Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +14 -0
- train_results.json +8 -0
- trainer_state.json +682 -0
- training_args.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-Coder-3B-Instruct-sft
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-Coder-3B-Instruct-sft
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-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="edbeeching/Qwen2.5-Coder-3B-Instruct-sft", 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/huggingface/huggingface/runs/gb8rn6vf)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.50.0.dev0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.2.0
|
| 41 |
+
- Tokenizers: 0.21.0
|
| 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": 38010460569600.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 2.1351,
|
| 5 |
+
"train_samples": 1000,
|
| 6 |
+
"train_samples_per_second": 2851.346,
|
| 7 |
+
"train_steps_per_second": 44.962
|
| 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": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.50.0.dev0"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 38010460569600.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 2.1351,
|
| 5 |
+
"train_samples": 1000,
|
| 6 |
+
"train_samples_per_second": 2851.346,
|
| 7 |
+
"train_steps_per_second": 44.962
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,682 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2846975088967972,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0035587188612099642,
|
| 13 |
+
"grad_norm": 3.714656812928013,
|
| 14 |
+
"learning_rate": 3.521126760563381e-06,
|
| 15 |
+
"loss": 1.2324,
|
| 16 |
+
"mean_token_accuracy": 0.706312108039856,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0071174377224199285,
|
| 21 |
+
"grad_norm": 2.538884412766077,
|
| 22 |
+
"learning_rate": 7.042253521126762e-06,
|
| 23 |
+
"loss": 1.1399,
|
| 24 |
+
"mean_token_accuracy": 0.7131082773208618,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.010676156583629894,
|
| 29 |
+
"grad_norm": 1.7771129703443833,
|
| 30 |
+
"learning_rate": 1.056338028169014e-05,
|
| 31 |
+
"loss": 0.9862,
|
| 32 |
+
"mean_token_accuracy": 0.7257840037345886,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.014234875444839857,
|
| 37 |
+
"grad_norm": 1.1549668455493816,
|
| 38 |
+
"learning_rate": 1.4084507042253523e-05,
|
| 39 |
+
"loss": 0.8305,
|
| 40 |
+
"mean_token_accuracy": 0.7594800233840943,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.017793594306049824,
|
| 45 |
+
"grad_norm": 0.8084059187346242,
|
| 46 |
+
"learning_rate": 1.7605633802816902e-05,
|
| 47 |
+
"loss": 0.7989,
|
| 48 |
+
"mean_token_accuracy": 0.7640575289726257,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.021352313167259787,
|
| 53 |
+
"grad_norm": 0.8267562843107086,
|
| 54 |
+
"learning_rate": 2.112676056338028e-05,
|
| 55 |
+
"loss": 0.7668,
|
| 56 |
+
"mean_token_accuracy": 0.7727443218231201,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02491103202846975,
|
| 61 |
+
"grad_norm": 0.7851378820161544,
|
| 62 |
+
"learning_rate": 2.4647887323943664e-05,
|
| 63 |
+
"loss": 0.7649,
|
| 64 |
+
"mean_token_accuracy": 0.7709716081619262,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.028469750889679714,
|
| 69 |
+
"grad_norm": 0.7637956379243507,
|
| 70 |
+
"learning_rate": 2.8169014084507046e-05,
|
| 71 |
+
"loss": 0.7394,
|
| 72 |
+
"mean_token_accuracy": 0.7772023797035217,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03202846975088968,
|
| 77 |
+
"grad_norm": 0.7732620068824387,
|
| 78 |
+
"learning_rate": 3.1690140845070426e-05,
|
| 79 |
+
"loss": 0.7346,
|
| 80 |
+
"mean_token_accuracy": 0.779318380355835,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03558718861209965,
|
| 85 |
+
"grad_norm": 0.7696301616562734,
|
| 86 |
+
"learning_rate": 3.5211267605633805e-05,
|
| 87 |
+
"loss": 0.7206,
|
| 88 |
+
"mean_token_accuracy": 0.7811890006065368,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.03914590747330961,
|
| 93 |
+
"grad_norm": 0.7965650840150478,
|
| 94 |
+
"learning_rate": 3.8732394366197184e-05,
|
| 95 |
+
"loss": 0.7099,
|
| 96 |
+
"mean_token_accuracy": 0.7832624912261963,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.042704626334519574,
|
| 101 |
+
"grad_norm": 0.732913212165206,
|
| 102 |
+
"learning_rate": 4.225352112676056e-05,
|
| 103 |
+
"loss": 0.7365,
|
| 104 |
+
"mean_token_accuracy": 0.778208339214325,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.046263345195729534,
|
| 109 |
+
"grad_norm": 0.840463903142822,
|
| 110 |
+
"learning_rate": 4.577464788732395e-05,
|
| 111 |
+
"loss": 0.7158,
|
| 112 |
+
"mean_token_accuracy": 0.7836069345474244,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.0498220640569395,
|
| 117 |
+
"grad_norm": 0.7796733146584423,
|
| 118 |
+
"learning_rate": 4.929577464788733e-05,
|
| 119 |
+
"loss": 0.6948,
|
| 120 |
+
"mean_token_accuracy": 0.7882483005523682,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.05338078291814947,
|
| 125 |
+
"grad_norm": 0.7826425373484522,
|
| 126 |
+
"learning_rate": 4.999900170848507e-05,
|
| 127 |
+
"loss": 0.7299,
|
| 128 |
+
"mean_token_accuracy": 0.7795511484146118,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05693950177935943,
|
| 133 |
+
"grad_norm": 0.7664471564553723,
|
| 134 |
+
"learning_rate": 4.9994946301028825e-05,
|
| 135 |
+
"loss": 0.7205,
|
| 136 |
+
"mean_token_accuracy": 0.7806410670280457,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.060498220640569395,
|
| 141 |
+
"grad_norm": 0.6968982746230619,
|
| 142 |
+
"learning_rate": 4.99877719462654e-05,
|
| 143 |
+
"loss": 0.7217,
|
| 144 |
+
"mean_token_accuracy": 0.7813021302223205,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.06405693950177936,
|
| 149 |
+
"grad_norm": 0.7093605930206083,
|
| 150 |
+
"learning_rate": 4.997747963892645e-05,
|
| 151 |
+
"loss": 0.7337,
|
| 152 |
+
"mean_token_accuracy": 0.7769145965576172,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.06761565836298933,
|
| 157 |
+
"grad_norm": 0.7406894880280147,
|
| 158 |
+
"learning_rate": 4.99640708060509e-05,
|
| 159 |
+
"loss": 0.7337,
|
| 160 |
+
"mean_token_accuracy": 0.7780750393867493,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.0711743772241993,
|
| 165 |
+
"grad_norm": 0.7318985545441932,
|
| 166 |
+
"learning_rate": 4.994754730678713e-05,
|
| 167 |
+
"loss": 0.727,
|
| 168 |
+
"mean_token_accuracy": 0.7799831032752991,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.07473309608540925,
|
| 173 |
+
"grad_norm": 0.7639016380490891,
|
| 174 |
+
"learning_rate": 4.992791143213523e-05,
|
| 175 |
+
"loss": 0.7247,
|
| 176 |
+
"mean_token_accuracy": 0.7811060786247254,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07829181494661921,
|
| 181 |
+
"grad_norm": 0.8011798663105023,
|
| 182 |
+
"learning_rate": 4.990516590462928e-05,
|
| 183 |
+
"loss": 0.7161,
|
| 184 |
+
"mean_token_accuracy": 0.7826329588890075,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.08185053380782918,
|
| 189 |
+
"grad_norm": 0.7616291847324664,
|
| 190 |
+
"learning_rate": 4.9879313877959934e-05,
|
| 191 |
+
"loss": 0.7172,
|
| 192 |
+
"mean_token_accuracy": 0.7815984845161438,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.08540925266903915,
|
| 197 |
+
"grad_norm": 0.6970328489587734,
|
| 198 |
+
"learning_rate": 4.985035893653713e-05,
|
| 199 |
+
"loss": 0.6988,
|
| 200 |
+
"mean_token_accuracy": 0.7884742975234985,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.08896797153024912,
|
| 205 |
+
"grad_norm": 0.6887071171016819,
|
| 206 |
+
"learning_rate": 4.9818305094993096e-05,
|
| 207 |
+
"loss": 0.7252,
|
| 208 |
+
"mean_token_accuracy": 0.7797473907470703,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.09252669039145907,
|
| 213 |
+
"grad_norm": 0.782855999297394,
|
| 214 |
+
"learning_rate": 4.978315679762574e-05,
|
| 215 |
+
"loss": 0.7182,
|
| 216 |
+
"mean_token_accuracy": 0.7811893105506897,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.09608540925266904,
|
| 221 |
+
"grad_norm": 0.6962527878171872,
|
| 222 |
+
"learning_rate": 4.9744918917782446e-05,
|
| 223 |
+
"loss": 0.7274,
|
| 224 |
+
"mean_token_accuracy": 0.7792230010032654,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.099644128113879,
|
| 229 |
+
"grad_norm": 0.6966111313941732,
|
| 230 |
+
"learning_rate": 4.9703596757184346e-05,
|
| 231 |
+
"loss": 0.6958,
|
| 232 |
+
"mean_token_accuracy": 0.78841632604599,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.10320284697508897,
|
| 237 |
+
"grad_norm": 0.6965295119485749,
|
| 238 |
+
"learning_rate": 4.965919604519125e-05,
|
| 239 |
+
"loss": 0.7158,
|
| 240 |
+
"mean_token_accuracy": 0.782188069820404,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.10676156583629894,
|
| 245 |
+
"grad_norm": 0.7008145512070334,
|
| 246 |
+
"learning_rate": 4.96117229380073e-05,
|
| 247 |
+
"loss": 0.7311,
|
| 248 |
+
"mean_token_accuracy": 0.7790884852409363,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.1103202846975089,
|
| 253 |
+
"grad_norm": 0.7210254246058475,
|
| 254 |
+
"learning_rate": 4.956118401782734e-05,
|
| 255 |
+
"loss": 0.6856,
|
| 256 |
+
"mean_token_accuracy": 0.7896694540977478,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.11387900355871886,
|
| 261 |
+
"grad_norm": 0.7230055796086301,
|
| 262 |
+
"learning_rate": 4.950758629192433e-05,
|
| 263 |
+
"loss": 0.7205,
|
| 264 |
+
"mean_token_accuracy": 0.7811832308769227,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.11743772241992882,
|
| 269 |
+
"grad_norm": 0.7177778907287135,
|
| 270 |
+
"learning_rate": 4.945093719167778e-05,
|
| 271 |
+
"loss": 0.7033,
|
| 272 |
+
"mean_token_accuracy": 0.7855350494384765,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.12099644128113879,
|
| 277 |
+
"grad_norm": 0.6993140429254685,
|
| 278 |
+
"learning_rate": 4.939124457154336e-05,
|
| 279 |
+
"loss": 0.716,
|
| 280 |
+
"mean_token_accuracy": 0.7823803782463074,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.12455516014234876,
|
| 285 |
+
"grad_norm": 0.749036299071456,
|
| 286 |
+
"learning_rate": 4.932851670796389e-05,
|
| 287 |
+
"loss": 0.6944,
|
| 288 |
+
"mean_token_accuracy": 0.78707515001297,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.12811387900355872,
|
| 293 |
+
"grad_norm": 0.8003534588080977,
|
| 294 |
+
"learning_rate": 4.926276229822181e-05,
|
| 295 |
+
"loss": 0.7039,
|
| 296 |
+
"mean_token_accuracy": 0.7855878114700318,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.13167259786476868,
|
| 301 |
+
"grad_norm": 0.6511982930622267,
|
| 302 |
+
"learning_rate": 4.919399045923326e-05,
|
| 303 |
+
"loss": 0.7046,
|
| 304 |
+
"mean_token_accuracy": 0.7856501579284668,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.13523131672597866,
|
| 309 |
+
"grad_norm": 0.6631202589315934,
|
| 310 |
+
"learning_rate": 4.9122210726284046e-05,
|
| 311 |
+
"loss": 0.6918,
|
| 312 |
+
"mean_token_accuracy": 0.789514684677124,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.1387900355871886,
|
| 317 |
+
"grad_norm": 0.6877007898563937,
|
| 318 |
+
"learning_rate": 4.904743305170753e-05,
|
| 319 |
+
"loss": 0.6973,
|
| 320 |
+
"mean_token_accuracy": 0.7876662492752076,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.1423487544483986,
|
| 325 |
+
"grad_norm": 0.6594871153113472,
|
| 326 |
+
"learning_rate": 4.896966780350477e-05,
|
| 327 |
+
"loss": 0.7106,
|
| 328 |
+
"mean_token_accuracy": 0.7843179941177368,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.14590747330960854,
|
| 333 |
+
"grad_norm": 0.7077337595180323,
|
| 334 |
+
"learning_rate": 4.888892576390694e-05,
|
| 335 |
+
"loss": 0.7124,
|
| 336 |
+
"mean_token_accuracy": 0.7831673264503479,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.1494661921708185,
|
| 341 |
+
"grad_norm": 0.6734240121888417,
|
| 342 |
+
"learning_rate": 4.88052181278804e-05,
|
| 343 |
+
"loss": 0.6822,
|
| 344 |
+
"mean_token_accuracy": 0.7912026405334472,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15302491103202848,
|
| 349 |
+
"grad_norm": 0.6209145189032446,
|
| 350 |
+
"learning_rate": 4.871855650157446e-05,
|
| 351 |
+
"loss": 0.7311,
|
| 352 |
+
"mean_token_accuracy": 0.779719889163971,
|
| 353 |
+
"step": 215
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.15658362989323843,
|
| 357 |
+
"grad_norm": 0.6857572196473167,
|
| 358 |
+
"learning_rate": 4.8628952900712265e-05,
|
| 359 |
+
"loss": 0.7039,
|
| 360 |
+
"mean_token_accuracy": 0.7850899338722229,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.1601423487544484,
|
| 365 |
+
"grad_norm": 0.721269601531556,
|
| 366 |
+
"learning_rate": 4.853641974892466e-05,
|
| 367 |
+
"loss": 0.6751,
|
| 368 |
+
"mean_token_accuracy": 0.7923677682876586,
|
| 369 |
+
"step": 225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.16370106761565836,
|
| 373 |
+
"grad_norm": 0.6569686267689558,
|
| 374 |
+
"learning_rate": 4.8440969876027794e-05,
|
| 375 |
+
"loss": 0.6902,
|
| 376 |
+
"mean_token_accuracy": 0.7885013699531556,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.16725978647686832,
|
| 381 |
+
"grad_norm": 0.652284057104664,
|
| 382 |
+
"learning_rate": 4.834261651624412e-05,
|
| 383 |
+
"loss": 0.7002,
|
| 384 |
+
"mean_token_accuracy": 0.7859378337860108,
|
| 385 |
+
"step": 235
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.1708185053380783,
|
| 389 |
+
"grad_norm": 0.6985712892311762,
|
| 390 |
+
"learning_rate": 4.824137330636756e-05,
|
| 391 |
+
"loss": 0.6937,
|
| 392 |
+
"mean_token_accuracy": 0.7884337782859803,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.17437722419928825,
|
| 397 |
+
"grad_norm": 0.6981291268835246,
|
| 398 |
+
"learning_rate": 4.8137254283872696e-05,
|
| 399 |
+
"loss": 0.706,
|
| 400 |
+
"mean_token_accuracy": 0.7852147102355957,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.17793594306049823,
|
| 405 |
+
"grad_norm": 0.6830081055108704,
|
| 406 |
+
"learning_rate": 4.803027388496845e-05,
|
| 407 |
+
"loss": 0.6813,
|
| 408 |
+
"mean_token_accuracy": 0.7909272313117981,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.18149466192170818,
|
| 413 |
+
"grad_norm": 0.6763389483738134,
|
| 414 |
+
"learning_rate": 4.7920446942596535e-05,
|
| 415 |
+
"loss": 0.7104,
|
| 416 |
+
"mean_token_accuracy": 0.7841034054756164,
|
| 417 |
+
"step": 255
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.18505338078291814,
|
| 421 |
+
"grad_norm": 0.6758095067389677,
|
| 422 |
+
"learning_rate": 4.780778868437481e-05,
|
| 423 |
+
"loss": 0.6912,
|
| 424 |
+
"mean_token_accuracy": 0.7872965097427368,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.18861209964412812,
|
| 429 |
+
"grad_norm": 0.6654497461754171,
|
| 430 |
+
"learning_rate": 4.769231473048598e-05,
|
| 431 |
+
"loss": 0.7035,
|
| 432 |
+
"mean_token_accuracy": 0.7856454253196716,
|
| 433 |
+
"step": 265
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.19217081850533807,
|
| 437 |
+
"grad_norm": 0.6692448464596932,
|
| 438 |
+
"learning_rate": 4.757404109151184e-05,
|
| 439 |
+
"loss": 0.6956,
|
| 440 |
+
"mean_token_accuracy": 0.7881039142608642,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.19572953736654805,
|
| 445 |
+
"grad_norm": 0.6384295872220533,
|
| 446 |
+
"learning_rate": 4.745298416621336e-05,
|
| 447 |
+
"loss": 0.6941,
|
| 448 |
+
"mean_token_accuracy": 0.7865496397018432,
|
| 449 |
+
"step": 275
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.199288256227758,
|
| 453 |
+
"grad_norm": 0.6917569136927582,
|
| 454 |
+
"learning_rate": 4.7329160739257035e-05,
|
| 455 |
+
"loss": 0.6653,
|
| 456 |
+
"mean_token_accuracy": 0.7947100758552551,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.20284697508896798,
|
| 461 |
+
"grad_norm": 0.6237053314088369,
|
| 462 |
+
"learning_rate": 4.720258797888762e-05,
|
| 463 |
+
"loss": 0.6954,
|
| 464 |
+
"mean_token_accuracy": 0.787773597240448,
|
| 465 |
+
"step": 285
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.20640569395017794,
|
| 469 |
+
"grad_norm": 0.6404989768357283,
|
| 470 |
+
"learning_rate": 4.707328343454777e-05,
|
| 471 |
+
"loss": 0.7143,
|
| 472 |
+
"mean_token_accuracy": 0.7825374364852905,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.2099644128113879,
|
| 477 |
+
"grad_norm": 0.6609383386205755,
|
| 478 |
+
"learning_rate": 4.694126503444479e-05,
|
| 479 |
+
"loss": 0.7104,
|
| 480 |
+
"mean_token_accuracy": 0.7829306364059448,
|
| 481 |
+
"step": 295
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.21352313167259787,
|
| 485 |
+
"grad_norm": 0.6390075364325144,
|
| 486 |
+
"learning_rate": 4.680655108306484e-05,
|
| 487 |
+
"loss": 0.7068,
|
| 488 |
+
"mean_token_accuracy": 0.7846204996109009,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.21708185053380782,
|
| 493 |
+
"grad_norm": 0.7320785611015472,
|
| 494 |
+
"learning_rate": 4.666916025863505e-05,
|
| 495 |
+
"loss": 0.6866,
|
| 496 |
+
"mean_token_accuracy": 0.7891976118087769,
|
| 497 |
+
"step": 305
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.2206405693950178,
|
| 501 |
+
"grad_norm": 0.6542388529582787,
|
| 502 |
+
"learning_rate": 4.652911161053369e-05,
|
| 503 |
+
"loss": 0.6684,
|
| 504 |
+
"mean_token_accuracy": 0.7946648597717285,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.22419928825622776,
|
| 509 |
+
"grad_norm": 0.6387809858585279,
|
| 510 |
+
"learning_rate": 4.6386424556649046e-05,
|
| 511 |
+
"loss": 0.7067,
|
| 512 |
+
"mean_token_accuracy": 0.784406590461731,
|
| 513 |
+
"step": 315
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2277580071174377,
|
| 517 |
+
"grad_norm": 0.6511518481529157,
|
| 518 |
+
"learning_rate": 4.624111888068704e-05,
|
| 519 |
+
"loss": 0.6669,
|
| 520 |
+
"mean_token_accuracy": 0.7934553146362304,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2313167259786477,
|
| 525 |
+
"grad_norm": 0.7857269281531926,
|
| 526 |
+
"learning_rate": 4.6093214729428236e-05,
|
| 527 |
+
"loss": 0.6977,
|
| 528 |
+
"mean_token_accuracy": 0.7871865391731262,
|
| 529 |
+
"step": 325
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.23487544483985764,
|
| 533 |
+
"grad_norm": 0.708401390320286,
|
| 534 |
+
"learning_rate": 4.5942732609934436e-05,
|
| 535 |
+
"loss": 0.6917,
|
| 536 |
+
"mean_token_accuracy": 0.7883163809776306,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.23843416370106763,
|
| 541 |
+
"grad_norm": 0.6537859721831119,
|
| 542 |
+
"learning_rate": 4.57896933867054e-05,
|
| 543 |
+
"loss": 0.7016,
|
| 544 |
+
"mean_token_accuracy": 0.785762631893158,
|
| 545 |
+
"step": 335
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.24199288256227758,
|
| 549 |
+
"grad_norm": 0.6322721246524066,
|
| 550 |
+
"learning_rate": 4.563411827878591e-05,
|
| 551 |
+
"loss": 0.6591,
|
| 552 |
+
"mean_token_accuracy": 0.7976097822189331,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.24555160142348753,
|
| 557 |
+
"grad_norm": 0.613702823629008,
|
| 558 |
+
"learning_rate": 4.5476028856823774e-05,
|
| 559 |
+
"loss": 0.6831,
|
| 560 |
+
"mean_token_accuracy": 0.7909620523452758,
|
| 561 |
+
"step": 345
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.2491103202846975,
|
| 565 |
+
"grad_norm": 0.6470379557892744,
|
| 566 |
+
"learning_rate": 4.531544704007899e-05,
|
| 567 |
+
"loss": 0.6877,
|
| 568 |
+
"mean_token_accuracy": 0.7888366222381592,
|
| 569 |
+
"step": 350
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.2526690391459075,
|
| 573 |
+
"grad_norm": 0.6349334832549038,
|
| 574 |
+
"learning_rate": 4.5152395093384655e-05,
|
| 575 |
+
"loss": 0.6855,
|
| 576 |
+
"mean_token_accuracy": 0.7899898767471314,
|
| 577 |
+
"step": 355
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.25622775800711745,
|
| 581 |
+
"grad_norm": 0.6462491719466713,
|
| 582 |
+
"learning_rate": 4.4986895624059934e-05,
|
| 583 |
+
"loss": 0.6932,
|
| 584 |
+
"mean_token_accuracy": 0.7873799800872803,
|
| 585 |
+
"step": 360
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2597864768683274,
|
| 589 |
+
"grad_norm": 0.630603740544669,
|
| 590 |
+
"learning_rate": 4.481897157877545e-05,
|
| 591 |
+
"loss": 0.709,
|
| 592 |
+
"mean_token_accuracy": 0.7845431327819824,
|
| 593 |
+
"step": 365
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.26334519572953735,
|
| 597 |
+
"grad_norm": 0.6086861709084705,
|
| 598 |
+
"learning_rate": 4.464864624037182e-05,
|
| 599 |
+
"loss": 0.6825,
|
| 600 |
+
"mean_token_accuracy": 0.7913990497589112,
|
| 601 |
+
"step": 370
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.2669039145907473,
|
| 605 |
+
"grad_norm": 1.2548196206715339,
|
| 606 |
+
"learning_rate": 4.447594322463137e-05,
|
| 607 |
+
"loss": 0.6954,
|
| 608 |
+
"mean_token_accuracy": 0.7860358953475952,
|
| 609 |
+
"step": 375
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.2704626334519573,
|
| 613 |
+
"grad_norm": 0.7181263405100091,
|
| 614 |
+
"learning_rate": 4.4300886477003836e-05,
|
| 615 |
+
"loss": 0.6813,
|
| 616 |
+
"mean_token_accuracy": 0.7917158126831054,
|
| 617 |
+
"step": 380
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.27402135231316727,
|
| 621 |
+
"grad_norm": 0.6711130910236095,
|
| 622 |
+
"learning_rate": 4.412350026928628e-05,
|
| 623 |
+
"loss": 0.6896,
|
| 624 |
+
"mean_token_accuracy": 0.7883881092071533,
|
| 625 |
+
"step": 385
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2775800711743772,
|
| 629 |
+
"grad_norm": 0.6035405028151128,
|
| 630 |
+
"learning_rate": 4.3943809196257794e-05,
|
| 631 |
+
"loss": 0.6848,
|
| 632 |
+
"mean_token_accuracy": 0.7895100355148316,
|
| 633 |
+
"step": 390
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.28113879003558717,
|
| 637 |
+
"grad_norm": 0.5844919307530534,
|
| 638 |
+
"learning_rate": 4.37618381722694e-05,
|
| 639 |
+
"loss": 0.6668,
|
| 640 |
+
"mean_token_accuracy": 0.7936931371688842,
|
| 641 |
+
"step": 395
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2846975088967972,
|
| 645 |
+
"grad_norm": 0.6492460475437084,
|
| 646 |
+
"learning_rate": 4.357761242778965e-05,
|
| 647 |
+
"loss": 0.6684,
|
| 648 |
+
"mean_token_accuracy": 0.7950313925743103,
|
| 649 |
+
"step": 400
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.2846975088967972,
|
| 653 |
+
"step": 400,
|
| 654 |
+
"total_flos": 38010460569600.0,
|
| 655 |
+
"train_loss": 0.0,
|
| 656 |
+
"train_runtime": 2.1351,
|
| 657 |
+
"train_samples_per_second": 2851.346,
|
| 658 |
+
"train_steps_per_second": 44.962
|
| 659 |
+
}
|
| 660 |
+
],
|
| 661 |
+
"logging_steps": 5,
|
| 662 |
+
"max_steps": 96,
|
| 663 |
+
"num_input_tokens_seen": 0,
|
| 664 |
+
"num_train_epochs": 1,
|
| 665 |
+
"save_steps": 100,
|
| 666 |
+
"stateful_callbacks": {
|
| 667 |
+
"TrainerControl": {
|
| 668 |
+
"args": {
|
| 669 |
+
"should_epoch_stop": false,
|
| 670 |
+
"should_evaluate": false,
|
| 671 |
+
"should_log": false,
|
| 672 |
+
"should_save": true,
|
| 673 |
+
"should_training_stop": false
|
| 674 |
+
},
|
| 675 |
+
"attributes": {}
|
| 676 |
+
}
|
| 677 |
+
},
|
| 678 |
+
"total_flos": 38010460569600.0,
|
| 679 |
+
"train_batch_size": 8,
|
| 680 |
+
"trial_name": null,
|
| 681 |
+
"trial_params": null
|
| 682 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e412316b9fc7ff57b6ff8f6af938a177f10e118f39327ae33d8b810d2861cfd4
|
| 3 |
size 7672
|