Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +12 -0
- train_results.json +8 -0
- trainer_state.json +658 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Llama3.1-8B-WebArena-Lite-SFT-epoch-3
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Llama3.1-8B-WebArena-Lite-SFT-epoch-3
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="weizhepei/Llama3.1-8B-WebArena-Lite-SFT-epoch-3", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/uva-llm/huggingface/runs/grivc38g)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.4.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 311859968540672.0,
|
| 3 |
+
"train_loss": 0.15194854576576938,
|
| 4 |
+
"train_runtime": 8344.2681,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 3.401,
|
| 7 |
+
"train_steps_per_second": 0.053
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.49.0"
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 311859968540672.0,
|
| 3 |
+
"train_loss": 0.15194854576576938,
|
| 4 |
+
"train_runtime": 8344.2681,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 3.401,
|
| 7 |
+
"train_steps_per_second": 0.053
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,658 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 444,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.033783783783783786,
|
| 13 |
+
"grad_norm": 7.693039168386045,
|
| 14 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 15 |
+
"loss": 0.5133,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06756756756756757,
|
| 20 |
+
"grad_norm": 4.296719547848672,
|
| 21 |
+
"learning_rate": 2.173913043478261e-05,
|
| 22 |
+
"loss": 0.3581,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10135135135135136,
|
| 27 |
+
"grad_norm": 3.2417658261755915,
|
| 28 |
+
"learning_rate": 3.260869565217392e-05,
|
| 29 |
+
"loss": 0.3547,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13513513513513514,
|
| 34 |
+
"grad_norm": 2.8412337980778553,
|
| 35 |
+
"learning_rate": 4.347826086956522e-05,
|
| 36 |
+
"loss": 0.2666,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16891891891891891,
|
| 41 |
+
"grad_norm": 4.90451510502916,
|
| 42 |
+
"learning_rate": 4.9997494236918504e-05,
|
| 43 |
+
"loss": 0.3582,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20270270270270271,
|
| 48 |
+
"grad_norm": 22.780898735414855,
|
| 49 |
+
"learning_rate": 4.996931081151707e-05,
|
| 50 |
+
"loss": 0.3768,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23648648648648649,
|
| 55 |
+
"grad_norm": 3.320519938493738,
|
| 56 |
+
"learning_rate": 4.990985111773183e-05,
|
| 57 |
+
"loss": 0.4268,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2702702702702703,
|
| 62 |
+
"grad_norm": 2.5294359467709095,
|
| 63 |
+
"learning_rate": 4.981919792077782e-05,
|
| 64 |
+
"loss": 0.2873,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30405405405405406,
|
| 69 |
+
"grad_norm": 2.3280683716637873,
|
| 70 |
+
"learning_rate": 4.969747740582118e-05,
|
| 71 |
+
"loss": 0.2544,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33783783783783783,
|
| 76 |
+
"grad_norm": 2.8289139949817335,
|
| 77 |
+
"learning_rate": 4.95448590023351e-05,
|
| 78 |
+
"loss": 0.2697,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3716216216216216,
|
| 83 |
+
"grad_norm": 2.1629521504260993,
|
| 84 |
+
"learning_rate": 4.936155514826161e-05,
|
| 85 |
+
"loss": 0.3052,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.40540540540540543,
|
| 90 |
+
"grad_norm": 1.9564591527643984,
|
| 91 |
+
"learning_rate": 4.914782099430755e-05,
|
| 92 |
+
"loss": 0.2319,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4391891891891892,
|
| 97 |
+
"grad_norm": 2.6620448846059714,
|
| 98 |
+
"learning_rate": 4.890395404878627e-05,
|
| 99 |
+
"loss": 0.2613,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.47297297297297297,
|
| 104 |
+
"grad_norm": 2.333611941701714,
|
| 105 |
+
"learning_rate": 4.863029376349949e-05,
|
| 106 |
+
"loss": 0.2595,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5067567567567568,
|
| 111 |
+
"grad_norm": 2.5677617585089147,
|
| 112 |
+
"learning_rate": 4.8327221061235635e-05,
|
| 113 |
+
"loss": 0.2733,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5405405405405406,
|
| 118 |
+
"grad_norm": 1.8945353614021259,
|
| 119 |
+
"learning_rate": 4.799515780554253e-05,
|
| 120 |
+
"loss": 0.2298,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5743243243243243,
|
| 125 |
+
"grad_norm": 1.9687212656745774,
|
| 126 |
+
"learning_rate": 4.763456621351229e-05,
|
| 127 |
+
"loss": 0.2657,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6081081081081081,
|
| 132 |
+
"grad_norm": 2.2237600068784653,
|
| 133 |
+
"learning_rate": 4.724594821239601e-05,
|
| 134 |
+
"loss": 0.244,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6418918918918919,
|
| 139 |
+
"grad_norm": 2.1737571541215295,
|
| 140 |
+
"learning_rate": 4.6829844740943586e-05,
|
| 141 |
+
"loss": 0.2409,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6756756756756757,
|
| 146 |
+
"grad_norm": 1.7570800060495113,
|
| 147 |
+
"learning_rate": 4.6386834996441395e-05,
|
| 148 |
+
"loss": 0.2054,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7094594594594594,
|
| 153 |
+
"grad_norm": 1.5936369087529354,
|
| 154 |
+
"learning_rate": 4.5917535628495714e-05,
|
| 155 |
+
"loss": 0.2658,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7432432432432432,
|
| 160 |
+
"grad_norm": 1.687954605448381,
|
| 161 |
+
"learning_rate": 4.542259988068434e-05,
|
| 162 |
+
"loss": 0.2306,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.777027027027027,
|
| 167 |
+
"grad_norm": 1.6798383407257704,
|
| 168 |
+
"learning_rate": 4.4902716681270805e-05,
|
| 169 |
+
"loss": 0.2051,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8108108108108109,
|
| 174 |
+
"grad_norm": 1.9894543465428474,
|
| 175 |
+
"learning_rate": 4.435860968424745e-05,
|
| 176 |
+
"loss": 0.2885,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8445945945945946,
|
| 181 |
+
"grad_norm": 1.5663367660943097,
|
| 182 |
+
"learning_rate": 4.379103626204153e-05,
|
| 183 |
+
"loss": 0.2412,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8783783783783784,
|
| 188 |
+
"grad_norm": 1.4832323634362194,
|
| 189 |
+
"learning_rate": 4.320078645128699e-05,
|
| 190 |
+
"loss": 0.2374,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9121621621621622,
|
| 195 |
+
"grad_norm": 1.999609063337418,
|
| 196 |
+
"learning_rate": 4.258868185312901e-05,
|
| 197 |
+
"loss": 0.21,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9459459459459459,
|
| 202 |
+
"grad_norm": 1.449925989442346,
|
| 203 |
+
"learning_rate": 4.195557448959231e-05,
|
| 204 |
+
"loss": 0.2533,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9797297297297297,
|
| 209 |
+
"grad_norm": 1.278422978606916,
|
| 210 |
+
"learning_rate": 4.130234561760477e-05,
|
| 211 |
+
"loss": 0.235,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0135135135135136,
|
| 216 |
+
"grad_norm": 1.1102776403418126,
|
| 217 |
+
"learning_rate": 4.0629904502327556e-05,
|
| 218 |
+
"loss": 0.2101,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0472972972972974,
|
| 223 |
+
"grad_norm": 1.452689044129832,
|
| 224 |
+
"learning_rate": 3.993918715149896e-05,
|
| 225 |
+
"loss": 0.1268,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0810810810810811,
|
| 230 |
+
"grad_norm": 2.564080697825406,
|
| 231 |
+
"learning_rate": 3.923115501255381e-05,
|
| 232 |
+
"loss": 0.1504,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.114864864864865,
|
| 237 |
+
"grad_norm": 1.4284081142136367,
|
| 238 |
+
"learning_rate": 3.8506793634331925e-05,
|
| 239 |
+
"loss": 0.1501,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.1486486486486487,
|
| 244 |
+
"grad_norm": 1.3921371445923525,
|
| 245 |
+
"learning_rate": 3.7767111295238555e-05,
|
| 246 |
+
"loss": 0.1517,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.1824324324324325,
|
| 251 |
+
"grad_norm": 1.0189911635230715,
|
| 252 |
+
"learning_rate": 3.701313759976626e-05,
|
| 253 |
+
"loss": 0.1482,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.2162162162162162,
|
| 258 |
+
"grad_norm": 1.4942069614270297,
|
| 259 |
+
"learning_rate": 3.624592204533184e-05,
|
| 260 |
+
"loss": 0.1297,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.25,
|
| 265 |
+
"grad_norm": 1.3920628246297202,
|
| 266 |
+
"learning_rate": 3.546653256142321e-05,
|
| 267 |
+
"loss": 0.1325,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.2837837837837838,
|
| 272 |
+
"grad_norm": 1.0187887226878,
|
| 273 |
+
"learning_rate": 3.467605402308966e-05,
|
| 274 |
+
"loss": 0.142,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.3175675675675675,
|
| 279 |
+
"grad_norm": 1.1984277342370044,
|
| 280 |
+
"learning_rate": 3.3875586740844675e-05,
|
| 281 |
+
"loss": 0.1347,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.3513513513513513,
|
| 286 |
+
"grad_norm": 1.1170028929426064,
|
| 287 |
+
"learning_rate": 3.3066244929083246e-05,
|
| 288 |
+
"loss": 0.1304,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.385135135135135,
|
| 293 |
+
"grad_norm": 1.0186976243308743,
|
| 294 |
+
"learning_rate": 3.2249155155145665e-05,
|
| 295 |
+
"loss": 0.141,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.4189189189189189,
|
| 300 |
+
"grad_norm": 1.2898941169402762,
|
| 301 |
+
"learning_rate": 3.142545477118649e-05,
|
| 302 |
+
"loss": 0.1354,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.4527027027027026,
|
| 307 |
+
"grad_norm": 0.9961209346671913,
|
| 308 |
+
"learning_rate": 3.059629033103166e-05,
|
| 309 |
+
"loss": 0.1302,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.4864864864864864,
|
| 314 |
+
"grad_norm": 0.9875250619369351,
|
| 315 |
+
"learning_rate": 2.9762815994227135e-05,
|
| 316 |
+
"loss": 0.1403,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.5202702702702702,
|
| 321 |
+
"grad_norm": 1.0982139109346354,
|
| 322 |
+
"learning_rate": 2.8926191919500854e-05,
|
| 323 |
+
"loss": 0.1235,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.554054054054054,
|
| 328 |
+
"grad_norm": 0.9668045928793142,
|
| 329 |
+
"learning_rate": 2.808758264987406e-05,
|
| 330 |
+
"loss": 0.1257,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5878378378378377,
|
| 335 |
+
"grad_norm": 0.8581177979692445,
|
| 336 |
+
"learning_rate": 2.7248155491669854e-05,
|
| 337 |
+
"loss": 0.1174,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.6216216216216215,
|
| 342 |
+
"grad_norm": 1.1046256528106388,
|
| 343 |
+
"learning_rate": 2.6409078889675382e-05,
|
| 344 |
+
"loss": 0.1214,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.6554054054054053,
|
| 349 |
+
"grad_norm": 0.880781318496101,
|
| 350 |
+
"learning_rate": 2.5571520800719363e-05,
|
| 351 |
+
"loss": 0.1376,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.689189189189189,
|
| 356 |
+
"grad_norm": 0.8458236531048872,
|
| 357 |
+
"learning_rate": 2.473664706792873e-05,
|
| 358 |
+
"loss": 0.1026,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.722972972972973,
|
| 363 |
+
"grad_norm": 3.38684923966137,
|
| 364 |
+
"learning_rate": 2.390561979792763e-05,
|
| 365 |
+
"loss": 0.1335,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.7567567567567568,
|
| 370 |
+
"grad_norm": 0.8747529589638384,
|
| 371 |
+
"learning_rate": 2.3079595743237243e-05,
|
| 372 |
+
"loss": 0.1089,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.7905405405405406,
|
| 377 |
+
"grad_norm": 1.061409594201986,
|
| 378 |
+
"learning_rate": 2.2259724692128448e-05,
|
| 379 |
+
"loss": 0.1211,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.8243243243243243,
|
| 384 |
+
"grad_norm": 0.7187465056471518,
|
| 385 |
+
"learning_rate": 2.144714786816836e-05,
|
| 386 |
+
"loss": 0.093,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.8581081081081081,
|
| 391 |
+
"grad_norm": 0.7427271054292853,
|
| 392 |
+
"learning_rate": 2.0642996341688498e-05,
|
| 393 |
+
"loss": 0.1061,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.8918918918918919,
|
| 398 |
+
"grad_norm": 0.9102492961843579,
|
| 399 |
+
"learning_rate": 1.9848389455385845e-05,
|
| 400 |
+
"loss": 0.1117,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.9256756756756757,
|
| 405 |
+
"grad_norm": 0.6300885493957281,
|
| 406 |
+
"learning_rate": 1.9064433266248287e-05,
|
| 407 |
+
"loss": 0.1089,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.9594594594594594,
|
| 412 |
+
"grad_norm": 0.8142160296904185,
|
| 413 |
+
"learning_rate": 1.829221900597305e-05,
|
| 414 |
+
"loss": 0.1039,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.9932432432432432,
|
| 419 |
+
"grad_norm": 2.6048425820022088,
|
| 420 |
+
"learning_rate": 1.7532821562021373e-05,
|
| 421 |
+
"loss": 0.1028,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.027027027027027,
|
| 426 |
+
"grad_norm": 0.7413049752502284,
|
| 427 |
+
"learning_rate": 1.6787297981423618e-05,
|
| 428 |
+
"loss": 0.0681,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.060810810810811,
|
| 433 |
+
"grad_norm": 1.1954219728615871,
|
| 434 |
+
"learning_rate": 1.6056685999417336e-05,
|
| 435 |
+
"loss": 0.0589,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.0945945945945947,
|
| 440 |
+
"grad_norm": 0.5252454560354707,
|
| 441 |
+
"learning_rate": 1.5342002594966657e-05,
|
| 442 |
+
"loss": 0.0606,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.1283783783783785,
|
| 447 |
+
"grad_norm": 0.6859669085189071,
|
| 448 |
+
"learning_rate": 1.4644242575173363e-05,
|
| 449 |
+
"loss": 0.056,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.1621621621621623,
|
| 454 |
+
"grad_norm": 0.7090167332441359,
|
| 455 |
+
"learning_rate": 1.3964377190550165e-05,
|
| 456 |
+
"loss": 0.0608,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.195945945945946,
|
| 461 |
+
"grad_norm": 0.47669323187220364,
|
| 462 |
+
"learning_rate": 1.330335278308384e-05,
|
| 463 |
+
"loss": 0.0462,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.22972972972973,
|
| 468 |
+
"grad_norm": 0.3967741627628627,
|
| 469 |
+
"learning_rate": 1.2662089468969717e-05,
|
| 470 |
+
"loss": 0.0506,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.2635135135135136,
|
| 475 |
+
"grad_norm": 0.7073240580865503,
|
| 476 |
+
"learning_rate": 1.2041479857851485e-05,
|
| 477 |
+
"loss": 0.0584,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.2972972972972974,
|
| 482 |
+
"grad_norm": 0.534095245997379,
|
| 483 |
+
"learning_rate": 1.14423878103487e-05,
|
| 484 |
+
"loss": 0.0448,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.331081081081081,
|
| 489 |
+
"grad_norm": 0.5592832360622514,
|
| 490 |
+
"learning_rate": 1.086564723560177e-05,
|
| 491 |
+
"loss": 0.0515,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.364864864864865,
|
| 496 |
+
"grad_norm": 0.5012383371857895,
|
| 497 |
+
"learning_rate": 1.031206093050798e-05,
|
| 498 |
+
"loss": 0.0468,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.3986486486486487,
|
| 503 |
+
"grad_norm": 0.5873919693251372,
|
| 504 |
+
"learning_rate": 9.78239946226439e-06,
|
| 505 |
+
"loss": 0.0481,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.4324324324324325,
|
| 510 |
+
"grad_norm": 0.7663749270398796,
|
| 511 |
+
"learning_rate": 9.277400095772979e-06,
|
| 512 |
+
"loss": 0.051,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.4662162162162162,
|
| 517 |
+
"grad_norm": 0.593558971064878,
|
| 518 |
+
"learning_rate": 8.797765767401159e-06,
|
| 519 |
+
"loss": 0.0554,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.5,
|
| 524 |
+
"grad_norm": 0.5159284273389936,
|
| 525 |
+
"learning_rate": 8.34416410652601e-06,
|
| 526 |
+
"loss": 0.0448,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.5337837837837838,
|
| 531 |
+
"grad_norm": 0.6366287598455895,
|
| 532 |
+
"learning_rate": 7.917226506224227e-06,
|
| 533 |
+
"loss": 0.0472,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.5675675675675675,
|
| 538 |
+
"grad_norm": 0.9410891314952453,
|
| 539 |
+
"learning_rate": 7.51754724440146e-06,
|
| 540 |
+
"loss": 0.0502,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.6013513513513513,
|
| 545 |
+
"grad_norm": 0.47104911363203844,
|
| 546 |
+
"learning_rate": 7.145682656584196e-06,
|
| 547 |
+
"loss": 0.0494,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.635135135135135,
|
| 552 |
+
"grad_norm": 0.48833508181607244,
|
| 553 |
+
"learning_rate": 6.802150361525786e-06,
|
| 554 |
+
"loss": 0.0454,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.668918918918919,
|
| 559 |
+
"grad_norm": 0.5274580172661194,
|
| 560 |
+
"learning_rate": 6.487428540704467e-06,
|
| 561 |
+
"loss": 0.0405,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.7027027027027026,
|
| 566 |
+
"grad_norm": 0.4401735004442807,
|
| 567 |
+
"learning_rate": 6.201955272716275e-06,
|
| 568 |
+
"loss": 0.0387,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.7364864864864864,
|
| 573 |
+
"grad_norm": 0.5222808193914125,
|
| 574 |
+
"learning_rate": 5.946127923489382e-06,
|
| 575 |
+
"loss": 0.0501,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.77027027027027,
|
| 580 |
+
"grad_norm": 0.885902051673082,
|
| 581 |
+
"learning_rate": 5.720302593168628e-06,
|
| 582 |
+
"loss": 0.05,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.804054054054054,
|
| 587 |
+
"grad_norm": 0.4765687214481478,
|
| 588 |
+
"learning_rate": 5.524793620440148e-06,
|
| 589 |
+
"loss": 0.038,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.8378378378378377,
|
| 594 |
+
"grad_norm": 0.5896068685310154,
|
| 595 |
+
"learning_rate": 5.3598731449861e-06,
|
| 596 |
+
"loss": 0.0466,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.8716216216216215,
|
| 601 |
+
"grad_norm": 0.4787445681998641,
|
| 602 |
+
"learning_rate": 5.225770728678475e-06,
|
| 603 |
+
"loss": 0.0486,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.9054054054054053,
|
| 608 |
+
"grad_norm": 0.7298521032646316,
|
| 609 |
+
"learning_rate": 5.122673036039321e-06,
|
| 610 |
+
"loss": 0.0534,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.939189189189189,
|
| 615 |
+
"grad_norm": 0.5563651328125397,
|
| 616 |
+
"learning_rate": 5.050723574412132e-06,
|
| 617 |
+
"loss": 0.0399,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.972972972972973,
|
| 622 |
+
"grad_norm": 0.42205363383969957,
|
| 623 |
+
"learning_rate": 5.010022494206098e-06,
|
| 624 |
+
"loss": 0.0405,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.0,
|
| 629 |
+
"step": 444,
|
| 630 |
+
"total_flos": 311859968540672.0,
|
| 631 |
+
"train_loss": 0.15194854576576938,
|
| 632 |
+
"train_runtime": 8344.2681,
|
| 633 |
+
"train_samples_per_second": 3.401,
|
| 634 |
+
"train_steps_per_second": 0.053
|
| 635 |
+
}
|
| 636 |
+
],
|
| 637 |
+
"logging_steps": 5,
|
| 638 |
+
"max_steps": 444,
|
| 639 |
+
"num_input_tokens_seen": 0,
|
| 640 |
+
"num_train_epochs": 3,
|
| 641 |
+
"save_steps": 500,
|
| 642 |
+
"stateful_callbacks": {
|
| 643 |
+
"TrainerControl": {
|
| 644 |
+
"args": {
|
| 645 |
+
"should_epoch_stop": false,
|
| 646 |
+
"should_evaluate": false,
|
| 647 |
+
"should_log": false,
|
| 648 |
+
"should_save": true,
|
| 649 |
+
"should_training_stop": true
|
| 650 |
+
},
|
| 651 |
+
"attributes": {}
|
| 652 |
+
}
|
| 653 |
+
},
|
| 654 |
+
"total_flos": 311859968540672.0,
|
| 655 |
+
"train_batch_size": 8,
|
| 656 |
+
"trial_name": null,
|
| 657 |
+
"trial_params": null
|
| 658 |
+
}
|