Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +14 -0
- train_results.json +8 -0
- trainer_state.json +1756 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Open-R1-Distill
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Open-R1-Distill
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="nicolastzj/Qwen2.5-1.5B-Open-R1-Distill", 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 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0
|
| 38 |
+
- Transformers: 4.50.0
|
| 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": 489077052801024.0,
|
| 3 |
+
"train_loss": 0.5499481136067826,
|
| 4 |
+
"train_runtime": 13659.0836,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.512,
|
| 7 |
+
"train_steps_per_second": 0.079
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.50.0"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 489077052801024.0,
|
| 3 |
+
"train_loss": 0.5499481136067826,
|
| 4 |
+
"train_runtime": 13659.0836,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 2.512,
|
| 7 |
+
"train_steps_per_second": 0.079
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1073,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004659832246039142,
|
| 14 |
+
"grad_norm": 1.998449806393913,
|
| 15 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 16 |
+
"loss": 0.872,
|
| 17 |
+
"num_tokens": 2621440.0,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.009319664492078284,
|
| 22 |
+
"grad_norm": 1.256739479469204,
|
| 23 |
+
"learning_rate": 9.259259259259259e-06,
|
| 24 |
+
"loss": 0.8068,
|
| 25 |
+
"num_tokens": 5242880.0,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.013979496738117428,
|
| 30 |
+
"grad_norm": 1.1091509583062644,
|
| 31 |
+
"learning_rate": 1.388888888888889e-05,
|
| 32 |
+
"loss": 0.7748,
|
| 33 |
+
"num_tokens": 7864320.0,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.01863932898415657,
|
| 38 |
+
"grad_norm": 0.6322466417839099,
|
| 39 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 40 |
+
"loss": 0.7147,
|
| 41 |
+
"num_tokens": 10465392.0,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.023299161230195712,
|
| 46 |
+
"grad_norm": 0.6086481225962176,
|
| 47 |
+
"learning_rate": 2.314814814814815e-05,
|
| 48 |
+
"loss": 0.7004,
|
| 49 |
+
"num_tokens": 13086832.0,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.027958993476234855,
|
| 54 |
+
"grad_norm": 0.47016676042004046,
|
| 55 |
+
"learning_rate": 2.777777777777778e-05,
|
| 56 |
+
"loss": 0.6883,
|
| 57 |
+
"num_tokens": 15708272.0,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032618825722273995,
|
| 62 |
+
"grad_norm": 0.5176327524533699,
|
| 63 |
+
"learning_rate": 3.240740740740741e-05,
|
| 64 |
+
"loss": 0.6519,
|
| 65 |
+
"num_tokens": 18329712.0,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03727865796831314,
|
| 70 |
+
"grad_norm": 0.4773463314263538,
|
| 71 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 72 |
+
"loss": 0.6508,
|
| 73 |
+
"num_tokens": 20951152.0,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.04193849021435228,
|
| 78 |
+
"grad_norm": 0.4897990600343135,
|
| 79 |
+
"learning_rate": 4.166666666666667e-05,
|
| 80 |
+
"loss": 0.6394,
|
| 81 |
+
"num_tokens": 23572592.0,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.046598322460391424,
|
| 86 |
+
"grad_norm": 0.4586386344910554,
|
| 87 |
+
"learning_rate": 4.62962962962963e-05,
|
| 88 |
+
"loss": 0.6407,
|
| 89 |
+
"num_tokens": 26194032.0,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05125815470643057,
|
| 94 |
+
"grad_norm": 0.5242035067839318,
|
| 95 |
+
"learning_rate": 4.999989306901785e-05,
|
| 96 |
+
"loss": 0.6223,
|
| 97 |
+
"num_tokens": 28815472.0,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.05591798695246971,
|
| 102 |
+
"grad_norm": 0.4907568699268535,
|
| 103 |
+
"learning_rate": 4.999615059136074e-05,
|
| 104 |
+
"loss": 0.6337,
|
| 105 |
+
"num_tokens": 31436912.0,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06057781919850885,
|
| 110 |
+
"grad_norm": 0.48494637468440327,
|
| 111 |
+
"learning_rate": 4.9987062580928735e-05,
|
| 112 |
+
"loss": 0.6151,
|
| 113 |
+
"num_tokens": 34058352.0,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06523765144454799,
|
| 118 |
+
"grad_norm": 0.5204573463723345,
|
| 119 |
+
"learning_rate": 4.997263119721384e-05,
|
| 120 |
+
"loss": 0.6106,
|
| 121 |
+
"num_tokens": 36666389.0,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06989748369058714,
|
| 126 |
+
"grad_norm": 0.511345605671194,
|
| 127 |
+
"learning_rate": 4.995285986939984e-05,
|
| 128 |
+
"loss": 0.6137,
|
| 129 |
+
"num_tokens": 39287829.0,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.07455731593662628,
|
| 134 |
+
"grad_norm": 0.5458440715726992,
|
| 135 |
+
"learning_rate": 4.992775329554741e-05,
|
| 136 |
+
"loss": 0.608,
|
| 137 |
+
"num_tokens": 41909269.0,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.07921714818266543,
|
| 142 |
+
"grad_norm": 0.5292314383909796,
|
| 143 |
+
"learning_rate": 4.989731744147782e-05,
|
| 144 |
+
"loss": 0.6218,
|
| 145 |
+
"num_tokens": 44530709.0,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.08387698042870456,
|
| 150 |
+
"grad_norm": 0.5313608746777474,
|
| 151 |
+
"learning_rate": 4.98615595393553e-05,
|
| 152 |
+
"loss": 0.608,
|
| 153 |
+
"num_tokens": 47152149.0,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.08853681267474371,
|
| 158 |
+
"grad_norm": 0.5125462844723893,
|
| 159 |
+
"learning_rate": 4.9820488085968514e-05,
|
| 160 |
+
"loss": 0.6023,
|
| 161 |
+
"num_tokens": 49773589.0,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.09319664492078285,
|
| 166 |
+
"grad_norm": 0.5324438033561257,
|
| 167 |
+
"learning_rate": 4.9774112840711616e-05,
|
| 168 |
+
"loss": 0.5869,
|
| 169 |
+
"num_tokens": 52353719.0,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.097856477166822,
|
| 174 |
+
"grad_norm": 0.47538853167529876,
|
| 175 |
+
"learning_rate": 4.972244482326516e-05,
|
| 176 |
+
"loss": 0.6017,
|
| 177 |
+
"num_tokens": 54952917.0,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10251630941286113,
|
| 182 |
+
"grad_norm": 0.4413854744906226,
|
| 183 |
+
"learning_rate": 4.9665496310977647e-05,
|
| 184 |
+
"loss": 0.5976,
|
| 185 |
+
"num_tokens": 57574357.0,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.10717614165890028,
|
| 190 |
+
"grad_norm": 0.4448440531927556,
|
| 191 |
+
"learning_rate": 4.960328083594817e-05,
|
| 192 |
+
"loss": 0.5946,
|
| 193 |
+
"num_tokens": 60191231.0,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.11183597390493942,
|
| 198 |
+
"grad_norm": 0.45688972182826976,
|
| 199 |
+
"learning_rate": 4.953581318181091e-05,
|
| 200 |
+
"loss": 0.5968,
|
| 201 |
+
"num_tokens": 62792124.0,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.11649580615097857,
|
| 206 |
+
"grad_norm": 0.45814890396413577,
|
| 207 |
+
"learning_rate": 4.946310938022225e-05,
|
| 208 |
+
"loss": 0.5814,
|
| 209 |
+
"num_tokens": 65405812.0,
|
| 210 |
+
"step": 125
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.1211556383970177,
|
| 214 |
+
"grad_norm": 0.44108939383654355,
|
| 215 |
+
"learning_rate": 4.9385186707051365e-05,
|
| 216 |
+
"loss": 0.6095,
|
| 217 |
+
"num_tokens": 68027252.0,
|
| 218 |
+
"step": 130
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.12581547064305684,
|
| 222 |
+
"grad_norm": 0.4462451093951662,
|
| 223 |
+
"learning_rate": 4.93020636782751e-05,
|
| 224 |
+
"loss": 0.5886,
|
| 225 |
+
"num_tokens": 70648692.0,
|
| 226 |
+
"step": 135
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.13047530288909598,
|
| 230 |
+
"grad_norm": 0.546119960612233,
|
| 231 |
+
"learning_rate": 4.921376004557819e-05,
|
| 232 |
+
"loss": 0.5737,
|
| 233 |
+
"num_tokens": 73260442.0,
|
| 234 |
+
"step": 140
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.13513513513513514,
|
| 238 |
+
"grad_norm": 0.4110970339574924,
|
| 239 |
+
"learning_rate": 4.9120296791659924e-05,
|
| 240 |
+
"loss": 0.5797,
|
| 241 |
+
"num_tokens": 75881882.0,
|
| 242 |
+
"step": 145
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.13979496738117428,
|
| 246 |
+
"grad_norm": 0.49170509329372597,
|
| 247 |
+
"learning_rate": 4.902169612524819e-05,
|
| 248 |
+
"loss": 0.5854,
|
| 249 |
+
"num_tokens": 78503322.0,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.14445479962721341,
|
| 254 |
+
"grad_norm": 0.5237422035225896,
|
| 255 |
+
"learning_rate": 4.891798147582226e-05,
|
| 256 |
+
"loss": 0.5626,
|
| 257 |
+
"num_tokens": 81124762.0,
|
| 258 |
+
"step": 155
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.14911463187325255,
|
| 262 |
+
"grad_norm": 0.5482951099151655,
|
| 263 |
+
"learning_rate": 4.880917748804547e-05,
|
| 264 |
+
"loss": 0.5784,
|
| 265 |
+
"num_tokens": 83727556.0,
|
| 266 |
+
"step": 160
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.15377446411929171,
|
| 270 |
+
"grad_norm": 0.4787391010621317,
|
| 271 |
+
"learning_rate": 4.8695310015909164e-05,
|
| 272 |
+
"loss": 0.5789,
|
| 273 |
+
"num_tokens": 86348996.0,
|
| 274 |
+
"step": 165
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.15843429636533085,
|
| 278 |
+
"grad_norm": 0.42027445628314714,
|
| 279 |
+
"learning_rate": 4.8576406116589275e-05,
|
| 280 |
+
"loss": 0.5835,
|
| 281 |
+
"num_tokens": 88959058.0,
|
| 282 |
+
"step": 170
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16309412861137,
|
| 286 |
+
"grad_norm": 0.4791039950571978,
|
| 287 |
+
"learning_rate": 4.845249404401699e-05,
|
| 288 |
+
"loss": 0.5673,
|
| 289 |
+
"num_tokens": 91580498.0,
|
| 290 |
+
"step": 175
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.16775396085740912,
|
| 294 |
+
"grad_norm": 0.37678010058800837,
|
| 295 |
+
"learning_rate": 4.8323603242165074e-05,
|
| 296 |
+
"loss": 0.5803,
|
| 297 |
+
"num_tokens": 94201938.0,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1724137931034483,
|
| 302 |
+
"grad_norm": 0.4228477465487975,
|
| 303 |
+
"learning_rate": 4.818976433805137e-05,
|
| 304 |
+
"loss": 0.5686,
|
| 305 |
+
"num_tokens": 96817927.0,
|
| 306 |
+
"step": 185
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.17707362534948742,
|
| 310 |
+
"grad_norm": 0.429202278180492,
|
| 311 |
+
"learning_rate": 4.8051009134461225e-05,
|
| 312 |
+
"loss": 0.5766,
|
| 313 |
+
"num_tokens": 99432200.0,
|
| 314 |
+
"step": 190
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.18173345759552656,
|
| 318 |
+
"grad_norm": 0.55704551415839,
|
| 319 |
+
"learning_rate": 4.7907370602390526e-05,
|
| 320 |
+
"loss": 0.5679,
|
| 321 |
+
"num_tokens": 102049300.0,
|
| 322 |
+
"step": 195
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.1863932898415657,
|
| 326 |
+
"grad_norm": 0.4644938204189707,
|
| 327 |
+
"learning_rate": 4.775888287321112e-05,
|
| 328 |
+
"loss": 0.5768,
|
| 329 |
+
"num_tokens": 104670740.0,
|
| 330 |
+
"step": 200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.19105312208760486,
|
| 334 |
+
"grad_norm": 0.5294386888638182,
|
| 335 |
+
"learning_rate": 4.760558123056053e-05,
|
| 336 |
+
"loss": 0.5689,
|
| 337 |
+
"num_tokens": 107287613.0,
|
| 338 |
+
"step": 205
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.195712954333644,
|
| 342 |
+
"grad_norm": 0.46224965685117586,
|
| 343 |
+
"learning_rate": 4.744750210195784e-05,
|
| 344 |
+
"loss": 0.5831,
|
| 345 |
+
"num_tokens": 109909053.0,
|
| 346 |
+
"step": 210
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.20037278657968313,
|
| 350 |
+
"grad_norm": 0.5425533433102366,
|
| 351 |
+
"learning_rate": 4.728468305014781e-05,
|
| 352 |
+
"loss": 0.5786,
|
| 353 |
+
"num_tokens": 112530493.0,
|
| 354 |
+
"step": 215
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.20503261882572227,
|
| 358 |
+
"grad_norm": 0.42347749913911686,
|
| 359 |
+
"learning_rate": 4.7117162764175255e-05,
|
| 360 |
+
"loss": 0.5778,
|
| 361 |
+
"num_tokens": 115151933.0,
|
| 362 |
+
"step": 220
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.2096924510717614,
|
| 366 |
+
"grad_norm": 0.38692741901956657,
|
| 367 |
+
"learning_rate": 4.6944981050191676e-05,
|
| 368 |
+
"loss": 0.574,
|
| 369 |
+
"num_tokens": 117765441.0,
|
| 370 |
+
"step": 225
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.21435228331780057,
|
| 374 |
+
"grad_norm": 0.47676417314687364,
|
| 375 |
+
"learning_rate": 4.6768178821996615e-05,
|
| 376 |
+
"loss": 0.5739,
|
| 377 |
+
"num_tokens": 120376968.0,
|
| 378 |
+
"step": 230
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.2190121155638397,
|
| 382 |
+
"grad_norm": 0.4831661338365006,
|
| 383 |
+
"learning_rate": 4.6586798091315654e-05,
|
| 384 |
+
"loss": 0.5619,
|
| 385 |
+
"num_tokens": 122996669.0,
|
| 386 |
+
"step": 235
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.22367194780987884,
|
| 390 |
+
"grad_norm": 0.4834641257820034,
|
| 391 |
+
"learning_rate": 4.6400881957817626e-05,
|
| 392 |
+
"loss": 0.5647,
|
| 393 |
+
"num_tokens": 125607410.0,
|
| 394 |
+
"step": 240
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.22833178005591798,
|
| 398 |
+
"grad_norm": 0.46452138557419015,
|
| 399 |
+
"learning_rate": 4.621047459887328e-05,
|
| 400 |
+
"loss": 0.5683,
|
| 401 |
+
"num_tokens": 128215486.0,
|
| 402 |
+
"step": 245
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.23299161230195714,
|
| 406 |
+
"grad_norm": 0.3890160732358865,
|
| 407 |
+
"learning_rate": 4.601562125905785e-05,
|
| 408 |
+
"loss": 0.5633,
|
| 409 |
+
"num_tokens": 130831913.0,
|
| 410 |
+
"step": 250
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.23765144454799628,
|
| 414 |
+
"grad_norm": 0.3885400524730455,
|
| 415 |
+
"learning_rate": 4.581636823940004e-05,
|
| 416 |
+
"loss": 0.5571,
|
| 417 |
+
"num_tokens": 133447076.0,
|
| 418 |
+
"step": 255
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.2423112767940354,
|
| 422 |
+
"grad_norm": 0.4051804433465413,
|
| 423 |
+
"learning_rate": 4.561276288637997e-05,
|
| 424 |
+
"loss": 0.5761,
|
| 425 |
+
"num_tokens": 136036466.0,
|
| 426 |
+
"step": 260
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.24697110904007455,
|
| 430 |
+
"grad_norm": 0.3869612039115619,
|
| 431 |
+
"learning_rate": 4.5404853580678756e-05,
|
| 432 |
+
"loss": 0.5668,
|
| 433 |
+
"num_tokens": 138657906.0,
|
| 434 |
+
"step": 265
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.2516309412861137,
|
| 438 |
+
"grad_norm": 0.3824203954374748,
|
| 439 |
+
"learning_rate": 4.5192689725682245e-05,
|
| 440 |
+
"loss": 0.5639,
|
| 441 |
+
"num_tokens": 141273912.0,
|
| 442 |
+
"step": 270
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.25629077353215285,
|
| 446 |
+
"grad_norm": 0.43425853343882076,
|
| 447 |
+
"learning_rate": 4.497632173574181e-05,
|
| 448 |
+
"loss": 0.558,
|
| 449 |
+
"num_tokens": 143880811.0,
|
| 450 |
+
"step": 275
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.26095060577819196,
|
| 454 |
+
"grad_norm": 0.5082236509259811,
|
| 455 |
+
"learning_rate": 4.475580102419491e-05,
|
| 456 |
+
"loss": 0.566,
|
| 457 |
+
"num_tokens": 146502251.0,
|
| 458 |
+
"step": 280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2656104380242311,
|
| 462 |
+
"grad_norm": 0.4389702184002063,
|
| 463 |
+
"learning_rate": 4.453117999114822e-05,
|
| 464 |
+
"loss": 0.5583,
|
| 465 |
+
"num_tokens": 149113471.0,
|
| 466 |
+
"step": 285
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.2702702702702703,
|
| 470 |
+
"grad_norm": 0.4092125654916106,
|
| 471 |
+
"learning_rate": 4.4302512011026374e-05,
|
| 472 |
+
"loss": 0.562,
|
| 473 |
+
"num_tokens": 151734911.0,
|
| 474 |
+
"step": 290
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.2749301025163094,
|
| 478 |
+
"grad_norm": 0.43304579044765457,
|
| 479 |
+
"learning_rate": 4.406985141988911e-05,
|
| 480 |
+
"loss": 0.5694,
|
| 481 |
+
"num_tokens": 154356351.0,
|
| 482 |
+
"step": 295
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.27958993476234856,
|
| 486 |
+
"grad_norm": 0.4401168079359455,
|
| 487 |
+
"learning_rate": 4.383325350251993e-05,
|
| 488 |
+
"loss": 0.5555,
|
| 489 |
+
"num_tokens": 156977308.0,
|
| 490 |
+
"step": 300
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.2842497670083877,
|
| 494 |
+
"grad_norm": 0.40023075838141015,
|
| 495 |
+
"learning_rate": 4.359277447928938e-05,
|
| 496 |
+
"loss": 0.5539,
|
| 497 |
+
"num_tokens": 159598748.0,
|
| 498 |
+
"step": 305
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.28890959925442683,
|
| 502 |
+
"grad_norm": 0.3888784489132035,
|
| 503 |
+
"learning_rate": 4.3348471492795916e-05,
|
| 504 |
+
"loss": 0.5481,
|
| 505 |
+
"num_tokens": 162220188.0,
|
| 506 |
+
"step": 310
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.293569431500466,
|
| 510 |
+
"grad_norm": 0.3530018272721705,
|
| 511 |
+
"learning_rate": 4.310040259428774e-05,
|
| 512 |
+
"loss": 0.5608,
|
| 513 |
+
"num_tokens": 164828478.0,
|
| 514 |
+
"step": 315
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2982292637465051,
|
| 518 |
+
"grad_norm": 0.4540512283549639,
|
| 519 |
+
"learning_rate": 4.2848626729868625e-05,
|
| 520 |
+
"loss": 0.558,
|
| 521 |
+
"num_tokens": 167423794.0,
|
| 522 |
+
"step": 320
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.30288909599254427,
|
| 526 |
+
"grad_norm": 0.39220355050306954,
|
| 527 |
+
"learning_rate": 4.259320372649117e-05,
|
| 528 |
+
"loss": 0.5488,
|
| 529 |
+
"num_tokens": 170045234.0,
|
| 530 |
+
"step": 325
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.30754892823858343,
|
| 534 |
+
"grad_norm": 0.3832162907954315,
|
| 535 |
+
"learning_rate": 4.233419427774074e-05,
|
| 536 |
+
"loss": 0.5443,
|
| 537 |
+
"num_tokens": 172657586.0,
|
| 538 |
+
"step": 330
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.31220876048462254,
|
| 542 |
+
"grad_norm": 0.35517274554952427,
|
| 543 |
+
"learning_rate": 4.207165992941342e-05,
|
| 544 |
+
"loss": 0.5489,
|
| 545 |
+
"num_tokens": 175279026.0,
|
| 546 |
+
"step": 335
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.3168685927306617,
|
| 550 |
+
"grad_norm": 0.4281597539197837,
|
| 551 |
+
"learning_rate": 4.1805663064891564e-05,
|
| 552 |
+
"loss": 0.5494,
|
| 553 |
+
"num_tokens": 177900466.0,
|
| 554 |
+
"step": 340
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.32152842497670087,
|
| 558 |
+
"grad_norm": 0.5001190538270193,
|
| 559 |
+
"learning_rate": 4.153626689032021e-05,
|
| 560 |
+
"loss": 0.559,
|
| 561 |
+
"num_tokens": 180509493.0,
|
| 562 |
+
"step": 345
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.32618825722274,
|
| 566 |
+
"grad_norm": 0.49296401671267065,
|
| 567 |
+
"learning_rate": 4.1263535419588095e-05,
|
| 568 |
+
"loss": 0.5492,
|
| 569 |
+
"num_tokens": 183130933.0,
|
| 570 |
+
"step": 350
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.33084808946877914,
|
| 574 |
+
"grad_norm": 0.3828042143578297,
|
| 575 |
+
"learning_rate": 4.0987533459116615e-05,
|
| 576 |
+
"loss": 0.5508,
|
| 577 |
+
"num_tokens": 185752373.0,
|
| 578 |
+
"step": 355
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.33550792171481825,
|
| 582 |
+
"grad_norm": 0.4176449923313789,
|
| 583 |
+
"learning_rate": 4.0708326592460606e-05,
|
| 584 |
+
"loss": 0.5475,
|
| 585 |
+
"num_tokens": 188373813.0,
|
| 586 |
+
"step": 360
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.3401677539608574,
|
| 590 |
+
"grad_norm": 0.4418002253376823,
|
| 591 |
+
"learning_rate": 4.0425981164724344e-05,
|
| 592 |
+
"loss": 0.5594,
|
| 593 |
+
"num_tokens": 190995062.0,
|
| 594 |
+
"step": 365
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.3448275862068966,
|
| 598 |
+
"grad_norm": 0.3929605148670868,
|
| 599 |
+
"learning_rate": 4.014056426679663e-05,
|
| 600 |
+
"loss": 0.5517,
|
| 601 |
+
"num_tokens": 193616502.0,
|
| 602 |
+
"step": 370
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.3494874184529357,
|
| 606 |
+
"grad_norm": 0.4306146052326153,
|
| 607 |
+
"learning_rate": 3.9852143719408665e-05,
|
| 608 |
+
"loss": 0.5528,
|
| 609 |
+
"num_tokens": 196237942.0,
|
| 610 |
+
"step": 375
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.35414725069897485,
|
| 614 |
+
"grad_norm": 0.3963350882877667,
|
| 615 |
+
"learning_rate": 3.956078805701849e-05,
|
| 616 |
+
"loss": 0.5365,
|
| 617 |
+
"num_tokens": 198859382.0,
|
| 618 |
+
"step": 380
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.35880708294501396,
|
| 622 |
+
"grad_norm": 0.36919376066976295,
|
| 623 |
+
"learning_rate": 3.926656651152588e-05,
|
| 624 |
+
"loss": 0.5416,
|
| 625 |
+
"num_tokens": 201480822.0,
|
| 626 |
+
"step": 385
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3634669151910531,
|
| 630 |
+
"grad_norm": 0.3813818124725696,
|
| 631 |
+
"learning_rate": 3.896954899582137e-05,
|
| 632 |
+
"loss": 0.546,
|
| 633 |
+
"num_tokens": 204102262.0,
|
| 634 |
+
"step": 390
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.3681267474370923,
|
| 638 |
+
"grad_norm": 0.37003535585302494,
|
| 639 |
+
"learning_rate": 3.8669806087173693e-05,
|
| 640 |
+
"loss": 0.55,
|
| 641 |
+
"num_tokens": 206723702.0,
|
| 642 |
+
"step": 395
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.3727865796831314,
|
| 646 |
+
"grad_norm": 0.3307085809925778,
|
| 647 |
+
"learning_rate": 3.8367409010459074e-05,
|
| 648 |
+
"loss": 0.5494,
|
| 649 |
+
"num_tokens": 209345142.0,
|
| 650 |
+
"step": 400
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.37744641192917056,
|
| 654 |
+
"grad_norm": 0.352044882470442,
|
| 655 |
+
"learning_rate": 3.806242962123692e-05,
|
| 656 |
+
"loss": 0.5506,
|
| 657 |
+
"num_tokens": 211966582.0,
|
| 658 |
+
"step": 405
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.3821062441752097,
|
| 662 |
+
"grad_norm": 0.37835031784481976,
|
| 663 |
+
"learning_rate": 3.77549403886754e-05,
|
| 664 |
+
"loss": 0.5423,
|
| 665 |
+
"num_tokens": 214586037.0,
|
| 666 |
+
"step": 410
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.38676607642124883,
|
| 670 |
+
"grad_norm": 0.3546636336054353,
|
| 671 |
+
"learning_rate": 3.74450143783314e-05,
|
| 672 |
+
"loss": 0.5342,
|
| 673 |
+
"num_tokens": 217207477.0,
|
| 674 |
+
"step": 415
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.391425908667288,
|
| 678 |
+
"grad_norm": 0.4496324303788921,
|
| 679 |
+
"learning_rate": 3.713272523478867e-05,
|
| 680 |
+
"loss": 0.5564,
|
| 681 |
+
"num_tokens": 219820636.0,
|
| 682 |
+
"step": 420
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.3960857409133271,
|
| 686 |
+
"grad_norm": 0.39935576087862956,
|
| 687 |
+
"learning_rate": 3.6818147164158374e-05,
|
| 688 |
+
"loss": 0.5361,
|
| 689 |
+
"num_tokens": 222442076.0,
|
| 690 |
+
"step": 425
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.40074557315936626,
|
| 694 |
+
"grad_norm": 0.43545551941242694,
|
| 695 |
+
"learning_rate": 3.650135491644632e-05,
|
| 696 |
+
"loss": 0.5347,
|
| 697 |
+
"num_tokens": 225063516.0,
|
| 698 |
+
"step": 430
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.40540540540540543,
|
| 702 |
+
"grad_norm": 0.43333557421048186,
|
| 703 |
+
"learning_rate": 3.618242376779078e-05,
|
| 704 |
+
"loss": 0.5413,
|
| 705 |
+
"num_tokens": 227684956.0,
|
| 706 |
+
"step": 435
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.41006523765144454,
|
| 710 |
+
"grad_norm": 0.3858417873809833,
|
| 711 |
+
"learning_rate": 3.5861429502575474e-05,
|
| 712 |
+
"loss": 0.5397,
|
| 713 |
+
"num_tokens": 230306396.0,
|
| 714 |
+
"step": 440
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4147250698974837,
|
| 718 |
+
"grad_norm": 0.36647391805709406,
|
| 719 |
+
"learning_rate": 3.55384483954216e-05,
|
| 720 |
+
"loss": 0.5424,
|
| 721 |
+
"num_tokens": 232927836.0,
|
| 722 |
+
"step": 445
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.4193849021435228,
|
| 726 |
+
"grad_norm": 0.337022005682903,
|
| 727 |
+
"learning_rate": 3.521355719306354e-05,
|
| 728 |
+
"loss": 0.5359,
|
| 729 |
+
"num_tokens": 235549276.0,
|
| 730 |
+
"step": 450
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.424044734389562,
|
| 734 |
+
"grad_norm": 0.41508200394702593,
|
| 735 |
+
"learning_rate": 3.488683309611229e-05,
|
| 736 |
+
"loss": 0.5372,
|
| 737 |
+
"num_tokens": 238170716.0,
|
| 738 |
+
"step": 455
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.42870456663560114,
|
| 742 |
+
"grad_norm": 0.36749255381110946,
|
| 743 |
+
"learning_rate": 3.455835374071104e-05,
|
| 744 |
+
"loss": 0.5485,
|
| 745 |
+
"num_tokens": 240792156.0,
|
| 746 |
+
"step": 460
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.43336439888164024,
|
| 750 |
+
"grad_norm": 0.4042736719765033,
|
| 751 |
+
"learning_rate": 3.422819718008729e-05,
|
| 752 |
+
"loss": 0.5412,
|
| 753 |
+
"num_tokens": 243413596.0,
|
| 754 |
+
"step": 465
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.4380242311276794,
|
| 758 |
+
"grad_norm": 0.3624283509782478,
|
| 759 |
+
"learning_rate": 3.389644186600587e-05,
|
| 760 |
+
"loss": 0.5337,
|
| 761 |
+
"num_tokens": 246029886.0,
|
| 762 |
+
"step": 470
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.4426840633737186,
|
| 766 |
+
"grad_norm": 0.33123648036491127,
|
| 767 |
+
"learning_rate": 3.356316663012723e-05,
|
| 768 |
+
"loss": 0.5462,
|
| 769 |
+
"num_tokens": 248637925.0,
|
| 770 |
+
"step": 475
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.4473438956197577,
|
| 774 |
+
"grad_norm": 0.3889858576939345,
|
| 775 |
+
"learning_rate": 3.3228450665275444e-05,
|
| 776 |
+
"loss": 0.5357,
|
| 777 |
+
"num_tokens": 251259365.0,
|
| 778 |
+
"step": 480
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.45200372786579684,
|
| 782 |
+
"grad_norm": 0.3785036602219516,
|
| 783 |
+
"learning_rate": 3.289237350662047e-05,
|
| 784 |
+
"loss": 0.5396,
|
| 785 |
+
"num_tokens": 253880805.0,
|
| 786 |
+
"step": 485
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.45666356011183595,
|
| 790 |
+
"grad_norm": 0.4353747155378151,
|
| 791 |
+
"learning_rate": 3.255501501277896e-05,
|
| 792 |
+
"loss": 0.5549,
|
| 793 |
+
"num_tokens": 256502245.0,
|
| 794 |
+
"step": 490
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4613233923578751,
|
| 798 |
+
"grad_norm": 0.4050741703062612,
|
| 799 |
+
"learning_rate": 3.221645534683832e-05,
|
| 800 |
+
"loss": 0.5399,
|
| 801 |
+
"num_tokens": 259123685.0,
|
| 802 |
+
"step": 495
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.4659832246039143,
|
| 806 |
+
"grad_norm": 0.4866921553849842,
|
| 807 |
+
"learning_rate": 3.187677495730829e-05,
|
| 808 |
+
"loss": 0.5358,
|
| 809 |
+
"num_tokens": 261736444.0,
|
| 810 |
+
"step": 500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.4706430568499534,
|
| 814 |
+
"grad_norm": 0.4587943402420001,
|
| 815 |
+
"learning_rate": 3.153605455900487e-05,
|
| 816 |
+
"loss": 0.5439,
|
| 817 |
+
"num_tokens": 264341546.0,
|
| 818 |
+
"step": 505
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.47530288909599255,
|
| 822 |
+
"grad_norm": 0.38829538173868505,
|
| 823 |
+
"learning_rate": 3.11943751138708e-05,
|
| 824 |
+
"loss": 0.5462,
|
| 825 |
+
"num_tokens": 266962986.0,
|
| 826 |
+
"step": 510
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.47996272134203166,
|
| 830 |
+
"grad_norm": 0.3730180664198904,
|
| 831 |
+
"learning_rate": 3.0851817811737425e-05,
|
| 832 |
+
"loss": 0.5391,
|
| 833 |
+
"num_tokens": 269584426.0,
|
| 834 |
+
"step": 515
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.4846225535880708,
|
| 838 |
+
"grad_norm": 0.37866232943446554,
|
| 839 |
+
"learning_rate": 3.0508464051032376e-05,
|
| 840 |
+
"loss": 0.5354,
|
| 841 |
+
"num_tokens": 272205866.0,
|
| 842 |
+
"step": 520
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.48928238583411,
|
| 846 |
+
"grad_norm": 0.3996473635616858,
|
| 847 |
+
"learning_rate": 3.016439541943768e-05,
|
| 848 |
+
"loss": 0.542,
|
| 849 |
+
"num_tokens": 274825267.0,
|
| 850 |
+
"step": 525
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.4939422180801491,
|
| 854 |
+
"grad_norm": 0.3690068819352055,
|
| 855 |
+
"learning_rate": 2.9819693674502906e-05,
|
| 856 |
+
"loss": 0.5371,
|
| 857 |
+
"num_tokens": 277446221.0,
|
| 858 |
+
"step": 530
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.49860205032618826,
|
| 862 |
+
"grad_norm": 0.33041792129305897,
|
| 863 |
+
"learning_rate": 2.9474440724217926e-05,
|
| 864 |
+
"loss": 0.5277,
|
| 865 |
+
"num_tokens": 280061887.0,
|
| 866 |
+
"step": 535
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5032618825722274,
|
| 870 |
+
"grad_norm": 0.4049882691952909,
|
| 871 |
+
"learning_rate": 2.9128718607549994e-05,
|
| 872 |
+
"loss": 0.5382,
|
| 873 |
+
"num_tokens": 282683327.0,
|
| 874 |
+
"step": 540
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.5079217148182665,
|
| 878 |
+
"grad_norm": 0.3880881979544033,
|
| 879 |
+
"learning_rate": 2.878260947494961e-05,
|
| 880 |
+
"loss": 0.5467,
|
| 881 |
+
"num_tokens": 285291439.0,
|
| 882 |
+
"step": 545
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.5125815470643057,
|
| 886 |
+
"grad_norm": 0.3676763284615962,
|
| 887 |
+
"learning_rate": 2.8436195568829943e-05,
|
| 888 |
+
"loss": 0.5335,
|
| 889 |
+
"num_tokens": 287912879.0,
|
| 890 |
+
"step": 550
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.5172413793103449,
|
| 894 |
+
"grad_norm": 0.3573053418195904,
|
| 895 |
+
"learning_rate": 2.8089559204024457e-05,
|
| 896 |
+
"loss": 0.5464,
|
| 897 |
+
"num_tokens": 290525783.0,
|
| 898 |
+
"step": 555
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5219012115563839,
|
| 902 |
+
"grad_norm": 0.3688702244339766,
|
| 903 |
+
"learning_rate": 2.7742782748227176e-05,
|
| 904 |
+
"loss": 0.5267,
|
| 905 |
+
"num_tokens": 293122806.0,
|
| 906 |
+
"step": 560
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5265610438024231,
|
| 910 |
+
"grad_norm": 0.3264982445089474,
|
| 911 |
+
"learning_rate": 2.739594860242054e-05,
|
| 912 |
+
"loss": 0.5447,
|
| 913 |
+
"num_tokens": 295734627.0,
|
| 914 |
+
"step": 565
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.5312208760484622,
|
| 918 |
+
"grad_norm": 0.37218016393262376,
|
| 919 |
+
"learning_rate": 2.7049139181295312e-05,
|
| 920 |
+
"loss": 0.5366,
|
| 921 |
+
"num_tokens": 298356067.0,
|
| 922 |
+
"step": 570
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.5358807082945014,
|
| 926 |
+
"grad_norm": 0.40949056037443726,
|
| 927 |
+
"learning_rate": 2.6702436893667138e-05,
|
| 928 |
+
"loss": 0.5338,
|
| 929 |
+
"num_tokens": 300977507.0,
|
| 930 |
+
"step": 575
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.5405405405405406,
|
| 934 |
+
"grad_norm": 0.44953426948977215,
|
| 935 |
+
"learning_rate": 2.6355924122894643e-05,
|
| 936 |
+
"loss": 0.5357,
|
| 937 |
+
"num_tokens": 303598947.0,
|
| 938 |
+
"step": 580
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.5452003727865797,
|
| 942 |
+
"grad_norm": 0.37235757303090433,
|
| 943 |
+
"learning_rate": 2.6009683207303477e-05,
|
| 944 |
+
"loss": 0.5379,
|
| 945 |
+
"num_tokens": 306213321.0,
|
| 946 |
+
"step": 585
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.5498602050326188,
|
| 950 |
+
"grad_norm": 0.3114124146988319,
|
| 951 |
+
"learning_rate": 2.5663796420621073e-05,
|
| 952 |
+
"loss": 0.5425,
|
| 953 |
+
"num_tokens": 308834761.0,
|
| 954 |
+
"step": 590
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.554520037278658,
|
| 958 |
+
"grad_norm": 0.29340628937505203,
|
| 959 |
+
"learning_rate": 2.5318345952426808e-05,
|
| 960 |
+
"loss": 0.524,
|
| 961 |
+
"num_tokens": 311456201.0,
|
| 962 |
+
"step": 595
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5591798695246971,
|
| 966 |
+
"grad_norm": 0.32681730311572604,
|
| 967 |
+
"learning_rate": 2.4973413888622105e-05,
|
| 968 |
+
"loss": 0.5326,
|
| 969 |
+
"num_tokens": 314077641.0,
|
| 970 |
+
"step": 600
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.5638397017707363,
|
| 974 |
+
"grad_norm": 0.30856771349437806,
|
| 975 |
+
"learning_rate": 2.4629082191925196e-05,
|
| 976 |
+
"loss": 0.528,
|
| 977 |
+
"num_tokens": 316699081.0,
|
| 978 |
+
"step": 605
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.5684995340167754,
|
| 982 |
+
"grad_norm": 0.3391949427770666,
|
| 983 |
+
"learning_rate": 2.4285432682395144e-05,
|
| 984 |
+
"loss": 0.5249,
|
| 985 |
+
"num_tokens": 319309553.0,
|
| 986 |
+
"step": 610
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.5731593662628145,
|
| 990 |
+
"grad_norm": 0.34366076846099736,
|
| 991 |
+
"learning_rate": 2.3942547017989775e-05,
|
| 992 |
+
"loss": 0.5214,
|
| 993 |
+
"num_tokens": 321923946.0,
|
| 994 |
+
"step": 615
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.5778191985088537,
|
| 998 |
+
"grad_norm": 0.34342395182840796,
|
| 999 |
+
"learning_rate": 2.3600506675162127e-05,
|
| 1000 |
+
"loss": 0.5259,
|
| 1001 |
+
"num_tokens": 324545386.0,
|
| 1002 |
+
"step": 620
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.5824790307548928,
|
| 1006 |
+
"grad_norm": 0.34236650485422987,
|
| 1007 |
+
"learning_rate": 2.3259392929500012e-05,
|
| 1008 |
+
"loss": 0.5278,
|
| 1009 |
+
"num_tokens": 327166826.0,
|
| 1010 |
+
"step": 625
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.587138863000932,
|
| 1014 |
+
"grad_norm": 0.3504672454637485,
|
| 1015 |
+
"learning_rate": 2.291928683641334e-05,
|
| 1016 |
+
"loss": 0.5458,
|
| 1017 |
+
"num_tokens": 329788266.0,
|
| 1018 |
+
"step": 630
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5917986952469712,
|
| 1022 |
+
"grad_norm": 0.355920545900854,
|
| 1023 |
+
"learning_rate": 2.2580269211873718e-05,
|
| 1024 |
+
"loss": 0.5477,
|
| 1025 |
+
"num_tokens": 332409706.0,
|
| 1026 |
+
"step": 635
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.5964585274930102,
|
| 1030 |
+
"grad_norm": 0.3154817635849218,
|
| 1031 |
+
"learning_rate": 2.2242420613210983e-05,
|
| 1032 |
+
"loss": 0.5253,
|
| 1033 |
+
"num_tokens": 335031146.0,
|
| 1034 |
+
"step": 640
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6011183597390494,
|
| 1038 |
+
"grad_norm": 0.34687948323417755,
|
| 1039 |
+
"learning_rate": 2.1905821319971172e-05,
|
| 1040 |
+
"loss": 0.5154,
|
| 1041 |
+
"num_tokens": 337649451.0,
|
| 1042 |
+
"step": 645
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.6057781919850885,
|
| 1046 |
+
"grad_norm": 0.3217303319364846,
|
| 1047 |
+
"learning_rate": 2.1570551314840516e-05,
|
| 1048 |
+
"loss": 0.5198,
|
| 1049 |
+
"num_tokens": 340270891.0,
|
| 1050 |
+
"step": 650
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.6104380242311277,
|
| 1054 |
+
"grad_norm": 0.3817310796038483,
|
| 1055 |
+
"learning_rate": 2.1236690264639942e-05,
|
| 1056 |
+
"loss": 0.524,
|
| 1057 |
+
"num_tokens": 342889310.0,
|
| 1058 |
+
"step": 655
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.6150978564771669,
|
| 1062 |
+
"grad_norm": 0.31813978968484635,
|
| 1063 |
+
"learning_rate": 2.0904317501394677e-05,
|
| 1064 |
+
"loss": 0.5087,
|
| 1065 |
+
"num_tokens": 345504904.0,
|
| 1066 |
+
"step": 660
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6197576887232059,
|
| 1070 |
+
"grad_norm": 0.3224766506891993,
|
| 1071 |
+
"learning_rate": 2.0573512003483364e-05,
|
| 1072 |
+
"loss": 0.5256,
|
| 1073 |
+
"num_tokens": 348126344.0,
|
| 1074 |
+
"step": 665
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6244175209692451,
|
| 1078 |
+
"grad_norm": 0.4124524670248634,
|
| 1079 |
+
"learning_rate": 2.0244352376871227e-05,
|
| 1080 |
+
"loss": 0.5189,
|
| 1081 |
+
"num_tokens": 350734169.0,
|
| 1082 |
+
"step": 670
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.6290773532152842,
|
| 1086 |
+
"grad_norm": 0.32699397384931833,
|
| 1087 |
+
"learning_rate": 1.9916916836431753e-05,
|
| 1088 |
+
"loss": 0.5386,
|
| 1089 |
+
"num_tokens": 353342019.0,
|
| 1090 |
+
"step": 675
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.6337371854613234,
|
| 1094 |
+
"grad_norm": 0.35065707617633546,
|
| 1095 |
+
"learning_rate": 1.9591283187361252e-05,
|
| 1096 |
+
"loss": 0.5211,
|
| 1097 |
+
"num_tokens": 355956520.0,
|
| 1098 |
+
"step": 680
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.6383970177073626,
|
| 1102 |
+
"grad_norm": 0.2980338394469612,
|
| 1103 |
+
"learning_rate": 1.9267528806690816e-05,
|
| 1104 |
+
"loss": 0.5241,
|
| 1105 |
+
"num_tokens": 358570028.0,
|
| 1106 |
+
"step": 685
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.6430568499534017,
|
| 1110 |
+
"grad_norm": 0.3227338261481323,
|
| 1111 |
+
"learning_rate": 1.8945730624899976e-05,
|
| 1112 |
+
"loss": 0.5352,
|
| 1113 |
+
"num_tokens": 361191468.0,
|
| 1114 |
+
"step": 690
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.6477166821994408,
|
| 1118 |
+
"grad_norm": 0.32043155003091367,
|
| 1119 |
+
"learning_rate": 1.8625965107636544e-05,
|
| 1120 |
+
"loss": 0.5166,
|
| 1121 |
+
"num_tokens": 363812908.0,
|
| 1122 |
+
"step": 695
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.65237651444548,
|
| 1126 |
+
"grad_norm": 0.3648515865996954,
|
| 1127 |
+
"learning_rate": 1.8308308237546762e-05,
|
| 1128 |
+
"loss": 0.5298,
|
| 1129 |
+
"num_tokens": 366434348.0,
|
| 1130 |
+
"step": 700
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6570363466915191,
|
| 1134 |
+
"grad_norm": 0.37389946535051116,
|
| 1135 |
+
"learning_rate": 1.7992835496220416e-05,
|
| 1136 |
+
"loss": 0.5288,
|
| 1137 |
+
"num_tokens": 369055788.0,
|
| 1138 |
+
"step": 705
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.6616961789375583,
|
| 1142 |
+
"grad_norm": 0.3034664742128409,
|
| 1143 |
+
"learning_rate": 1.7679621846254836e-05,
|
| 1144 |
+
"loss": 0.5343,
|
| 1145 |
+
"num_tokens": 371677228.0,
|
| 1146 |
+
"step": 710
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.6663560111835974,
|
| 1150 |
+
"grad_norm": 0.328914891312262,
|
| 1151 |
+
"learning_rate": 1.736874171344232e-05,
|
| 1152 |
+
"loss": 0.5189,
|
| 1153 |
+
"num_tokens": 374298668.0,
|
| 1154 |
+
"step": 715
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.6710158434296365,
|
| 1158 |
+
"grad_norm": 0.3090206804534066,
|
| 1159 |
+
"learning_rate": 1.706026896908507e-05,
|
| 1160 |
+
"loss": 0.5338,
|
| 1161 |
+
"num_tokens": 376908695.0,
|
| 1162 |
+
"step": 720
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.6756756756756757,
|
| 1166 |
+
"grad_norm": 0.3192942324698935,
|
| 1167 |
+
"learning_rate": 1.6754276912441947e-05,
|
| 1168 |
+
"loss": 0.5392,
|
| 1169 |
+
"num_tokens": 379526026.0,
|
| 1170 |
+
"step": 725
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.6803355079217148,
|
| 1174 |
+
"grad_norm": 0.3372174234895642,
|
| 1175 |
+
"learning_rate": 1.645083825331104e-05,
|
| 1176 |
+
"loss": 0.5337,
|
| 1177 |
+
"num_tokens": 382146337.0,
|
| 1178 |
+
"step": 730
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.684995340167754,
|
| 1182 |
+
"grad_norm": 0.3282721933361981,
|
| 1183 |
+
"learning_rate": 1.6150025094752447e-05,
|
| 1184 |
+
"loss": 0.5231,
|
| 1185 |
+
"num_tokens": 384767777.0,
|
| 1186 |
+
"step": 735
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6896551724137931,
|
| 1190 |
+
"grad_norm": 0.34317450659314563,
|
| 1191 |
+
"learning_rate": 1.585190891595507e-05,
|
| 1192 |
+
"loss": 0.5286,
|
| 1193 |
+
"num_tokens": 387384301.0,
|
| 1194 |
+
"step": 740
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.6943150046598322,
|
| 1198 |
+
"grad_norm": 0.2732139951154636,
|
| 1199 |
+
"learning_rate": 1.555656055525181e-05,
|
| 1200 |
+
"loss": 0.5167,
|
| 1201 |
+
"num_tokens": 390005741.0,
|
| 1202 |
+
"step": 745
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.6989748369058714,
|
| 1206 |
+
"grad_norm": 0.2941779597956366,
|
| 1207 |
+
"learning_rate": 1.5264050193286954e-05,
|
| 1208 |
+
"loss": 0.5173,
|
| 1209 |
+
"num_tokens": 392611427.0,
|
| 1210 |
+
"step": 750
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.7036346691519105,
|
| 1214 |
+
"grad_norm": 0.3069143377644817,
|
| 1215 |
+
"learning_rate": 1.497444733633982e-05,
|
| 1216 |
+
"loss": 0.5333,
|
| 1217 |
+
"num_tokens": 395213883.0,
|
| 1218 |
+
"step": 755
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.7082945013979497,
|
| 1222 |
+
"grad_norm": 0.30111041380792275,
|
| 1223 |
+
"learning_rate": 1.4687820799808719e-05,
|
| 1224 |
+
"loss": 0.5197,
|
| 1225 |
+
"num_tokens": 397835323.0,
|
| 1226 |
+
"step": 760
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.7129543336439889,
|
| 1230 |
+
"grad_norm": 0.3357207033661807,
|
| 1231 |
+
"learning_rate": 1.4404238691859062e-05,
|
| 1232 |
+
"loss": 0.516,
|
| 1233 |
+
"num_tokens": 400443842.0,
|
| 1234 |
+
"step": 765
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7176141658900279,
|
| 1238 |
+
"grad_norm": 0.27150504050082613,
|
| 1239 |
+
"learning_rate": 1.4123768397239456e-05,
|
| 1240 |
+
"loss": 0.5224,
|
| 1241 |
+
"num_tokens": 403065282.0,
|
| 1242 |
+
"step": 770
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7222739981360671,
|
| 1246 |
+
"grad_norm": 0.2916567078355186,
|
| 1247 |
+
"learning_rate": 1.3846476561269767e-05,
|
| 1248 |
+
"loss": 0.519,
|
| 1249 |
+
"num_tokens": 405686722.0,
|
| 1250 |
+
"step": 775
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.7269338303821062,
|
| 1254 |
+
"grad_norm": 0.2630940238225838,
|
| 1255 |
+
"learning_rate": 1.357242907400492e-05,
|
| 1256 |
+
"loss": 0.524,
|
| 1257 |
+
"num_tokens": 408298322.0,
|
| 1258 |
+
"step": 780
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.7315936626281454,
|
| 1262 |
+
"grad_norm": 0.27190388528430437,
|
| 1263 |
+
"learning_rate": 1.330169105457802e-05,
|
| 1264 |
+
"loss": 0.5359,
|
| 1265 |
+
"num_tokens": 410917246.0,
|
| 1266 |
+
"step": 785
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.7362534948741846,
|
| 1270 |
+
"grad_norm": 0.2802779467199635,
|
| 1271 |
+
"learning_rate": 1.3034326835726802e-05,
|
| 1272 |
+
"loss": 0.5242,
|
| 1273 |
+
"num_tokens": 413538686.0,
|
| 1274 |
+
"step": 790
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.7409133271202236,
|
| 1278 |
+
"grad_norm": 0.2968719752067062,
|
| 1279 |
+
"learning_rate": 1.2770399948506906e-05,
|
| 1280 |
+
"loss": 0.5137,
|
| 1281 |
+
"num_tokens": 416160126.0,
|
| 1282 |
+
"step": 795
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.7455731593662628,
|
| 1286 |
+
"grad_norm": 0.28947826623097084,
|
| 1287 |
+
"learning_rate": 1.2509973107195624e-05,
|
| 1288 |
+
"loss": 0.5304,
|
| 1289 |
+
"num_tokens": 418781566.0,
|
| 1290 |
+
"step": 800
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.750232991612302,
|
| 1294 |
+
"grad_norm": 0.31936379000510656,
|
| 1295 |
+
"learning_rate": 1.2253108194389685e-05,
|
| 1296 |
+
"loss": 0.5174,
|
| 1297 |
+
"num_tokens": 421401116.0,
|
| 1298 |
+
"step": 805
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7548928238583411,
|
| 1302 |
+
"grad_norm": 0.28560905300574,
|
| 1303 |
+
"learning_rate": 1.1999866246300815e-05,
|
| 1304 |
+
"loss": 0.5102,
|
| 1305 |
+
"num_tokens": 424003342.0,
|
| 1306 |
+
"step": 810
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.7595526561043803,
|
| 1310 |
+
"grad_norm": 0.27647949781689973,
|
| 1311 |
+
"learning_rate": 1.175030743825226e-05,
|
| 1312 |
+
"loss": 0.526,
|
| 1313 |
+
"num_tokens": 426624782.0,
|
| 1314 |
+
"step": 815
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.7642124883504194,
|
| 1318 |
+
"grad_norm": 0.32275759748651767,
|
| 1319 |
+
"learning_rate": 1.1504491070379925e-05,
|
| 1320 |
+
"loss": 0.5318,
|
| 1321 |
+
"num_tokens": 429246222.0,
|
| 1322 |
+
"step": 820
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.7688723205964585,
|
| 1326 |
+
"grad_norm": 0.2752182729466672,
|
| 1327 |
+
"learning_rate": 1.1262475553541516e-05,
|
| 1328 |
+
"loss": 0.5224,
|
| 1329 |
+
"num_tokens": 431867662.0,
|
| 1330 |
+
"step": 825
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.7735321528424977,
|
| 1334 |
+
"grad_norm": 0.27734053232169165,
|
| 1335 |
+
"learning_rate": 1.1024318395436947e-05,
|
| 1336 |
+
"loss": 0.5112,
|
| 1337 |
+
"num_tokens": 434474764.0,
|
| 1338 |
+
"step": 830
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.7781919850885368,
|
| 1342 |
+
"grad_norm": 0.2727508038731573,
|
| 1343 |
+
"learning_rate": 1.0790076186943354e-05,
|
| 1344 |
+
"loss": 0.513,
|
| 1345 |
+
"num_tokens": 437096204.0,
|
| 1346 |
+
"step": 835
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.782851817334576,
|
| 1350 |
+
"grad_norm": 0.26485944225101965,
|
| 1351 |
+
"learning_rate": 1.0559804588667984e-05,
|
| 1352 |
+
"loss": 0.515,
|
| 1353 |
+
"num_tokens": 439717644.0,
|
| 1354 |
+
"step": 840
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7875116495806151,
|
| 1358 |
+
"grad_norm": 0.28511391870004127,
|
| 1359 |
+
"learning_rate": 1.0333558317722149e-05,
|
| 1360 |
+
"loss": 0.5184,
|
| 1361 |
+
"num_tokens": 442322749.0,
|
| 1362 |
+
"step": 845
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.7921714818266542,
|
| 1366 |
+
"grad_norm": 0.26624698807596014,
|
| 1367 |
+
"learning_rate": 1.0111391134719311e-05,
|
| 1368 |
+
"loss": 0.5264,
|
| 1369 |
+
"num_tokens": 444944189.0,
|
| 1370 |
+
"step": 850
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.7968313140726934,
|
| 1374 |
+
"grad_norm": 0.28268167049567766,
|
| 1375 |
+
"learning_rate": 9.89335583100052e-06,
|
| 1376 |
+
"loss": 0.5331,
|
| 1377 |
+
"num_tokens": 447549445.0,
|
| 1378 |
+
"step": 855
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.8014911463187325,
|
| 1382 |
+
"grad_norm": 0.28123662017619494,
|
| 1383 |
+
"learning_rate": 9.679504216090155e-06,
|
| 1384 |
+
"loss": 0.5199,
|
| 1385 |
+
"num_tokens": 450170885.0,
|
| 1386 |
+
"step": 860
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.8061509785647717,
|
| 1390 |
+
"grad_norm": 0.25854248407494884,
|
| 1391 |
+
"learning_rate": 9.469887105384895e-06,
|
| 1392 |
+
"loss": 0.5235,
|
| 1393 |
+
"num_tokens": 452792325.0,
|
| 1394 |
+
"step": 865
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.8108108108108109,
|
| 1398 |
+
"grad_norm": 0.2690029674997426,
|
| 1399 |
+
"learning_rate": 9.264554308079026e-06,
|
| 1400 |
+
"loss": 0.5179,
|
| 1401 |
+
"num_tokens": 455413765.0,
|
| 1402 |
+
"step": 870
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8154706430568499,
|
| 1406 |
+
"grad_norm": 0.28789872575639314,
|
| 1407 |
+
"learning_rate": 9.06355461532878e-06,
|
| 1408 |
+
"loss": 0.5138,
|
| 1409 |
+
"num_tokens": 458035205.0,
|
| 1410 |
+
"step": 875
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.8201304753028891,
|
| 1414 |
+
"grad_norm": 0.28110004832587115,
|
| 1415 |
+
"learning_rate": 8.866935788658539e-06,
|
| 1416 |
+
"loss": 0.5259,
|
| 1417 |
+
"num_tokens": 460656645.0,
|
| 1418 |
+
"step": 880
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.8247903075489282,
|
| 1422 |
+
"grad_norm": 0.25143705424850427,
|
| 1423 |
+
"learning_rate": 8.674744548611804e-06,
|
| 1424 |
+
"loss": 0.522,
|
| 1425 |
+
"num_tokens": 463278085.0,
|
| 1426 |
+
"step": 885
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.8294501397949674,
|
| 1430 |
+
"grad_norm": 0.2732574230809433,
|
| 1431 |
+
"learning_rate": 8.487026563649433e-06,
|
| 1432 |
+
"loss": 0.5155,
|
| 1433 |
+
"num_tokens": 465899525.0,
|
| 1434 |
+
"step": 890
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.8341099720410066,
|
| 1438 |
+
"grad_norm": 0.26576606178374057,
|
| 1439 |
+
"learning_rate": 8.303826439297903e-06,
|
| 1440 |
+
"loss": 0.5069,
|
| 1441 |
+
"num_tokens": 468520965.0,
|
| 1442 |
+
"step": 895
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.8387698042870456,
|
| 1446 |
+
"grad_norm": 0.2598544734188271,
|
| 1447 |
+
"learning_rate": 8.125187707550183e-06,
|
| 1448 |
+
"loss": 0.5053,
|
| 1449 |
+
"num_tokens": 471142405.0,
|
| 1450 |
+
"step": 900
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.8434296365330848,
|
| 1454 |
+
"grad_norm": 0.2775093330158093,
|
| 1455 |
+
"learning_rate": 7.95115281652163e-06,
|
| 1456 |
+
"loss": 0.521,
|
| 1457 |
+
"num_tokens": 473763845.0,
|
| 1458 |
+
"step": 905
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.848089468779124,
|
| 1462 |
+
"grad_norm": 0.2655255633343213,
|
| 1463 |
+
"learning_rate": 7.781763120363474e-06,
|
| 1464 |
+
"loss": 0.5142,
|
| 1465 |
+
"num_tokens": 476385285.0,
|
| 1466 |
+
"step": 910
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8527493010251631,
|
| 1470 |
+
"grad_norm": 0.27879924781692983,
|
| 1471 |
+
"learning_rate": 7.6170588694362915e-06,
|
| 1472 |
+
"loss": 0.5171,
|
| 1473 |
+
"num_tokens": 478994969.0,
|
| 1474 |
+
"step": 915
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.8574091332712023,
|
| 1478 |
+
"grad_norm": 0.27650293415137006,
|
| 1479 |
+
"learning_rate": 7.4570792007456745e-06,
|
| 1480 |
+
"loss": 0.5128,
|
| 1481 |
+
"num_tokens": 481616409.0,
|
| 1482 |
+
"step": 920
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.8620689655172413,
|
| 1486 |
+
"grad_norm": 0.2565882273178327,
|
| 1487 |
+
"learning_rate": 7.3018621286425035e-06,
|
| 1488 |
+
"loss": 0.5146,
|
| 1489 |
+
"num_tokens": 484237849.0,
|
| 1490 |
+
"step": 925
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.8667287977632805,
|
| 1494 |
+
"grad_norm": 0.2798920754325045,
|
| 1495 |
+
"learning_rate": 7.151444535790017e-06,
|
| 1496 |
+
"loss": 0.5136,
|
| 1497 |
+
"num_tokens": 486854794.0,
|
| 1498 |
+
"step": 930
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.8713886300093197,
|
| 1502 |
+
"grad_norm": 0.274910793467222,
|
| 1503 |
+
"learning_rate": 7.005862164399716e-06,
|
| 1504 |
+
"loss": 0.5143,
|
| 1505 |
+
"num_tokens": 489476234.0,
|
| 1506 |
+
"step": 935
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.8760484622553588,
|
| 1510 |
+
"grad_norm": 0.2637455400772512,
|
| 1511 |
+
"learning_rate": 6.865149607738324e-06,
|
| 1512 |
+
"loss": 0.5189,
|
| 1513 |
+
"num_tokens": 492097674.0,
|
| 1514 |
+
"step": 940
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.880708294501398,
|
| 1518 |
+
"grad_norm": 0.2693552025597566,
|
| 1519 |
+
"learning_rate": 6.7293403019077394e-06,
|
| 1520 |
+
"loss": 0.5202,
|
| 1521 |
+
"num_tokens": 494719114.0,
|
| 1522 |
+
"step": 945
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8853681267474371,
|
| 1526 |
+
"grad_norm": 0.2809957126844594,
|
| 1527 |
+
"learning_rate": 6.598466517899961e-06,
|
| 1528 |
+
"loss": 0.5173,
|
| 1529 |
+
"num_tokens": 497312162.0,
|
| 1530 |
+
"step": 950
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.8900279589934762,
|
| 1534 |
+
"grad_norm": 0.2555841643925506,
|
| 1535 |
+
"learning_rate": 6.472559353928814e-06,
|
| 1536 |
+
"loss": 0.5019,
|
| 1537 |
+
"num_tokens": 499933602.0,
|
| 1538 |
+
"step": 955
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.8946877912395154,
|
| 1542 |
+
"grad_norm": 0.27086227539515284,
|
| 1543 |
+
"learning_rate": 6.35164872804046e-06,
|
| 1544 |
+
"loss": 0.5122,
|
| 1545 |
+
"num_tokens": 502555042.0,
|
| 1546 |
+
"step": 960
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.8993476234855545,
|
| 1550 |
+
"grad_norm": 0.29546748023753766,
|
| 1551 |
+
"learning_rate": 6.235763371004234e-06,
|
| 1552 |
+
"loss": 0.5057,
|
| 1553 |
+
"num_tokens": 505176482.0,
|
| 1554 |
+
"step": 965
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.9040074557315937,
|
| 1558 |
+
"grad_norm": 0.26696035195466766,
|
| 1559 |
+
"learning_rate": 6.124930819485644e-06,
|
| 1560 |
+
"loss": 0.5204,
|
| 1561 |
+
"num_tokens": 507789906.0,
|
| 1562 |
+
"step": 970
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.9086672879776329,
|
| 1566 |
+
"grad_norm": 0.2583326601655603,
|
| 1567 |
+
"learning_rate": 6.0191774095031244e-06,
|
| 1568 |
+
"loss": 0.519,
|
| 1569 |
+
"num_tokens": 510411346.0,
|
| 1570 |
+
"step": 975
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.9133271202236719,
|
| 1574 |
+
"grad_norm": 0.2634964969787786,
|
| 1575 |
+
"learning_rate": 5.9185282701700745e-06,
|
| 1576 |
+
"loss": 0.499,
|
| 1577 |
+
"num_tokens": 513031521.0,
|
| 1578 |
+
"step": 980
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.9179869524697111,
|
| 1582 |
+
"grad_norm": 0.26303275219066763,
|
| 1583 |
+
"learning_rate": 5.823007317723664e-06,
|
| 1584 |
+
"loss": 0.5214,
|
| 1585 |
+
"num_tokens": 515652961.0,
|
| 1586 |
+
"step": 985
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.9226467847157502,
|
| 1590 |
+
"grad_norm": 0.24466594684826756,
|
| 1591 |
+
"learning_rate": 5.732637249841873e-06,
|
| 1592 |
+
"loss": 0.5159,
|
| 1593 |
+
"num_tokens": 518274401.0,
|
| 1594 |
+
"step": 990
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.9273066169617894,
|
| 1598 |
+
"grad_norm": 0.2556427215997019,
|
| 1599 |
+
"learning_rate": 5.647439540250082e-06,
|
| 1600 |
+
"loss": 0.5167,
|
| 1601 |
+
"num_tokens": 520895841.0,
|
| 1602 |
+
"step": 995
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.9319664492078286,
|
| 1606 |
+
"grad_norm": 0.2602051972545975,
|
| 1607 |
+
"learning_rate": 5.567434433618465e-06,
|
| 1608 |
+
"loss": 0.5221,
|
| 1609 |
+
"num_tokens": 523517281.0,
|
| 1610 |
+
"step": 1000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.9366262814538676,
|
| 1614 |
+
"grad_norm": 0.2626632425661083,
|
| 1615 |
+
"learning_rate": 5.492640940751462e-06,
|
| 1616 |
+
"loss": 0.5093,
|
| 1617 |
+
"num_tokens": 526138721.0,
|
| 1618 |
+
"step": 1005
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 0.9412861136999068,
|
| 1622 |
+
"grad_norm": 0.2653112910486034,
|
| 1623 |
+
"learning_rate": 5.423076834070447e-06,
|
| 1624 |
+
"loss": 0.5285,
|
| 1625 |
+
"num_tokens": 528760161.0,
|
| 1626 |
+
"step": 1010
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.9459459459459459,
|
| 1630 |
+
"grad_norm": 0.2785801997629486,
|
| 1631 |
+
"learning_rate": 5.358758643390628e-06,
|
| 1632 |
+
"loss": 0.5117,
|
| 1633 |
+
"num_tokens": 531376706.0,
|
| 1634 |
+
"step": 1015
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.9506057781919851,
|
| 1638 |
+
"grad_norm": 0.25744114435589993,
|
| 1639 |
+
"learning_rate": 5.299701651993246e-06,
|
| 1640 |
+
"loss": 0.5123,
|
| 1641 |
+
"num_tokens": 533998146.0,
|
| 1642 |
+
"step": 1020
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.9552656104380243,
|
| 1646 |
+
"grad_norm": 0.26732388420603614,
|
| 1647 |
+
"learning_rate": 5.245919892993957e-06,
|
| 1648 |
+
"loss": 0.5127,
|
| 1649 |
+
"num_tokens": 536619586.0,
|
| 1650 |
+
"step": 1025
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.9599254426840633,
|
| 1654 |
+
"grad_norm": 0.24599793005738302,
|
| 1655 |
+
"learning_rate": 5.197426146008291e-06,
|
| 1656 |
+
"loss": 0.5112,
|
| 1657 |
+
"num_tokens": 539227681.0,
|
| 1658 |
+
"step": 1030
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.9645852749301025,
|
| 1662 |
+
"grad_norm": 0.25678851543737874,
|
| 1663 |
+
"learning_rate": 5.1542319341149565e-06,
|
| 1664 |
+
"loss": 0.5153,
|
| 1665 |
+
"num_tokens": 541849121.0,
|
| 1666 |
+
"step": 1035
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.9692451071761417,
|
| 1670 |
+
"grad_norm": 0.2528003102793364,
|
| 1671 |
+
"learning_rate": 5.1163475211177235e-06,
|
| 1672 |
+
"loss": 0.5065,
|
| 1673 |
+
"num_tokens": 544470561.0,
|
| 1674 |
+
"step": 1040
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.9739049394221808,
|
| 1678 |
+
"grad_norm": 0.2718075845891858,
|
| 1679 |
+
"learning_rate": 5.083781909106557e-06,
|
| 1680 |
+
"loss": 0.5051,
|
| 1681 |
+
"num_tokens": 547092001.0,
|
| 1682 |
+
"step": 1045
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.97856477166822,
|
| 1686 |
+
"grad_norm": 0.2564809919160912,
|
| 1687 |
+
"learning_rate": 5.056542836318518e-06,
|
| 1688 |
+
"loss": 0.5123,
|
| 1689 |
+
"num_tokens": 549691697.0,
|
| 1690 |
+
"step": 1050
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.983224603914259,
|
| 1694 |
+
"grad_norm": 0.26937692120479134,
|
| 1695 |
+
"learning_rate": 5.034636775299023e-06,
|
| 1696 |
+
"loss": 0.5058,
|
| 1697 |
+
"num_tokens": 552313137.0,
|
| 1698 |
+
"step": 1055
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.9878844361602982,
|
| 1702 |
+
"grad_norm": 0.2643881537184476,
|
| 1703 |
+
"learning_rate": 5.018068931363828e-06,
|
| 1704 |
+
"loss": 0.5072,
|
| 1705 |
+
"num_tokens": 554934577.0,
|
| 1706 |
+
"step": 1060
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.9925442684063374,
|
| 1710 |
+
"grad_norm": 0.252068033315109,
|
| 1711 |
+
"learning_rate": 5.006843241362149e-06,
|
| 1712 |
+
"loss": 0.5095,
|
| 1713 |
+
"num_tokens": 557556017.0,
|
| 1714 |
+
"step": 1065
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.9972041006523765,
|
| 1718 |
+
"grad_norm": 0.25623813154655356,
|
| 1719 |
+
"learning_rate": 5.000962372741178e-06,
|
| 1720 |
+
"loss": 0.5069,
|
| 1721 |
+
"num_tokens": 560177457.0,
|
| 1722 |
+
"step": 1070
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.0,
|
| 1726 |
+
"num_tokens": 561750321.0,
|
| 1727 |
+
"step": 1073,
|
| 1728 |
+
"total_flos": 489077052801024.0,
|
| 1729 |
+
"train_loss": 0.5499481136067826,
|
| 1730 |
+
"train_runtime": 13659.0836,
|
| 1731 |
+
"train_samples_per_second": 2.512,
|
| 1732 |
+
"train_steps_per_second": 0.079
|
| 1733 |
+
}
|
| 1734 |
+
],
|
| 1735 |
+
"logging_steps": 5,
|
| 1736 |
+
"max_steps": 1073,
|
| 1737 |
+
"num_input_tokens_seen": 0,
|
| 1738 |
+
"num_train_epochs": 1,
|
| 1739 |
+
"save_steps": 100,
|
| 1740 |
+
"stateful_callbacks": {
|
| 1741 |
+
"TrainerControl": {
|
| 1742 |
+
"args": {
|
| 1743 |
+
"should_epoch_stop": false,
|
| 1744 |
+
"should_evaluate": false,
|
| 1745 |
+
"should_log": false,
|
| 1746 |
+
"should_save": true,
|
| 1747 |
+
"should_training_stop": true
|
| 1748 |
+
},
|
| 1749 |
+
"attributes": {}
|
| 1750 |
+
}
|
| 1751 |
+
},
|
| 1752 |
+
"total_flos": 489077052801024.0,
|
| 1753 |
+
"train_batch_size": 8,
|
| 1754 |
+
"trial_name": null,
|
| 1755 |
+
"trial_params": null
|
| 1756 |
+
}
|