Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +12 -0
- train_results.json +8 -0
- trainer_state.json +2114 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-5-no-sys
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-5-no-sys
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-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="weizhepei/Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-5-no-sys", 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/uva-llm/huggingface/runs/vditl2it)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.4.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 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": 605863668678656.0,
|
| 3 |
+
"train_loss": 0.36788542065266017,
|
| 4 |
+
"train_runtime": 21782.9524,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 2.171,
|
| 7 |
+
"train_steps_per_second": 0.068
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.49.0"
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 605863668678656.0,
|
| 3 |
+
"train_loss": 0.36788542065266017,
|
| 4 |
+
"train_runtime": 21782.9524,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 2.171,
|
| 7 |
+
"train_steps_per_second": 0.068
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1480,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016891891891891893,
|
| 13 |
+
"grad_norm": 6.5734802912605454,
|
| 14 |
+
"learning_rate": 3.3783783783783788e-06,
|
| 15 |
+
"loss": 1.3273,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.033783783783783786,
|
| 20 |
+
"grad_norm": 6.1632920104999585,
|
| 21 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 22 |
+
"loss": 1.184,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05067567567567568,
|
| 27 |
+
"grad_norm": 3.9191468793106843,
|
| 28 |
+
"learning_rate": 1.0135135135135136e-05,
|
| 29 |
+
"loss": 1.0141,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06756756756756757,
|
| 34 |
+
"grad_norm": 6.836338097725109,
|
| 35 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 36 |
+
"loss": 0.9461,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08445945945945946,
|
| 41 |
+
"grad_norm": 6.14454491803722,
|
| 42 |
+
"learning_rate": 1.6891891891891892e-05,
|
| 43 |
+
"loss": 0.9414,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10135135135135136,
|
| 48 |
+
"grad_norm": 3.011838488661273,
|
| 49 |
+
"learning_rate": 2.0270270270270273e-05,
|
| 50 |
+
"loss": 0.9043,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11824324324324324,
|
| 55 |
+
"grad_norm": 3.080629137119366,
|
| 56 |
+
"learning_rate": 2.364864864864865e-05,
|
| 57 |
+
"loss": 0.9097,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13513513513513514,
|
| 62 |
+
"grad_norm": 2.8246920844764523,
|
| 63 |
+
"learning_rate": 2.702702702702703e-05,
|
| 64 |
+
"loss": 0.9112,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15202702702702703,
|
| 69 |
+
"grad_norm": 2.8003645624320987,
|
| 70 |
+
"learning_rate": 3.0405405405405407e-05,
|
| 71 |
+
"loss": 0.9513,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16891891891891891,
|
| 76 |
+
"grad_norm": 2.6192832071723293,
|
| 77 |
+
"learning_rate": 3.3783783783783784e-05,
|
| 78 |
+
"loss": 0.9393,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1858108108108108,
|
| 83 |
+
"grad_norm": 2.6347662580290607,
|
| 84 |
+
"learning_rate": 3.7162162162162165e-05,
|
| 85 |
+
"loss": 0.9217,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.20270270270270271,
|
| 90 |
+
"grad_norm": 2.6944921391744545,
|
| 91 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 92 |
+
"loss": 0.9496,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2195945945945946,
|
| 97 |
+
"grad_norm": 2.423675002168339,
|
| 98 |
+
"learning_rate": 4.391891891891892e-05,
|
| 99 |
+
"loss": 0.9423,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23648648648648649,
|
| 104 |
+
"grad_norm": 2.6803364488285326,
|
| 105 |
+
"learning_rate": 4.72972972972973e-05,
|
| 106 |
+
"loss": 0.9677,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2533783783783784,
|
| 111 |
+
"grad_norm": 2.2781274624283685,
|
| 112 |
+
"learning_rate": 4.999994383297182e-05,
|
| 113 |
+
"loss": 0.966,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2702702702702703,
|
| 118 |
+
"grad_norm": 2.4018446311363544,
|
| 119 |
+
"learning_rate": 4.9997978016429605e-05,
|
| 120 |
+
"loss": 0.9715,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.28716216216216217,
|
| 125 |
+
"grad_norm": 2.3728527784166036,
|
| 126 |
+
"learning_rate": 4.9993204128893056e-05,
|
| 127 |
+
"loss": 0.977,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.30405405405405406,
|
| 132 |
+
"grad_norm": 2.047106826030879,
|
| 133 |
+
"learning_rate": 4.9985622766211935e-05,
|
| 134 |
+
"loss": 0.9353,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32094594594594594,
|
| 139 |
+
"grad_norm": 2.1267608330495125,
|
| 140 |
+
"learning_rate": 4.997523487464928e-05,
|
| 141 |
+
"loss": 0.9432,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33783783783783783,
|
| 146 |
+
"grad_norm": 2.1225078532563537,
|
| 147 |
+
"learning_rate": 4.996204175076325e-05,
|
| 148 |
+
"loss": 0.9651,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3547297297297297,
|
| 153 |
+
"grad_norm": 2.0337324708472906,
|
| 154 |
+
"learning_rate": 4.99460450412453e-05,
|
| 155 |
+
"loss": 0.9648,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3716216216216216,
|
| 160 |
+
"grad_norm": 1.916581074879566,
|
| 161 |
+
"learning_rate": 4.99272467427147e-05,
|
| 162 |
+
"loss": 0.9675,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3885135135135135,
|
| 167 |
+
"grad_norm": 2.121919880463027,
|
| 168 |
+
"learning_rate": 4.990564920146926e-05,
|
| 169 |
+
"loss": 0.9856,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.40540540540540543,
|
| 174 |
+
"grad_norm": 2.214799458005234,
|
| 175 |
+
"learning_rate": 4.9881255113192526e-05,
|
| 176 |
+
"loss": 0.929,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4222972972972973,
|
| 181 |
+
"grad_norm": 2.163453291125734,
|
| 182 |
+
"learning_rate": 4.985406752261731e-05,
|
| 183 |
+
"loss": 0.9473,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4391891891891892,
|
| 188 |
+
"grad_norm": 1.9198145369029436,
|
| 189 |
+
"learning_rate": 4.982408982314565e-05,
|
| 190 |
+
"loss": 0.9678,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4560810810810811,
|
| 195 |
+
"grad_norm": 2.0248877076532077,
|
| 196 |
+
"learning_rate": 4.9791325756425264e-05,
|
| 197 |
+
"loss": 0.9328,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.47297297297297297,
|
| 202 |
+
"grad_norm": 1.807231483694689,
|
| 203 |
+
"learning_rate": 4.975577941188258e-05,
|
| 204 |
+
"loss": 0.9373,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.48986486486486486,
|
| 209 |
+
"grad_norm": 1.8706434071195257,
|
| 210 |
+
"learning_rate": 4.971745522621225e-05,
|
| 211 |
+
"loss": 0.9626,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5067567567567568,
|
| 216 |
+
"grad_norm": 1.7945270289752226,
|
| 217 |
+
"learning_rate": 4.967635798282344e-05,
|
| 218 |
+
"loss": 0.9705,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5236486486486487,
|
| 223 |
+
"grad_norm": 1.8616405046783886,
|
| 224 |
+
"learning_rate": 4.963249281124278e-05,
|
| 225 |
+
"loss": 0.9072,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5405405405405406,
|
| 230 |
+
"grad_norm": 1.666683134269227,
|
| 231 |
+
"learning_rate": 4.958586518647407e-05,
|
| 232 |
+
"loss": 0.898,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5574324324324325,
|
| 237 |
+
"grad_norm": 1.594107803207033,
|
| 238 |
+
"learning_rate": 4.953648092831505e-05,
|
| 239 |
+
"loss": 0.9251,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5743243243243243,
|
| 244 |
+
"grad_norm": 1.8741745620159964,
|
| 245 |
+
"learning_rate": 4.9484346200630855e-05,
|
| 246 |
+
"loss": 0.9687,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5912162162162162,
|
| 251 |
+
"grad_norm": 1.905205634059141,
|
| 252 |
+
"learning_rate": 4.9429467510584794e-05,
|
| 253 |
+
"loss": 0.8999,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6081081081081081,
|
| 258 |
+
"grad_norm": 1.9962261429841193,
|
| 259 |
+
"learning_rate": 4.937185170782607e-05,
|
| 260 |
+
"loss": 0.9368,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.625,
|
| 265 |
+
"grad_norm": 2.1664869693090165,
|
| 266 |
+
"learning_rate": 4.931150598363494e-05,
|
| 267 |
+
"loss": 0.9061,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6418918918918919,
|
| 272 |
+
"grad_norm": 1.6870468109861425,
|
| 273 |
+
"learning_rate": 4.9248437870025035e-05,
|
| 274 |
+
"loss": 0.8989,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6587837837837838,
|
| 279 |
+
"grad_norm": 1.6966567361912948,
|
| 280 |
+
"learning_rate": 4.9182655238803365e-05,
|
| 281 |
+
"loss": 0.8989,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6756756756756757,
|
| 286 |
+
"grad_norm": 1.692847679116018,
|
| 287 |
+
"learning_rate": 4.911416630058772e-05,
|
| 288 |
+
"loss": 0.8889,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6925675675675675,
|
| 293 |
+
"grad_norm": 1.666285584632242,
|
| 294 |
+
"learning_rate": 4.9042979603781884e-05,
|
| 295 |
+
"loss": 0.9038,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7094594594594594,
|
| 300 |
+
"grad_norm": 1.7022768095416743,
|
| 301 |
+
"learning_rate": 4.896910403350873e-05,
|
| 302 |
+
"loss": 0.9247,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7263513513513513,
|
| 307 |
+
"grad_norm": 1.6583467639807945,
|
| 308 |
+
"learning_rate": 4.8892548810501146e-05,
|
| 309 |
+
"loss": 0.9042,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7432432432432432,
|
| 314 |
+
"grad_norm": 1.5684890837209118,
|
| 315 |
+
"learning_rate": 4.88133234899512e-05,
|
| 316 |
+
"loss": 0.8875,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7601351351351351,
|
| 321 |
+
"grad_norm": 1.7067630214310312,
|
| 322 |
+
"learning_rate": 4.873143796031752e-05,
|
| 323 |
+
"loss": 0.8797,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.777027027027027,
|
| 328 |
+
"grad_norm": 1.5501274222949621,
|
| 329 |
+
"learning_rate": 4.864690244209105e-05,
|
| 330 |
+
"loss": 0.8903,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.793918918918919,
|
| 335 |
+
"grad_norm": 1.6739236540233466,
|
| 336 |
+
"learning_rate": 4.855972748651939e-05,
|
| 337 |
+
"loss": 0.9036,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8108108108108109,
|
| 342 |
+
"grad_norm": 1.5251028899529802,
|
| 343 |
+
"learning_rate": 4.8469923974289874e-05,
|
| 344 |
+
"loss": 0.876,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8277027027027027,
|
| 349 |
+
"grad_norm": 1.6416347283581953,
|
| 350 |
+
"learning_rate": 4.837750311417146e-05,
|
| 351 |
+
"loss": 0.8777,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8445945945945946,
|
| 356 |
+
"grad_norm": 1.7148770313619208,
|
| 357 |
+
"learning_rate": 4.828247644161577e-05,
|
| 358 |
+
"loss": 0.9305,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8614864864864865,
|
| 363 |
+
"grad_norm": 1.6917833006591425,
|
| 364 |
+
"learning_rate": 4.8184855817317226e-05,
|
| 365 |
+
"loss": 0.8902,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8783783783783784,
|
| 370 |
+
"grad_norm": 1.4551269904823192,
|
| 371 |
+
"learning_rate": 4.808465342573274e-05,
|
| 372 |
+
"loss": 0.866,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8952702702702703,
|
| 377 |
+
"grad_norm": 1.6585601416449522,
|
| 378 |
+
"learning_rate": 4.7981881773560886e-05,
|
| 379 |
+
"loss": 0.896,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9121621621621622,
|
| 384 |
+
"grad_norm": 1.5413455024296299,
|
| 385 |
+
"learning_rate": 4.787655368818087e-05,
|
| 386 |
+
"loss": 0.8684,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9290540540540541,
|
| 391 |
+
"grad_norm": 1.4770164865772377,
|
| 392 |
+
"learning_rate": 4.77686823160515e-05,
|
| 393 |
+
"loss": 0.8704,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9459459459459459,
|
| 398 |
+
"grad_norm": 1.642857550796514,
|
| 399 |
+
"learning_rate": 4.765828112107034e-05,
|
| 400 |
+
"loss": 0.8749,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9628378378378378,
|
| 405 |
+
"grad_norm": 2.028272824380857,
|
| 406 |
+
"learning_rate": 4.75453638828932e-05,
|
| 407 |
+
"loss": 0.8654,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9797297297297297,
|
| 412 |
+
"grad_norm": 1.4679639397479571,
|
| 413 |
+
"learning_rate": 4.742994469521421e-05,
|
| 414 |
+
"loss": 0.8601,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9966216216216216,
|
| 419 |
+
"grad_norm": 1.4327374675646831,
|
| 420 |
+
"learning_rate": 4.7312037964006806e-05,
|
| 421 |
+
"loss": 0.8564,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.0135135135135136,
|
| 426 |
+
"grad_norm": 1.6103445933566929,
|
| 427 |
+
"learning_rate": 4.719165840572557e-05,
|
| 428 |
+
"loss": 0.6356,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.0304054054054055,
|
| 433 |
+
"grad_norm": 1.2609614774524984,
|
| 434 |
+
"learning_rate": 4.7068821045469464e-05,
|
| 435 |
+
"loss": 0.5569,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0472972972972974,
|
| 440 |
+
"grad_norm": 1.6175496296524783,
|
| 441 |
+
"learning_rate": 4.694354121510644e-05,
|
| 442 |
+
"loss": 0.5491,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0641891891891893,
|
| 447 |
+
"grad_norm": 1.426861182551709,
|
| 448 |
+
"learning_rate": 4.681583455135985e-05,
|
| 449 |
+
"loss": 0.5354,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0810810810810811,
|
| 454 |
+
"grad_norm": 1.3646672710235592,
|
| 455 |
+
"learning_rate": 4.668571699385668e-05,
|
| 456 |
+
"loss": 0.5427,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.097972972972973,
|
| 461 |
+
"grad_norm": 1.5346272239009828,
|
| 462 |
+
"learning_rate": 4.655320478313817e-05,
|
| 463 |
+
"loss": 0.5359,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.114864864864865,
|
| 468 |
+
"grad_norm": 1.3759835475947566,
|
| 469 |
+
"learning_rate": 4.641831445863265e-05,
|
| 470 |
+
"loss": 0.5638,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.1317567567567568,
|
| 475 |
+
"grad_norm": 1.4909239756270425,
|
| 476 |
+
"learning_rate": 4.628106285659124e-05,
|
| 477 |
+
"loss": 0.5741,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.1486486486486487,
|
| 482 |
+
"grad_norm": 1.7461008672361147,
|
| 483 |
+
"learning_rate": 4.614146710798645e-05,
|
| 484 |
+
"loss": 0.5461,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.1655405405405406,
|
| 489 |
+
"grad_norm": 1.5678203614090302,
|
| 490 |
+
"learning_rate": 4.599954463637394e-05,
|
| 491 |
+
"loss": 0.5898,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1824324324324325,
|
| 496 |
+
"grad_norm": 1.3911715983555075,
|
| 497 |
+
"learning_rate": 4.585531315571788e-05,
|
| 498 |
+
"loss": 0.5478,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1993243243243243,
|
| 503 |
+
"grad_norm": 1.521721643927216,
|
| 504 |
+
"learning_rate": 4.570879066817991e-05,
|
| 505 |
+
"loss": 0.5528,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.2162162162162162,
|
| 510 |
+
"grad_norm": 1.4667462390466979,
|
| 511 |
+
"learning_rate": 4.555999546187229e-05,
|
| 512 |
+
"loss": 0.5754,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.2331081081081081,
|
| 517 |
+
"grad_norm": 1.5550072973306515,
|
| 518 |
+
"learning_rate": 4.5408946108575215e-05,
|
| 519 |
+
"loss": 0.5708,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.25,
|
| 524 |
+
"grad_norm": 1.3431454538729617,
|
| 525 |
+
"learning_rate": 4.5255661461418854e-05,
|
| 526 |
+
"loss": 0.5577,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2668918918918919,
|
| 531 |
+
"grad_norm": 1.4814401713234768,
|
| 532 |
+
"learning_rate": 4.510016065253016e-05,
|
| 533 |
+
"loss": 0.5643,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2837837837837838,
|
| 538 |
+
"grad_norm": 1.3784794077594908,
|
| 539 |
+
"learning_rate": 4.4942463090644896e-05,
|
| 540 |
+
"loss": 0.5925,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.3006756756756757,
|
| 545 |
+
"grad_norm": 1.3720445672478283,
|
| 546 |
+
"learning_rate": 4.478258845868522e-05,
|
| 547 |
+
"loss": 0.5807,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.3175675675675675,
|
| 552 |
+
"grad_norm": 1.4533572289367873,
|
| 553 |
+
"learning_rate": 4.462055671130289e-05,
|
| 554 |
+
"loss": 0.5796,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.3344594594594594,
|
| 559 |
+
"grad_norm": 1.5146363381910304,
|
| 560 |
+
"learning_rate": 4.445638807238865e-05,
|
| 561 |
+
"loss": 0.5804,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.3513513513513513,
|
| 566 |
+
"grad_norm": 1.5458264427252129,
|
| 567 |
+
"learning_rate": 4.4290103032548094e-05,
|
| 568 |
+
"loss": 0.5722,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.3682432432432432,
|
| 573 |
+
"grad_norm": 1.3173722679798987,
|
| 574 |
+
"learning_rate": 4.412172234654399e-05,
|
| 575 |
+
"loss": 0.5531,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.385135135135135,
|
| 580 |
+
"grad_norm": 1.4883033189800094,
|
| 581 |
+
"learning_rate": 4.395126703070589e-05,
|
| 582 |
+
"loss": 0.5577,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.402027027027027,
|
| 587 |
+
"grad_norm": 1.3909336605285059,
|
| 588 |
+
"learning_rate": 4.3778758360306986e-05,
|
| 589 |
+
"loss": 0.578,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.4189189189189189,
|
| 594 |
+
"grad_norm": 1.3005774948488031,
|
| 595 |
+
"learning_rate": 4.360421786690862e-05,
|
| 596 |
+
"loss": 0.5583,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.4358108108108107,
|
| 601 |
+
"grad_norm": 1.4342849633761854,
|
| 602 |
+
"learning_rate": 4.3427667335672815e-05,
|
| 603 |
+
"loss": 0.5842,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.4527027027027026,
|
| 608 |
+
"grad_norm": 1.4154466456437151,
|
| 609 |
+
"learning_rate": 4.324912880264326e-05,
|
| 610 |
+
"loss": 0.5491,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.4695945945945945,
|
| 615 |
+
"grad_norm": 1.4449023037096216,
|
| 616 |
+
"learning_rate": 4.30686245519948e-05,
|
| 617 |
+
"loss": 0.5459,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.4864864864864864,
|
| 622 |
+
"grad_norm": 1.2746647387428396,
|
| 623 |
+
"learning_rate": 4.288617711325207e-05,
|
| 624 |
+
"loss": 0.5819,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.5033783783783785,
|
| 629 |
+
"grad_norm": 1.447467776474505,
|
| 630 |
+
"learning_rate": 4.2701809258477575e-05,
|
| 631 |
+
"loss": 0.5784,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.5202702702702702,
|
| 636 |
+
"grad_norm": 1.2391202211909191,
|
| 637 |
+
"learning_rate": 4.251554399942928e-05,
|
| 638 |
+
"loss": 0.5701,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.5371621621621623,
|
| 643 |
+
"grad_norm": 1.2268682468986518,
|
| 644 |
+
"learning_rate": 4.2327404584688495e-05,
|
| 645 |
+
"loss": 0.5995,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.554054054054054,
|
| 650 |
+
"grad_norm": 1.3918773327038636,
|
| 651 |
+
"learning_rate": 4.21374144967581e-05,
|
| 652 |
+
"loss": 0.5644,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.570945945945946,
|
| 657 |
+
"grad_norm": 1.4547926883844007,
|
| 658 |
+
"learning_rate": 4.194559744913157e-05,
|
| 659 |
+
"loss": 0.5642,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.5878378378378377,
|
| 664 |
+
"grad_norm": 1.3596176232205965,
|
| 665 |
+
"learning_rate": 4.1751977383333224e-05,
|
| 666 |
+
"loss": 0.5591,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.6047297297297298,
|
| 671 |
+
"grad_norm": 1.3130436197901627,
|
| 672 |
+
"learning_rate": 4.1556578465929955e-05,
|
| 673 |
+
"loss": 0.571,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.6216216216216215,
|
| 678 |
+
"grad_norm": 1.402701522056968,
|
| 679 |
+
"learning_rate": 4.1359425085514906e-05,
|
| 680 |
+
"loss": 0.5927,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.6385135135135136,
|
| 685 |
+
"grad_norm": 1.2781385628050617,
|
| 686 |
+
"learning_rate": 4.1160541849663404e-05,
|
| 687 |
+
"loss": 0.5745,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.6554054054054053,
|
| 692 |
+
"grad_norm": 1.3121044373462736,
|
| 693 |
+
"learning_rate": 4.095995358186162e-05,
|
| 694 |
+
"loss": 0.5734,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.6722972972972974,
|
| 699 |
+
"grad_norm": 1.3358239819906057,
|
| 700 |
+
"learning_rate": 4.0757685318408186e-05,
|
| 701 |
+
"loss": 0.5553,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.689189189189189,
|
| 706 |
+
"grad_norm": 1.3109247815754774,
|
| 707 |
+
"learning_rate": 4.055376230528936e-05,
|
| 708 |
+
"loss": 0.5621,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.7060810810810811,
|
| 713 |
+
"grad_norm": 1.3687138517149326,
|
| 714 |
+
"learning_rate": 4.034820999502794e-05,
|
| 715 |
+
"loss": 0.571,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.722972972972973,
|
| 720 |
+
"grad_norm": 1.2988387849104504,
|
| 721 |
+
"learning_rate": 4.0141054043506406e-05,
|
| 722 |
+
"loss": 0.5741,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.739864864864865,
|
| 727 |
+
"grad_norm": 1.3411202779787594,
|
| 728 |
+
"learning_rate": 3.993232030676473e-05,
|
| 729 |
+
"loss": 0.5685,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.7567567567567568,
|
| 734 |
+
"grad_norm": 1.2949335901614112,
|
| 735 |
+
"learning_rate": 3.972203483777315e-05,
|
| 736 |
+
"loss": 0.558,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.7736486486486487,
|
| 741 |
+
"grad_norm": 1.3721749127594483,
|
| 742 |
+
"learning_rate": 3.95102238831804e-05,
|
| 743 |
+
"loss": 0.5915,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.7905405405405406,
|
| 748 |
+
"grad_norm": 1.350082387281707,
|
| 749 |
+
"learning_rate": 3.929691388003772e-05,
|
| 750 |
+
"loss": 0.5685,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.8074324324324325,
|
| 755 |
+
"grad_norm": 1.3245276027947501,
|
| 756 |
+
"learning_rate": 3.908213145249916e-05,
|
| 757 |
+
"loss": 0.5691,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.8243243243243243,
|
| 762 |
+
"grad_norm": 1.4137310799251641,
|
| 763 |
+
"learning_rate": 3.886590340849852e-05,
|
| 764 |
+
"loss": 0.566,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.8412162162162162,
|
| 769 |
+
"grad_norm": 1.356555489682696,
|
| 770 |
+
"learning_rate": 3.864825673640326e-05,
|
| 771 |
+
"loss": 0.551,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.8581081081081081,
|
| 776 |
+
"grad_norm": 1.2815437787372281,
|
| 777 |
+
"learning_rate": 3.842921860164607e-05,
|
| 778 |
+
"loss": 0.5655,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.875,
|
| 783 |
+
"grad_norm": 1.3576111263757158,
|
| 784 |
+
"learning_rate": 3.8208816343334156e-05,
|
| 785 |
+
"loss": 0.5497,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.8918918918918919,
|
| 790 |
+
"grad_norm": 1.2750346506851613,
|
| 791 |
+
"learning_rate": 3.798707747083694e-05,
|
| 792 |
+
"loss": 0.5746,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.9087837837837838,
|
| 797 |
+
"grad_norm": 1.317301287962323,
|
| 798 |
+
"learning_rate": 3.776402966035251e-05,
|
| 799 |
+
"loss": 0.584,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.9256756756756757,
|
| 804 |
+
"grad_norm": 1.2204583503286293,
|
| 805 |
+
"learning_rate": 3.753970075145322e-05,
|
| 806 |
+
"loss": 0.5518,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.9425675675675675,
|
| 811 |
+
"grad_norm": 1.2700469074124594,
|
| 812 |
+
"learning_rate": 3.731411874361094e-05,
|
| 813 |
+
"loss": 0.5466,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.9594594594594594,
|
| 818 |
+
"grad_norm": 1.2657661298703708,
|
| 819 |
+
"learning_rate": 3.7087311792702265e-05,
|
| 820 |
+
"loss": 0.5659,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.9763513513513513,
|
| 825 |
+
"grad_norm": 1.2536149686511529,
|
| 826 |
+
"learning_rate": 3.685930820749433e-05,
|
| 827 |
+
"loss": 0.5555,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.9932432432432432,
|
| 832 |
+
"grad_norm": 1.2809671695628992,
|
| 833 |
+
"learning_rate": 3.663013644611139e-05,
|
| 834 |
+
"loss": 0.5563,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.010135135135135,
|
| 839 |
+
"grad_norm": 1.103796522043604,
|
| 840 |
+
"learning_rate": 3.639982511248289e-05,
|
| 841 |
+
"loss": 0.3723,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.027027027027027,
|
| 846 |
+
"grad_norm": 1.2569696258546523,
|
| 847 |
+
"learning_rate": 3.616840295277328e-05,
|
| 848 |
+
"loss": 0.2453,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.043918918918919,
|
| 853 |
+
"grad_norm": 1.202522926688232,
|
| 854 |
+
"learning_rate": 3.593589885179405e-05,
|
| 855 |
+
"loss": 0.2582,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.060810810810811,
|
| 860 |
+
"grad_norm": 1.141634620637362,
|
| 861 |
+
"learning_rate": 3.5702341829398525e-05,
|
| 862 |
+
"loss": 0.25,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.0777027027027026,
|
| 867 |
+
"grad_norm": 1.2434462048859511,
|
| 868 |
+
"learning_rate": 3.5467761036859736e-05,
|
| 869 |
+
"loss": 0.2524,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.0945945945945947,
|
| 874 |
+
"grad_norm": 1.2503774124889013,
|
| 875 |
+
"learning_rate": 3.523218575323198e-05,
|
| 876 |
+
"loss": 0.2426,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.1114864864864864,
|
| 881 |
+
"grad_norm": 1.0984336540308752,
|
| 882 |
+
"learning_rate": 3.499564538169629e-05,
|
| 883 |
+
"loss": 0.2442,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.1283783783783785,
|
| 888 |
+
"grad_norm": 1.3274920050931374,
|
| 889 |
+
"learning_rate": 3.475816944589058e-05,
|
| 890 |
+
"loss": 0.2426,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.14527027027027,
|
| 895 |
+
"grad_norm": 1.2086016497404501,
|
| 896 |
+
"learning_rate": 3.451978758622458e-05,
|
| 897 |
+
"loss": 0.2549,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.1621621621621623,
|
| 902 |
+
"grad_norm": 1.1812293557905968,
|
| 903 |
+
"learning_rate": 3.4280529556180404e-05,
|
| 904 |
+
"loss": 0.2383,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.179054054054054,
|
| 909 |
+
"grad_norm": 1.4704829661444183,
|
| 910 |
+
"learning_rate": 3.4040425218598755e-05,
|
| 911 |
+
"loss": 0.2441,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.195945945945946,
|
| 916 |
+
"grad_norm": 1.2763011019642492,
|
| 917 |
+
"learning_rate": 3.379950454195172e-05,
|
| 918 |
+
"loss": 0.252,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.2128378378378377,
|
| 923 |
+
"grad_norm": 1.2711259414467864,
|
| 924 |
+
"learning_rate": 3.355779759660223e-05,
|
| 925 |
+
"loss": 0.2482,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.22972972972973,
|
| 930 |
+
"grad_norm": 1.2196154702915583,
|
| 931 |
+
"learning_rate": 3.331533455105084e-05,
|
| 932 |
+
"loss": 0.2422,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.2466216216216215,
|
| 937 |
+
"grad_norm": 1.0928327721884867,
|
| 938 |
+
"learning_rate": 3.307214566817027e-05,
|
| 939 |
+
"loss": 0.2493,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.2635135135135136,
|
| 944 |
+
"grad_norm": 1.1577331879228163,
|
| 945 |
+
"learning_rate": 3.2828261301428206e-05,
|
| 946 |
+
"loss": 0.2547,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.2804054054054053,
|
| 951 |
+
"grad_norm": 1.142585348862718,
|
| 952 |
+
"learning_rate": 3.2583711891098665e-05,
|
| 953 |
+
"loss": 0.2545,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.2972972972972974,
|
| 958 |
+
"grad_norm": 1.3931724258065883,
|
| 959 |
+
"learning_rate": 3.23385279604627e-05,
|
| 960 |
+
"loss": 0.2555,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.314189189189189,
|
| 965 |
+
"grad_norm": 1.12997531420638,
|
| 966 |
+
"learning_rate": 3.209274011199861e-05,
|
| 967 |
+
"loss": 0.2503,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.331081081081081,
|
| 972 |
+
"grad_norm": 1.1911209479824547,
|
| 973 |
+
"learning_rate": 3.18463790235623e-05,
|
| 974 |
+
"loss": 0.252,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.347972972972973,
|
| 979 |
+
"grad_norm": 1.2118767972123496,
|
| 980 |
+
"learning_rate": 3.159947544455828e-05,
|
| 981 |
+
"loss": 0.2489,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.364864864864865,
|
| 986 |
+
"grad_norm": 1.1732170281780285,
|
| 987 |
+
"learning_rate": 3.135206019210167e-05,
|
| 988 |
+
"loss": 0.2452,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.3817567567567566,
|
| 993 |
+
"grad_norm": 1.171003404202182,
|
| 994 |
+
"learning_rate": 3.110416414717181e-05,
|
| 995 |
+
"loss": 0.2565,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.3986486486486487,
|
| 1000 |
+
"grad_norm": 1.087800299348181,
|
| 1001 |
+
"learning_rate": 3.085581825075782e-05,
|
| 1002 |
+
"loss": 0.2428,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.4155405405405403,
|
| 1007 |
+
"grad_norm": 1.1798352511221857,
|
| 1008 |
+
"learning_rate": 3.060705349999677e-05,
|
| 1009 |
+
"loss": 0.2597,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.4324324324324325,
|
| 1014 |
+
"grad_norm": 1.1164619974303382,
|
| 1015 |
+
"learning_rate": 3.0357900944304774e-05,
|
| 1016 |
+
"loss": 0.2558,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.4493243243243246,
|
| 1021 |
+
"grad_norm": 1.1783745618133863,
|
| 1022 |
+
"learning_rate": 3.0108391681501564e-05,
|
| 1023 |
+
"loss": 0.2502,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.4662162162162162,
|
| 1028 |
+
"grad_norm": 1.2059356558094934,
|
| 1029 |
+
"learning_rate": 2.9858556853929048e-05,
|
| 1030 |
+
"loss": 0.2549,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.483108108108108,
|
| 1035 |
+
"grad_norm": 1.1084513675225853,
|
| 1036 |
+
"learning_rate": 2.96084276445643e-05,
|
| 1037 |
+
"loss": 0.2623,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.5,
|
| 1042 |
+
"grad_norm": 1.1268704196768717,
|
| 1043 |
+
"learning_rate": 2.9358035273127483e-05,
|
| 1044 |
+
"loss": 0.2445,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.516891891891892,
|
| 1049 |
+
"grad_norm": 1.2073238153053072,
|
| 1050 |
+
"learning_rate": 2.910741099218514e-05,
|
| 1051 |
+
"loss": 0.2523,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.5337837837837838,
|
| 1056 |
+
"grad_norm": 1.1875133895260694,
|
| 1057 |
+
"learning_rate": 2.8856586083249487e-05,
|
| 1058 |
+
"loss": 0.2587,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.5506756756756754,
|
| 1063 |
+
"grad_norm": 1.1828390695293125,
|
| 1064 |
+
"learning_rate": 2.860559185287397e-05,
|
| 1065 |
+
"loss": 0.2555,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.5675675675675675,
|
| 1070 |
+
"grad_norm": 1.1686470252895278,
|
| 1071 |
+
"learning_rate": 2.83544596287458e-05,
|
| 1072 |
+
"loss": 0.246,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.5844594594594597,
|
| 1077 |
+
"grad_norm": 1.2445669104213888,
|
| 1078 |
+
"learning_rate": 2.8103220755775776e-05,
|
| 1079 |
+
"loss": 0.2536,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.6013513513513513,
|
| 1084 |
+
"grad_norm": 1.1612663427931047,
|
| 1085 |
+
"learning_rate": 2.785190659218604e-05,
|
| 1086 |
+
"loss": 0.2511,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.618243243243243,
|
| 1091 |
+
"grad_norm": 1.169020666404516,
|
| 1092 |
+
"learning_rate": 2.760054850559603e-05,
|
| 1093 |
+
"loss": 0.2464,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.635135135135135,
|
| 1098 |
+
"grad_norm": 1.1211602172208788,
|
| 1099 |
+
"learning_rate": 2.7349177869107462e-05,
|
| 1100 |
+
"loss": 0.2425,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.652027027027027,
|
| 1105 |
+
"grad_norm": 1.1295937771546627,
|
| 1106 |
+
"learning_rate": 2.709782605738842e-05,
|
| 1107 |
+
"loss": 0.251,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.668918918918919,
|
| 1112 |
+
"grad_norm": 1.1985208404439514,
|
| 1113 |
+
"learning_rate": 2.684652444275741e-05,
|
| 1114 |
+
"loss": 0.2511,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.685810810810811,
|
| 1119 |
+
"grad_norm": 1.1712043419573621,
|
| 1120 |
+
"learning_rate": 2.6595304391267605e-05,
|
| 1121 |
+
"loss": 0.2409,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.7027027027027026,
|
| 1126 |
+
"grad_norm": 1.1600530170137202,
|
| 1127 |
+
"learning_rate": 2.634419725879193e-05,
|
| 1128 |
+
"loss": 0.2461,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.7195945945945947,
|
| 1133 |
+
"grad_norm": 1.0980080565697286,
|
| 1134 |
+
"learning_rate": 2.60932343871094e-05,
|
| 1135 |
+
"loss": 0.2351,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.7364864864864864,
|
| 1140 |
+
"grad_norm": 1.204458523946955,
|
| 1141 |
+
"learning_rate": 2.58424470999932e-05,
|
| 1142 |
+
"loss": 0.2415,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.7533783783783785,
|
| 1147 |
+
"grad_norm": 1.2137349551053236,
|
| 1148 |
+
"learning_rate": 2.5591866699301055e-05,
|
| 1149 |
+
"loss": 0.2411,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.77027027027027,
|
| 1154 |
+
"grad_norm": 1.2375233171662754,
|
| 1155 |
+
"learning_rate": 2.534152446106825e-05,
|
| 1156 |
+
"loss": 0.2429,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.7871621621621623,
|
| 1161 |
+
"grad_norm": 1.1646244068445126,
|
| 1162 |
+
"learning_rate": 2.5091451631604033e-05,
|
| 1163 |
+
"loss": 0.2359,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.804054054054054,
|
| 1168 |
+
"grad_norm": 1.1619752616590404,
|
| 1169 |
+
"learning_rate": 2.4841679423591523e-05,
|
| 1170 |
+
"loss": 0.2368,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.820945945945946,
|
| 1175 |
+
"grad_norm": 1.1047288053357993,
|
| 1176 |
+
"learning_rate": 2.4592239012191977e-05,
|
| 1177 |
+
"loss": 0.2391,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.8378378378378377,
|
| 1182 |
+
"grad_norm": 1.074588438071139,
|
| 1183 |
+
"learning_rate": 2.4343161531153647e-05,
|
| 1184 |
+
"loss": 0.234,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.85472972972973,
|
| 1189 |
+
"grad_norm": 1.1971487515181058,
|
| 1190 |
+
"learning_rate": 2.4094478068925884e-05,
|
| 1191 |
+
"loss": 0.2459,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.8716216216216215,
|
| 1196 |
+
"grad_norm": 1.18752516936673,
|
| 1197 |
+
"learning_rate": 2.3846219664778824e-05,
|
| 1198 |
+
"loss": 0.2337,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.8885135135135136,
|
| 1203 |
+
"grad_norm": 1.0648986336743749,
|
| 1204 |
+
"learning_rate": 2.3598417304929226e-05,
|
| 1205 |
+
"loss": 0.2385,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.9054054054054053,
|
| 1210 |
+
"grad_norm": 1.2273436401598625,
|
| 1211 |
+
"learning_rate": 2.3351101918672985e-05,
|
| 1212 |
+
"loss": 0.2307,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.9222972972972974,
|
| 1217 |
+
"grad_norm": 1.1562044904763753,
|
| 1218 |
+
"learning_rate": 2.3104304374524704e-05,
|
| 1219 |
+
"loss": 0.2313,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.939189189189189,
|
| 1224 |
+
"grad_norm": 1.1200371062184964,
|
| 1225 |
+
"learning_rate": 2.2858055476364822e-05,
|
| 1226 |
+
"loss": 0.2382,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.956081081081081,
|
| 1231 |
+
"grad_norm": 1.0863337573648397,
|
| 1232 |
+
"learning_rate": 2.2612385959594877e-05,
|
| 1233 |
+
"loss": 0.2357,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.972972972972973,
|
| 1238 |
+
"grad_norm": 1.1238376465153148,
|
| 1239 |
+
"learning_rate": 2.2367326487301317e-05,
|
| 1240 |
+
"loss": 0.2366,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.989864864864865,
|
| 1245 |
+
"grad_norm": 1.1679762876800548,
|
| 1246 |
+
"learning_rate": 2.2122907646428214e-05,
|
| 1247 |
+
"loss": 0.233,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.0067567567567566,
|
| 1252 |
+
"grad_norm": 0.7617860489835798,
|
| 1253 |
+
"learning_rate": 2.1879159943959686e-05,
|
| 1254 |
+
"loss": 0.1782,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.0236486486486487,
|
| 1259 |
+
"grad_norm": 0.7980232728533272,
|
| 1260 |
+
"learning_rate": 2.1636113803112097e-05,
|
| 1261 |
+
"loss": 0.0889,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.0405405405405403,
|
| 1266 |
+
"grad_norm": 1.0371057007455198,
|
| 1267 |
+
"learning_rate": 2.139379955953686e-05,
|
| 1268 |
+
"loss": 0.0855,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.0574324324324325,
|
| 1273 |
+
"grad_norm": 0.922694869510506,
|
| 1274 |
+
"learning_rate": 2.1152247457534065e-05,
|
| 1275 |
+
"loss": 0.082,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.074324324324324,
|
| 1280 |
+
"grad_norm": 0.8665469624615858,
|
| 1281 |
+
"learning_rate": 2.0911487646277623e-05,
|
| 1282 |
+
"loss": 0.0842,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.0912162162162162,
|
| 1287 |
+
"grad_norm": 0.8466103971895397,
|
| 1288 |
+
"learning_rate": 2.067155017605212e-05,
|
| 1289 |
+
"loss": 0.0818,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 3.108108108108108,
|
| 1294 |
+
"grad_norm": 0.8200266011697321,
|
| 1295 |
+
"learning_rate": 2.0432464994502203e-05,
|
| 1296 |
+
"loss": 0.0839,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 3.125,
|
| 1301 |
+
"grad_norm": 0.805011414682386,
|
| 1302 |
+
"learning_rate": 2.0194261942894628e-05,
|
| 1303 |
+
"loss": 0.0798,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.141891891891892,
|
| 1308 |
+
"grad_norm": 0.9572346016824955,
|
| 1309 |
+
"learning_rate": 1.995697075239365e-05,
|
| 1310 |
+
"loss": 0.0856,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.1587837837837838,
|
| 1315 |
+
"grad_norm": 0.8204526811751627,
|
| 1316 |
+
"learning_rate": 1.972062104035017e-05,
|
| 1317 |
+
"loss": 0.079,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 3.175675675675676,
|
| 1322 |
+
"grad_norm": 0.8185257809669213,
|
| 1323 |
+
"learning_rate": 1.9485242306605028e-05,
|
| 1324 |
+
"loss": 0.0865,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.1925675675675675,
|
| 1329 |
+
"grad_norm": 0.8796508468976082,
|
| 1330 |
+
"learning_rate": 1.9250863929807027e-05,
|
| 1331 |
+
"loss": 0.0786,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 3.2094594594594597,
|
| 1336 |
+
"grad_norm": 0.8756829385022001,
|
| 1337 |
+
"learning_rate": 1.9017515163746058e-05,
|
| 1338 |
+
"loss": 0.0836,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 3.2263513513513513,
|
| 1343 |
+
"grad_norm": 0.8157354792396803,
|
| 1344 |
+
"learning_rate": 1.878522513370177e-05,
|
| 1345 |
+
"loss": 0.0852,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.2432432432432434,
|
| 1350 |
+
"grad_norm": 0.8590600023617616,
|
| 1351 |
+
"learning_rate": 1.855402283280836e-05,
|
| 1352 |
+
"loss": 0.0835,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.260135135135135,
|
| 1357 |
+
"grad_norm": 0.8643752542390469,
|
| 1358 |
+
"learning_rate": 1.8323937118435786e-05,
|
| 1359 |
+
"loss": 0.0814,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 3.277027027027027,
|
| 1364 |
+
"grad_norm": 0.9225152379758252,
|
| 1365 |
+
"learning_rate": 1.8094996708587958e-05,
|
| 1366 |
+
"loss": 0.0861,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 3.293918918918919,
|
| 1371 |
+
"grad_norm": 0.9044834326870717,
|
| 1372 |
+
"learning_rate": 1.7867230178318334e-05,
|
| 1373 |
+
"loss": 0.0819,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.310810810810811,
|
| 1378 |
+
"grad_norm": 0.8920506863920826,
|
| 1379 |
+
"learning_rate": 1.7640665956163306e-05,
|
| 1380 |
+
"loss": 0.0809,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.3277027027027026,
|
| 1385 |
+
"grad_norm": 0.9035029361545068,
|
| 1386 |
+
"learning_rate": 1.7415332320593964e-05,
|
| 1387 |
+
"loss": 0.0782,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.3445945945945947,
|
| 1392 |
+
"grad_norm": 0.8458923715737863,
|
| 1393 |
+
"learning_rate": 1.719125739648648e-05,
|
| 1394 |
+
"loss": 0.0795,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.3614864864864864,
|
| 1399 |
+
"grad_norm": 0.8283053816212952,
|
| 1400 |
+
"learning_rate": 1.6968469151611766e-05,
|
| 1401 |
+
"loss": 0.0766,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.3783783783783785,
|
| 1406 |
+
"grad_norm": 0.8124298394489518,
|
| 1407 |
+
"learning_rate": 1.6746995393144668e-05,
|
| 1408 |
+
"loss": 0.0795,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 3.39527027027027,
|
| 1413 |
+
"grad_norm": 0.84974780220989,
|
| 1414 |
+
"learning_rate": 1.6526863764193228e-05,
|
| 1415 |
+
"loss": 0.0816,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 3.4121621621621623,
|
| 1420 |
+
"grad_norm": 0.9040056390996183,
|
| 1421 |
+
"learning_rate": 1.6308101740348433e-05,
|
| 1422 |
+
"loss": 0.0862,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 3.429054054054054,
|
| 1427 |
+
"grad_norm": 0.8503065695427434,
|
| 1428 |
+
"learning_rate": 1.6090736626254894e-05,
|
| 1429 |
+
"loss": 0.0821,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.445945945945946,
|
| 1434 |
+
"grad_norm": 0.922976948565284,
|
| 1435 |
+
"learning_rate": 1.5874795552202773e-05,
|
| 1436 |
+
"loss": 0.0767,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.4628378378378377,
|
| 1441 |
+
"grad_norm": 0.8359859623361058,
|
| 1442 |
+
"learning_rate": 1.5660305470741603e-05,
|
| 1443 |
+
"loss": 0.0822,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 3.47972972972973,
|
| 1448 |
+
"grad_norm": 0.7993044555598261,
|
| 1449 |
+
"learning_rate": 1.5447293153316163e-05,
|
| 1450 |
+
"loss": 0.0725,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.4966216216216215,
|
| 1455 |
+
"grad_norm": 0.8837194556202582,
|
| 1456 |
+
"learning_rate": 1.523578518692505e-05,
|
| 1457 |
+
"loss": 0.0803,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 3.5135135135135136,
|
| 1462 |
+
"grad_norm": 0.8671077384687282,
|
| 1463 |
+
"learning_rate": 1.5025807970802252e-05,
|
| 1464 |
+
"loss": 0.0759,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 3.5304054054054053,
|
| 1469 |
+
"grad_norm": 0.851094402030443,
|
| 1470 |
+
"learning_rate": 1.481738771312209e-05,
|
| 1471 |
+
"loss": 0.079,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 3.5472972972972974,
|
| 1476 |
+
"grad_norm": 0.8361299277027681,
|
| 1477 |
+
"learning_rate": 1.4610550427728103e-05,
|
| 1478 |
+
"loss": 0.076,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.564189189189189,
|
| 1483 |
+
"grad_norm": 0.8472817077547173,
|
| 1484 |
+
"learning_rate": 1.4405321930886161e-05,
|
| 1485 |
+
"loss": 0.0762,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 3.581081081081081,
|
| 1490 |
+
"grad_norm": 0.8496742173511822,
|
| 1491 |
+
"learning_rate": 1.4201727838062181e-05,
|
| 1492 |
+
"loss": 0.0777,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 3.597972972972973,
|
| 1497 |
+
"grad_norm": 0.9073909261434937,
|
| 1498 |
+
"learning_rate": 1.3999793560724966e-05,
|
| 1499 |
+
"loss": 0.0778,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 3.614864864864865,
|
| 1504 |
+
"grad_norm": 0.8148037450824118,
|
| 1505 |
+
"learning_rate": 1.3799544303174514e-05,
|
| 1506 |
+
"loss": 0.0753,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 3.631756756756757,
|
| 1511 |
+
"grad_norm": 0.792903387483005,
|
| 1512 |
+
"learning_rate": 1.3601005059396104e-05,
|
| 1513 |
+
"loss": 0.0743,
|
| 1514 |
+
"step": 1075
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 3.6486486486486487,
|
| 1518 |
+
"grad_norm": 0.8138776105456261,
|
| 1519 |
+
"learning_rate": 1.3404200609940754e-05,
|
| 1520 |
+
"loss": 0.0771,
|
| 1521 |
+
"step": 1080
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 3.6655405405405403,
|
| 1525 |
+
"grad_norm": 0.8412665781860845,
|
| 1526 |
+
"learning_rate": 1.3209155518832203e-05,
|
| 1527 |
+
"loss": 0.0748,
|
| 1528 |
+
"step": 1085
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.6824324324324325,
|
| 1532 |
+
"grad_norm": 0.8443573738089697,
|
| 1533 |
+
"learning_rate": 1.3015894130500977e-05,
|
| 1534 |
+
"loss": 0.0729,
|
| 1535 |
+
"step": 1090
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.6993243243243246,
|
| 1539 |
+
"grad_norm": 0.8610810221368033,
|
| 1540 |
+
"learning_rate": 1.2824440566745865e-05,
|
| 1541 |
+
"loss": 0.0744,
|
| 1542 |
+
"step": 1095
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 3.7162162162162162,
|
| 1546 |
+
"grad_norm": 0.7968023292862391,
|
| 1547 |
+
"learning_rate": 1.2634818723723174e-05,
|
| 1548 |
+
"loss": 0.0752,
|
| 1549 |
+
"step": 1100
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 3.733108108108108,
|
| 1553 |
+
"grad_norm": 0.7623771883673489,
|
| 1554 |
+
"learning_rate": 1.2447052268964122e-05,
|
| 1555 |
+
"loss": 0.0698,
|
| 1556 |
+
"step": 1105
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.75,
|
| 1560 |
+
"grad_norm": 0.8911604401532162,
|
| 1561 |
+
"learning_rate": 1.2261164638420832e-05,
|
| 1562 |
+
"loss": 0.0728,
|
| 1563 |
+
"step": 1110
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.766891891891892,
|
| 1567 |
+
"grad_norm": 0.8291626224492225,
|
| 1568 |
+
"learning_rate": 1.2077179033541139e-05,
|
| 1569 |
+
"loss": 0.0725,
|
| 1570 |
+
"step": 1115
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 3.7837837837837838,
|
| 1574 |
+
"grad_norm": 0.7888246317862425,
|
| 1575 |
+
"learning_rate": 1.1895118418372734e-05,
|
| 1576 |
+
"loss": 0.0751,
|
| 1577 |
+
"step": 1120
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.8006756756756754,
|
| 1581 |
+
"grad_norm": 0.7596045011769311,
|
| 1582 |
+
"learning_rate": 1.171500551669697e-05,
|
| 1583 |
+
"loss": 0.0707,
|
| 1584 |
+
"step": 1125
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 3.8175675675675675,
|
| 1588 |
+
"grad_norm": 0.8261890861433314,
|
| 1589 |
+
"learning_rate": 1.1536862809192518e-05,
|
| 1590 |
+
"loss": 0.0699,
|
| 1591 |
+
"step": 1130
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 3.8344594594594597,
|
| 1595 |
+
"grad_norm": 0.8157898272197499,
|
| 1596 |
+
"learning_rate": 1.1360712530629513e-05,
|
| 1597 |
+
"loss": 0.0739,
|
| 1598 |
+
"step": 1135
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 3.8513513513513513,
|
| 1602 |
+
"grad_norm": 0.7953827120772039,
|
| 1603 |
+
"learning_rate": 1.1186576667094342e-05,
|
| 1604 |
+
"loss": 0.0727,
|
| 1605 |
+
"step": 1140
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.868243243243243,
|
| 1609 |
+
"grad_norm": 0.8106925387796762,
|
| 1610 |
+
"learning_rate": 1.1014476953245423e-05,
|
| 1611 |
+
"loss": 0.0689,
|
| 1612 |
+
"step": 1145
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 3.885135135135135,
|
| 1616 |
+
"grad_norm": 0.7915344112028949,
|
| 1617 |
+
"learning_rate": 1.0844434869600428e-05,
|
| 1618 |
+
"loss": 0.0696,
|
| 1619 |
+
"step": 1150
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 3.902027027027027,
|
| 1623 |
+
"grad_norm": 0.8231236378626898,
|
| 1624 |
+
"learning_rate": 1.0676471639855235e-05,
|
| 1625 |
+
"loss": 0.0701,
|
| 1626 |
+
"step": 1155
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 3.918918918918919,
|
| 1630 |
+
"grad_norm": 0.8574639286128795,
|
| 1631 |
+
"learning_rate": 1.0510608228234848e-05,
|
| 1632 |
+
"loss": 0.0678,
|
| 1633 |
+
"step": 1160
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.935810810810811,
|
| 1637 |
+
"grad_norm": 0.7703198418021956,
|
| 1638 |
+
"learning_rate": 1.0346865336876809e-05,
|
| 1639 |
+
"loss": 0.0679,
|
| 1640 |
+
"step": 1165
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 3.9527027027027026,
|
| 1644 |
+
"grad_norm": 0.8086225426905125,
|
| 1645 |
+
"learning_rate": 1.0185263403247256e-05,
|
| 1646 |
+
"loss": 0.0669,
|
| 1647 |
+
"step": 1170
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.9695945945945947,
|
| 1651 |
+
"grad_norm": 0.8488002772643025,
|
| 1652 |
+
"learning_rate": 1.002582259759002e-05,
|
| 1653 |
+
"loss": 0.0684,
|
| 1654 |
+
"step": 1175
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 3.9864864864864864,
|
| 1658 |
+
"grad_norm": 0.8980288101695698,
|
| 1659 |
+
"learning_rate": 9.868562820409103e-06,
|
| 1660 |
+
"loss": 0.0686,
|
| 1661 |
+
"step": 1180
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 4.003378378378378,
|
| 1665 |
+
"grad_norm": 0.3986041630321839,
|
| 1666 |
+
"learning_rate": 9.713503699984825e-06,
|
| 1667 |
+
"loss": 0.0548,
|
| 1668 |
+
"step": 1185
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 4.02027027027027,
|
| 1672 |
+
"grad_norm": 0.43726382965712174,
|
| 1673 |
+
"learning_rate": 9.560664589923895e-06,
|
| 1674 |
+
"loss": 0.0219,
|
| 1675 |
+
"step": 1190
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 4.037162162162162,
|
| 1679 |
+
"grad_norm": 0.36710468007751074,
|
| 1680 |
+
"learning_rate": 9.410064566743841e-06,
|
| 1681 |
+
"loss": 0.0208,
|
| 1682 |
+
"step": 1195
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 4.054054054054054,
|
| 1686 |
+
"grad_norm": 0.37287043834241884,
|
| 1687 |
+
"learning_rate": 9.261722427491953e-06,
|
| 1688 |
+
"loss": 0.0194,
|
| 1689 |
+
"step": 1200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.070945945945946,
|
| 1693 |
+
"grad_norm": 0.5533039626983974,
|
| 1694 |
+
"learning_rate": 9.115656687399149e-06,
|
| 1695 |
+
"loss": 0.02,
|
| 1696 |
+
"step": 1205
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 4.087837837837838,
|
| 1700 |
+
"grad_norm": 0.5313826064857297,
|
| 1701 |
+
"learning_rate": 8.971885577569058e-06,
|
| 1702 |
+
"loss": 0.0177,
|
| 1703 |
+
"step": 1210
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 4.10472972972973,
|
| 1707 |
+
"grad_norm": 0.44890915578901536,
|
| 1708 |
+
"learning_rate": 8.83042704270243e-06,
|
| 1709 |
+
"loss": 0.0189,
|
| 1710 |
+
"step": 1215
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 4.121621621621622,
|
| 1714 |
+
"grad_norm": 0.5560917251637355,
|
| 1715 |
+
"learning_rate": 8.691298738857432e-06,
|
| 1716 |
+
"loss": 0.019,
|
| 1717 |
+
"step": 1220
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 4.138513513513513,
|
| 1721 |
+
"grad_norm": 0.5436237010579721,
|
| 1722 |
+
"learning_rate": 8.554518031245934e-06,
|
| 1723 |
+
"loss": 0.0185,
|
| 1724 |
+
"step": 1225
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 4.155405405405405,
|
| 1728 |
+
"grad_norm": 0.4740850367041631,
|
| 1729 |
+
"learning_rate": 8.420101992066028e-06,
|
| 1730 |
+
"loss": 0.0166,
|
| 1731 |
+
"step": 1230
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 4.172297297297297,
|
| 1735 |
+
"grad_norm": 0.49052875884939057,
|
| 1736 |
+
"learning_rate": 8.288067398371214e-06,
|
| 1737 |
+
"loss": 0.0167,
|
| 1738 |
+
"step": 1235
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 4.1891891891891895,
|
| 1742 |
+
"grad_norm": 0.43052256280300827,
|
| 1743 |
+
"learning_rate": 8.158430729976372e-06,
|
| 1744 |
+
"loss": 0.0186,
|
| 1745 |
+
"step": 1240
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 4.206081081081081,
|
| 1749 |
+
"grad_norm": 0.4777607693530672,
|
| 1750 |
+
"learning_rate": 8.031208167400833e-06,
|
| 1751 |
+
"loss": 0.0194,
|
| 1752 |
+
"step": 1245
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 4.222972972972973,
|
| 1756 |
+
"grad_norm": 0.4366669926231541,
|
| 1757 |
+
"learning_rate": 7.906415589848834e-06,
|
| 1758 |
+
"loss": 0.0175,
|
| 1759 |
+
"step": 1250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 4.239864864864865,
|
| 1763 |
+
"grad_norm": 0.4875801354190107,
|
| 1764 |
+
"learning_rate": 7.78406857322756e-06,
|
| 1765 |
+
"loss": 0.0176,
|
| 1766 |
+
"step": 1255
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 4.256756756756757,
|
| 1770 |
+
"grad_norm": 0.5496320514624984,
|
| 1771 |
+
"learning_rate": 7.664182388203037e-06,
|
| 1772 |
+
"loss": 0.0183,
|
| 1773 |
+
"step": 1260
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 4.273648648648648,
|
| 1777 |
+
"grad_norm": 0.4131315904135289,
|
| 1778 |
+
"learning_rate": 7.54677199829414e-06,
|
| 1779 |
+
"loss": 0.0175,
|
| 1780 |
+
"step": 1265
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 4.29054054054054,
|
| 1784 |
+
"grad_norm": 0.5104334470158947,
|
| 1785 |
+
"learning_rate": 7.4318520580049444e-06,
|
| 1786 |
+
"loss": 0.0173,
|
| 1787 |
+
"step": 1270
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 4.3074324324324325,
|
| 1791 |
+
"grad_norm": 0.5028181787292044,
|
| 1792 |
+
"learning_rate": 7.3194369109956e-06,
|
| 1793 |
+
"loss": 0.0193,
|
| 1794 |
+
"step": 1275
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 4.324324324324325,
|
| 1798 |
+
"grad_norm": 0.42628529148210376,
|
| 1799 |
+
"learning_rate": 7.209540588292083e-06,
|
| 1800 |
+
"loss": 0.0158,
|
| 1801 |
+
"step": 1280
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 4.341216216216216,
|
| 1805 |
+
"grad_norm": 0.44913562810367375,
|
| 1806 |
+
"learning_rate": 7.102176806534873e-06,
|
| 1807 |
+
"loss": 0.0177,
|
| 1808 |
+
"step": 1285
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 4.358108108108108,
|
| 1812 |
+
"grad_norm": 0.5514097182218852,
|
| 1813 |
+
"learning_rate": 6.9973589662669455e-06,
|
| 1814 |
+
"loss": 0.017,
|
| 1815 |
+
"step": 1290
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 4.375,
|
| 1819 |
+
"grad_norm": 0.5163780905038693,
|
| 1820 |
+
"learning_rate": 6.8951001502612065e-06,
|
| 1821 |
+
"loss": 0.0168,
|
| 1822 |
+
"step": 1295
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 4.391891891891892,
|
| 1826 |
+
"grad_norm": 0.49290296808784145,
|
| 1827 |
+
"learning_rate": 6.7954131218875404e-06,
|
| 1828 |
+
"loss": 0.016,
|
| 1829 |
+
"step": 1300
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 4.408783783783784,
|
| 1833 |
+
"grad_norm": 0.430553207351477,
|
| 1834 |
+
"learning_rate": 6.69831032351977e-06,
|
| 1835 |
+
"loss": 0.0169,
|
| 1836 |
+
"step": 1305
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 4.425675675675675,
|
| 1840 |
+
"grad_norm": 0.4642297721283167,
|
| 1841 |
+
"learning_rate": 6.603803874982687e-06,
|
| 1842 |
+
"loss": 0.0173,
|
| 1843 |
+
"step": 1310
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 4.4425675675675675,
|
| 1847 |
+
"grad_norm": 0.41074319788773356,
|
| 1848 |
+
"learning_rate": 6.511905572039298e-06,
|
| 1849 |
+
"loss": 0.0191,
|
| 1850 |
+
"step": 1315
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 4.45945945945946,
|
| 1854 |
+
"grad_norm": 0.42290407551524545,
|
| 1855 |
+
"learning_rate": 6.422626884918559e-06,
|
| 1856 |
+
"loss": 0.0187,
|
| 1857 |
+
"step": 1320
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 4.476351351351352,
|
| 1861 |
+
"grad_norm": 0.47394273027675116,
|
| 1862 |
+
"learning_rate": 6.33597895688373e-06,
|
| 1863 |
+
"loss": 0.0173,
|
| 1864 |
+
"step": 1325
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 4.493243243243243,
|
| 1868 |
+
"grad_norm": 0.4957247279877308,
|
| 1869 |
+
"learning_rate": 6.2519726028415145e-06,
|
| 1870 |
+
"loss": 0.0176,
|
| 1871 |
+
"step": 1330
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 4.510135135135135,
|
| 1875 |
+
"grad_norm": 0.40363156811514256,
|
| 1876 |
+
"learning_rate": 6.170618307992231e-06,
|
| 1877 |
+
"loss": 0.0156,
|
| 1878 |
+
"step": 1335
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 4.527027027027027,
|
| 1882 |
+
"grad_norm": 0.46394127923496636,
|
| 1883 |
+
"learning_rate": 6.091926226521089e-06,
|
| 1884 |
+
"loss": 0.0166,
|
| 1885 |
+
"step": 1340
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 4.543918918918919,
|
| 1889 |
+
"grad_norm": 0.4892778778622955,
|
| 1890 |
+
"learning_rate": 6.015906180330808e-06,
|
| 1891 |
+
"loss": 0.016,
|
| 1892 |
+
"step": 1345
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 4.5608108108108105,
|
| 1896 |
+
"grad_norm": 0.39032273135281653,
|
| 1897 |
+
"learning_rate": 5.942567657815696e-06,
|
| 1898 |
+
"loss": 0.0168,
|
| 1899 |
+
"step": 1350
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 4.577702702702703,
|
| 1903 |
+
"grad_norm": 0.4719537909270886,
|
| 1904 |
+
"learning_rate": 5.871919812677383e-06,
|
| 1905 |
+
"loss": 0.0164,
|
| 1906 |
+
"step": 1355
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 4.594594594594595,
|
| 1910 |
+
"grad_norm": 0.4245185329209189,
|
| 1911 |
+
"learning_rate": 5.8039714627822754e-06,
|
| 1912 |
+
"loss": 0.0156,
|
| 1913 |
+
"step": 1360
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.611486486486487,
|
| 1917 |
+
"grad_norm": 0.41475267241989133,
|
| 1918 |
+
"learning_rate": 5.738731089060995e-06,
|
| 1919 |
+
"loss": 0.0153,
|
| 1920 |
+
"step": 1365
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 4.628378378378378,
|
| 1924 |
+
"grad_norm": 0.5352228892671703,
|
| 1925 |
+
"learning_rate": 5.676206834449797e-06,
|
| 1926 |
+
"loss": 0.0165,
|
| 1927 |
+
"step": 1370
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 4.64527027027027,
|
| 1931 |
+
"grad_norm": 0.37701331899842194,
|
| 1932 |
+
"learning_rate": 5.616406502874251e-06,
|
| 1933 |
+
"loss": 0.0146,
|
| 1934 |
+
"step": 1375
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 4.662162162162162,
|
| 1938 |
+
"grad_norm": 0.39899803271574863,
|
| 1939 |
+
"learning_rate": 5.55933755827518e-06,
|
| 1940 |
+
"loss": 0.0148,
|
| 1941 |
+
"step": 1380
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 4.679054054054054,
|
| 1945 |
+
"grad_norm": 0.48339475577967467,
|
| 1946 |
+
"learning_rate": 5.505007123677063e-06,
|
| 1947 |
+
"loss": 0.0161,
|
| 1948 |
+
"step": 1385
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 4.695945945945946,
|
| 1952 |
+
"grad_norm": 0.47920447606296807,
|
| 1953 |
+
"learning_rate": 5.453421980298957e-06,
|
| 1954 |
+
"loss": 0.0161,
|
| 1955 |
+
"step": 1390
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 4.712837837837838,
|
| 1959 |
+
"grad_norm": 0.45349300791214964,
|
| 1960 |
+
"learning_rate": 5.4045885667081375e-06,
|
| 1961 |
+
"loss": 0.0162,
|
| 1962 |
+
"step": 1395
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 4.72972972972973,
|
| 1966 |
+
"grad_norm": 0.4524858740954348,
|
| 1967 |
+
"learning_rate": 5.358512978016445e-06,
|
| 1968 |
+
"loss": 0.0156,
|
| 1969 |
+
"step": 1400
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 4.746621621621622,
|
| 1973 |
+
"grad_norm": 0.4052610898199223,
|
| 1974 |
+
"learning_rate": 5.315200965119541e-06,
|
| 1975 |
+
"loss": 0.0144,
|
| 1976 |
+
"step": 1405
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 4.763513513513513,
|
| 1980 |
+
"grad_norm": 0.4648951449721674,
|
| 1981 |
+
"learning_rate": 5.27465793397911e-06,
|
| 1982 |
+
"loss": 0.0174,
|
| 1983 |
+
"step": 1410
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 4.780405405405405,
|
| 1987 |
+
"grad_norm": 0.4310666293350422,
|
| 1988 |
+
"learning_rate": 5.236888944948117e-06,
|
| 1989 |
+
"loss": 0.0157,
|
| 1990 |
+
"step": 1415
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 4.797297297297297,
|
| 1994 |
+
"grad_norm": 0.4423747920595358,
|
| 1995 |
+
"learning_rate": 5.201898712139201e-06,
|
| 1996 |
+
"loss": 0.0139,
|
| 1997 |
+
"step": 1420
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 4.8141891891891895,
|
| 2001 |
+
"grad_norm": 0.40535469669136887,
|
| 2002 |
+
"learning_rate": 5.1696916028362964e-06,
|
| 2003 |
+
"loss": 0.0161,
|
| 2004 |
+
"step": 1425
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 4.831081081081081,
|
| 2008 |
+
"grad_norm": 0.5159753334356647,
|
| 2009 |
+
"learning_rate": 5.1402716369495194e-06,
|
| 2010 |
+
"loss": 0.0172,
|
| 2011 |
+
"step": 1430
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 4.847972972972973,
|
| 2015 |
+
"grad_norm": 0.49504962870437985,
|
| 2016 |
+
"learning_rate": 5.113642486513428e-06,
|
| 2017 |
+
"loss": 0.0148,
|
| 2018 |
+
"step": 1435
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 4.864864864864865,
|
| 2022 |
+
"grad_norm": 0.4125316130138178,
|
| 2023 |
+
"learning_rate": 5.089807475228711e-06,
|
| 2024 |
+
"loss": 0.0142,
|
| 2025 |
+
"step": 1440
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 4.881756756756757,
|
| 2029 |
+
"grad_norm": 0.4694139851875935,
|
| 2030 |
+
"learning_rate": 5.06876957804733e-06,
|
| 2031 |
+
"loss": 0.0157,
|
| 2032 |
+
"step": 1445
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 4.898648648648649,
|
| 2036 |
+
"grad_norm": 0.44686436058551265,
|
| 2037 |
+
"learning_rate": 5.050531420801205e-06,
|
| 2038 |
+
"loss": 0.0159,
|
| 2039 |
+
"step": 1450
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 4.91554054054054,
|
| 2043 |
+
"grad_norm": 0.4838100458198807,
|
| 2044 |
+
"learning_rate": 5.03509527987448e-06,
|
| 2045 |
+
"loss": 0.0164,
|
| 2046 |
+
"step": 1455
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 4.9324324324324325,
|
| 2050 |
+
"grad_norm": 0.44838862569063753,
|
| 2051 |
+
"learning_rate": 5.022463081919386e-06,
|
| 2052 |
+
"loss": 0.0135,
|
| 2053 |
+
"step": 1460
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 4.949324324324325,
|
| 2057 |
+
"grad_norm": 0.33222610870493824,
|
| 2058 |
+
"learning_rate": 5.012636403615775e-06,
|
| 2059 |
+
"loss": 0.0157,
|
| 2060 |
+
"step": 1465
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 4.966216216216216,
|
| 2064 |
+
"grad_norm": 0.4899278481273953,
|
| 2065 |
+
"learning_rate": 5.005616471474332e-06,
|
| 2066 |
+
"loss": 0.015,
|
| 2067 |
+
"step": 1470
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.983108108108108,
|
| 2071 |
+
"grad_norm": 0.46395409247351443,
|
| 2072 |
+
"learning_rate": 5.001404161683473e-06,
|
| 2073 |
+
"loss": 0.0157,
|
| 2074 |
+
"step": 1475
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 5.0,
|
| 2078 |
+
"grad_norm": 0.38146340884683544,
|
| 2079 |
+
"learning_rate": 5e-06,
|
| 2080 |
+
"loss": 0.0141,
|
| 2081 |
+
"step": 1480
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 5.0,
|
| 2085 |
+
"step": 1480,
|
| 2086 |
+
"total_flos": 605863668678656.0,
|
| 2087 |
+
"train_loss": 0.36788542065266017,
|
| 2088 |
+
"train_runtime": 21782.9524,
|
| 2089 |
+
"train_samples_per_second": 2.171,
|
| 2090 |
+
"train_steps_per_second": 0.068
|
| 2091 |
+
}
|
| 2092 |
+
],
|
| 2093 |
+
"logging_steps": 5,
|
| 2094 |
+
"max_steps": 1480,
|
| 2095 |
+
"num_input_tokens_seen": 0,
|
| 2096 |
+
"num_train_epochs": 5,
|
| 2097 |
+
"save_steps": 500,
|
| 2098 |
+
"stateful_callbacks": {
|
| 2099 |
+
"TrainerControl": {
|
| 2100 |
+
"args": {
|
| 2101 |
+
"should_epoch_stop": false,
|
| 2102 |
+
"should_evaluate": false,
|
| 2103 |
+
"should_log": false,
|
| 2104 |
+
"should_save": true,
|
| 2105 |
+
"should_training_stop": true
|
| 2106 |
+
},
|
| 2107 |
+
"attributes": {}
|
| 2108 |
+
}
|
| 2109 |
+
},
|
| 2110 |
+
"total_flos": 605863668678656.0,
|
| 2111 |
+
"train_batch_size": 4,
|
| 2112 |
+
"trial_name": null,
|
| 2113 |
+
"trial_params": null
|
| 2114 |
+
}
|