Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +14 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +1163 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Open-R1-Distill-eos
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Open-R1-Distill-eos
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="flyingbugs/Qwen2.5-1.5B-Open-R1-Distill-eos", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/jahc2e17)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.54.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
+
- Tokenizers: 0.21.2
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1465863748190208.0,
|
| 3 |
+
"train_loss": 0.52242068924121,
|
| 4 |
+
"train_runtime": 15658.3478,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 6.572,
|
| 7 |
+
"train_steps_per_second": 0.051
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.54.0"
|
| 14 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3087467144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7afe98e27bed91a0d4f4fe77fb25060fa8a97d2b5e2f69361c14ef5d9baa091b
|
| 3 |
size 3087467144
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1465863748190208.0,
|
| 3 |
+
"train_loss": 0.52242068924121,
|
| 4 |
+
"train_runtime": 15658.3478,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 6.572,
|
| 7 |
+
"train_steps_per_second": 0.051
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 804,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018656716417910446,
|
| 14 |
+
"grad_norm": 1.9214146781432249,
|
| 15 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 16 |
+
"loss": 0.857,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03731343283582089,
|
| 21 |
+
"grad_norm": 1.7625595046451557,
|
| 22 |
+
"learning_rate": 1.0975609756097562e-05,
|
| 23 |
+
"loss": 0.8038,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.055970149253731345,
|
| 28 |
+
"grad_norm": 0.6948661270341572,
|
| 29 |
+
"learning_rate": 1.707317073170732e-05,
|
| 30 |
+
"loss": 0.7448,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07462686567164178,
|
| 35 |
+
"grad_norm": 0.5136824696543728,
|
| 36 |
+
"learning_rate": 2.3170731707317075e-05,
|
| 37 |
+
"loss": 0.7055,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09328358208955224,
|
| 42 |
+
"grad_norm": 0.4018338347498522,
|
| 43 |
+
"learning_rate": 2.926829268292683e-05,
|
| 44 |
+
"loss": 0.6712,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11194029850746269,
|
| 49 |
+
"grad_norm": 0.28711501314318655,
|
| 50 |
+
"learning_rate": 3.5365853658536584e-05,
|
| 51 |
+
"loss": 0.6599,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13059701492537312,
|
| 56 |
+
"grad_norm": 0.2894771986907634,
|
| 57 |
+
"learning_rate": 4.146341463414634e-05,
|
| 58 |
+
"loss": 0.6395,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14925373134328357,
|
| 63 |
+
"grad_norm": 0.2821436189327092,
|
| 64 |
+
"learning_rate": 4.75609756097561e-05,
|
| 65 |
+
"loss": 0.627,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16791044776119404,
|
| 70 |
+
"grad_norm": 0.3279211667096163,
|
| 71 |
+
"learning_rate": 4.999828351434079e-05,
|
| 72 |
+
"loss": 0.6245,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1865671641791045,
|
| 77 |
+
"grad_norm": 0.2537209910093848,
|
| 78 |
+
"learning_rate": 4.998779482816942e-05,
|
| 79 |
+
"loss": 0.6048,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20522388059701493,
|
| 84 |
+
"grad_norm": 0.30352094230828874,
|
| 85 |
+
"learning_rate": 4.996777549883426e-05,
|
| 86 |
+
"loss": 0.6056,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22388059701492538,
|
| 91 |
+
"grad_norm": 0.35358905732065365,
|
| 92 |
+
"learning_rate": 4.9938234010808136e-05,
|
| 93 |
+
"loss": 0.5995,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24253731343283583,
|
| 98 |
+
"grad_norm": 0.5881353923808288,
|
| 99 |
+
"learning_rate": 4.989918288418841e-05,
|
| 100 |
+
"loss": 0.5898,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.26119402985074625,
|
| 105 |
+
"grad_norm": 0.4365964873532165,
|
| 106 |
+
"learning_rate": 4.9850638669390816e-05,
|
| 107 |
+
"loss": 0.5856,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2798507462686567,
|
| 112 |
+
"grad_norm": 0.3310629283404945,
|
| 113 |
+
"learning_rate": 4.97926219401351e-05,
|
| 114 |
+
"loss": 0.583,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.29850746268656714,
|
| 119 |
+
"grad_norm": 0.39095858353376106,
|
| 120 |
+
"learning_rate": 4.9725157284725665e-05,
|
| 121 |
+
"loss": 0.5818,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.31716417910447764,
|
| 126 |
+
"grad_norm": 0.4130266981460891,
|
| 127 |
+
"learning_rate": 4.964827329563061e-05,
|
| 128 |
+
"loss": 0.5777,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3358208955223881,
|
| 133 |
+
"grad_norm": 0.3251791282337107,
|
| 134 |
+
"learning_rate": 4.956200255736394e-05,
|
| 135 |
+
"loss": 0.5802,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.35447761194029853,
|
| 140 |
+
"grad_norm": 0.2800299594598508,
|
| 141 |
+
"learning_rate": 4.9466381632675714e-05,
|
| 142 |
+
"loss": 0.5777,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.373134328358209,
|
| 147 |
+
"grad_norm": 0.30351899813854083,
|
| 148 |
+
"learning_rate": 4.936145104705629e-05,
|
| 149 |
+
"loss": 0.5732,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3917910447761194,
|
| 154 |
+
"grad_norm": 0.3184280675590268,
|
| 155 |
+
"learning_rate": 4.9247255271560994e-05,
|
| 156 |
+
"loss": 0.5693,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.41044776119402987,
|
| 161 |
+
"grad_norm": 0.35433866607808917,
|
| 162 |
+
"learning_rate": 4.9123842703962754e-05,
|
| 163 |
+
"loss": 0.5762,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.4291044776119403,
|
| 168 |
+
"grad_norm": 0.28639350303291805,
|
| 169 |
+
"learning_rate": 4.899126564824033e-05,
|
| 170 |
+
"loss": 0.5666,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.44776119402985076,
|
| 175 |
+
"grad_norm": 0.3274186200975153,
|
| 176 |
+
"learning_rate": 4.884958029241127e-05,
|
| 177 |
+
"loss": 0.5674,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4664179104477612,
|
| 182 |
+
"grad_norm": 0.336381141981706,
|
| 183 |
+
"learning_rate": 4.869884668471853e-05,
|
| 184 |
+
"loss": 0.5641,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.48507462686567165,
|
| 189 |
+
"grad_norm": 0.4812221145192079,
|
| 190 |
+
"learning_rate": 4.8539128708181276e-05,
|
| 191 |
+
"loss": 0.563,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.503731343283582,
|
| 196 |
+
"grad_norm": 0.2985625122934817,
|
| 197 |
+
"learning_rate": 4.8370494053520316e-05,
|
| 198 |
+
"loss": 0.5599,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5223880597014925,
|
| 203 |
+
"grad_norm": 0.40904102656943087,
|
| 204 |
+
"learning_rate": 4.8193014190469815e-05,
|
| 205 |
+
"loss": 0.5651,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5410447761194029,
|
| 210 |
+
"grad_norm": 0.30462346527690765,
|
| 211 |
+
"learning_rate": 4.800676433748746e-05,
|
| 212 |
+
"loss": 0.5571,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5597014925373134,
|
| 217 |
+
"grad_norm": 0.29542772666907074,
|
| 218 |
+
"learning_rate": 4.781182342987577e-05,
|
| 219 |
+
"loss": 0.5548,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5783582089552238,
|
| 224 |
+
"grad_norm": 0.3051473053785931,
|
| 225 |
+
"learning_rate": 4.7608274086328275e-05,
|
| 226 |
+
"loss": 0.555,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5970149253731343,
|
| 231 |
+
"grad_norm": 0.27345084859980273,
|
| 232 |
+
"learning_rate": 4.739620257391446e-05,
|
| 233 |
+
"loss": 0.5525,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6156716417910447,
|
| 238 |
+
"grad_norm": 0.289181458801349,
|
| 239 |
+
"learning_rate": 4.7175698771518656e-05,
|
| 240 |
+
"loss": 0.551,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6343283582089553,
|
| 245 |
+
"grad_norm": 0.41307993000424736,
|
| 246 |
+
"learning_rate": 4.6946856131748076e-05,
|
| 247 |
+
"loss": 0.5517,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6529850746268657,
|
| 252 |
+
"grad_norm": 0.5340748917517905,
|
| 253 |
+
"learning_rate": 4.6709771641326244e-05,
|
| 254 |
+
"loss": 0.5509,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6716417910447762,
|
| 259 |
+
"grad_norm": 0.3291048059480862,
|
| 260 |
+
"learning_rate": 4.6464545779988757e-05,
|
| 261 |
+
"loss": 0.5428,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6902985074626866,
|
| 266 |
+
"grad_norm": 0.28986748904908194,
|
| 267 |
+
"learning_rate": 4.621128247789846e-05,
|
| 268 |
+
"loss": 0.5456,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7089552238805971,
|
| 273 |
+
"grad_norm": 0.25439473449314687,
|
| 274 |
+
"learning_rate": 4.595008907159847e-05,
|
| 275 |
+
"loss": 0.5485,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7276119402985075,
|
| 280 |
+
"grad_norm": 0.22286184197901884,
|
| 281 |
+
"learning_rate": 4.568107625852136e-05,
|
| 282 |
+
"loss": 0.5508,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.746268656716418,
|
| 287 |
+
"grad_norm": 0.2642945823026863,
|
| 288 |
+
"learning_rate": 4.5404358050074115e-05,
|
| 289 |
+
"loss": 0.5448,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7649253731343284,
|
| 294 |
+
"grad_norm": 0.27448365288562576,
|
| 295 |
+
"learning_rate": 4.512005172331842e-05,
|
| 296 |
+
"loss": 0.5424,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7835820895522388,
|
| 301 |
+
"grad_norm": 0.2971424901345131,
|
| 302 |
+
"learning_rate": 4.482827777126706e-05,
|
| 303 |
+
"loss": 0.5471,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8022388059701493,
|
| 308 |
+
"grad_norm": 0.35310755203104544,
|
| 309 |
+
"learning_rate": 4.4529159851817255e-05,
|
| 310 |
+
"loss": 0.541,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8208955223880597,
|
| 315 |
+
"grad_norm": 0.308625434473984,
|
| 316 |
+
"learning_rate": 4.422282473534271e-05,
|
| 317 |
+
"loss": 0.5405,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8395522388059702,
|
| 322 |
+
"grad_norm": 0.31816940842512614,
|
| 323 |
+
"learning_rate": 4.3909402250966534e-05,
|
| 324 |
+
"loss": 0.546,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8582089552238806,
|
| 329 |
+
"grad_norm": 0.22827227012944756,
|
| 330 |
+
"learning_rate": 4.358902523153791e-05,
|
| 331 |
+
"loss": 0.542,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8768656716417911,
|
| 336 |
+
"grad_norm": 0.24079886565005823,
|
| 337 |
+
"learning_rate": 4.326182945733555e-05,
|
| 338 |
+
"loss": 0.5416,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8955223880597015,
|
| 343 |
+
"grad_norm": 0.3638342950483874,
|
| 344 |
+
"learning_rate": 4.292795359852221e-05,
|
| 345 |
+
"loss": 0.5372,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.914179104477612,
|
| 350 |
+
"grad_norm": 0.3256070901197167,
|
| 351 |
+
"learning_rate": 4.2587539156374295e-05,
|
| 352 |
+
"loss": 0.5405,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9328358208955224,
|
| 357 |
+
"grad_norm": 0.3165450063227312,
|
| 358 |
+
"learning_rate": 4.2240730403311586e-05,
|
| 359 |
+
"loss": 0.5364,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9514925373134329,
|
| 364 |
+
"grad_norm": 0.30669208285819877,
|
| 365 |
+
"learning_rate": 4.188767432175263e-05,
|
| 366 |
+
"loss": 0.5322,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9701492537313433,
|
| 371 |
+
"grad_norm": 0.257272912960744,
|
| 372 |
+
"learning_rate": 4.1528520541821506e-05,
|
| 373 |
+
"loss": 0.5353,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.9888059701492538,
|
| 378 |
+
"grad_norm": 0.30370874605896786,
|
| 379 |
+
"learning_rate": 4.116342127793245e-05,
|
| 380 |
+
"loss": 0.5385,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.007462686567164,
|
| 385 |
+
"grad_norm": 0.23367419347190874,
|
| 386 |
+
"learning_rate": 4.0792531264279285e-05,
|
| 387 |
+
"loss": 0.5246,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0261194029850746,
|
| 392 |
+
"grad_norm": 0.28960025979101867,
|
| 393 |
+
"learning_rate": 4.041600768925687e-05,
|
| 394 |
+
"loss": 0.5175,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.044776119402985,
|
| 399 |
+
"grad_norm": 0.3544154485769114,
|
| 400 |
+
"learning_rate": 4.0034010128842484e-05,
|
| 401 |
+
"loss": 0.5183,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.0634328358208955,
|
| 406 |
+
"grad_norm": 0.2830781283593527,
|
| 407 |
+
"learning_rate": 3.964670047896525e-05,
|
| 408 |
+
"loss": 0.5181,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.0820895522388059,
|
| 413 |
+
"grad_norm": 0.26140038642658264,
|
| 414 |
+
"learning_rate": 3.925424288689239e-05,
|
| 415 |
+
"loss": 0.5087,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1007462686567164,
|
| 420 |
+
"grad_norm": 0.2617191990469776,
|
| 421 |
+
"learning_rate": 3.8856803681661296e-05,
|
| 422 |
+
"loss": 0.516,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1194029850746268,
|
| 427 |
+
"grad_norm": 0.26589479989678716,
|
| 428 |
+
"learning_rate": 3.8454551303586964e-05,
|
| 429 |
+
"loss": 0.5111,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1380597014925373,
|
| 434 |
+
"grad_norm": 0.2406368600470144,
|
| 435 |
+
"learning_rate": 3.8047656232874624e-05,
|
| 436 |
+
"loss": 0.5139,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.1567164179104479,
|
| 441 |
+
"grad_norm": 0.25755826798857223,
|
| 442 |
+
"learning_rate": 3.763629091736781e-05,
|
| 443 |
+
"loss": 0.5116,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.1753731343283582,
|
| 448 |
+
"grad_norm": 0.33892425739707405,
|
| 449 |
+
"learning_rate": 3.722062969946254e-05,
|
| 450 |
+
"loss": 0.5118,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.1940298507462686,
|
| 455 |
+
"grad_norm": 0.23443314308723368,
|
| 456 |
+
"learning_rate": 3.6800848742218644e-05,
|
| 457 |
+
"loss": 0.5133,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.212686567164179,
|
| 462 |
+
"grad_norm": 0.23884530654624148,
|
| 463 |
+
"learning_rate": 3.6377125954699254e-05,
|
| 464 |
+
"loss": 0.5113,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.2313432835820897,
|
| 469 |
+
"grad_norm": 0.2090085180372967,
|
| 470 |
+
"learning_rate": 3.5949640916570566e-05,
|
| 471 |
+
"loss": 0.5085,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.25,
|
| 476 |
+
"grad_norm": 0.23291376449474052,
|
| 477 |
+
"learning_rate": 3.551857480199336e-05,
|
| 478 |
+
"loss": 0.5135,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.2686567164179103,
|
| 483 |
+
"grad_norm": 0.24011296587040026,
|
| 484 |
+
"learning_rate": 3.5084110302838916e-05,
|
| 485 |
+
"loss": 0.505,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.287313432835821,
|
| 490 |
+
"grad_norm": 0.21935005312866615,
|
| 491 |
+
"learning_rate": 3.464643155126162e-05,
|
| 492 |
+
"loss": 0.5104,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3059701492537314,
|
| 497 |
+
"grad_norm": 0.2261621862735514,
|
| 498 |
+
"learning_rate": 3.4205724041661135e-05,
|
| 499 |
+
"loss": 0.5081,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.3246268656716418,
|
| 504 |
+
"grad_norm": 0.2574439184051825,
|
| 505 |
+
"learning_rate": 3.376217455206732e-05,
|
| 506 |
+
"loss": 0.5115,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.3432835820895521,
|
| 511 |
+
"grad_norm": 0.2129876722579311,
|
| 512 |
+
"learning_rate": 3.3315971064981025e-05,
|
| 513 |
+
"loss": 0.506,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.3619402985074627,
|
| 518 |
+
"grad_norm": 0.20753843021299664,
|
| 519 |
+
"learning_rate": 3.286730268770452e-05,
|
| 520 |
+
"loss": 0.5038,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.3805970149253732,
|
| 525 |
+
"grad_norm": 0.3217141035376458,
|
| 526 |
+
"learning_rate": 3.2416359572195155e-05,
|
| 527 |
+
"loss": 0.5132,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.3992537313432836,
|
| 532 |
+
"grad_norm": 0.21539693831207604,
|
| 533 |
+
"learning_rate": 3.1963332834476247e-05,
|
| 534 |
+
"loss": 0.5081,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.417910447761194,
|
| 539 |
+
"grad_norm": 0.27467469680387524,
|
| 540 |
+
"learning_rate": 3.150841447363948e-05,
|
| 541 |
+
"loss": 0.5067,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.4365671641791045,
|
| 546 |
+
"grad_norm": 0.23691311945378055,
|
| 547 |
+
"learning_rate": 3.1051797290472966e-05,
|
| 548 |
+
"loss": 0.5018,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.455223880597015,
|
| 553 |
+
"grad_norm": 0.30787370613511683,
|
| 554 |
+
"learning_rate": 3.059367480574958e-05,
|
| 555 |
+
"loss": 0.5035,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.4738805970149254,
|
| 560 |
+
"grad_norm": 0.21214521272783723,
|
| 561 |
+
"learning_rate": 3.0134241178210103e-05,
|
| 562 |
+
"loss": 0.5004,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.4925373134328357,
|
| 567 |
+
"grad_norm": 0.2567066053575565,
|
| 568 |
+
"learning_rate": 2.9673691122276086e-05,
|
| 569 |
+
"loss": 0.5041,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.5111940298507462,
|
| 574 |
+
"grad_norm": 0.23880722667167875,
|
| 575 |
+
"learning_rate": 2.9212219825527075e-05,
|
| 576 |
+
"loss": 0.4981,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.5298507462686568,
|
| 581 |
+
"grad_norm": 0.19930339353323281,
|
| 582 |
+
"learning_rate": 2.8750022865977443e-05,
|
| 583 |
+
"loss": 0.502,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.5485074626865671,
|
| 588 |
+
"grad_norm": 0.24784475664597616,
|
| 589 |
+
"learning_rate": 2.82872961291876e-05,
|
| 590 |
+
"loss": 0.5068,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.5671641791044775,
|
| 595 |
+
"grad_norm": 0.2637097189189239,
|
| 596 |
+
"learning_rate": 2.7824235725245042e-05,
|
| 597 |
+
"loss": 0.5031,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.585820895522388,
|
| 602 |
+
"grad_norm": 0.20097295957360145,
|
| 603 |
+
"learning_rate": 2.7361037905650032e-05,
|
| 604 |
+
"loss": 0.5051,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.6044776119402986,
|
| 609 |
+
"grad_norm": 0.1855097808926682,
|
| 610 |
+
"learning_rate": 2.689789898014155e-05,
|
| 611 |
+
"loss": 0.5043,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.623134328358209,
|
| 616 |
+
"grad_norm": 0.19387268984078115,
|
| 617 |
+
"learning_rate": 2.6435015233498443e-05,
|
| 618 |
+
"loss": 0.503,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6417910447761193,
|
| 623 |
+
"grad_norm": 0.1959979856590692,
|
| 624 |
+
"learning_rate": 2.5972582842351156e-05,
|
| 625 |
+
"loss": 0.5031,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.6604477611940298,
|
| 630 |
+
"grad_norm": 0.2130968015995863,
|
| 631 |
+
"learning_rate": 2.551079779203932e-05,
|
| 632 |
+
"loss": 0.5056,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.6791044776119404,
|
| 637 |
+
"grad_norm": 0.19562804614219742,
|
| 638 |
+
"learning_rate": 2.504985579355047e-05,
|
| 639 |
+
"loss": 0.4971,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.6977611940298507,
|
| 644 |
+
"grad_norm": 0.20132877928156498,
|
| 645 |
+
"learning_rate": 2.458995220057491e-05,
|
| 646 |
+
"loss": 0.5048,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.716417910447761,
|
| 651 |
+
"grad_norm": 0.19111009428414005,
|
| 652 |
+
"learning_rate": 2.4131281926712146e-05,
|
| 653 |
+
"loss": 0.5051,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.7350746268656716,
|
| 658 |
+
"grad_norm": 0.19713565236023642,
|
| 659 |
+
"learning_rate": 2.3674039362863687e-05,
|
| 660 |
+
"loss": 0.5052,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.7537313432835822,
|
| 665 |
+
"grad_norm": 0.2278886953059889,
|
| 666 |
+
"learning_rate": 2.3218418294847517e-05,
|
| 667 |
+
"loss": 0.503,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.7723880597014925,
|
| 672 |
+
"grad_norm": 0.21076902236368567,
|
| 673 |
+
"learning_rate": 2.2764611821268918e-05,
|
| 674 |
+
"loss": 0.5004,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.7910447761194028,
|
| 679 |
+
"grad_norm": 0.2018936557220544,
|
| 680 |
+
"learning_rate": 2.231281227168257e-05,
|
| 681 |
+
"loss": 0.4972,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.8097014925373134,
|
| 686 |
+
"grad_norm": 0.1900377713824044,
|
| 687 |
+
"learning_rate": 2.18632111250806e-05,
|
| 688 |
+
"loss": 0.4987,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.828358208955224,
|
| 693 |
+
"grad_norm": 0.1818444743971112,
|
| 694 |
+
"learning_rate": 2.141599892874107e-05,
|
| 695 |
+
"loss": 0.4988,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.8470149253731343,
|
| 700 |
+
"grad_norm": 0.1843911681060789,
|
| 701 |
+
"learning_rate": 2.09713652174714e-05,
|
| 702 |
+
"loss": 0.5045,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.8656716417910446,
|
| 707 |
+
"grad_norm": 0.1756356146626833,
|
| 708 |
+
"learning_rate": 2.0529498433280807e-05,
|
| 709 |
+
"loss": 0.5062,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.8843283582089554,
|
| 714 |
+
"grad_norm": 0.17919268852808168,
|
| 715 |
+
"learning_rate": 2.0090585845516012e-05,
|
| 716 |
+
"loss": 0.5011,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.9029850746268657,
|
| 721 |
+
"grad_norm": 0.1861488051548517,
|
| 722 |
+
"learning_rate": 1.965481347149376e-05,
|
| 723 |
+
"loss": 0.4964,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.921641791044776,
|
| 728 |
+
"grad_norm": 0.1808039014665401,
|
| 729 |
+
"learning_rate": 1.9222365997664165e-05,
|
| 730 |
+
"loss": 0.5038,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9402985074626866,
|
| 735 |
+
"grad_norm": 0.18185075285557611,
|
| 736 |
+
"learning_rate": 1.8793426701337947e-05,
|
| 737 |
+
"loss": 0.5033,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.9589552238805972,
|
| 742 |
+
"grad_norm": 0.1802698151327418,
|
| 743 |
+
"learning_rate": 1.8368177373010954e-05,
|
| 744 |
+
"loss": 0.498,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9776119402985075,
|
| 749 |
+
"grad_norm": 0.1839298648566157,
|
| 750 |
+
"learning_rate": 1.7946798239318775e-05,
|
| 751 |
+
"loss": 0.5033,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9962686567164178,
|
| 756 |
+
"grad_norm": 0.1787192449198445,
|
| 757 |
+
"learning_rate": 1.75294678866542e-05,
|
| 758 |
+
"loss": 0.4937,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.014925373134328,
|
| 763 |
+
"grad_norm": 0.19908015949978794,
|
| 764 |
+
"learning_rate": 1.7116363185479754e-05,
|
| 765 |
+
"loss": 0.4861,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.033582089552239,
|
| 770 |
+
"grad_norm": 0.17330047242909324,
|
| 771 |
+
"learning_rate": 1.670765921536755e-05,
|
| 772 |
+
"loss": 0.4807,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.0522388059701493,
|
| 777 |
+
"grad_norm": 0.1887761738499672,
|
| 778 |
+
"learning_rate": 1.6303529190798088e-05,
|
| 779 |
+
"loss": 0.4807,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.0708955223880596,
|
| 784 |
+
"grad_norm": 0.18086274895322357,
|
| 785 |
+
"learning_rate": 1.590414438774954e-05,
|
| 786 |
+
"loss": 0.478,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.08955223880597,
|
| 791 |
+
"grad_norm": 0.1666312790289245,
|
| 792 |
+
"learning_rate": 1.550967407110856e-05,
|
| 793 |
+
"loss": 0.4801,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.1082089552238807,
|
| 798 |
+
"grad_norm": 0.16804347810729678,
|
| 799 |
+
"learning_rate": 1.5120285422933478e-05,
|
| 800 |
+
"loss": 0.4814,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.126865671641791,
|
| 805 |
+
"grad_norm": 0.1741311542160614,
|
| 806 |
+
"learning_rate": 1.4736143471600173e-05,
|
| 807 |
+
"loss": 0.4841,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.1455223880597014,
|
| 812 |
+
"grad_norm": 0.16178175453073618,
|
| 813 |
+
"learning_rate": 1.4357411021860773e-05,
|
| 814 |
+
"loss": 0.4768,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.1641791044776117,
|
| 819 |
+
"grad_norm": 0.16621312000057425,
|
| 820 |
+
"learning_rate": 1.3984248585844645e-05,
|
| 821 |
+
"loss": 0.4804,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.1828358208955225,
|
| 826 |
+
"grad_norm": 0.16578503722378288,
|
| 827 |
+
"learning_rate": 1.3616814315031146e-05,
|
| 828 |
+
"loss": 0.4806,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.201492537313433,
|
| 833 |
+
"grad_norm": 0.17421634398822453,
|
| 834 |
+
"learning_rate": 1.3255263933222833e-05,
|
| 835 |
+
"loss": 0.477,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.220149253731343,
|
| 840 |
+
"grad_norm": 0.1584162460344385,
|
| 841 |
+
"learning_rate": 1.2899750670547473e-05,
|
| 842 |
+
"loss": 0.4761,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.2388059701492535,
|
| 847 |
+
"grad_norm": 0.1669406945768043,
|
| 848 |
+
"learning_rate": 1.2550425198516973e-05,
|
| 849 |
+
"loss": 0.4807,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.2574626865671643,
|
| 854 |
+
"grad_norm": 0.1755571617029938,
|
| 855 |
+
"learning_rate": 1.2207435566170722e-05,
|
| 856 |
+
"loss": 0.4836,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.2761194029850746,
|
| 861 |
+
"grad_norm": 0.16049791652334905,
|
| 862 |
+
"learning_rate": 1.1870927137330267e-05,
|
| 863 |
+
"loss": 0.48,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.294776119402985,
|
| 868 |
+
"grad_norm": 0.14841988134789108,
|
| 869 |
+
"learning_rate": 1.1541042528992152e-05,
|
| 870 |
+
"loss": 0.4797,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.3134328358208958,
|
| 875 |
+
"grad_norm": 0.14669420324350554,
|
| 876 |
+
"learning_rate": 1.1217921550884774e-05,
|
| 877 |
+
"loss": 0.4781,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.332089552238806,
|
| 882 |
+
"grad_norm": 0.16275970644355697,
|
| 883 |
+
"learning_rate": 1.0901701146215085e-05,
|
| 884 |
+
"loss": 0.4677,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.3507462686567164,
|
| 889 |
+
"grad_norm": 0.15639224942974775,
|
| 890 |
+
"learning_rate": 1.0592515333630128e-05,
|
| 891 |
+
"loss": 0.4795,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.3694029850746268,
|
| 896 |
+
"grad_norm": 0.17837315275471302,
|
| 897 |
+
"learning_rate": 1.029049515041808e-05,
|
| 898 |
+
"loss": 0.4757,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.388059701492537,
|
| 903 |
+
"grad_norm": 0.15999076690352537,
|
| 904 |
+
"learning_rate": 9.99576859697277e-06,
|
| 905 |
+
"loss": 0.483,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.406716417910448,
|
| 910 |
+
"grad_norm": 0.14623430655091096,
|
| 911 |
+
"learning_rate": 9.708460582545337e-06,
|
| 912 |
+
"loss": 0.479,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.425373134328358,
|
| 917 |
+
"grad_norm": 0.14446705361316536,
|
| 918 |
+
"learning_rate": 9.428692872305925e-06,
|
| 919 |
+
"loss": 0.4782,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.4440298507462686,
|
| 924 |
+
"grad_norm": 0.1499556136205738,
|
| 925 |
+
"learning_rate": 9.15658403573792e-06,
|
| 926 |
+
"loss": 0.4771,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.4626865671641793,
|
| 931 |
+
"grad_norm": 0.13688966492338145,
|
| 932 |
+
"learning_rate": 8.892249396386513e-06,
|
| 933 |
+
"loss": 0.477,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.4813432835820897,
|
| 938 |
+
"grad_norm": 0.1405824099115518,
|
| 939 |
+
"learning_rate": 8.635800982982958e-06,
|
| 940 |
+
"loss": 0.4801,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.5,
|
| 945 |
+
"grad_norm": 0.1556802805035451,
|
| 946 |
+
"learning_rate": 8.387347481965244e-06,
|
| 947 |
+
"loss": 0.4767,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.5186567164179103,
|
| 952 |
+
"grad_norm": 0.14957588217337456,
|
| 953 |
+
"learning_rate": 8.14699419141525e-06,
|
| 954 |
+
"loss": 0.4796,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.5373134328358207,
|
| 959 |
+
"grad_norm": 0.15266928757717518,
|
| 960 |
+
"learning_rate": 7.914842976431932e-06,
|
| 961 |
+
"loss": 0.4752,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.5559701492537314,
|
| 966 |
+
"grad_norm": 0.15337919631830368,
|
| 967 |
+
"learning_rate": 7.690992225959465e-06,
|
| 968 |
+
"loss": 0.4805,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.574626865671642,
|
| 973 |
+
"grad_norm": 0.14478875983801728,
|
| 974 |
+
"learning_rate": 7.4755368110886366e-06,
|
| 975 |
+
"loss": 0.4768,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.593283582089552,
|
| 980 |
+
"grad_norm": 0.15398254303144288,
|
| 981 |
+
"learning_rate": 7.268568044849132e-06,
|
| 982 |
+
"loss": 0.4765,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.611940298507463,
|
| 987 |
+
"grad_norm": 0.15439199576307303,
|
| 988 |
+
"learning_rate": 7.0701736435098155e-06,
|
| 989 |
+
"loss": 0.4782,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.6305970149253732,
|
| 994 |
+
"grad_norm": 0.14978173171132997,
|
| 995 |
+
"learning_rate": 6.880437689403316e-06,
|
| 996 |
+
"loss": 0.4741,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.6492537313432836,
|
| 1001 |
+
"grad_norm": 0.1412522116274614,
|
| 1002 |
+
"learning_rate": 6.699440595290754e-06,
|
| 1003 |
+
"loss": 0.4778,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.667910447761194,
|
| 1008 |
+
"grad_norm": 0.15039092893602207,
|
| 1009 |
+
"learning_rate": 6.527259070281722e-06,
|
| 1010 |
+
"loss": 0.4816,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.6865671641791042,
|
| 1015 |
+
"grad_norm": 0.14048749084616627,
|
| 1016 |
+
"learning_rate": 6.363966087323844e-06,
|
| 1017 |
+
"loss": 0.48,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.705223880597015,
|
| 1022 |
+
"grad_norm": 0.14837195306929193,
|
| 1023 |
+
"learning_rate": 6.209630852275836e-06,
|
| 1024 |
+
"loss": 0.4715,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.7238805970149254,
|
| 1029 |
+
"grad_norm": 0.14480369337511617,
|
| 1030 |
+
"learning_rate": 6.06431877457709e-06,
|
| 1031 |
+
"loss": 0.4752,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.7425373134328357,
|
| 1036 |
+
"grad_norm": 0.14464453043475206,
|
| 1037 |
+
"learning_rate": 5.928091439526226e-06,
|
| 1038 |
+
"loss": 0.4758,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.7611940298507465,
|
| 1043 |
+
"grad_norm": 0.14318518863987956,
|
| 1044 |
+
"learning_rate": 5.801006582180398e-06,
|
| 1045 |
+
"loss": 0.4795,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.779850746268657,
|
| 1050 |
+
"grad_norm": 0.1378858672961454,
|
| 1051 |
+
"learning_rate": 5.683118062886346e-06,
|
| 1052 |
+
"loss": 0.478,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.798507462686567,
|
| 1057 |
+
"grad_norm": 0.1473158474351985,
|
| 1058 |
+
"learning_rate": 5.574475844453634e-06,
|
| 1059 |
+
"loss": 0.477,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.8171641791044775,
|
| 1064 |
+
"grad_norm": 0.13519605107478774,
|
| 1065 |
+
"learning_rate": 5.475125970979702e-06,
|
| 1066 |
+
"loss": 0.4777,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.835820895522388,
|
| 1071 |
+
"grad_norm": 0.1469374974433458,
|
| 1072 |
+
"learning_rate": 5.385110548335753e-06,
|
| 1073 |
+
"loss": 0.4746,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.8544776119402986,
|
| 1078 |
+
"grad_norm": 0.13682187728455042,
|
| 1079 |
+
"learning_rate": 5.30446772632166e-06,
|
| 1080 |
+
"loss": 0.4778,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.873134328358209,
|
| 1085 |
+
"grad_norm": 0.1468534460053792,
|
| 1086 |
+
"learning_rate": 5.233231682497572e-06,
|
| 1087 |
+
"loss": 0.4791,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.8917910447761193,
|
| 1092 |
+
"grad_norm": 0.1381366037912041,
|
| 1093 |
+
"learning_rate": 5.171432607698975e-06,
|
| 1094 |
+
"loss": 0.4737,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.91044776119403,
|
| 1099 |
+
"grad_norm": 0.13873604296833256,
|
| 1100 |
+
"learning_rate": 5.119096693241395e-06,
|
| 1101 |
+
"loss": 0.4785,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.9291044776119404,
|
| 1106 |
+
"grad_norm": 0.1354800953615682,
|
| 1107 |
+
"learning_rate": 5.07624611982014e-06,
|
| 1108 |
+
"loss": 0.4719,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.9477611940298507,
|
| 1113 |
+
"grad_norm": 0.1412434132198824,
|
| 1114 |
+
"learning_rate": 5.0428990481098275e-06,
|
| 1115 |
+
"loss": 0.481,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.966417910447761,
|
| 1120 |
+
"grad_norm": 0.14472205562980991,
|
| 1121 |
+
"learning_rate": 5.01906961106762e-06,
|
| 1122 |
+
"loss": 0.4742,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.9850746268656714,
|
| 1127 |
+
"grad_norm": 0.1389514632202056,
|
| 1128 |
+
"learning_rate": 5.004767907943488e-06,
|
| 1129 |
+
"loss": 0.4824,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.0,
|
| 1134 |
+
"step": 804,
|
| 1135 |
+
"total_flos": 1465863748190208.0,
|
| 1136 |
+
"train_loss": 0.52242068924121,
|
| 1137 |
+
"train_runtime": 15658.3478,
|
| 1138 |
+
"train_samples_per_second": 6.572,
|
| 1139 |
+
"train_steps_per_second": 0.051
|
| 1140 |
+
}
|
| 1141 |
+
],
|
| 1142 |
+
"logging_steps": 5,
|
| 1143 |
+
"max_steps": 804,
|
| 1144 |
+
"num_input_tokens_seen": 0,
|
| 1145 |
+
"num_train_epochs": 3,
|
| 1146 |
+
"save_steps": 100,
|
| 1147 |
+
"stateful_callbacks": {
|
| 1148 |
+
"TrainerControl": {
|
| 1149 |
+
"args": {
|
| 1150 |
+
"should_epoch_stop": false,
|
| 1151 |
+
"should_evaluate": false,
|
| 1152 |
+
"should_log": false,
|
| 1153 |
+
"should_save": true,
|
| 1154 |
+
"should_training_stop": true
|
| 1155 |
+
},
|
| 1156 |
+
"attributes": {}
|
| 1157 |
+
}
|
| 1158 |
+
},
|
| 1159 |
+
"total_flos": 1465863748190208.0,
|
| 1160 |
+
"train_batch_size": 16,
|
| 1161 |
+
"trial_name": null,
|
| 1162 |
+
"trial_params": null
|
| 1163 |
+
}
|