Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +3045 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: open-r1/OpenR1-Qwen-7B
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: OpenR1-Qwen-7B-P25-V2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for OpenR1-Qwen-7B-P25-V2
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [open-r1/OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B).
|
| 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="ZMC2019/OpenR1-Qwen-7B-P25-V2", 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/chenzhuoming911/huggingface/runs/iq1vub68)
|
| 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: 3.5.0
|
| 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": 1.8367600516462019e+18,
|
| 3 |
+
"train_loss": 0.34532702185789893,
|
| 4 |
+
"train_runtime": 73160.0405,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.469,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.49.0"
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1.8367600516462019e+18,
|
| 3 |
+
"train_loss": 0.34532702185789893,
|
| 4 |
+
"train_runtime": 73160.0405,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 0.469,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3045 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2146,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004659832246039142,
|
| 13 |
+
"grad_norm": 14.767192461253016,
|
| 14 |
+
"learning_rate": 4.651162790697675e-07,
|
| 15 |
+
"loss": 0.8454,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009319664492078284,
|
| 20 |
+
"grad_norm": 10.691157784855342,
|
| 21 |
+
"learning_rate": 9.30232558139535e-07,
|
| 22 |
+
"loss": 0.8295,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013979496738117428,
|
| 27 |
+
"grad_norm": 4.753711347195471,
|
| 28 |
+
"learning_rate": 1.3953488372093025e-06,
|
| 29 |
+
"loss": 0.789,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01863932898415657,
|
| 34 |
+
"grad_norm": 4.574744947370259,
|
| 35 |
+
"learning_rate": 1.86046511627907e-06,
|
| 36 |
+
"loss": 0.7631,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023299161230195712,
|
| 41 |
+
"grad_norm": 2.938678417992091,
|
| 42 |
+
"learning_rate": 2.3255813953488376e-06,
|
| 43 |
+
"loss": 0.6551,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.027958993476234855,
|
| 48 |
+
"grad_norm": 0.6490882548563339,
|
| 49 |
+
"learning_rate": 2.790697674418605e-06,
|
| 50 |
+
"loss": 0.5661,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.032618825722273995,
|
| 55 |
+
"grad_norm": 0.6582256367580213,
|
| 56 |
+
"learning_rate": 3.2558139534883724e-06,
|
| 57 |
+
"loss": 0.5106,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03727865796831314,
|
| 62 |
+
"grad_norm": 0.5913603077065485,
|
| 63 |
+
"learning_rate": 3.72093023255814e-06,
|
| 64 |
+
"loss": 0.4935,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04193849021435228,
|
| 69 |
+
"grad_norm": 0.3873817321001381,
|
| 70 |
+
"learning_rate": 4.186046511627907e-06,
|
| 71 |
+
"loss": 0.4726,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.046598322460391424,
|
| 76 |
+
"grad_norm": 0.28334846470708785,
|
| 77 |
+
"learning_rate": 4.651162790697675e-06,
|
| 78 |
+
"loss": 0.4644,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05125815470643057,
|
| 83 |
+
"grad_norm": 0.35730577672386,
|
| 84 |
+
"learning_rate": 5.116279069767442e-06,
|
| 85 |
+
"loss": 0.4477,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05591798695246971,
|
| 90 |
+
"grad_norm": 0.22651422858035802,
|
| 91 |
+
"learning_rate": 5.58139534883721e-06,
|
| 92 |
+
"loss": 0.432,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06057781919850885,
|
| 97 |
+
"grad_norm": 0.20330529851492612,
|
| 98 |
+
"learning_rate": 6.046511627906977e-06,
|
| 99 |
+
"loss": 0.4219,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06523765144454799,
|
| 104 |
+
"grad_norm": 0.21798246079136097,
|
| 105 |
+
"learning_rate": 6.511627906976745e-06,
|
| 106 |
+
"loss": 0.4257,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06989748369058714,
|
| 111 |
+
"grad_norm": 0.19806053096479337,
|
| 112 |
+
"learning_rate": 6.976744186046513e-06,
|
| 113 |
+
"loss": 0.4136,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07455731593662628,
|
| 118 |
+
"grad_norm": 0.21322493838033024,
|
| 119 |
+
"learning_rate": 7.44186046511628e-06,
|
| 120 |
+
"loss": 0.4081,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07921714818266543,
|
| 125 |
+
"grad_norm": 0.1988425295831395,
|
| 126 |
+
"learning_rate": 7.906976744186048e-06,
|
| 127 |
+
"loss": 0.4059,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08387698042870456,
|
| 132 |
+
"grad_norm": 0.17732217907185543,
|
| 133 |
+
"learning_rate": 8.372093023255815e-06,
|
| 134 |
+
"loss": 0.4139,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08853681267474371,
|
| 139 |
+
"grad_norm": 0.18197721641419914,
|
| 140 |
+
"learning_rate": 8.837209302325582e-06,
|
| 141 |
+
"loss": 0.3999,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09319664492078285,
|
| 146 |
+
"grad_norm": 0.18805703800459986,
|
| 147 |
+
"learning_rate": 9.30232558139535e-06,
|
| 148 |
+
"loss": 0.3929,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.097856477166822,
|
| 153 |
+
"grad_norm": 0.17447861554875335,
|
| 154 |
+
"learning_rate": 9.767441860465117e-06,
|
| 155 |
+
"loss": 0.3899,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10251630941286113,
|
| 160 |
+
"grad_norm": 0.17823985753713623,
|
| 161 |
+
"learning_rate": 1.0232558139534884e-05,
|
| 162 |
+
"loss": 0.3917,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10717614165890028,
|
| 167 |
+
"grad_norm": 0.1843804114434655,
|
| 168 |
+
"learning_rate": 1.0697674418604651e-05,
|
| 169 |
+
"loss": 0.3908,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11183597390493942,
|
| 174 |
+
"grad_norm": 0.1813727816186044,
|
| 175 |
+
"learning_rate": 1.116279069767442e-05,
|
| 176 |
+
"loss": 0.3847,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11649580615097857,
|
| 181 |
+
"grad_norm": 0.18362844363862849,
|
| 182 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 183 |
+
"loss": 0.3798,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1211556383970177,
|
| 188 |
+
"grad_norm": 0.1976501054723186,
|
| 189 |
+
"learning_rate": 1.2093023255813954e-05,
|
| 190 |
+
"loss": 0.3869,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12581547064305684,
|
| 195 |
+
"grad_norm": 0.18549227048975853,
|
| 196 |
+
"learning_rate": 1.2558139534883723e-05,
|
| 197 |
+
"loss": 0.3837,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.13047530288909598,
|
| 202 |
+
"grad_norm": 0.20270496221730072,
|
| 203 |
+
"learning_rate": 1.302325581395349e-05,
|
| 204 |
+
"loss": 0.3763,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13513513513513514,
|
| 209 |
+
"grad_norm": 0.20776510982034277,
|
| 210 |
+
"learning_rate": 1.3488372093023257e-05,
|
| 211 |
+
"loss": 0.3964,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13979496738117428,
|
| 216 |
+
"grad_norm": 0.2239648466821673,
|
| 217 |
+
"learning_rate": 1.3953488372093025e-05,
|
| 218 |
+
"loss": 0.3779,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14445479962721341,
|
| 223 |
+
"grad_norm": 0.2159680681931303,
|
| 224 |
+
"learning_rate": 1.441860465116279e-05,
|
| 225 |
+
"loss": 0.3895,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14911463187325255,
|
| 230 |
+
"grad_norm": 0.2230512293592664,
|
| 231 |
+
"learning_rate": 1.488372093023256e-05,
|
| 232 |
+
"loss": 0.3748,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15377446411929171,
|
| 237 |
+
"grad_norm": 0.19857008911014462,
|
| 238 |
+
"learning_rate": 1.5348837209302328e-05,
|
| 239 |
+
"loss": 0.379,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15843429636533085,
|
| 244 |
+
"grad_norm": 0.1876370992998556,
|
| 245 |
+
"learning_rate": 1.5813953488372095e-05,
|
| 246 |
+
"loss": 0.3599,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16309412861137,
|
| 251 |
+
"grad_norm": 0.19594094926576977,
|
| 252 |
+
"learning_rate": 1.6279069767441862e-05,
|
| 253 |
+
"loss": 0.3755,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16775396085740912,
|
| 258 |
+
"grad_norm": 0.19588958100246756,
|
| 259 |
+
"learning_rate": 1.674418604651163e-05,
|
| 260 |
+
"loss": 0.3714,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1724137931034483,
|
| 265 |
+
"grad_norm": 0.200501028483886,
|
| 266 |
+
"learning_rate": 1.7209302325581396e-05,
|
| 267 |
+
"loss": 0.3714,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17707362534948742,
|
| 272 |
+
"grad_norm": 0.21928747309088611,
|
| 273 |
+
"learning_rate": 1.7674418604651163e-05,
|
| 274 |
+
"loss": 0.3787,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18173345759552656,
|
| 279 |
+
"grad_norm": 0.24229931775136032,
|
| 280 |
+
"learning_rate": 1.813953488372093e-05,
|
| 281 |
+
"loss": 0.3725,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1863932898415657,
|
| 286 |
+
"grad_norm": 0.23749429090981541,
|
| 287 |
+
"learning_rate": 1.86046511627907e-05,
|
| 288 |
+
"loss": 0.375,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.19105312208760486,
|
| 293 |
+
"grad_norm": 0.20750507399981963,
|
| 294 |
+
"learning_rate": 1.9069767441860468e-05,
|
| 295 |
+
"loss": 0.3682,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.195712954333644,
|
| 300 |
+
"grad_norm": 0.247680918714745,
|
| 301 |
+
"learning_rate": 1.9534883720930235e-05,
|
| 302 |
+
"loss": 0.3766,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20037278657968313,
|
| 307 |
+
"grad_norm": 0.20635992002934314,
|
| 308 |
+
"learning_rate": 2e-05,
|
| 309 |
+
"loss": 0.3656,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20503261882572227,
|
| 314 |
+
"grad_norm": 0.21391797130718435,
|
| 315 |
+
"learning_rate": 1.9948213360952874e-05,
|
| 316 |
+
"loss": 0.371,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2096924510717614,
|
| 321 |
+
"grad_norm": 0.21826086561242994,
|
| 322 |
+
"learning_rate": 1.989642672190575e-05,
|
| 323 |
+
"loss": 0.3575,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21435228331780057,
|
| 328 |
+
"grad_norm": 0.2058918265850917,
|
| 329 |
+
"learning_rate": 1.9844640082858625e-05,
|
| 330 |
+
"loss": 0.3678,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2190121155638397,
|
| 335 |
+
"grad_norm": 0.21256383645525231,
|
| 336 |
+
"learning_rate": 1.9792853443811498e-05,
|
| 337 |
+
"loss": 0.3652,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22367194780987884,
|
| 342 |
+
"grad_norm": 0.2091365846820082,
|
| 343 |
+
"learning_rate": 1.9741066804764374e-05,
|
| 344 |
+
"loss": 0.3664,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22833178005591798,
|
| 349 |
+
"grad_norm": 0.2379635390767414,
|
| 350 |
+
"learning_rate": 1.9689280165717246e-05,
|
| 351 |
+
"loss": 0.369,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23299161230195714,
|
| 356 |
+
"grad_norm": 0.21145510152697863,
|
| 357 |
+
"learning_rate": 1.963749352667012e-05,
|
| 358 |
+
"loss": 0.3639,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23765144454799628,
|
| 363 |
+
"grad_norm": 0.23770392971510992,
|
| 364 |
+
"learning_rate": 1.9585706887622994e-05,
|
| 365 |
+
"loss": 0.3679,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2423112767940354,
|
| 370 |
+
"grad_norm": 0.2432075399312,
|
| 371 |
+
"learning_rate": 1.953392024857587e-05,
|
| 372 |
+
"loss": 0.3692,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24697110904007455,
|
| 377 |
+
"grad_norm": 0.2625016034254708,
|
| 378 |
+
"learning_rate": 1.9482133609528746e-05,
|
| 379 |
+
"loss": 0.3672,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2516309412861137,
|
| 384 |
+
"grad_norm": 0.2145060352354748,
|
| 385 |
+
"learning_rate": 1.9430346970481618e-05,
|
| 386 |
+
"loss": 0.3641,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.25629077353215285,
|
| 391 |
+
"grad_norm": 0.2473831855865487,
|
| 392 |
+
"learning_rate": 1.937856033143449e-05,
|
| 393 |
+
"loss": 0.3664,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26095060577819196,
|
| 398 |
+
"grad_norm": 0.22052729908882035,
|
| 399 |
+
"learning_rate": 1.9326773692387366e-05,
|
| 400 |
+
"loss": 0.3623,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2656104380242311,
|
| 405 |
+
"grad_norm": 0.23934016164519892,
|
| 406 |
+
"learning_rate": 1.927498705334024e-05,
|
| 407 |
+
"loss": 0.3655,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2702702702702703,
|
| 412 |
+
"grad_norm": 0.23940932697090694,
|
| 413 |
+
"learning_rate": 1.9223200414293114e-05,
|
| 414 |
+
"loss": 0.3701,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.2749301025163094,
|
| 419 |
+
"grad_norm": 0.28885349201279675,
|
| 420 |
+
"learning_rate": 1.917141377524599e-05,
|
| 421 |
+
"loss": 0.3787,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27958993476234856,
|
| 426 |
+
"grad_norm": 0.2732454315192837,
|
| 427 |
+
"learning_rate": 1.9119627136198862e-05,
|
| 428 |
+
"loss": 0.3748,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2842497670083877,
|
| 433 |
+
"grad_norm": 0.287512960553777,
|
| 434 |
+
"learning_rate": 1.9067840497151738e-05,
|
| 435 |
+
"loss": 0.3648,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.28890959925442683,
|
| 440 |
+
"grad_norm": 0.25791283197780085,
|
| 441 |
+
"learning_rate": 1.901605385810461e-05,
|
| 442 |
+
"loss": 0.3605,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.293569431500466,
|
| 447 |
+
"grad_norm": 0.22578196901427042,
|
| 448 |
+
"learning_rate": 1.8964267219057483e-05,
|
| 449 |
+
"loss": 0.3673,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2982292637465051,
|
| 454 |
+
"grad_norm": 0.26398442111942083,
|
| 455 |
+
"learning_rate": 1.891248058001036e-05,
|
| 456 |
+
"loss": 0.3526,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.30288909599254427,
|
| 461 |
+
"grad_norm": 0.2266594032196434,
|
| 462 |
+
"learning_rate": 1.8860693940963234e-05,
|
| 463 |
+
"loss": 0.3533,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.30754892823858343,
|
| 468 |
+
"grad_norm": 0.2034558825684523,
|
| 469 |
+
"learning_rate": 1.8808907301916107e-05,
|
| 470 |
+
"loss": 0.3625,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.31220876048462254,
|
| 475 |
+
"grad_norm": 0.21230490114636388,
|
| 476 |
+
"learning_rate": 1.8757120662868982e-05,
|
| 477 |
+
"loss": 0.3612,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3168685927306617,
|
| 482 |
+
"grad_norm": 0.21940627029273344,
|
| 483 |
+
"learning_rate": 1.8705334023821855e-05,
|
| 484 |
+
"loss": 0.3616,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.32152842497670087,
|
| 489 |
+
"grad_norm": 0.24083673925107846,
|
| 490 |
+
"learning_rate": 1.865354738477473e-05,
|
| 491 |
+
"loss": 0.3602,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.32618825722274,
|
| 496 |
+
"grad_norm": 0.2522525259887139,
|
| 497 |
+
"learning_rate": 1.8601760745727603e-05,
|
| 498 |
+
"loss": 0.3723,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.33084808946877914,
|
| 503 |
+
"grad_norm": 0.2573006621319903,
|
| 504 |
+
"learning_rate": 1.854997410668048e-05,
|
| 505 |
+
"loss": 0.3655,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.33550792171481825,
|
| 510 |
+
"grad_norm": 0.20987075999325422,
|
| 511 |
+
"learning_rate": 1.8498187467633354e-05,
|
| 512 |
+
"loss": 0.3583,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3401677539608574,
|
| 517 |
+
"grad_norm": 0.23358976426813405,
|
| 518 |
+
"learning_rate": 1.8446400828586227e-05,
|
| 519 |
+
"loss": 0.3566,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3448275862068966,
|
| 524 |
+
"grad_norm": 0.2399874778334468,
|
| 525 |
+
"learning_rate": 1.83946141895391e-05,
|
| 526 |
+
"loss": 0.3657,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3494874184529357,
|
| 531 |
+
"grad_norm": 0.2320299659051788,
|
| 532 |
+
"learning_rate": 1.8342827550491975e-05,
|
| 533 |
+
"loss": 0.3572,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35414725069897485,
|
| 538 |
+
"grad_norm": 0.2141358345167075,
|
| 539 |
+
"learning_rate": 1.8291040911444847e-05,
|
| 540 |
+
"loss": 0.3685,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.35880708294501396,
|
| 545 |
+
"grad_norm": 0.2394313640207702,
|
| 546 |
+
"learning_rate": 1.8239254272397723e-05,
|
| 547 |
+
"loss": 0.3667,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3634669151910531,
|
| 552 |
+
"grad_norm": 0.2535784041705651,
|
| 553 |
+
"learning_rate": 1.81874676333506e-05,
|
| 554 |
+
"loss": 0.3595,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3681267474370923,
|
| 559 |
+
"grad_norm": 0.267215419394161,
|
| 560 |
+
"learning_rate": 1.813568099430347e-05,
|
| 561 |
+
"loss": 0.3627,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3727865796831314,
|
| 566 |
+
"grad_norm": 0.22563546555156724,
|
| 567 |
+
"learning_rate": 1.8083894355256347e-05,
|
| 568 |
+
"loss": 0.3514,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.37744641192917056,
|
| 573 |
+
"grad_norm": 0.26175999603352973,
|
| 574 |
+
"learning_rate": 1.803210771620922e-05,
|
| 575 |
+
"loss": 0.3713,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3821062441752097,
|
| 580 |
+
"grad_norm": 0.2557512981709262,
|
| 581 |
+
"learning_rate": 1.798032107716209e-05,
|
| 582 |
+
"loss": 0.3641,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.38676607642124883,
|
| 587 |
+
"grad_norm": 0.2618244822212724,
|
| 588 |
+
"learning_rate": 1.7928534438114967e-05,
|
| 589 |
+
"loss": 0.3546,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.391425908667288,
|
| 594 |
+
"grad_norm": 0.24363536974797073,
|
| 595 |
+
"learning_rate": 1.7876747799067843e-05,
|
| 596 |
+
"loss": 0.3685,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.3960857409133271,
|
| 601 |
+
"grad_norm": 0.23592834779032065,
|
| 602 |
+
"learning_rate": 1.7824961160020715e-05,
|
| 603 |
+
"loss": 0.37,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.40074557315936626,
|
| 608 |
+
"grad_norm": 0.22757209094122816,
|
| 609 |
+
"learning_rate": 1.777317452097359e-05,
|
| 610 |
+
"loss": 0.3618,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.40540540540540543,
|
| 615 |
+
"grad_norm": 0.2247986656928316,
|
| 616 |
+
"learning_rate": 1.7721387881926463e-05,
|
| 617 |
+
"loss": 0.3703,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.41006523765144454,
|
| 622 |
+
"grad_norm": 0.22949520459408446,
|
| 623 |
+
"learning_rate": 1.766960124287934e-05,
|
| 624 |
+
"loss": 0.3622,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4147250698974837,
|
| 629 |
+
"grad_norm": 0.2429836044789581,
|
| 630 |
+
"learning_rate": 1.761781460383221e-05,
|
| 631 |
+
"loss": 0.3597,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4193849021435228,
|
| 636 |
+
"grad_norm": 0.2220744501031802,
|
| 637 |
+
"learning_rate": 1.7566027964785087e-05,
|
| 638 |
+
"loss": 0.3517,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.424044734389562,
|
| 643 |
+
"grad_norm": 0.24960146421273202,
|
| 644 |
+
"learning_rate": 1.7514241325737963e-05,
|
| 645 |
+
"loss": 0.3594,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42870456663560114,
|
| 650 |
+
"grad_norm": 0.23282637573412696,
|
| 651 |
+
"learning_rate": 1.7462454686690835e-05,
|
| 652 |
+
"loss": 0.3572,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.43336439888164024,
|
| 657 |
+
"grad_norm": 0.2583784107904954,
|
| 658 |
+
"learning_rate": 1.7410668047643708e-05,
|
| 659 |
+
"loss": 0.3536,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4380242311276794,
|
| 664 |
+
"grad_norm": 0.24668787220594343,
|
| 665 |
+
"learning_rate": 1.7358881408596583e-05,
|
| 666 |
+
"loss": 0.3651,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4426840633737186,
|
| 671 |
+
"grad_norm": 0.23401991763098598,
|
| 672 |
+
"learning_rate": 1.7307094769549456e-05,
|
| 673 |
+
"loss": 0.3556,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4473438956197577,
|
| 678 |
+
"grad_norm": 0.2568440187662543,
|
| 679 |
+
"learning_rate": 1.725530813050233e-05,
|
| 680 |
+
"loss": 0.3702,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.45200372786579684,
|
| 685 |
+
"grad_norm": 0.24082990346217126,
|
| 686 |
+
"learning_rate": 1.7203521491455207e-05,
|
| 687 |
+
"loss": 0.3612,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.45666356011183595,
|
| 692 |
+
"grad_norm": 0.23359205783172027,
|
| 693 |
+
"learning_rate": 1.715173485240808e-05,
|
| 694 |
+
"loss": 0.3557,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4613233923578751,
|
| 699 |
+
"grad_norm": 0.2759487778473591,
|
| 700 |
+
"learning_rate": 1.7099948213360955e-05,
|
| 701 |
+
"loss": 0.3592,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4659832246039143,
|
| 706 |
+
"grad_norm": 0.24487068910640383,
|
| 707 |
+
"learning_rate": 1.7048161574313828e-05,
|
| 708 |
+
"loss": 0.3676,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4706430568499534,
|
| 713 |
+
"grad_norm": 0.23375869795982646,
|
| 714 |
+
"learning_rate": 1.6996374935266703e-05,
|
| 715 |
+
"loss": 0.3563,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.47530288909599255,
|
| 720 |
+
"grad_norm": 0.23138038119764745,
|
| 721 |
+
"learning_rate": 1.6944588296219576e-05,
|
| 722 |
+
"loss": 0.3593,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.47996272134203166,
|
| 727 |
+
"grad_norm": 0.2317039737462331,
|
| 728 |
+
"learning_rate": 1.689280165717245e-05,
|
| 729 |
+
"loss": 0.3585,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4846225535880708,
|
| 734 |
+
"grad_norm": 0.24700148883977308,
|
| 735 |
+
"learning_rate": 1.6841015018125324e-05,
|
| 736 |
+
"loss": 0.3631,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.48928238583411,
|
| 741 |
+
"grad_norm": 0.24885633026286735,
|
| 742 |
+
"learning_rate": 1.67892283790782e-05,
|
| 743 |
+
"loss": 0.3629,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4939422180801491,
|
| 748 |
+
"grad_norm": 0.24542063920879958,
|
| 749 |
+
"learning_rate": 1.6737441740031072e-05,
|
| 750 |
+
"loss": 0.3579,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.49860205032618826,
|
| 755 |
+
"grad_norm": 0.23117849321213937,
|
| 756 |
+
"learning_rate": 1.6685655100983948e-05,
|
| 757 |
+
"loss": 0.362,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5032618825722274,
|
| 762 |
+
"grad_norm": 0.22596894744470808,
|
| 763 |
+
"learning_rate": 1.6633868461936823e-05,
|
| 764 |
+
"loss": 0.3492,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5079217148182665,
|
| 769 |
+
"grad_norm": 0.25472474761261105,
|
| 770 |
+
"learning_rate": 1.6582081822889696e-05,
|
| 771 |
+
"loss": 0.3561,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5125815470643057,
|
| 776 |
+
"grad_norm": 0.24056074693134755,
|
| 777 |
+
"learning_rate": 1.653029518384257e-05,
|
| 778 |
+
"loss": 0.3604,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5172413793103449,
|
| 783 |
+
"grad_norm": 0.24945961942773268,
|
| 784 |
+
"learning_rate": 1.6478508544795444e-05,
|
| 785 |
+
"loss": 0.3569,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5219012115563839,
|
| 790 |
+
"grad_norm": 0.23366003314070544,
|
| 791 |
+
"learning_rate": 1.6426721905748316e-05,
|
| 792 |
+
"loss": 0.3708,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5265610438024231,
|
| 797 |
+
"grad_norm": 0.20558481716658702,
|
| 798 |
+
"learning_rate": 1.6374935266701192e-05,
|
| 799 |
+
"loss": 0.3478,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5312208760484622,
|
| 804 |
+
"grad_norm": 0.2439084307260332,
|
| 805 |
+
"learning_rate": 1.6323148627654068e-05,
|
| 806 |
+
"loss": 0.3514,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5358807082945014,
|
| 811 |
+
"grad_norm": 0.24465930880345313,
|
| 812 |
+
"learning_rate": 1.6271361988606944e-05,
|
| 813 |
+
"loss": 0.3554,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5405405405405406,
|
| 818 |
+
"grad_norm": 0.2612036108887042,
|
| 819 |
+
"learning_rate": 1.6219575349559816e-05,
|
| 820 |
+
"loss": 0.3553,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5452003727865797,
|
| 825 |
+
"grad_norm": 0.22670651805729272,
|
| 826 |
+
"learning_rate": 1.6167788710512688e-05,
|
| 827 |
+
"loss": 0.3575,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5498602050326188,
|
| 832 |
+
"grad_norm": 0.20453871875485685,
|
| 833 |
+
"learning_rate": 1.6116002071465564e-05,
|
| 834 |
+
"loss": 0.3507,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.554520037278658,
|
| 839 |
+
"grad_norm": 0.23906772066616808,
|
| 840 |
+
"learning_rate": 1.6064215432418436e-05,
|
| 841 |
+
"loss": 0.3545,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5591798695246971,
|
| 846 |
+
"grad_norm": 0.2251010058012801,
|
| 847 |
+
"learning_rate": 1.6012428793371312e-05,
|
| 848 |
+
"loss": 0.3548,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5638397017707363,
|
| 853 |
+
"grad_norm": 0.2042911139628111,
|
| 854 |
+
"learning_rate": 1.5960642154324188e-05,
|
| 855 |
+
"loss": 0.3545,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5684995340167754,
|
| 860 |
+
"grad_norm": 0.3084593401305696,
|
| 861 |
+
"learning_rate": 1.590885551527706e-05,
|
| 862 |
+
"loss": 0.3634,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5731593662628145,
|
| 867 |
+
"grad_norm": 0.24668947749199188,
|
| 868 |
+
"learning_rate": 1.5857068876229933e-05,
|
| 869 |
+
"loss": 0.3534,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5778191985088537,
|
| 874 |
+
"grad_norm": 0.23815820060623935,
|
| 875 |
+
"learning_rate": 1.5805282237182808e-05,
|
| 876 |
+
"loss": 0.3473,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5824790307548928,
|
| 881 |
+
"grad_norm": 0.2581921333300729,
|
| 882 |
+
"learning_rate": 1.575349559813568e-05,
|
| 883 |
+
"loss": 0.365,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.587138863000932,
|
| 888 |
+
"grad_norm": 0.22365105248877565,
|
| 889 |
+
"learning_rate": 1.5701708959088556e-05,
|
| 890 |
+
"loss": 0.3605,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5917986952469712,
|
| 895 |
+
"grad_norm": 0.2497896525527162,
|
| 896 |
+
"learning_rate": 1.5649922320041432e-05,
|
| 897 |
+
"loss": 0.3621,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5964585274930102,
|
| 902 |
+
"grad_norm": 0.2076670286228493,
|
| 903 |
+
"learning_rate": 1.5598135680994304e-05,
|
| 904 |
+
"loss": 0.3589,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6011183597390494,
|
| 909 |
+
"grad_norm": 0.21352599605542535,
|
| 910 |
+
"learning_rate": 1.554634904194718e-05,
|
| 911 |
+
"loss": 0.3571,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6057781919850885,
|
| 916 |
+
"grad_norm": 0.23960611526431302,
|
| 917 |
+
"learning_rate": 1.5494562402900053e-05,
|
| 918 |
+
"loss": 0.3613,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6104380242311277,
|
| 923 |
+
"grad_norm": 0.232800207968001,
|
| 924 |
+
"learning_rate": 1.5442775763852925e-05,
|
| 925 |
+
"loss": 0.3627,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6150978564771669,
|
| 930 |
+
"grad_norm": 0.2258791731716894,
|
| 931 |
+
"learning_rate": 1.53909891248058e-05,
|
| 932 |
+
"loss": 0.3459,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6197576887232059,
|
| 937 |
+
"grad_norm": 0.2658353866044793,
|
| 938 |
+
"learning_rate": 1.5339202485758676e-05,
|
| 939 |
+
"loss": 0.3483,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6244175209692451,
|
| 944 |
+
"grad_norm": 0.23305204875594826,
|
| 945 |
+
"learning_rate": 1.5287415846711552e-05,
|
| 946 |
+
"loss": 0.3479,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6290773532152842,
|
| 951 |
+
"grad_norm": 0.2384841430708915,
|
| 952 |
+
"learning_rate": 1.5235629207664425e-05,
|
| 953 |
+
"loss": 0.3518,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6337371854613234,
|
| 958 |
+
"grad_norm": 0.2316602358596732,
|
| 959 |
+
"learning_rate": 1.5183842568617297e-05,
|
| 960 |
+
"loss": 0.3576,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6383970177073626,
|
| 965 |
+
"grad_norm": 0.26925303516021515,
|
| 966 |
+
"learning_rate": 1.5132055929570173e-05,
|
| 967 |
+
"loss": 0.3626,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6430568499534017,
|
| 972 |
+
"grad_norm": 0.273521638688401,
|
| 973 |
+
"learning_rate": 1.5080269290523047e-05,
|
| 974 |
+
"loss": 0.3512,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6477166821994408,
|
| 979 |
+
"grad_norm": 0.2060802961004555,
|
| 980 |
+
"learning_rate": 1.5028482651475919e-05,
|
| 981 |
+
"loss": 0.3572,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.65237651444548,
|
| 986 |
+
"grad_norm": 0.2288622125880128,
|
| 987 |
+
"learning_rate": 1.4976696012428795e-05,
|
| 988 |
+
"loss": 0.3634,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6570363466915191,
|
| 993 |
+
"grad_norm": 0.20752277736678076,
|
| 994 |
+
"learning_rate": 1.4924909373381669e-05,
|
| 995 |
+
"loss": 0.3533,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6616961789375583,
|
| 1000 |
+
"grad_norm": 0.2501395274655127,
|
| 1001 |
+
"learning_rate": 1.4873122734334541e-05,
|
| 1002 |
+
"loss": 0.3546,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6663560111835974,
|
| 1007 |
+
"grad_norm": 0.22880446120118658,
|
| 1008 |
+
"learning_rate": 1.4821336095287417e-05,
|
| 1009 |
+
"loss": 0.3472,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6710158434296365,
|
| 1014 |
+
"grad_norm": 0.2594277925537233,
|
| 1015 |
+
"learning_rate": 1.4769549456240291e-05,
|
| 1016 |
+
"loss": 0.3534,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6756756756756757,
|
| 1021 |
+
"grad_norm": 0.27706152102194753,
|
| 1022 |
+
"learning_rate": 1.4717762817193167e-05,
|
| 1023 |
+
"loss": 0.3564,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6803355079217148,
|
| 1028 |
+
"grad_norm": 0.23322150825276064,
|
| 1029 |
+
"learning_rate": 1.4665976178146039e-05,
|
| 1030 |
+
"loss": 0.352,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.684995340167754,
|
| 1035 |
+
"grad_norm": 0.2301436336123601,
|
| 1036 |
+
"learning_rate": 1.4614189539098913e-05,
|
| 1037 |
+
"loss": 0.3535,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6896551724137931,
|
| 1042 |
+
"grad_norm": 0.21931396895361877,
|
| 1043 |
+
"learning_rate": 1.4562402900051789e-05,
|
| 1044 |
+
"loss": 0.3486,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6943150046598322,
|
| 1049 |
+
"grad_norm": 0.24163388236718913,
|
| 1050 |
+
"learning_rate": 1.4510616261004661e-05,
|
| 1051 |
+
"loss": 0.3477,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6989748369058714,
|
| 1056 |
+
"grad_norm": 0.20365681061091856,
|
| 1057 |
+
"learning_rate": 1.4458829621957535e-05,
|
| 1058 |
+
"loss": 0.3488,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7036346691519105,
|
| 1063 |
+
"grad_norm": 0.2337817758782465,
|
| 1064 |
+
"learning_rate": 1.4407042982910411e-05,
|
| 1065 |
+
"loss": 0.3527,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7082945013979497,
|
| 1070 |
+
"grad_norm": 0.2405868217410285,
|
| 1071 |
+
"learning_rate": 1.4355256343863283e-05,
|
| 1072 |
+
"loss": 0.3542,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7129543336439889,
|
| 1077 |
+
"grad_norm": 0.22716685518132887,
|
| 1078 |
+
"learning_rate": 1.430346970481616e-05,
|
| 1079 |
+
"loss": 0.3433,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7176141658900279,
|
| 1084 |
+
"grad_norm": 0.2296954748413165,
|
| 1085 |
+
"learning_rate": 1.4251683065769033e-05,
|
| 1086 |
+
"loss": 0.351,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7222739981360671,
|
| 1091 |
+
"grad_norm": 0.2527911740889576,
|
| 1092 |
+
"learning_rate": 1.4199896426721906e-05,
|
| 1093 |
+
"loss": 0.3599,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7269338303821062,
|
| 1098 |
+
"grad_norm": 0.237870162257353,
|
| 1099 |
+
"learning_rate": 1.4148109787674781e-05,
|
| 1100 |
+
"loss": 0.3467,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7315936626281454,
|
| 1105 |
+
"grad_norm": 0.23987588369726734,
|
| 1106 |
+
"learning_rate": 1.4096323148627655e-05,
|
| 1107 |
+
"loss": 0.3517,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7362534948741846,
|
| 1112 |
+
"grad_norm": 0.27125345543342416,
|
| 1113 |
+
"learning_rate": 1.404453650958053e-05,
|
| 1114 |
+
"loss": 0.3565,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7409133271202236,
|
| 1119 |
+
"grad_norm": 0.22038142310417874,
|
| 1120 |
+
"learning_rate": 1.3992749870533403e-05,
|
| 1121 |
+
"loss": 0.3532,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7455731593662628,
|
| 1126 |
+
"grad_norm": 0.21707991862427248,
|
| 1127 |
+
"learning_rate": 1.3940963231486278e-05,
|
| 1128 |
+
"loss": 0.3516,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.750232991612302,
|
| 1133 |
+
"grad_norm": 0.22006541459822285,
|
| 1134 |
+
"learning_rate": 1.3889176592439152e-05,
|
| 1135 |
+
"loss": 0.3514,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7548928238583411,
|
| 1140 |
+
"grad_norm": 0.2532121724442404,
|
| 1141 |
+
"learning_rate": 1.3837389953392026e-05,
|
| 1142 |
+
"loss": 0.3636,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7595526561043803,
|
| 1147 |
+
"grad_norm": 0.23171770126485144,
|
| 1148 |
+
"learning_rate": 1.37856033143449e-05,
|
| 1149 |
+
"loss": 0.3475,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7642124883504194,
|
| 1154 |
+
"grad_norm": 0.27888374187325565,
|
| 1155 |
+
"learning_rate": 1.3733816675297775e-05,
|
| 1156 |
+
"loss": 0.3577,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7688723205964585,
|
| 1161 |
+
"grad_norm": 0.2880404787911838,
|
| 1162 |
+
"learning_rate": 1.3682030036250648e-05,
|
| 1163 |
+
"loss": 0.3499,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7735321528424977,
|
| 1168 |
+
"grad_norm": 0.24672798067284002,
|
| 1169 |
+
"learning_rate": 1.3630243397203522e-05,
|
| 1170 |
+
"loss": 0.3474,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7781919850885368,
|
| 1175 |
+
"grad_norm": 0.22126054050968327,
|
| 1176 |
+
"learning_rate": 1.3578456758156398e-05,
|
| 1177 |
+
"loss": 0.3499,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.782851817334576,
|
| 1182 |
+
"grad_norm": 0.25020155421404316,
|
| 1183 |
+
"learning_rate": 1.3526670119109272e-05,
|
| 1184 |
+
"loss": 0.3563,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7875116495806151,
|
| 1189 |
+
"grad_norm": 0.2327271527985915,
|
| 1190 |
+
"learning_rate": 1.3474883480062144e-05,
|
| 1191 |
+
"loss": 0.3639,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7921714818266542,
|
| 1196 |
+
"grad_norm": 0.2518085892560592,
|
| 1197 |
+
"learning_rate": 1.342309684101502e-05,
|
| 1198 |
+
"loss": 0.3506,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7968313140726934,
|
| 1203 |
+
"grad_norm": 0.24951300339031132,
|
| 1204 |
+
"learning_rate": 1.3371310201967894e-05,
|
| 1205 |
+
"loss": 0.3563,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8014911463187325,
|
| 1210 |
+
"grad_norm": 0.19924194513914378,
|
| 1211 |
+
"learning_rate": 1.3319523562920766e-05,
|
| 1212 |
+
"loss": 0.3629,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8061509785647717,
|
| 1217 |
+
"grad_norm": 0.25003552030143006,
|
| 1218 |
+
"learning_rate": 1.3267736923873642e-05,
|
| 1219 |
+
"loss": 0.348,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8108108108108109,
|
| 1224 |
+
"grad_norm": 0.24307899627814475,
|
| 1225 |
+
"learning_rate": 1.3215950284826516e-05,
|
| 1226 |
+
"loss": 0.3571,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8154706430568499,
|
| 1231 |
+
"grad_norm": 0.21078480288845156,
|
| 1232 |
+
"learning_rate": 1.3164163645779392e-05,
|
| 1233 |
+
"loss": 0.3545,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8201304753028891,
|
| 1238 |
+
"grad_norm": 0.23496877363911495,
|
| 1239 |
+
"learning_rate": 1.3112377006732264e-05,
|
| 1240 |
+
"loss": 0.35,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.8247903075489282,
|
| 1245 |
+
"grad_norm": 0.23754438146142418,
|
| 1246 |
+
"learning_rate": 1.3060590367685138e-05,
|
| 1247 |
+
"loss": 0.3572,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8294501397949674,
|
| 1252 |
+
"grad_norm": 0.26052536196367965,
|
| 1253 |
+
"learning_rate": 1.3008803728638014e-05,
|
| 1254 |
+
"loss": 0.3492,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8341099720410066,
|
| 1259 |
+
"grad_norm": 0.20695762420053648,
|
| 1260 |
+
"learning_rate": 1.2957017089590886e-05,
|
| 1261 |
+
"loss": 0.3662,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8387698042870456,
|
| 1266 |
+
"grad_norm": 0.2144227087561431,
|
| 1267 |
+
"learning_rate": 1.290523045054376e-05,
|
| 1268 |
+
"loss": 0.3515,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8434296365330848,
|
| 1273 |
+
"grad_norm": 0.19660702935819654,
|
| 1274 |
+
"learning_rate": 1.2853443811496636e-05,
|
| 1275 |
+
"loss": 0.3505,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.848089468779124,
|
| 1280 |
+
"grad_norm": 0.24655418170934199,
|
| 1281 |
+
"learning_rate": 1.2801657172449508e-05,
|
| 1282 |
+
"loss": 0.3549,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8527493010251631,
|
| 1287 |
+
"grad_norm": 0.24959870558662023,
|
| 1288 |
+
"learning_rate": 1.2749870533402384e-05,
|
| 1289 |
+
"loss": 0.3542,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8574091332712023,
|
| 1294 |
+
"grad_norm": 0.24939202340018593,
|
| 1295 |
+
"learning_rate": 1.2698083894355258e-05,
|
| 1296 |
+
"loss": 0.3529,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8620689655172413,
|
| 1301 |
+
"grad_norm": 0.2516391276986144,
|
| 1302 |
+
"learning_rate": 1.264629725530813e-05,
|
| 1303 |
+
"loss": 0.3446,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8667287977632805,
|
| 1308 |
+
"grad_norm": 0.21057329816992565,
|
| 1309 |
+
"learning_rate": 1.2594510616261006e-05,
|
| 1310 |
+
"loss": 0.3436,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8713886300093197,
|
| 1315 |
+
"grad_norm": 0.252888553135217,
|
| 1316 |
+
"learning_rate": 1.254272397721388e-05,
|
| 1317 |
+
"loss": 0.3516,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8760484622553588,
|
| 1322 |
+
"grad_norm": 0.24242068069037045,
|
| 1323 |
+
"learning_rate": 1.2490937338166753e-05,
|
| 1324 |
+
"loss": 0.352,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.880708294501398,
|
| 1329 |
+
"grad_norm": 0.24295740023564055,
|
| 1330 |
+
"learning_rate": 1.2439150699119628e-05,
|
| 1331 |
+
"loss": 0.3506,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8853681267474371,
|
| 1336 |
+
"grad_norm": 0.22863631282733143,
|
| 1337 |
+
"learning_rate": 1.2387364060072502e-05,
|
| 1338 |
+
"loss": 0.3613,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8900279589934762,
|
| 1343 |
+
"grad_norm": 0.2191581333955033,
|
| 1344 |
+
"learning_rate": 1.2335577421025375e-05,
|
| 1345 |
+
"loss": 0.3559,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8946877912395154,
|
| 1350 |
+
"grad_norm": 0.19128532949024207,
|
| 1351 |
+
"learning_rate": 1.228379078197825e-05,
|
| 1352 |
+
"loss": 0.3573,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8993476234855545,
|
| 1357 |
+
"grad_norm": 0.2750308888146951,
|
| 1358 |
+
"learning_rate": 1.2232004142931125e-05,
|
| 1359 |
+
"loss": 0.352,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9040074557315937,
|
| 1364 |
+
"grad_norm": 0.2379831965995701,
|
| 1365 |
+
"learning_rate": 1.2180217503884e-05,
|
| 1366 |
+
"loss": 0.3447,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9086672879776329,
|
| 1371 |
+
"grad_norm": 0.20411721240775887,
|
| 1372 |
+
"learning_rate": 1.2128430864836873e-05,
|
| 1373 |
+
"loss": 0.3606,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9133271202236719,
|
| 1378 |
+
"grad_norm": 0.24726535607310818,
|
| 1379 |
+
"learning_rate": 1.2076644225789747e-05,
|
| 1380 |
+
"loss": 0.3509,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9179869524697111,
|
| 1385 |
+
"grad_norm": 0.25484526322525997,
|
| 1386 |
+
"learning_rate": 1.2024857586742623e-05,
|
| 1387 |
+
"loss": 0.3505,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9226467847157502,
|
| 1392 |
+
"grad_norm": 0.2313975203490289,
|
| 1393 |
+
"learning_rate": 1.1973070947695495e-05,
|
| 1394 |
+
"loss": 0.3485,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9273066169617894,
|
| 1399 |
+
"grad_norm": 0.21915958189471746,
|
| 1400 |
+
"learning_rate": 1.1921284308648369e-05,
|
| 1401 |
+
"loss": 0.3493,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9319664492078286,
|
| 1406 |
+
"grad_norm": 0.21919124866455636,
|
| 1407 |
+
"learning_rate": 1.1869497669601245e-05,
|
| 1408 |
+
"loss": 0.3497,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.9366262814538676,
|
| 1413 |
+
"grad_norm": 0.2028359200370513,
|
| 1414 |
+
"learning_rate": 1.1817711030554117e-05,
|
| 1415 |
+
"loss": 0.3537,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9412861136999068,
|
| 1420 |
+
"grad_norm": 0.21945782585098136,
|
| 1421 |
+
"learning_rate": 1.1765924391506993e-05,
|
| 1422 |
+
"loss": 0.3508,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9459459459459459,
|
| 1427 |
+
"grad_norm": 0.2523778581926582,
|
| 1428 |
+
"learning_rate": 1.1714137752459867e-05,
|
| 1429 |
+
"loss": 0.3557,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9506057781919851,
|
| 1434 |
+
"grad_norm": 0.1984715311531445,
|
| 1435 |
+
"learning_rate": 1.166235111341274e-05,
|
| 1436 |
+
"loss": 0.3499,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9552656104380243,
|
| 1441 |
+
"grad_norm": 0.20598435799914297,
|
| 1442 |
+
"learning_rate": 1.1610564474365615e-05,
|
| 1443 |
+
"loss": 0.3573,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9599254426840633,
|
| 1448 |
+
"grad_norm": 0.19822137487156943,
|
| 1449 |
+
"learning_rate": 1.1558777835318489e-05,
|
| 1450 |
+
"loss": 0.3537,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9645852749301025,
|
| 1455 |
+
"grad_norm": 0.2115159681810218,
|
| 1456 |
+
"learning_rate": 1.1506991196271361e-05,
|
| 1457 |
+
"loss": 0.3529,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9692451071761417,
|
| 1462 |
+
"grad_norm": 0.22399685831955474,
|
| 1463 |
+
"learning_rate": 1.1455204557224237e-05,
|
| 1464 |
+
"loss": 0.3501,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9739049394221808,
|
| 1469 |
+
"grad_norm": 0.21539710641856932,
|
| 1470 |
+
"learning_rate": 1.1403417918177111e-05,
|
| 1471 |
+
"loss": 0.3438,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.97856477166822,
|
| 1476 |
+
"grad_norm": 0.2525250092102095,
|
| 1477 |
+
"learning_rate": 1.1351631279129983e-05,
|
| 1478 |
+
"loss": 0.3669,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.983224603914259,
|
| 1483 |
+
"grad_norm": 0.22688066232449872,
|
| 1484 |
+
"learning_rate": 1.129984464008286e-05,
|
| 1485 |
+
"loss": 0.3474,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9878844361602982,
|
| 1490 |
+
"grad_norm": 0.22444671482154194,
|
| 1491 |
+
"learning_rate": 1.1248058001035733e-05,
|
| 1492 |
+
"loss": 0.3492,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9925442684063374,
|
| 1497 |
+
"grad_norm": 0.2494658035397173,
|
| 1498 |
+
"learning_rate": 1.1196271361988609e-05,
|
| 1499 |
+
"loss": 0.3521,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9972041006523765,
|
| 1504 |
+
"grad_norm": 0.22375408565725688,
|
| 1505 |
+
"learning_rate": 1.1144484722941481e-05,
|
| 1506 |
+
"loss": 0.3504,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.0018639328984156,
|
| 1511 |
+
"grad_norm": 0.23743123795247612,
|
| 1512 |
+
"learning_rate": 1.1092698083894355e-05,
|
| 1513 |
+
"loss": 0.3269,
|
| 1514 |
+
"step": 1075
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.0065237651444547,
|
| 1518 |
+
"grad_norm": 0.23313660102890352,
|
| 1519 |
+
"learning_rate": 1.1040911444847231e-05,
|
| 1520 |
+
"loss": 0.3147,
|
| 1521 |
+
"step": 1080
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.011183597390494,
|
| 1525 |
+
"grad_norm": 0.2222831311931088,
|
| 1526 |
+
"learning_rate": 1.0989124805800104e-05,
|
| 1527 |
+
"loss": 0.3195,
|
| 1528 |
+
"step": 1085
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.015843429636533,
|
| 1532 |
+
"grad_norm": 0.22590081130460746,
|
| 1533 |
+
"learning_rate": 1.0937338166752978e-05,
|
| 1534 |
+
"loss": 0.3263,
|
| 1535 |
+
"step": 1090
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.0205032618825722,
|
| 1539 |
+
"grad_norm": 0.23070778966886485,
|
| 1540 |
+
"learning_rate": 1.0885551527705853e-05,
|
| 1541 |
+
"loss": 0.3143,
|
| 1542 |
+
"step": 1095
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.0251630941286114,
|
| 1546 |
+
"grad_norm": 0.2037603982755685,
|
| 1547 |
+
"learning_rate": 1.0833764888658726e-05,
|
| 1548 |
+
"loss": 0.3053,
|
| 1549 |
+
"step": 1100
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.0298229263746506,
|
| 1553 |
+
"grad_norm": 0.24097367185952903,
|
| 1554 |
+
"learning_rate": 1.0781978249611601e-05,
|
| 1555 |
+
"loss": 0.313,
|
| 1556 |
+
"step": 1105
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.0344827586206897,
|
| 1560 |
+
"grad_norm": 0.20433112740141812,
|
| 1561 |
+
"learning_rate": 1.0730191610564476e-05,
|
| 1562 |
+
"loss": 0.3114,
|
| 1563 |
+
"step": 1110
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.0391425908667289,
|
| 1567 |
+
"grad_norm": 0.21622277499075848,
|
| 1568 |
+
"learning_rate": 1.067840497151735e-05,
|
| 1569 |
+
"loss": 0.3145,
|
| 1570 |
+
"step": 1115
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.0438024231127678,
|
| 1574 |
+
"grad_norm": 0.23195997985450958,
|
| 1575 |
+
"learning_rate": 1.0626618332470224e-05,
|
| 1576 |
+
"loss": 0.3101,
|
| 1577 |
+
"step": 1120
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.048462255358807,
|
| 1581 |
+
"grad_norm": 0.19687727843381017,
|
| 1582 |
+
"learning_rate": 1.0574831693423098e-05,
|
| 1583 |
+
"loss": 0.3144,
|
| 1584 |
+
"step": 1125
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.0531220876048462,
|
| 1588 |
+
"grad_norm": 0.19398268395045887,
|
| 1589 |
+
"learning_rate": 1.0523045054375972e-05,
|
| 1590 |
+
"loss": 0.3143,
|
| 1591 |
+
"step": 1130
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.0577819198508853,
|
| 1595 |
+
"grad_norm": 0.21618958840342323,
|
| 1596 |
+
"learning_rate": 1.0471258415328846e-05,
|
| 1597 |
+
"loss": 0.3244,
|
| 1598 |
+
"step": 1135
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.0624417520969245,
|
| 1602 |
+
"grad_norm": 0.21854767532013517,
|
| 1603 |
+
"learning_rate": 1.041947177628172e-05,
|
| 1604 |
+
"loss": 0.3196,
|
| 1605 |
+
"step": 1140
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.0671015843429636,
|
| 1609 |
+
"grad_norm": 0.21752939753907818,
|
| 1610 |
+
"learning_rate": 1.0367685137234594e-05,
|
| 1611 |
+
"loss": 0.3128,
|
| 1612 |
+
"step": 1145
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.0717614165890028,
|
| 1616 |
+
"grad_norm": 0.2024866876281859,
|
| 1617 |
+
"learning_rate": 1.031589849818747e-05,
|
| 1618 |
+
"loss": 0.3066,
|
| 1619 |
+
"step": 1150
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.076421248835042,
|
| 1623 |
+
"grad_norm": 0.23303951985635973,
|
| 1624 |
+
"learning_rate": 1.0264111859140342e-05,
|
| 1625 |
+
"loss": 0.3126,
|
| 1626 |
+
"step": 1155
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.0810810810810811,
|
| 1630 |
+
"grad_norm": 0.18836388691330083,
|
| 1631 |
+
"learning_rate": 1.0212325220093218e-05,
|
| 1632 |
+
"loss": 0.312,
|
| 1633 |
+
"step": 1160
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.0857409133271203,
|
| 1637 |
+
"grad_norm": 0.2569075921016222,
|
| 1638 |
+
"learning_rate": 1.0160538581046092e-05,
|
| 1639 |
+
"loss": 0.3164,
|
| 1640 |
+
"step": 1165
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.0904007455731595,
|
| 1644 |
+
"grad_norm": 0.20845453486936005,
|
| 1645 |
+
"learning_rate": 1.0108751941998964e-05,
|
| 1646 |
+
"loss": 0.3225,
|
| 1647 |
+
"step": 1170
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.0950605778191984,
|
| 1651 |
+
"grad_norm": 0.19885909880508598,
|
| 1652 |
+
"learning_rate": 1.005696530295184e-05,
|
| 1653 |
+
"loss": 0.3125,
|
| 1654 |
+
"step": 1175
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.0997204100652376,
|
| 1658 |
+
"grad_norm": 0.2669275870745111,
|
| 1659 |
+
"learning_rate": 1.0005178663904714e-05,
|
| 1660 |
+
"loss": 0.3167,
|
| 1661 |
+
"step": 1180
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.1043802423112767,
|
| 1665 |
+
"grad_norm": 0.2232374749321823,
|
| 1666 |
+
"learning_rate": 9.953392024857588e-06,
|
| 1667 |
+
"loss": 0.3129,
|
| 1668 |
+
"step": 1185
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.109040074557316,
|
| 1672 |
+
"grad_norm": 0.19527295898259664,
|
| 1673 |
+
"learning_rate": 9.901605385810462e-06,
|
| 1674 |
+
"loss": 0.317,
|
| 1675 |
+
"step": 1190
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.113699906803355,
|
| 1679 |
+
"grad_norm": 0.22072636669010462,
|
| 1680 |
+
"learning_rate": 9.849818746763336e-06,
|
| 1681 |
+
"loss": 0.3228,
|
| 1682 |
+
"step": 1195
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.1183597390493942,
|
| 1686 |
+
"grad_norm": 0.1949253986918304,
|
| 1687 |
+
"learning_rate": 9.79803210771621e-06,
|
| 1688 |
+
"loss": 0.3162,
|
| 1689 |
+
"step": 1200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.1230195712954334,
|
| 1693 |
+
"grad_norm": 0.2168403291673588,
|
| 1694 |
+
"learning_rate": 9.746245468669084e-06,
|
| 1695 |
+
"loss": 0.3164,
|
| 1696 |
+
"step": 1205
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.1276794035414726,
|
| 1700 |
+
"grad_norm": 0.20528695943678604,
|
| 1701 |
+
"learning_rate": 9.694458829621958e-06,
|
| 1702 |
+
"loss": 0.3158,
|
| 1703 |
+
"step": 1210
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.1323392357875117,
|
| 1707 |
+
"grad_norm": 0.20323454642905758,
|
| 1708 |
+
"learning_rate": 9.642672190574832e-06,
|
| 1709 |
+
"loss": 0.3166,
|
| 1710 |
+
"step": 1215
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.1369990680335509,
|
| 1714 |
+
"grad_norm": 0.21352753091729954,
|
| 1715 |
+
"learning_rate": 9.590885551527706e-06,
|
| 1716 |
+
"loss": 0.3166,
|
| 1717 |
+
"step": 1220
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.14165890027959,
|
| 1721 |
+
"grad_norm": 0.2270069255362695,
|
| 1722 |
+
"learning_rate": 9.53909891248058e-06,
|
| 1723 |
+
"loss": 0.3152,
|
| 1724 |
+
"step": 1225
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.146318732525629,
|
| 1728 |
+
"grad_norm": 0.1933121328903308,
|
| 1729 |
+
"learning_rate": 9.487312273433454e-06,
|
| 1730 |
+
"loss": 0.317,
|
| 1731 |
+
"step": 1230
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.1509785647716682,
|
| 1735 |
+
"grad_norm": 0.20309447114485268,
|
| 1736 |
+
"learning_rate": 9.435525634386328e-06,
|
| 1737 |
+
"loss": 0.3193,
|
| 1738 |
+
"step": 1235
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.1556383970177073,
|
| 1742 |
+
"grad_norm": 0.21202399279436465,
|
| 1743 |
+
"learning_rate": 9.383738995339203e-06,
|
| 1744 |
+
"loss": 0.3131,
|
| 1745 |
+
"step": 1240
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.1602982292637465,
|
| 1749 |
+
"grad_norm": 0.20262516559107904,
|
| 1750 |
+
"learning_rate": 9.331952356292078e-06,
|
| 1751 |
+
"loss": 0.3205,
|
| 1752 |
+
"step": 1245
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.1649580615097856,
|
| 1756 |
+
"grad_norm": 0.1988930651334672,
|
| 1757 |
+
"learning_rate": 9.28016571724495e-06,
|
| 1758 |
+
"loss": 0.3145,
|
| 1759 |
+
"step": 1250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.1696178937558248,
|
| 1763 |
+
"grad_norm": 0.1976164571878271,
|
| 1764 |
+
"learning_rate": 9.228379078197825e-06,
|
| 1765 |
+
"loss": 0.2993,
|
| 1766 |
+
"step": 1255
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.174277726001864,
|
| 1770 |
+
"grad_norm": 0.20859209970330467,
|
| 1771 |
+
"learning_rate": 9.1765924391507e-06,
|
| 1772 |
+
"loss": 0.3165,
|
| 1773 |
+
"step": 1260
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.1789375582479031,
|
| 1777 |
+
"grad_norm": 0.21856326174939153,
|
| 1778 |
+
"learning_rate": 9.124805800103574e-06,
|
| 1779 |
+
"loss": 0.3112,
|
| 1780 |
+
"step": 1265
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.1835973904939423,
|
| 1784 |
+
"grad_norm": 0.2139917663911859,
|
| 1785 |
+
"learning_rate": 9.073019161056449e-06,
|
| 1786 |
+
"loss": 0.3222,
|
| 1787 |
+
"step": 1270
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.1882572227399812,
|
| 1791 |
+
"grad_norm": 0.20444481893780622,
|
| 1792 |
+
"learning_rate": 9.021232522009323e-06,
|
| 1793 |
+
"loss": 0.3156,
|
| 1794 |
+
"step": 1275
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.1929170549860204,
|
| 1798 |
+
"grad_norm": 0.21896418458298256,
|
| 1799 |
+
"learning_rate": 8.969445882962197e-06,
|
| 1800 |
+
"loss": 0.3192,
|
| 1801 |
+
"step": 1280
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.1975768872320596,
|
| 1805 |
+
"grad_norm": 0.20828809222865366,
|
| 1806 |
+
"learning_rate": 8.91765924391507e-06,
|
| 1807 |
+
"loss": 0.3225,
|
| 1808 |
+
"step": 1285
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.2022367194780987,
|
| 1812 |
+
"grad_norm": 0.19945387268340256,
|
| 1813 |
+
"learning_rate": 8.865872604867945e-06,
|
| 1814 |
+
"loss": 0.3113,
|
| 1815 |
+
"step": 1290
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.206896551724138,
|
| 1819 |
+
"grad_norm": 0.19091098433364817,
|
| 1820 |
+
"learning_rate": 8.814085965820819e-06,
|
| 1821 |
+
"loss": 0.3143,
|
| 1822 |
+
"step": 1295
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.211556383970177,
|
| 1826 |
+
"grad_norm": 0.2444756340798008,
|
| 1827 |
+
"learning_rate": 8.762299326773693e-06,
|
| 1828 |
+
"loss": 0.3224,
|
| 1829 |
+
"step": 1300
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.2162162162162162,
|
| 1833 |
+
"grad_norm": 0.21335472533568636,
|
| 1834 |
+
"learning_rate": 8.710512687726569e-06,
|
| 1835 |
+
"loss": 0.3197,
|
| 1836 |
+
"step": 1305
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.2208760484622554,
|
| 1840 |
+
"grad_norm": 0.2011901037726579,
|
| 1841 |
+
"learning_rate": 8.658726048679441e-06,
|
| 1842 |
+
"loss": 0.3099,
|
| 1843 |
+
"step": 1310
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.2255358807082946,
|
| 1847 |
+
"grad_norm": 0.19939445022217508,
|
| 1848 |
+
"learning_rate": 8.606939409632315e-06,
|
| 1849 |
+
"loss": 0.3271,
|
| 1850 |
+
"step": 1315
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.2301957129543337,
|
| 1854 |
+
"grad_norm": 0.20616420365814805,
|
| 1855 |
+
"learning_rate": 8.55515277058519e-06,
|
| 1856 |
+
"loss": 0.3162,
|
| 1857 |
+
"step": 1320
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.2348555452003729,
|
| 1861 |
+
"grad_norm": 0.19727962222530154,
|
| 1862 |
+
"learning_rate": 8.503366131538063e-06,
|
| 1863 |
+
"loss": 0.3216,
|
| 1864 |
+
"step": 1325
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.2395153774464118,
|
| 1868 |
+
"grad_norm": 0.19280265908630698,
|
| 1869 |
+
"learning_rate": 8.451579492490937e-06,
|
| 1870 |
+
"loss": 0.3148,
|
| 1871 |
+
"step": 1330
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.244175209692451,
|
| 1875 |
+
"grad_norm": 0.20437690863854796,
|
| 1876 |
+
"learning_rate": 8.399792853443813e-06,
|
| 1877 |
+
"loss": 0.3137,
|
| 1878 |
+
"step": 1335
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.2488350419384902,
|
| 1882 |
+
"grad_norm": 0.21131034344431252,
|
| 1883 |
+
"learning_rate": 8.348006214396687e-06,
|
| 1884 |
+
"loss": 0.3187,
|
| 1885 |
+
"step": 1340
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.2534948741845293,
|
| 1889 |
+
"grad_norm": 0.19470646825002752,
|
| 1890 |
+
"learning_rate": 8.29621957534956e-06,
|
| 1891 |
+
"loss": 0.3064,
|
| 1892 |
+
"step": 1345
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.2581547064305685,
|
| 1896 |
+
"grad_norm": 0.2093800867383876,
|
| 1897 |
+
"learning_rate": 8.244432936302435e-06,
|
| 1898 |
+
"loss": 0.3139,
|
| 1899 |
+
"step": 1350
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.2628145386766076,
|
| 1903 |
+
"grad_norm": 0.19557894552720384,
|
| 1904 |
+
"learning_rate": 8.192646297255309e-06,
|
| 1905 |
+
"loss": 0.3258,
|
| 1906 |
+
"step": 1355
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.2674743709226468,
|
| 1910 |
+
"grad_norm": 0.22037610848319983,
|
| 1911 |
+
"learning_rate": 8.140859658208183e-06,
|
| 1912 |
+
"loss": 0.3167,
|
| 1913 |
+
"step": 1360
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.272134203168686,
|
| 1917 |
+
"grad_norm": 0.19614411951293328,
|
| 1918 |
+
"learning_rate": 8.089073019161057e-06,
|
| 1919 |
+
"loss": 0.315,
|
| 1920 |
+
"step": 1365
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.2767940354147251,
|
| 1924 |
+
"grad_norm": 0.2184836880400932,
|
| 1925 |
+
"learning_rate": 8.037286380113931e-06,
|
| 1926 |
+
"loss": 0.3156,
|
| 1927 |
+
"step": 1370
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.281453867660764,
|
| 1931 |
+
"grad_norm": 0.21389038369245703,
|
| 1932 |
+
"learning_rate": 7.985499741066805e-06,
|
| 1933 |
+
"loss": 0.308,
|
| 1934 |
+
"step": 1375
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.2861136999068035,
|
| 1938 |
+
"grad_norm": 0.20539585029211851,
|
| 1939 |
+
"learning_rate": 7.93371310201968e-06,
|
| 1940 |
+
"loss": 0.3192,
|
| 1941 |
+
"step": 1380
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.2907735321528424,
|
| 1945 |
+
"grad_norm": 0.19934518228998827,
|
| 1946 |
+
"learning_rate": 7.881926462972553e-06,
|
| 1947 |
+
"loss": 0.3215,
|
| 1948 |
+
"step": 1385
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.2954333643988816,
|
| 1952 |
+
"grad_norm": 0.20741086597019026,
|
| 1953 |
+
"learning_rate": 7.830139823925427e-06,
|
| 1954 |
+
"loss": 0.314,
|
| 1955 |
+
"step": 1390
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.3000931966449207,
|
| 1959 |
+
"grad_norm": 0.22065169448140684,
|
| 1960 |
+
"learning_rate": 7.778353184878302e-06,
|
| 1961 |
+
"loss": 0.3199,
|
| 1962 |
+
"step": 1395
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.30475302889096,
|
| 1966 |
+
"grad_norm": 0.19477745041465316,
|
| 1967 |
+
"learning_rate": 7.726566545831177e-06,
|
| 1968 |
+
"loss": 0.3105,
|
| 1969 |
+
"step": 1400
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.309412861136999,
|
| 1973 |
+
"grad_norm": 0.19600332577375437,
|
| 1974 |
+
"learning_rate": 7.67477990678405e-06,
|
| 1975 |
+
"loss": 0.3201,
|
| 1976 |
+
"step": 1405
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.3140726933830382,
|
| 1980 |
+
"grad_norm": 0.20148776251738024,
|
| 1981 |
+
"learning_rate": 7.6229932677369245e-06,
|
| 1982 |
+
"loss": 0.314,
|
| 1983 |
+
"step": 1410
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.3187325256290774,
|
| 1987 |
+
"grad_norm": 0.2064755512233211,
|
| 1988 |
+
"learning_rate": 7.571206628689799e-06,
|
| 1989 |
+
"loss": 0.3209,
|
| 1990 |
+
"step": 1415
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.3233923578751166,
|
| 1994 |
+
"grad_norm": 0.2031518775941825,
|
| 1995 |
+
"learning_rate": 7.519419989642673e-06,
|
| 1996 |
+
"loss": 0.3049,
|
| 1997 |
+
"step": 1420
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.3280521901211557,
|
| 2001 |
+
"grad_norm": 0.19891962178529504,
|
| 2002 |
+
"learning_rate": 7.467633350595547e-06,
|
| 2003 |
+
"loss": 0.316,
|
| 2004 |
+
"step": 1425
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.3327120223671947,
|
| 2008 |
+
"grad_norm": 0.20917352538781994,
|
| 2009 |
+
"learning_rate": 7.415846711548422e-06,
|
| 2010 |
+
"loss": 0.3197,
|
| 2011 |
+
"step": 1430
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.337371854613234,
|
| 2015 |
+
"grad_norm": 0.18876283067477193,
|
| 2016 |
+
"learning_rate": 7.364060072501296e-06,
|
| 2017 |
+
"loss": 0.3231,
|
| 2018 |
+
"step": 1435
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.342031686859273,
|
| 2022 |
+
"grad_norm": 0.19676783428533887,
|
| 2023 |
+
"learning_rate": 7.312273433454169e-06,
|
| 2024 |
+
"loss": 0.3177,
|
| 2025 |
+
"step": 1440
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.3466915191053122,
|
| 2029 |
+
"grad_norm": 0.18572514729909312,
|
| 2030 |
+
"learning_rate": 7.260486794407044e-06,
|
| 2031 |
+
"loss": 0.3211,
|
| 2032 |
+
"step": 1445
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.3513513513513513,
|
| 2036 |
+
"grad_norm": 0.19146579294733382,
|
| 2037 |
+
"learning_rate": 7.208700155359918e-06,
|
| 2038 |
+
"loss": 0.3118,
|
| 2039 |
+
"step": 1450
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.3560111835973905,
|
| 2043 |
+
"grad_norm": 0.18852660444469807,
|
| 2044 |
+
"learning_rate": 7.156913516312793e-06,
|
| 2045 |
+
"loss": 0.3162,
|
| 2046 |
+
"step": 1455
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.3606710158434296,
|
| 2050 |
+
"grad_norm": 0.19324215253779436,
|
| 2051 |
+
"learning_rate": 7.105126877265666e-06,
|
| 2052 |
+
"loss": 0.3233,
|
| 2053 |
+
"step": 1460
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.3653308480894688,
|
| 2057 |
+
"grad_norm": 0.21358938430110477,
|
| 2058 |
+
"learning_rate": 7.05334023821854e-06,
|
| 2059 |
+
"loss": 0.3187,
|
| 2060 |
+
"step": 1465
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.369990680335508,
|
| 2064 |
+
"grad_norm": 0.19555774419476726,
|
| 2065 |
+
"learning_rate": 7.001553599171415e-06,
|
| 2066 |
+
"loss": 0.3148,
|
| 2067 |
+
"step": 1470
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.3746505125815471,
|
| 2071 |
+
"grad_norm": 0.17959759954123644,
|
| 2072 |
+
"learning_rate": 6.949766960124289e-06,
|
| 2073 |
+
"loss": 0.3139,
|
| 2074 |
+
"step": 1475
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.3793103448275863,
|
| 2078 |
+
"grad_norm": 0.18964982625602786,
|
| 2079 |
+
"learning_rate": 6.897980321077162e-06,
|
| 2080 |
+
"loss": 0.302,
|
| 2081 |
+
"step": 1480
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.3839701770736252,
|
| 2085 |
+
"grad_norm": 0.18930534523885367,
|
| 2086 |
+
"learning_rate": 6.846193682030037e-06,
|
| 2087 |
+
"loss": 0.3149,
|
| 2088 |
+
"step": 1485
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.3886300093196646,
|
| 2092 |
+
"grad_norm": 0.19639297256742036,
|
| 2093 |
+
"learning_rate": 6.794407042982911e-06,
|
| 2094 |
+
"loss": 0.3236,
|
| 2095 |
+
"step": 1490
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.3932898415657036,
|
| 2099 |
+
"grad_norm": 0.21467988374746413,
|
| 2100 |
+
"learning_rate": 6.742620403935786e-06,
|
| 2101 |
+
"loss": 0.3284,
|
| 2102 |
+
"step": 1495
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.3979496738117427,
|
| 2106 |
+
"grad_norm": 0.22648269852701486,
|
| 2107 |
+
"learning_rate": 6.690833764888659e-06,
|
| 2108 |
+
"loss": 0.3248,
|
| 2109 |
+
"step": 1500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.402609506057782,
|
| 2113 |
+
"grad_norm": 0.2122629193310997,
|
| 2114 |
+
"learning_rate": 6.639047125841533e-06,
|
| 2115 |
+
"loss": 0.3181,
|
| 2116 |
+
"step": 1505
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.407269338303821,
|
| 2120 |
+
"grad_norm": 0.21439399946575624,
|
| 2121 |
+
"learning_rate": 6.587260486794408e-06,
|
| 2122 |
+
"loss": 0.3111,
|
| 2123 |
+
"step": 1510
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.4119291705498602,
|
| 2127 |
+
"grad_norm": 0.21805459861989804,
|
| 2128 |
+
"learning_rate": 6.535473847747281e-06,
|
| 2129 |
+
"loss": 0.3194,
|
| 2130 |
+
"step": 1515
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.4165890027958994,
|
| 2134 |
+
"grad_norm": 0.18437558883318525,
|
| 2135 |
+
"learning_rate": 6.483687208700155e-06,
|
| 2136 |
+
"loss": 0.3186,
|
| 2137 |
+
"step": 1520
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.4212488350419386,
|
| 2141 |
+
"grad_norm": 0.19383647738248216,
|
| 2142 |
+
"learning_rate": 6.43190056965303e-06,
|
| 2143 |
+
"loss": 0.316,
|
| 2144 |
+
"step": 1525
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.4259086672879777,
|
| 2148 |
+
"grad_norm": 0.19238369432331215,
|
| 2149 |
+
"learning_rate": 6.380113930605904e-06,
|
| 2150 |
+
"loss": 0.3119,
|
| 2151 |
+
"step": 1530
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.4305684995340169,
|
| 2155 |
+
"grad_norm": 0.20161511281163794,
|
| 2156 |
+
"learning_rate": 6.3283272915587775e-06,
|
| 2157 |
+
"loss": 0.3173,
|
| 2158 |
+
"step": 1535
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.4352283317800558,
|
| 2162 |
+
"grad_norm": 0.18321974524601511,
|
| 2163 |
+
"learning_rate": 6.276540652511652e-06,
|
| 2164 |
+
"loss": 0.3138,
|
| 2165 |
+
"step": 1540
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.439888164026095,
|
| 2169 |
+
"grad_norm": 0.21285415491504464,
|
| 2170 |
+
"learning_rate": 6.2247540134645265e-06,
|
| 2171 |
+
"loss": 0.3152,
|
| 2172 |
+
"step": 1545
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.4445479962721341,
|
| 2176 |
+
"grad_norm": 0.19238925372724244,
|
| 2177 |
+
"learning_rate": 6.172967374417401e-06,
|
| 2178 |
+
"loss": 0.3148,
|
| 2179 |
+
"step": 1550
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.4492078285181733,
|
| 2183 |
+
"grad_norm": 0.21136751157123412,
|
| 2184 |
+
"learning_rate": 6.1211807353702746e-06,
|
| 2185 |
+
"loss": 0.3111,
|
| 2186 |
+
"step": 1555
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.4538676607642125,
|
| 2190 |
+
"grad_norm": 0.1979462412561175,
|
| 2191 |
+
"learning_rate": 6.069394096323149e-06,
|
| 2192 |
+
"loss": 0.3127,
|
| 2193 |
+
"step": 1560
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.4585274930102516,
|
| 2197 |
+
"grad_norm": 0.18992603381080705,
|
| 2198 |
+
"learning_rate": 6.0176074572760235e-06,
|
| 2199 |
+
"loss": 0.3154,
|
| 2200 |
+
"step": 1565
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.4631873252562908,
|
| 2204 |
+
"grad_norm": 0.18356342906034864,
|
| 2205 |
+
"learning_rate": 5.9658208182288976e-06,
|
| 2206 |
+
"loss": 0.3169,
|
| 2207 |
+
"step": 1570
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.46784715750233,
|
| 2211 |
+
"grad_norm": 0.18698833501026985,
|
| 2212 |
+
"learning_rate": 5.914034179181772e-06,
|
| 2213 |
+
"loss": 0.3192,
|
| 2214 |
+
"step": 1575
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.4725069897483691,
|
| 2218 |
+
"grad_norm": 0.18659658551949185,
|
| 2219 |
+
"learning_rate": 5.862247540134646e-06,
|
| 2220 |
+
"loss": 0.3202,
|
| 2221 |
+
"step": 1580
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.477166821994408,
|
| 2225 |
+
"grad_norm": 0.20607394729321243,
|
| 2226 |
+
"learning_rate": 5.81046090108752e-06,
|
| 2227 |
+
"loss": 0.3179,
|
| 2228 |
+
"step": 1585
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.4818266542404475,
|
| 2232 |
+
"grad_norm": 0.18871598623396943,
|
| 2233 |
+
"learning_rate": 5.758674262040395e-06,
|
| 2234 |
+
"loss": 0.32,
|
| 2235 |
+
"step": 1590
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.4864864864864864,
|
| 2239 |
+
"grad_norm": 0.19724974014550137,
|
| 2240 |
+
"learning_rate": 5.706887622993268e-06,
|
| 2241 |
+
"loss": 0.3143,
|
| 2242 |
+
"step": 1595
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.4911463187325256,
|
| 2246 |
+
"grad_norm": 0.19442309714878647,
|
| 2247 |
+
"learning_rate": 5.655100983946143e-06,
|
| 2248 |
+
"loss": 0.3155,
|
| 2249 |
+
"step": 1600
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.4958061509785647,
|
| 2253 |
+
"grad_norm": 0.2290940185613949,
|
| 2254 |
+
"learning_rate": 5.603314344899017e-06,
|
| 2255 |
+
"loss": 0.3241,
|
| 2256 |
+
"step": 1605
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 1.500465983224604,
|
| 2260 |
+
"grad_norm": 0.20552300203050755,
|
| 2261 |
+
"learning_rate": 5.55152770585189e-06,
|
| 2262 |
+
"loss": 0.3197,
|
| 2263 |
+
"step": 1610
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.505125815470643,
|
| 2267 |
+
"grad_norm": 0.2138342700269858,
|
| 2268 |
+
"learning_rate": 5.499741066804765e-06,
|
| 2269 |
+
"loss": 0.3149,
|
| 2270 |
+
"step": 1615
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 1.5097856477166822,
|
| 2274 |
+
"grad_norm": 0.1773024842853527,
|
| 2275 |
+
"learning_rate": 5.447954427757639e-06,
|
| 2276 |
+
"loss": 0.3143,
|
| 2277 |
+
"step": 1620
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.5144454799627214,
|
| 2281 |
+
"grad_norm": 0.1782828676659382,
|
| 2282 |
+
"learning_rate": 5.396167788710514e-06,
|
| 2283 |
+
"loss": 0.3085,
|
| 2284 |
+
"step": 1625
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 1.5191053122087603,
|
| 2288 |
+
"grad_norm": 0.20151066828643008,
|
| 2289 |
+
"learning_rate": 5.344381149663387e-06,
|
| 2290 |
+
"loss": 0.3092,
|
| 2291 |
+
"step": 1630
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.5237651444547997,
|
| 2295 |
+
"grad_norm": 0.1936112629982006,
|
| 2296 |
+
"learning_rate": 5.292594510616261e-06,
|
| 2297 |
+
"loss": 0.3092,
|
| 2298 |
+
"step": 1635
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.5284249767008387,
|
| 2302 |
+
"grad_norm": 0.20031650907945875,
|
| 2303 |
+
"learning_rate": 5.240807871569136e-06,
|
| 2304 |
+
"loss": 0.3079,
|
| 2305 |
+
"step": 1640
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.533084808946878,
|
| 2309 |
+
"grad_norm": 0.19466786072761738,
|
| 2310 |
+
"learning_rate": 5.18902123252201e-06,
|
| 2311 |
+
"loss": 0.325,
|
| 2312 |
+
"step": 1645
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 1.537744641192917,
|
| 2316 |
+
"grad_norm": 0.2014645297149083,
|
| 2317 |
+
"learning_rate": 5.137234593474883e-06,
|
| 2318 |
+
"loss": 0.3193,
|
| 2319 |
+
"step": 1650
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.5424044734389561,
|
| 2323 |
+
"grad_norm": 0.18800764754924237,
|
| 2324 |
+
"learning_rate": 5.085447954427758e-06,
|
| 2325 |
+
"loss": 0.3223,
|
| 2326 |
+
"step": 1655
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.5470643056849953,
|
| 2330 |
+
"grad_norm": 0.22145725970374222,
|
| 2331 |
+
"learning_rate": 5.033661315380632e-06,
|
| 2332 |
+
"loss": 0.3226,
|
| 2333 |
+
"step": 1660
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.5517241379310345,
|
| 2337 |
+
"grad_norm": 0.2264737586413433,
|
| 2338 |
+
"learning_rate": 4.981874676333506e-06,
|
| 2339 |
+
"loss": 0.3098,
|
| 2340 |
+
"step": 1665
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.5563839701770736,
|
| 2344 |
+
"grad_norm": 0.19843349190924084,
|
| 2345 |
+
"learning_rate": 4.930088037286381e-06,
|
| 2346 |
+
"loss": 0.3173,
|
| 2347 |
+
"step": 1670
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.5610438024231128,
|
| 2351 |
+
"grad_norm": 0.21010850815608753,
|
| 2352 |
+
"learning_rate": 4.878301398239254e-06,
|
| 2353 |
+
"loss": 0.3242,
|
| 2354 |
+
"step": 1675
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.565703634669152,
|
| 2358 |
+
"grad_norm": 0.2064935277967238,
|
| 2359 |
+
"learning_rate": 4.826514759192129e-06,
|
| 2360 |
+
"loss": 0.3184,
|
| 2361 |
+
"step": 1680
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.570363466915191,
|
| 2365 |
+
"grad_norm": 0.19388277530401346,
|
| 2366 |
+
"learning_rate": 4.774728120145003e-06,
|
| 2367 |
+
"loss": 0.3096,
|
| 2368 |
+
"step": 1685
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.5750232991612303,
|
| 2372 |
+
"grad_norm": 0.2009122264808897,
|
| 2373 |
+
"learning_rate": 4.7229414810978765e-06,
|
| 2374 |
+
"loss": 0.3233,
|
| 2375 |
+
"step": 1690
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.5796831314072692,
|
| 2379 |
+
"grad_norm": 0.1847210364496899,
|
| 2380 |
+
"learning_rate": 4.671154842050751e-06,
|
| 2381 |
+
"loss": 0.3229,
|
| 2382 |
+
"step": 1695
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 1.5843429636533086,
|
| 2386 |
+
"grad_norm": 0.19999440492528722,
|
| 2387 |
+
"learning_rate": 4.6193682030036255e-06,
|
| 2388 |
+
"loss": 0.3126,
|
| 2389 |
+
"step": 1700
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.5890027958993476,
|
| 2393 |
+
"grad_norm": 0.1967714404409244,
|
| 2394 |
+
"learning_rate": 4.5675815639564995e-06,
|
| 2395 |
+
"loss": 0.3161,
|
| 2396 |
+
"step": 1705
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 1.5936626281453867,
|
| 2400 |
+
"grad_norm": 0.19056228994472138,
|
| 2401 |
+
"learning_rate": 4.5157949249093736e-06,
|
| 2402 |
+
"loss": 0.3179,
|
| 2403 |
+
"step": 1710
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.598322460391426,
|
| 2407 |
+
"grad_norm": 0.19780527100077158,
|
| 2408 |
+
"learning_rate": 4.464008285862248e-06,
|
| 2409 |
+
"loss": 0.3107,
|
| 2410 |
+
"step": 1715
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.602982292637465,
|
| 2414 |
+
"grad_norm": 0.20087968051198601,
|
| 2415 |
+
"learning_rate": 4.412221646815122e-06,
|
| 2416 |
+
"loss": 0.3194,
|
| 2417 |
+
"step": 1720
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.6076421248835042,
|
| 2421 |
+
"grad_norm": 0.18138579556889722,
|
| 2422 |
+
"learning_rate": 4.3604350077679966e-06,
|
| 2423 |
+
"loss": 0.3167,
|
| 2424 |
+
"step": 1725
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.6123019571295434,
|
| 2428 |
+
"grad_norm": 0.19116121249902454,
|
| 2429 |
+
"learning_rate": 4.308648368720871e-06,
|
| 2430 |
+
"loss": 0.3119,
|
| 2431 |
+
"step": 1730
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.6169617893755825,
|
| 2435 |
+
"grad_norm": 0.20253537385722165,
|
| 2436 |
+
"learning_rate": 4.256861729673745e-06,
|
| 2437 |
+
"loss": 0.3186,
|
| 2438 |
+
"step": 1735
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.6216216216216215,
|
| 2442 |
+
"grad_norm": 0.19508207479386244,
|
| 2443 |
+
"learning_rate": 4.205075090626619e-06,
|
| 2444 |
+
"loss": 0.3175,
|
| 2445 |
+
"step": 1740
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.6262814538676609,
|
| 2449 |
+
"grad_norm": 0.18521359809563662,
|
| 2450 |
+
"learning_rate": 4.153288451579493e-06,
|
| 2451 |
+
"loss": 0.3168,
|
| 2452 |
+
"step": 1745
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.6309412861136998,
|
| 2456 |
+
"grad_norm": 0.21769599978818913,
|
| 2457 |
+
"learning_rate": 4.101501812532367e-06,
|
| 2458 |
+
"loss": 0.3192,
|
| 2459 |
+
"step": 1750
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.6356011183597392,
|
| 2463 |
+
"grad_norm": 0.1951979997638157,
|
| 2464 |
+
"learning_rate": 4.049715173485242e-06,
|
| 2465 |
+
"loss": 0.3151,
|
| 2466 |
+
"step": 1755
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.6402609506057781,
|
| 2470 |
+
"grad_norm": 0.20115642532305716,
|
| 2471 |
+
"learning_rate": 3.997928534438115e-06,
|
| 2472 |
+
"loss": 0.3221,
|
| 2473 |
+
"step": 1760
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 1.6449207828518173,
|
| 2477 |
+
"grad_norm": 0.18954273661107576,
|
| 2478 |
+
"learning_rate": 3.94614189539099e-06,
|
| 2479 |
+
"loss": 0.319,
|
| 2480 |
+
"step": 1765
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 1.6495806150978565,
|
| 2484 |
+
"grad_norm": 0.1898263373664628,
|
| 2485 |
+
"learning_rate": 3.894355256343864e-06,
|
| 2486 |
+
"loss": 0.3126,
|
| 2487 |
+
"step": 1770
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 1.6542404473438956,
|
| 2491 |
+
"grad_norm": 0.18770630530008564,
|
| 2492 |
+
"learning_rate": 3.842568617296738e-06,
|
| 2493 |
+
"loss": 0.3077,
|
| 2494 |
+
"step": 1775
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 1.6589002795899348,
|
| 2498 |
+
"grad_norm": 0.20920463370343462,
|
| 2499 |
+
"learning_rate": 3.790781978249612e-06,
|
| 2500 |
+
"loss": 0.319,
|
| 2501 |
+
"step": 1780
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 1.6635601118359737,
|
| 2505 |
+
"grad_norm": 0.2035848113749002,
|
| 2506 |
+
"learning_rate": 3.7389953392024856e-06,
|
| 2507 |
+
"loss": 0.3179,
|
| 2508 |
+
"step": 1785
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 1.6682199440820131,
|
| 2512 |
+
"grad_norm": 0.1838396556826729,
|
| 2513 |
+
"learning_rate": 3.68720870015536e-06,
|
| 2514 |
+
"loss": 0.316,
|
| 2515 |
+
"step": 1790
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 1.672879776328052,
|
| 2519 |
+
"grad_norm": 0.21088430204050254,
|
| 2520 |
+
"learning_rate": 3.635422061108234e-06,
|
| 2521 |
+
"loss": 0.3086,
|
| 2522 |
+
"step": 1795
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.6775396085740915,
|
| 2526 |
+
"grad_norm": 0.185482590257671,
|
| 2527 |
+
"learning_rate": 3.5836354220611086e-06,
|
| 2528 |
+
"loss": 0.3063,
|
| 2529 |
+
"step": 1800
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.6821994408201304,
|
| 2533 |
+
"grad_norm": 0.19312227185115607,
|
| 2534 |
+
"learning_rate": 3.5318487830139827e-06,
|
| 2535 |
+
"loss": 0.3083,
|
| 2536 |
+
"step": 1805
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 1.6868592730661698,
|
| 2540 |
+
"grad_norm": 0.1960317573244206,
|
| 2541 |
+
"learning_rate": 3.480062143966857e-06,
|
| 2542 |
+
"loss": 0.3122,
|
| 2543 |
+
"step": 1810
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 1.6915191053122087,
|
| 2547 |
+
"grad_norm": 0.19789243390438088,
|
| 2548 |
+
"learning_rate": 3.4282755049197308e-06,
|
| 2549 |
+
"loss": 0.3087,
|
| 2550 |
+
"step": 1815
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 1.696178937558248,
|
| 2554 |
+
"grad_norm": 0.18112744143370826,
|
| 2555 |
+
"learning_rate": 3.3764888658726052e-06,
|
| 2556 |
+
"loss": 0.3106,
|
| 2557 |
+
"step": 1820
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 1.700838769804287,
|
| 2561 |
+
"grad_norm": 0.21548231654348435,
|
| 2562 |
+
"learning_rate": 3.3247022268254793e-06,
|
| 2563 |
+
"loss": 0.3217,
|
| 2564 |
+
"step": 1825
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 1.7054986020503262,
|
| 2568 |
+
"grad_norm": 0.1814574471570304,
|
| 2569 |
+
"learning_rate": 3.2729155877783538e-06,
|
| 2570 |
+
"loss": 0.3193,
|
| 2571 |
+
"step": 1830
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 1.7101584342963654,
|
| 2575 |
+
"grad_norm": 0.22078602305323497,
|
| 2576 |
+
"learning_rate": 3.2211289487312274e-06,
|
| 2577 |
+
"loss": 0.3206,
|
| 2578 |
+
"step": 1835
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 1.7148182665424043,
|
| 2582 |
+
"grad_norm": 0.18658908941872768,
|
| 2583 |
+
"learning_rate": 3.169342309684102e-06,
|
| 2584 |
+
"loss": 0.3141,
|
| 2585 |
+
"step": 1840
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 1.7194780987884437,
|
| 2589 |
+
"grad_norm": 0.1782787618724745,
|
| 2590 |
+
"learning_rate": 3.117555670636976e-06,
|
| 2591 |
+
"loss": 0.3149,
|
| 2592 |
+
"step": 1845
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 1.7241379310344827,
|
| 2596 |
+
"grad_norm": 0.17932135518844652,
|
| 2597 |
+
"learning_rate": 3.0657690315898504e-06,
|
| 2598 |
+
"loss": 0.3017,
|
| 2599 |
+
"step": 1850
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 1.728797763280522,
|
| 2603 |
+
"grad_norm": 0.19474093174359786,
|
| 2604 |
+
"learning_rate": 3.013982392542724e-06,
|
| 2605 |
+
"loss": 0.3101,
|
| 2606 |
+
"step": 1855
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 1.733457595526561,
|
| 2610 |
+
"grad_norm": 0.19278349416418183,
|
| 2611 |
+
"learning_rate": 2.9621957534955985e-06,
|
| 2612 |
+
"loss": 0.311,
|
| 2613 |
+
"step": 1860
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 1.7381174277726001,
|
| 2617 |
+
"grad_norm": 0.18373595675432944,
|
| 2618 |
+
"learning_rate": 2.9104091144484725e-06,
|
| 2619 |
+
"loss": 0.314,
|
| 2620 |
+
"step": 1865
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 1.7427772600186393,
|
| 2624 |
+
"grad_norm": 0.1832866163272324,
|
| 2625 |
+
"learning_rate": 2.858622475401347e-06,
|
| 2626 |
+
"loss": 0.3099,
|
| 2627 |
+
"step": 1870
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.7474370922646785,
|
| 2631 |
+
"grad_norm": 0.1700878976485856,
|
| 2632 |
+
"learning_rate": 2.8068358363542206e-06,
|
| 2633 |
+
"loss": 0.3177,
|
| 2634 |
+
"step": 1875
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 1.7520969245107176,
|
| 2638 |
+
"grad_norm": 0.19630790934750134,
|
| 2639 |
+
"learning_rate": 2.7550491973070947e-06,
|
| 2640 |
+
"loss": 0.3147,
|
| 2641 |
+
"step": 1880
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.7567567567567568,
|
| 2645 |
+
"grad_norm": 0.1935390479382422,
|
| 2646 |
+
"learning_rate": 2.703262558259969e-06,
|
| 2647 |
+
"loss": 0.3191,
|
| 2648 |
+
"step": 1885
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 1.761416589002796,
|
| 2652 |
+
"grad_norm": 0.18024055440625963,
|
| 2653 |
+
"learning_rate": 2.6514759192128432e-06,
|
| 2654 |
+
"loss": 0.3125,
|
| 2655 |
+
"step": 1890
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 1.766076421248835,
|
| 2659 |
+
"grad_norm": 0.1851607633561796,
|
| 2660 |
+
"learning_rate": 2.5996892801657177e-06,
|
| 2661 |
+
"loss": 0.3135,
|
| 2662 |
+
"step": 1895
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 1.7707362534948743,
|
| 2666 |
+
"grad_norm": 0.18693937618463963,
|
| 2667 |
+
"learning_rate": 2.5479026411185913e-06,
|
| 2668 |
+
"loss": 0.3079,
|
| 2669 |
+
"step": 1900
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 1.7753960857409132,
|
| 2673 |
+
"grad_norm": 0.18306356346123398,
|
| 2674 |
+
"learning_rate": 2.496116002071466e-06,
|
| 2675 |
+
"loss": 0.3087,
|
| 2676 |
+
"step": 1905
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 1.7800559179869526,
|
| 2680 |
+
"grad_norm": 0.1750201835993522,
|
| 2681 |
+
"learning_rate": 2.44432936302434e-06,
|
| 2682 |
+
"loss": 0.316,
|
| 2683 |
+
"step": 1910
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 1.7847157502329916,
|
| 2687 |
+
"grad_norm": 0.18396826364198557,
|
| 2688 |
+
"learning_rate": 2.3925427239772143e-06,
|
| 2689 |
+
"loss": 0.303,
|
| 2690 |
+
"step": 1915
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 1.7893755824790307,
|
| 2694 |
+
"grad_norm": 0.18494502790887468,
|
| 2695 |
+
"learning_rate": 2.340756084930088e-06,
|
| 2696 |
+
"loss": 0.3195,
|
| 2697 |
+
"step": 1920
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 1.7940354147250699,
|
| 2701 |
+
"grad_norm": 0.17779334157355717,
|
| 2702 |
+
"learning_rate": 2.2889694458829624e-06,
|
| 2703 |
+
"loss": 0.3119,
|
| 2704 |
+
"step": 1925
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 1.798695246971109,
|
| 2708 |
+
"grad_norm": 0.18374129599917147,
|
| 2709 |
+
"learning_rate": 2.2371828068358365e-06,
|
| 2710 |
+
"loss": 0.3099,
|
| 2711 |
+
"step": 1930
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 1.8033550792171482,
|
| 2715 |
+
"grad_norm": 0.18305924460244258,
|
| 2716 |
+
"learning_rate": 2.1853961677887105e-06,
|
| 2717 |
+
"loss": 0.3156,
|
| 2718 |
+
"step": 1935
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 1.8080149114631874,
|
| 2722 |
+
"grad_norm": 0.17348252725460908,
|
| 2723 |
+
"learning_rate": 2.1336095287415846e-06,
|
| 2724 |
+
"loss": 0.3077,
|
| 2725 |
+
"step": 1940
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 1.8126747437092265,
|
| 2729 |
+
"grad_norm": 0.18002736644951658,
|
| 2730 |
+
"learning_rate": 2.081822889694459e-06,
|
| 2731 |
+
"loss": 0.3217,
|
| 2732 |
+
"step": 1945
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 1.8173345759552655,
|
| 2736 |
+
"grad_norm": 0.19097984942265778,
|
| 2737 |
+
"learning_rate": 2.030036250647333e-06,
|
| 2738 |
+
"loss": 0.3057,
|
| 2739 |
+
"step": 1950
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 1.8219944082013049,
|
| 2743 |
+
"grad_norm": 0.19397089209826424,
|
| 2744 |
+
"learning_rate": 1.978249611600207e-06,
|
| 2745 |
+
"loss": 0.312,
|
| 2746 |
+
"step": 1955
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 1.8266542404473438,
|
| 2750 |
+
"grad_norm": 0.1737258474947117,
|
| 2751 |
+
"learning_rate": 1.9264629725530816e-06,
|
| 2752 |
+
"loss": 0.3144,
|
| 2753 |
+
"step": 1960
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 1.8313140726933832,
|
| 2757 |
+
"grad_norm": 0.17866826131161348,
|
| 2758 |
+
"learning_rate": 1.8746763335059557e-06,
|
| 2759 |
+
"loss": 0.3158,
|
| 2760 |
+
"step": 1965
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 1.8359739049394221,
|
| 2764 |
+
"grad_norm": 0.1847963686612644,
|
| 2765 |
+
"learning_rate": 1.8228896944588297e-06,
|
| 2766 |
+
"loss": 0.3135,
|
| 2767 |
+
"step": 1970
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 1.8406337371854613,
|
| 2771 |
+
"grad_norm": 0.17225040204469855,
|
| 2772 |
+
"learning_rate": 1.771103055411704e-06,
|
| 2773 |
+
"loss": 0.3201,
|
| 2774 |
+
"step": 1975
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 1.8452935694315005,
|
| 2778 |
+
"grad_norm": 0.1784754273129112,
|
| 2779 |
+
"learning_rate": 1.719316416364578e-06,
|
| 2780 |
+
"loss": 0.3116,
|
| 2781 |
+
"step": 1980
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 1.8499534016775396,
|
| 2785 |
+
"grad_norm": 0.1873529018355137,
|
| 2786 |
+
"learning_rate": 1.6675297773174523e-06,
|
| 2787 |
+
"loss": 0.3068,
|
| 2788 |
+
"step": 1985
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 1.8546132339235788,
|
| 2792 |
+
"grad_norm": 0.18994212675755204,
|
| 2793 |
+
"learning_rate": 1.6157431382703264e-06,
|
| 2794 |
+
"loss": 0.3281,
|
| 2795 |
+
"step": 1990
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 1.8592730661696177,
|
| 2799 |
+
"grad_norm": 0.17280992253062147,
|
| 2800 |
+
"learning_rate": 1.5639564992232006e-06,
|
| 2801 |
+
"loss": 0.3137,
|
| 2802 |
+
"step": 1995
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 1.8639328984156571,
|
| 2806 |
+
"grad_norm": 0.18082977178380857,
|
| 2807 |
+
"learning_rate": 1.512169860176075e-06,
|
| 2808 |
+
"loss": 0.311,
|
| 2809 |
+
"step": 2000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 1.868592730661696,
|
| 2813 |
+
"grad_norm": 0.1865537678103653,
|
| 2814 |
+
"learning_rate": 1.460383221128949e-06,
|
| 2815 |
+
"loss": 0.3136,
|
| 2816 |
+
"step": 2005
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 1.8732525629077355,
|
| 2820 |
+
"grad_norm": 0.18177081525856895,
|
| 2821 |
+
"learning_rate": 1.4085965820818228e-06,
|
| 2822 |
+
"loss": 0.3179,
|
| 2823 |
+
"step": 2010
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 1.8779123951537744,
|
| 2827 |
+
"grad_norm": 0.17820198629127978,
|
| 2828 |
+
"learning_rate": 1.356809943034697e-06,
|
| 2829 |
+
"loss": 0.308,
|
| 2830 |
+
"step": 2015
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 1.8825722273998136,
|
| 2834 |
+
"grad_norm": 0.185863894794329,
|
| 2835 |
+
"learning_rate": 1.305023303987571e-06,
|
| 2836 |
+
"loss": 0.3065,
|
| 2837 |
+
"step": 2020
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 1.8872320596458527,
|
| 2841 |
+
"grad_norm": 0.18770653417781014,
|
| 2842 |
+
"learning_rate": 1.2532366649404454e-06,
|
| 2843 |
+
"loss": 0.3101,
|
| 2844 |
+
"step": 2025
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 1.8918918918918919,
|
| 2848 |
+
"grad_norm": 0.17409257528881936,
|
| 2849 |
+
"learning_rate": 1.2014500258933196e-06,
|
| 2850 |
+
"loss": 0.3121,
|
| 2851 |
+
"step": 2030
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 1.896551724137931,
|
| 2855 |
+
"grad_norm": 0.17868880226457717,
|
| 2856 |
+
"learning_rate": 1.1496633868461937e-06,
|
| 2857 |
+
"loss": 0.3127,
|
| 2858 |
+
"step": 2035
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 1.9012115563839702,
|
| 2862 |
+
"grad_norm": 0.18133974763519492,
|
| 2863 |
+
"learning_rate": 1.097876747799068e-06,
|
| 2864 |
+
"loss": 0.3136,
|
| 2865 |
+
"step": 2040
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 1.9058713886300094,
|
| 2869 |
+
"grad_norm": 0.18239370217368586,
|
| 2870 |
+
"learning_rate": 1.046090108751942e-06,
|
| 2871 |
+
"loss": 0.3241,
|
| 2872 |
+
"step": 2045
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 1.9105312208760483,
|
| 2876 |
+
"grad_norm": 0.17690424687928452,
|
| 2877 |
+
"learning_rate": 9.943034697048163e-07,
|
| 2878 |
+
"loss": 0.3186,
|
| 2879 |
+
"step": 2050
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 1.9151910531220877,
|
| 2883 |
+
"grad_norm": 0.17365540631574325,
|
| 2884 |
+
"learning_rate": 9.425168306576904e-07,
|
| 2885 |
+
"loss": 0.3092,
|
| 2886 |
+
"step": 2055
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 1.9198508853681266,
|
| 2890 |
+
"grad_norm": 0.1760791742900446,
|
| 2891 |
+
"learning_rate": 8.907301916105646e-07,
|
| 2892 |
+
"loss": 0.3182,
|
| 2893 |
+
"step": 2060
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 1.924510717614166,
|
| 2897 |
+
"grad_norm": 0.19407129934862996,
|
| 2898 |
+
"learning_rate": 8.389435525634387e-07,
|
| 2899 |
+
"loss": 0.313,
|
| 2900 |
+
"step": 2065
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 1.929170549860205,
|
| 2904 |
+
"grad_norm": 0.17237038499017496,
|
| 2905 |
+
"learning_rate": 7.871569135163129e-07,
|
| 2906 |
+
"loss": 0.316,
|
| 2907 |
+
"step": 2070
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 1.9338303821062441,
|
| 2911 |
+
"grad_norm": 0.18568643784585992,
|
| 2912 |
+
"learning_rate": 7.35370274469187e-07,
|
| 2913 |
+
"loss": 0.3232,
|
| 2914 |
+
"step": 2075
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 1.9384902143522833,
|
| 2918 |
+
"grad_norm": 0.18031325235805645,
|
| 2919 |
+
"learning_rate": 6.835836354220611e-07,
|
| 2920 |
+
"loss": 0.311,
|
| 2921 |
+
"step": 2080
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 1.9431500465983225,
|
| 2925 |
+
"grad_norm": 0.19850008316008122,
|
| 2926 |
+
"learning_rate": 6.317969963749353e-07,
|
| 2927 |
+
"loss": 0.313,
|
| 2928 |
+
"step": 2085
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 1.9478098788443616,
|
| 2932 |
+
"grad_norm": 0.18169347646543055,
|
| 2933 |
+
"learning_rate": 5.800103573278094e-07,
|
| 2934 |
+
"loss": 0.3148,
|
| 2935 |
+
"step": 2090
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 1.9524697110904008,
|
| 2939 |
+
"grad_norm": 0.18682984344018164,
|
| 2940 |
+
"learning_rate": 5.282237182806836e-07,
|
| 2941 |
+
"loss": 0.3016,
|
| 2942 |
+
"step": 2095
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 1.95712954333644,
|
| 2946 |
+
"grad_norm": 0.19368082644307608,
|
| 2947 |
+
"learning_rate": 4.764370792335578e-07,
|
| 2948 |
+
"loss": 0.3175,
|
| 2949 |
+
"step": 2100
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 1.961789375582479,
|
| 2953 |
+
"grad_norm": 0.17122020769064838,
|
| 2954 |
+
"learning_rate": 4.2465044018643194e-07,
|
| 2955 |
+
"loss": 0.3152,
|
| 2956 |
+
"step": 2105
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 1.9664492078285183,
|
| 2960 |
+
"grad_norm": 0.17219123727385735,
|
| 2961 |
+
"learning_rate": 3.728638011393061e-07,
|
| 2962 |
+
"loss": 0.318,
|
| 2963 |
+
"step": 2110
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 1.9711090400745572,
|
| 2967 |
+
"grad_norm": 0.16986195254826772,
|
| 2968 |
+
"learning_rate": 3.210771620921802e-07,
|
| 2969 |
+
"loss": 0.3211,
|
| 2970 |
+
"step": 2115
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 1.9757688723205966,
|
| 2974 |
+
"grad_norm": 0.1676620379896325,
|
| 2975 |
+
"learning_rate": 2.692905230450544e-07,
|
| 2976 |
+
"loss": 0.3147,
|
| 2977 |
+
"step": 2120
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 1.9804287045666356,
|
| 2981 |
+
"grad_norm": 0.1784700476744974,
|
| 2982 |
+
"learning_rate": 2.1750388399792857e-07,
|
| 2983 |
+
"loss": 0.3102,
|
| 2984 |
+
"step": 2125
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 1.9850885368126747,
|
| 2988 |
+
"grad_norm": 0.17753084232759492,
|
| 2989 |
+
"learning_rate": 1.657172449508027e-07,
|
| 2990 |
+
"loss": 0.3154,
|
| 2991 |
+
"step": 2130
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 1.9897483690587139,
|
| 2995 |
+
"grad_norm": 0.16810901109199483,
|
| 2996 |
+
"learning_rate": 1.1393060590367686e-07,
|
| 2997 |
+
"loss": 0.3064,
|
| 2998 |
+
"step": 2135
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 1.994408201304753,
|
| 3002 |
+
"grad_norm": 0.16989060528581737,
|
| 3003 |
+
"learning_rate": 6.214396685655102e-08,
|
| 3004 |
+
"loss": 0.3126,
|
| 3005 |
+
"step": 2140
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 1.9990680335507922,
|
| 3009 |
+
"grad_norm": 0.1916011537219613,
|
| 3010 |
+
"learning_rate": 1.0357327809425169e-08,
|
| 3011 |
+
"loss": 0.317,
|
| 3012 |
+
"step": 2145
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.0,
|
| 3016 |
+
"step": 2146,
|
| 3017 |
+
"total_flos": 1.8367600516462019e+18,
|
| 3018 |
+
"train_loss": 0.34532702185789893,
|
| 3019 |
+
"train_runtime": 73160.0405,
|
| 3020 |
+
"train_samples_per_second": 0.469,
|
| 3021 |
+
"train_steps_per_second": 0.029
|
| 3022 |
+
}
|
| 3023 |
+
],
|
| 3024 |
+
"logging_steps": 5,
|
| 3025 |
+
"max_steps": 2146,
|
| 3026 |
+
"num_input_tokens_seen": 0,
|
| 3027 |
+
"num_train_epochs": 2,
|
| 3028 |
+
"save_steps": 500,
|
| 3029 |
+
"stateful_callbacks": {
|
| 3030 |
+
"TrainerControl": {
|
| 3031 |
+
"args": {
|
| 3032 |
+
"should_epoch_stop": false,
|
| 3033 |
+
"should_evaluate": false,
|
| 3034 |
+
"should_log": false,
|
| 3035 |
+
"should_save": true,
|
| 3036 |
+
"should_training_stop": true
|
| 3037 |
+
},
|
| 3038 |
+
"attributes": {}
|
| 3039 |
+
}
|
| 3040 |
+
},
|
| 3041 |
+
"total_flos": 1.8367600516462019e+18,
|
| 3042 |
+
"train_batch_size": 1,
|
| 3043 |
+
"trial_name": null,
|
| 3044 |
+
"trial_params": null
|
| 3045 |
+
}
|