055412186414535e-06,
|
| 687 |
+
"loss": 0.1627,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4564508616674429,
|
| 692 |
+
"grad_norm": 0.26743452865617695,
|
| 693 |
+
"learning_rate": 7.5408682490951815e-06,
|
| 694 |
+
"loss": 0.1658,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.46110852352119236,
|
| 699 |
+
"grad_norm": 0.26129007423168416,
|
| 700 |
+
"learning_rate": 7.47619527954891e-06,
|
| 701 |
+
"loss": 0.165,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4657661853749418,
|
| 706 |
+
"grad_norm": 0.2595733527250995,
|
| 707 |
+
"learning_rate": 7.411522310002639e-06,
|
| 708 |
+
"loss": 0.1657,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4704238472286912,
|
| 713 |
+
"grad_norm": 0.25844757902441573,
|
| 714 |
+
"learning_rate": 7.346849340456368e-06,
|
| 715 |
+
"loss": 0.1649,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4750815090824406,
|
| 720 |
+
"grad_norm": 0.2622868883005882,
|
| 721 |
+
"learning_rate": 7.282176370910099e-06,
|
| 722 |
+
"loss": 0.164,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.47973917093619,
|
| 727 |
+
"grad_norm": 0.271729936927589,
|
| 728 |
+
"learning_rate": 7.217503401363828e-06,
|
| 729 |
+
"loss": 0.1747,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.48439683278993945,
|
| 734 |
+
"grad_norm": 0.2574849448431822,
|
| 735 |
+
"learning_rate": 7.1528304318175565e-06,
|
| 736 |
+
"loss": 0.1732,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.4890544946436889,
|
| 741 |
+
"grad_norm": 0.27066134685503324,
|
| 742 |
+
"learning_rate": 7.088157462271285e-06,
|
| 743 |
+
"loss": 0.1696,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.49371215649743827,
|
| 748 |
+
"grad_norm": 0.2653096067066601,
|
| 749 |
+
"learning_rate": 7.023484492725014e-06,
|
| 750 |
+
"loss": 0.1677,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.4983698183511877,
|
| 755 |
+
"grad_norm": 0.27909543445048357,
|
| 756 |
+
"learning_rate": 6.958811523178745e-06,
|
| 757 |
+
"loss": 0.1822,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5030274802049371,
|
| 762 |
+
"grad_norm": 0.2769655577925874,
|
| 763 |
+
"learning_rate": 6.894138553632473e-06,
|
| 764 |
+
"loss": 0.1696,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5076851420586865,
|
| 769 |
+
"grad_norm": 0.26849291485435933,
|
| 770 |
+
"learning_rate": 6.829465584086203e-06,
|
| 771 |
+
"loss": 0.162,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5123428039124359,
|
| 776 |
+
"grad_norm": 0.27953178230154135,
|
| 777 |
+
"learning_rate": 6.7647926145399315e-06,
|
| 778 |
+
"loss": 0.1665,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5170004657661854,
|
| 783 |
+
"grad_norm": 0.27405454583485805,
|
| 784 |
+
"learning_rate": 6.70011964499366e-06,
|
| 785 |
+
"loss": 0.1694,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5216581276199348,
|
| 790 |
+
"grad_norm": 0.2740222190152269,
|
| 791 |
+
"learning_rate": 6.635446675447389e-06,
|
| 792 |
+
"loss": 0.1646,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5263157894736842,
|
| 797 |
+
"grad_norm": 0.7602170085587757,
|
| 798 |
+
"learning_rate": 6.570773705901118e-06,
|
| 799 |
+
"loss": 0.1657,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5309734513274337,
|
| 804 |
+
"grad_norm": 0.2584103943073394,
|
| 805 |
+
"learning_rate": 6.506100736354848e-06,
|
| 806 |
+
"loss": 0.1649,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5356311131811831,
|
| 811 |
+
"grad_norm": 0.26950477543591644,
|
| 812 |
+
"learning_rate": 6.441427766808577e-06,
|
| 813 |
+
"loss": 0.1708,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5402887750349324,
|
| 818 |
+
"grad_norm": 0.26072213478350703,
|
| 819 |
+
"learning_rate": 6.3767547972623065e-06,
|
| 820 |
+
"loss": 0.1607,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5449464368886818,
|
| 825 |
+
"grad_norm": 0.26461848812873434,
|
| 826 |
+
"learning_rate": 6.312081827716035e-06,
|
| 827 |
+
"loss": 0.1626,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5496040987424313,
|
| 832 |
+
"grad_norm": 0.27484753032372317,
|
| 833 |
+
"learning_rate": 6.247408858169764e-06,
|
| 834 |
+
"loss": 0.1662,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5542617605961807,
|
| 839 |
+
"grad_norm": 0.2669289751240214,
|
| 840 |
+
"learning_rate": 6.182735888623494e-06,
|
| 841 |
+
"loss": 0.166,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5589194224499301,
|
| 846 |
+
"grad_norm": 0.27747179721115395,
|
| 847 |
+
"learning_rate": 6.118062919077223e-06,
|
| 848 |
+
"loss": 0.167,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5635770843036796,
|
| 853 |
+
"grad_norm": 0.2800864127645871,
|
| 854 |
+
"learning_rate": 6.053389949530952e-06,
|
| 855 |
+
"loss": 0.16,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.568234746157429,
|
| 860 |
+
"grad_norm": 0.26632979430405584,
|
| 861 |
+
"learning_rate": 5.9887169799846815e-06,
|
| 862 |
+
"loss": 0.1619,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5728924080111784,
|
| 867 |
+
"grad_norm": 0.27009799635223,
|
| 868 |
+
"learning_rate": 5.92404401043841e-06,
|
| 869 |
+
"loss": 0.1619,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5775500698649279,
|
| 874 |
+
"grad_norm": 0.27774363917057693,
|
| 875 |
+
"learning_rate": 5.859371040892139e-06,
|
| 876 |
+
"loss": 0.1647,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5822077317186772,
|
| 881 |
+
"grad_norm": 0.2864615057196472,
|
| 882 |
+
"learning_rate": 5.794698071345868e-06,
|
| 883 |
+
"loss": 0.1625,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5868653935724266,
|
| 888 |
+
"grad_norm": 0.2650937325121556,
|
| 889 |
+
"learning_rate": 5.730025101799597e-06,
|
| 890 |
+
"loss": 0.1594,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5915230554261761,
|
| 895 |
+
"grad_norm": 0.2573833742516468,
|
| 896 |
+
"learning_rate": 5.665352132253327e-06,
|
| 897 |
+
"loss": 0.1605,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5961807172799255,
|
| 902 |
+
"grad_norm": 0.27315698290396995,
|
| 903 |
+
"learning_rate": 5.600679162707056e-06,
|
| 904 |
+
"loss": 0.1597,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6008383791336749,
|
| 909 |
+
"grad_norm": 0.26423497853342065,
|
| 910 |
+
"learning_rate": 5.536006193160785e-06,
|
| 911 |
+
"loss": 0.1614,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6054960409874243,
|
| 916 |
+
"grad_norm": 0.2608815901503087,
|
| 917 |
+
"learning_rate": 5.471333223614514e-06,
|
| 918 |
+
"loss": 0.1739,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6101537028411738,
|
| 923 |
+
"grad_norm": 0.26783123486538235,
|
| 924 |
+
"learning_rate": 5.406660254068243e-06,
|
| 925 |
+
"loss": 0.1643,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6148113646949231,
|
| 930 |
+
"grad_norm": 0.26730705557977275,
|
| 931 |
+
"learning_rate": 5.341987284521973e-06,
|
| 932 |
+
"loss": 0.1622,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6194690265486725,
|
| 937 |
+
"grad_norm": 0.2622414321812453,
|
| 938 |
+
"learning_rate": 5.277314314975702e-06,
|
| 939 |
+
"loss": 0.167,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.624126688402422,
|
| 944 |
+
"grad_norm": 0.2633976167684346,
|
| 945 |
+
"learning_rate": 5.212641345429431e-06,
|
| 946 |
+
"loss": 0.1598,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6287843502561714,
|
| 951 |
+
"grad_norm": 0.2684202062052881,
|
| 952 |
+
"learning_rate": 5.1479683758831604e-06,
|
| 953 |
+
"loss": 0.1609,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6334420121099208,
|
| 958 |
+
"grad_norm": 0.2627809723242797,
|
| 959 |
+
"learning_rate": 5.083295406336889e-06,
|
| 960 |
+
"loss": 0.1603,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6380996739636703,
|
| 965 |
+
"grad_norm": 0.265704976643566,
|
| 966 |
+
"learning_rate": 5.018622436790618e-06,
|
| 967 |
+
"loss": 0.1607,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6427573358174197,
|
| 972 |
+
"grad_norm": 0.27967934379491166,
|
| 973 |
+
"learning_rate": 4.953949467244347e-06,
|
| 974 |
+
"loss": 0.1656,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6474149976711691,
|
| 979 |
+
"grad_norm": 0.25929536968534295,
|
| 980 |
+
"learning_rate": 4.889276497698076e-06,
|
| 981 |
+
"loss": 0.1594,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6520726595249184,
|
| 986 |
+
"grad_norm": 0.25425814337951297,
|
| 987 |
+
"learning_rate": 4.824603528151806e-06,
|
| 988 |
+
"loss": 0.16,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6567303213786679,
|
| 993 |
+
"grad_norm": 0.2605141313456326,
|
| 994 |
+
"learning_rate": 4.759930558605535e-06,
|
| 995 |
+
"loss": 0.1591,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6613879832324173,
|
| 1000 |
+
"grad_norm": 0.2628498648021744,
|
| 1001 |
+
"learning_rate": 4.695257589059264e-06,
|
| 1002 |
+
"loss": 0.1611,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6660456450861667,
|
| 1007 |
+
"grad_norm": 0.2656348432308299,
|
| 1008 |
+
"learning_rate": 4.630584619512993e-06,
|
| 1009 |
+
"loss": 0.1587,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6707033069399162,
|
| 1014 |
+
"grad_norm": 0.25679778603479775,
|
| 1015 |
+
"learning_rate": 4.565911649966722e-06,
|
| 1016 |
+
"loss": 0.1567,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6753609687936656,
|
| 1021 |
+
"grad_norm": 0.26349404998781073,
|
| 1022 |
+
"learning_rate": 4.501238680420452e-06,
|
| 1023 |
+
"loss": 0.1589,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.680018630647415,
|
| 1028 |
+
"grad_norm": 0.26604359602122024,
|
| 1029 |
+
"learning_rate": 4.436565710874181e-06,
|
| 1030 |
+
"loss": 0.1629,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6846762925011645,
|
| 1035 |
+
"grad_norm": 0.2624098613004824,
|
| 1036 |
+
"learning_rate": 4.37189274132791e-06,
|
| 1037 |
+
"loss": 0.1576,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6893339543549138,
|
| 1042 |
+
"grad_norm": 0.26284959161244814,
|
| 1043 |
+
"learning_rate": 4.307219771781639e-06,
|
| 1044 |
+
"loss": 0.155,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6939916162086632,
|
| 1049 |
+
"grad_norm": 0.27480457215357684,
|
| 1050 |
+
"learning_rate": 4.242546802235368e-06,
|
| 1051 |
+
"loss": 0.1611,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6986492780624126,
|
| 1056 |
+
"grad_norm": 0.27235238478589757,
|
| 1057 |
+
"learning_rate": 4.177873832689098e-06,
|
| 1058 |
+
"loss": 0.1599,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7033069399161621,
|
| 1063 |
+
"grad_norm": 0.24606327627056684,
|
| 1064 |
+
"learning_rate": 4.113200863142826e-06,
|
| 1065 |
+
"loss": 0.1566,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7079646017699115,
|
| 1070 |
+
"grad_norm": 0.26325977339404516,
|
| 1071 |
+
"learning_rate": 4.048527893596555e-06,
|
| 1072 |
+
"loss": 0.1573,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7126222636236609,
|
| 1077 |
+
"grad_norm": 0.2590300604219625,
|
| 1078 |
+
"learning_rate": 3.983854924050285e-06,
|
| 1079 |
+
"loss": 0.1595,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7172799254774104,
|
| 1084 |
+
"grad_norm": 0.2703508293105258,
|
| 1085 |
+
"learning_rate": 3.9191819545040135e-06,
|
| 1086 |
+
"loss": 0.1598,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7219375873311598,
|
| 1091 |
+
"grad_norm": 0.26534307979517235,
|
| 1092 |
+
"learning_rate": 3.854508984957743e-06,
|
| 1093 |
+
"loss": 0.1556,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7265952491849091,
|
| 1098 |
+
"grad_norm": 0.2684730237636614,
|
| 1099 |
+
"learning_rate": 3.789836015411472e-06,
|
| 1100 |
+
"loss": 0.1576,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7312529110386586,
|
| 1105 |
+
"grad_norm": 0.2650435640388583,
|
| 1106 |
+
"learning_rate": 3.725163045865201e-06,
|
| 1107 |
+
"loss": 0.1571,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.735910572892408,
|
| 1112 |
+
"grad_norm": 0.2522376688312189,
|
| 1113 |
+
"learning_rate": 3.6604900763189307e-06,
|
| 1114 |
+
"loss": 0.1593,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7405682347461574,
|
| 1119 |
+
"grad_norm": 0.2506150698960538,
|
| 1120 |
+
"learning_rate": 3.5958171067726596e-06,
|
| 1121 |
+
"loss": 0.1553,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7452258965999069,
|
| 1126 |
+
"grad_norm": 0.2594538863035446,
|
| 1127 |
+
"learning_rate": 3.5311441372263885e-06,
|
| 1128 |
+
"loss": 0.1569,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7498835584536563,
|
| 1133 |
+
"grad_norm": 0.25558612322504,
|
| 1134 |
+
"learning_rate": 3.4664711676801178e-06,
|
| 1135 |
+
"loss": 0.1585,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7545412203074057,
|
| 1140 |
+
"grad_norm": 0.26102886268856207,
|
| 1141 |
+
"learning_rate": 3.4017981981338467e-06,
|
| 1142 |
+
"loss": 0.1561,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.759198882161155,
|
| 1147 |
+
"grad_norm": 0.26907436310026045,
|
| 1148 |
+
"learning_rate": 3.337125228587576e-06,
|
| 1149 |
+
"loss": 0.1555,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7638565440149045,
|
| 1154 |
+
"grad_norm": 0.259769426429665,
|
| 1155 |
+
"learning_rate": 3.2724522590413053e-06,
|
| 1156 |
+
"loss": 0.157,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7685142058686539,
|
| 1161 |
+
"grad_norm": 0.25217961471316624,
|
| 1162 |
+
"learning_rate": 3.2077792894950346e-06,
|
| 1163 |
+
"loss": 0.1534,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7731718677224033,
|
| 1168 |
+
"grad_norm": 0.2506397155433677,
|
| 1169 |
+
"learning_rate": 3.1431063199487635e-06,
|
| 1170 |
+
"loss": 0.1549,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7778295295761528,
|
| 1175 |
+
"grad_norm": 0.26415761643041025,
|
| 1176 |
+
"learning_rate": 3.0784333504024924e-06,
|
| 1177 |
+
"loss": 0.1592,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7824871914299022,
|
| 1182 |
+
"grad_norm": 0.26004483777453874,
|
| 1183 |
+
"learning_rate": 3.0137603808562217e-06,
|
| 1184 |
+
"loss": 0.1567,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7871448532836516,
|
| 1189 |
+
"grad_norm": 0.25821787817947156,
|
| 1190 |
+
"learning_rate": 2.949087411309951e-06,
|
| 1191 |
+
"loss": 0.157,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7918025151374011,
|
| 1196 |
+
"grad_norm": 0.25779306478346414,
|
| 1197 |
+
"learning_rate": 2.8844144417636803e-06,
|
| 1198 |
+
"loss": 0.1564,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7964601769911505,
|
| 1203 |
+
"grad_norm": 0.25714243733812403,
|
| 1204 |
+
"learning_rate": 2.819741472217409e-06,
|
| 1205 |
+
"loss": 0.1583,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8011178388448998,
|
| 1210 |
+
"grad_norm": 0.2626304563600335,
|
| 1211 |
+
"learning_rate": 2.7550685026711385e-06,
|
| 1212 |
+
"loss": 0.1542,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8057755006986492,
|
| 1217 |
+
"grad_norm": 0.2507263040233167,
|
| 1218 |
+
"learning_rate": 2.690395533124868e-06,
|
| 1219 |
+
"loss": 0.1563,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8104331625523987,
|
| 1224 |
+
"grad_norm": 0.27022602376135396,
|
| 1225 |
+
"learning_rate": 2.6257225635785967e-06,
|
| 1226 |
+
"loss": 0.1587,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8150908244061481,
|
| 1231 |
+
"grad_norm": 0.2510911400803603,
|
| 1232 |
+
"learning_rate": 2.5610495940323256e-06,
|
| 1233 |
+
"loss": 0.1576,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8197484862598975,
|
| 1238 |
+
"grad_norm": 0.25251347824676273,
|
| 1239 |
+
"learning_rate": 2.496376624486055e-06,
|
| 1240 |
+
"loss": 0.1544,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.824406148113647,
|
| 1245 |
+
"grad_norm": 0.2562650636887177,
|
| 1246 |
+
"learning_rate": 2.431703654939784e-06,
|
| 1247 |
+
"loss": 0.1536,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8290638099673964,
|
| 1252 |
+
"grad_norm": 0.2528102819764459,
|
| 1253 |
+
"learning_rate": 2.3670306853935135e-06,
|
| 1254 |
+
"loss": 0.1548,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8337214718211458,
|
| 1259 |
+
"grad_norm": 0.2546638497156449,
|
| 1260 |
+
"learning_rate": 2.3023577158472424e-06,
|
| 1261 |
+
"loss": 0.1559,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8383791336748952,
|
| 1266 |
+
"grad_norm": 0.25597040826829004,
|
| 1267 |
+
"learning_rate": 2.2376847463009717e-06,
|
| 1268 |
+
"loss": 0.1553,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8430367955286446,
|
| 1273 |
+
"grad_norm": 0.2586436071509003,
|
| 1274 |
+
"learning_rate": 2.1730117767547006e-06,
|
| 1275 |
+
"loss": 0.1545,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.847694457382394,
|
| 1280 |
+
"grad_norm": 0.25860599198589496,
|
| 1281 |
+
"learning_rate": 2.10833880720843e-06,
|
| 1282 |
+
"loss": 0.1565,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8523521192361434,
|
| 1287 |
+
"grad_norm": 0.26192165555009833,
|
| 1288 |
+
"learning_rate": 2.043665837662159e-06,
|
| 1289 |
+
"loss": 0.1558,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8570097810898929,
|
| 1294 |
+
"grad_norm": 0.26820769391663646,
|
| 1295 |
+
"learning_rate": 1.978992868115888e-06,
|
| 1296 |
+
"loss": 0.1565,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8616674429436423,
|
| 1301 |
+
"grad_norm": 0.25587730713784773,
|
| 1302 |
+
"learning_rate": 1.9143198985696174e-06,
|
| 1303 |
+
"loss": 0.1572,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8663251047973917,
|
| 1308 |
+
"grad_norm": 0.26772485282945807,
|
| 1309 |
+
"learning_rate": 1.8496469290233465e-06,
|
| 1310 |
+
"loss": 0.1625,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8709827666511412,
|
| 1315 |
+
"grad_norm": 0.25858623580730566,
|
| 1316 |
+
"learning_rate": 1.7849739594770758e-06,
|
| 1317 |
+
"loss": 0.1556,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8756404285048905,
|
| 1322 |
+
"grad_norm": 0.25843957782716953,
|
| 1323 |
+
"learning_rate": 1.7203009899308049e-06,
|
| 1324 |
+
"loss": 0.154,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.8802980903586399,
|
| 1329 |
+
"grad_norm": 0.2645639546093885,
|
| 1330 |
+
"learning_rate": 1.6556280203845338e-06,
|
| 1331 |
+
"loss": 0.1529,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8849557522123894,
|
| 1336 |
+
"grad_norm": 0.2514079549647452,
|
| 1337 |
+
"learning_rate": 1.590955050838263e-06,
|
| 1338 |
+
"loss": 0.1524,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8896134140661388,
|
| 1343 |
+
"grad_norm": 0.25913877416372477,
|
| 1344 |
+
"learning_rate": 1.5262820812919922e-06,
|
| 1345 |
+
"loss": 0.1586,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8942710759198882,
|
| 1350 |
+
"grad_norm": 0.2565695678520263,
|
| 1351 |
+
"learning_rate": 1.4616091117457213e-06,
|
| 1352 |
+
"loss": 0.1561,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8989287377736377,
|
| 1357 |
+
"grad_norm": 0.25666882042964145,
|
| 1358 |
+
"learning_rate": 1.3969361421994504e-06,
|
| 1359 |
+
"loss": 0.1561,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9035863996273871,
|
| 1364 |
+
"grad_norm": 0.26241147095236395,
|
| 1365 |
+
"learning_rate": 1.3322631726531797e-06,
|
| 1366 |
+
"loss": 0.1577,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9082440614811365,
|
| 1371 |
+
"grad_norm": 0.25174282512219825,
|
| 1372 |
+
"learning_rate": 1.2675902031069086e-06,
|
| 1373 |
+
"loss": 0.1531,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9129017233348858,
|
| 1378 |
+
"grad_norm": 0.2579214155785866,
|
| 1379 |
+
"learning_rate": 1.2029172335606379e-06,
|
| 1380 |
+
"loss": 0.1552,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9175593851886353,
|
| 1385 |
+
"grad_norm": 0.2553091002401554,
|
| 1386 |
+
"learning_rate": 1.1382442640143672e-06,
|
| 1387 |
+
"loss": 0.1578,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9222170470423847,
|
| 1392 |
+
"grad_norm": 0.2472887184008492,
|
| 1393 |
+
"learning_rate": 1.073571294468096e-06,
|
| 1394 |
+
"loss": 0.1482,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9268747088961341,
|
| 1399 |
+
"grad_norm": 0.25694988864619567,
|
| 1400 |
+
"learning_rate": 1.0088983249218254e-06,
|
| 1401 |
+
"loss": 0.1537,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9315323707498836,
|
| 1406 |
+
"grad_norm": 0.2506144298658388,
|
| 1407 |
+
"learning_rate": 9.442253553755545e-07,
|
| 1408 |
+
"loss": 0.1566,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.936190032603633,
|
| 1413 |
+
"grad_norm": 0.2588881249955873,
|
| 1414 |
+
"learning_rate": 8.795523858292837e-07,
|
| 1415 |
+
"loss": 0.1547,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9408476944573824,
|
| 1420 |
+
"grad_norm": 0.2513845239249848,
|
| 1421 |
+
"learning_rate": 8.148794162830128e-07,
|
| 1422 |
+
"loss": 0.1522,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9455053563111319,
|
| 1427 |
+
"grad_norm": 0.24592664210897303,
|
| 1428 |
+
"learning_rate": 7.50206446736742e-07,
|
| 1429 |
+
"loss": 0.1504,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9501630181648812,
|
| 1434 |
+
"grad_norm": 0.25799243946965783,
|
| 1435 |
+
"learning_rate": 6.855334771904711e-07,
|
| 1436 |
+
"loss": 0.1531,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9548206800186306,
|
| 1441 |
+
"grad_norm": 0.2579844822252104,
|
| 1442 |
+
"learning_rate": 6.208605076442003e-07,
|
| 1443 |
+
"loss": 0.1516,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.95947834187238,
|
| 1448 |
+
"grad_norm": 0.25155633116394316,
|
| 1449 |
+
"learning_rate": 5.561875380979294e-07,
|
| 1450 |
+
"loss": 0.1496,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9641360037261295,
|
| 1455 |
+
"grad_norm": 0.2576362696416594,
|
| 1456 |
+
"learning_rate": 4.915145685516585e-07,
|
| 1457 |
+
"loss": 0.1534,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9687936655798789,
|
| 1462 |
+
"grad_norm": 0.25856541740340644,
|
| 1463 |
+
"learning_rate": 4.2684159900538766e-07,
|
| 1464 |
+
"loss": 0.1562,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9734513274336283,
|
| 1469 |
+
"grad_norm": 0.25196518536807605,
|
| 1470 |
+
"learning_rate": 3.6216862945911676e-07,
|
| 1471 |
+
"loss": 0.154,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9781089892873778,
|
| 1476 |
+
"grad_norm": 0.25200197047153655,
|
| 1477 |
+
"learning_rate": 2.974956599128459e-07,
|
| 1478 |
+
"loss": 0.1566,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9827666511411272,
|
| 1483 |
+
"grad_norm": 0.2571549198839855,
|
| 1484 |
+
"learning_rate": 2.3282269036657506e-07,
|
| 1485 |
+
"loss": 0.1545,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9874243129948765,
|
| 1490 |
+
"grad_norm": 0.2692221532676563,
|
| 1491 |
+
"learning_rate": 1.6814972082030424e-07,
|
| 1492 |
+
"loss": 0.1568,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.992081974848626,
|
| 1497 |
+
"grad_norm": 0.25769138678170556,
|
| 1498 |
+
"learning_rate": 1.0347675127403336e-07,
|
| 1499 |
+
"loss": 0.1509,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9967396367023754,
|
| 1504 |
+
"grad_norm": 0.4528420569939411,
|
| 1505 |
+
"learning_rate": 3.880378172776252e-08,
|
| 1506 |
+
"loss": 0.1539,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.999534233814625,
|
| 1511 |
+
"step": 1073,
|
| 1512 |
+
"total_flos": 9.192833840127672e+17,
|
| 1513 |
+
"train_loss": 0.17092923446448186,
|
| 1514 |
+
"train_runtime": 41238.1916,
|
| 1515 |
+
"train_samples_per_second": 0.416,
|
| 1516 |
+
"train_steps_per_second": 0.026
|
| 1517 |
+
}
|
| 1518 |
+
],
|
| 1519 |
+
"logging_steps": 5,
|
| 1520 |
+
"max_steps": 1073,
|
| 1521 |
+
"num_input_tokens_seen": 0,
|
| 1522 |
+
"num_train_epochs": 1,
|
| 1523 |
+
"save_steps": 500,
|
| 1524 |
+
"stateful_callbacks": {
|
| 1525 |
+
"TrainerControl": {
|
| 1526 |
+
"args": {
|
| 1527 |
+
"should_epoch_stop": false,
|
| 1528 |
+
"should_evaluate": false,
|
| 1529 |
+
"should_log": false,
|
| 1530 |
+
"should_save": true,
|
| 1531 |
+
"should_training_stop": true
|
| 1532 |
+
},
|
| 1533 |
+
"attributes": {}
|
| 1534 |
+
}
|
| 1535 |
+
},
|
| 1536 |
+
"total_flos": 9.192833840127672e+17,
|
| 1537 |
+
"train_batch_size": 1,
|
| 1538 |
+
"trial_name": null,
|
| 1539 |
+
"trial_params": null
|
| 1540 |
+
}
|