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 +413 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Open-R1-Distill
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Open-R1-Distill
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="LauOverload/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<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/yibin-leon-liu-scale/huggingface/runs/ysnca430)
|
| 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: 3.3.2
|
| 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": 488621249396736.0,
|
| 3 |
+
"train_loss": 0.5793006446824145,
|
| 4 |
+
"train_runtime": 6368.3771,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 5.386,
|
| 7 |
+
"train_steps_per_second": 0.042
|
| 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": "4.49.0"
|
| 14 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 488621249396736.0,
|
| 3 |
+
"train_loss": 0.5793006446824145,
|
| 4 |
+
"train_runtime": 6368.3771,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 5.386,
|
| 7 |
+
"train_steps_per_second": 0.042
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,413 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 268,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.018656716417910446,
|
| 13 |
+
"grad_norm": 1.835107629276508,
|
| 14 |
+
"learning_rate": 1.785714285714286e-05,
|
| 15 |
+
"loss": 0.8456,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03731343283582089,
|
| 20 |
+
"grad_norm": 0.7882040911801051,
|
| 21 |
+
"learning_rate": 3.571428571428572e-05,
|
| 22 |
+
"loss": 0.7682,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.055970149253731345,
|
| 27 |
+
"grad_norm": 0.5091377581238422,
|
| 28 |
+
"learning_rate": 4.999827900623038e-05,
|
| 29 |
+
"loss": 0.7026,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07462686567164178,
|
| 34 |
+
"grad_norm": 0.39640533914329873,
|
| 35 |
+
"learning_rate": 4.993807186343243e-05,
|
| 36 |
+
"loss": 0.6745,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09328358208955224,
|
| 41 |
+
"grad_norm": 0.3826979759238508,
|
| 42 |
+
"learning_rate": 4.979207812402531e-05,
|
| 43 |
+
"loss": 0.6436,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11194029850746269,
|
| 48 |
+
"grad_norm": 0.29829270274143943,
|
| 49 |
+
"learning_rate": 4.956085596012407e-05,
|
| 50 |
+
"loss": 0.6362,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13059701492537312,
|
| 55 |
+
"grad_norm": 0.2799446940559179,
|
| 56 |
+
"learning_rate": 4.924528939432311e-05,
|
| 57 |
+
"loss": 0.6199,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14925373134328357,
|
| 62 |
+
"grad_norm": 0.246134801859443,
|
| 63 |
+
"learning_rate": 4.884658491984735e-05,
|
| 64 |
+
"loss": 0.6106,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16791044776119404,
|
| 69 |
+
"grad_norm": 0.21138691507307888,
|
| 70 |
+
"learning_rate": 4.8366266887814235e-05,
|
| 71 |
+
"loss": 0.6112,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1865671641791045,
|
| 76 |
+
"grad_norm": 0.24408082745774676,
|
| 77 |
+
"learning_rate": 4.780617167924209e-05,
|
| 78 |
+
"loss": 0.5938,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.20522388059701493,
|
| 83 |
+
"grad_norm": 0.25190282011967147,
|
| 84 |
+
"learning_rate": 4.716844068408693e-05,
|
| 85 |
+
"loss": 0.5964,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22388059701492538,
|
| 90 |
+
"grad_norm": 0.2728670734244554,
|
| 91 |
+
"learning_rate": 4.6455512114150546e-05,
|
| 92 |
+
"loss": 0.5918,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.24253731343283583,
|
| 97 |
+
"grad_norm": 0.5358031169637717,
|
| 98 |
+
"learning_rate": 4.5670111681161296e-05,
|
| 99 |
+
"loss": 0.5829,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.26119402985074625,
|
| 104 |
+
"grad_norm": 0.43024464920115174,
|
| 105 |
+
"learning_rate": 4.481524217566783e-05,
|
| 106 |
+
"loss": 0.5801,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2798507462686567,
|
| 111 |
+
"grad_norm": 0.449216255212431,
|
| 112 |
+
"learning_rate": 4.3894171986588217e-05,
|
| 113 |
+
"loss": 0.5787,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.29850746268656714,
|
| 118 |
+
"grad_norm": 0.46214752258663655,
|
| 119 |
+
"learning_rate": 4.29104226053073e-05,
|
| 120 |
+
"loss": 0.5775,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.31716417910447764,
|
| 125 |
+
"grad_norm": 0.349625042640265,
|
| 126 |
+
"learning_rate": 4.186775516209732e-05,
|
| 127 |
+
"loss": 0.5729,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3358208955223881,
|
| 132 |
+
"grad_norm": 0.3335887081213479,
|
| 133 |
+
"learning_rate": 4.077015604633669e-05,
|
| 134 |
+
"loss": 0.5753,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.35447761194029853,
|
| 139 |
+
"grad_norm": 0.31279430637270356,
|
| 140 |
+
"learning_rate": 3.962182166550441e-05,
|
| 141 |
+
"loss": 0.5737,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.373134328358209,
|
| 146 |
+
"grad_norm": 0.2743562946295297,
|
| 147 |
+
"learning_rate": 3.8427142401220634e-05,
|
| 148 |
+
"loss": 0.5696,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3917910447761194,
|
| 153 |
+
"grad_norm": 0.24899144226320521,
|
| 154 |
+
"learning_rate": 3.71906858236735e-05,
|
| 155 |
+
"loss": 0.5659,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.41044776119402987,
|
| 160 |
+
"grad_norm": 0.25495025233466706,
|
| 161 |
+
"learning_rate": 3.591717922860785e-05,
|
| 162 |
+
"loss": 0.5732,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4291044776119403,
|
| 167 |
+
"grad_norm": 0.22494976688173987,
|
| 168 |
+
"learning_rate": 3.46114915636416e-05,
|
| 169 |
+
"loss": 0.5641,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.44776119402985076,
|
| 174 |
+
"grad_norm": 0.25113062077158455,
|
| 175 |
+
"learning_rate": 3.3278614813010034e-05,
|
| 176 |
+
"loss": 0.5651,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4664179104477612,
|
| 181 |
+
"grad_norm": 0.24398287838876176,
|
| 182 |
+
"learning_rate": 3.1923644911909e-05,
|
| 183 |
+
"loss": 0.5619,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.48507462686567165,
|
| 188 |
+
"grad_norm": 0.2180925266351972,
|
| 189 |
+
"learning_rate": 3.0551762263406576e-05,
|
| 190 |
+
"loss": 0.5606,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.503731343283582,
|
| 195 |
+
"grad_norm": 0.22561955109417736,
|
| 196 |
+
"learning_rate": 2.9168211932412042e-05,
|
| 197 |
+
"loss": 0.5578,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5223880597014925,
|
| 202 |
+
"grad_norm": 0.20175082305394765,
|
| 203 |
+
"learning_rate": 2.777828359242567e-05,
|
| 204 |
+
"loss": 0.5632,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5410447761194029,
|
| 209 |
+
"grad_norm": 0.23198667738069967,
|
| 210 |
+
"learning_rate": 2.6387291301738377e-05,
|
| 211 |
+
"loss": 0.5559,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5597014925373134,
|
| 216 |
+
"grad_norm": 0.21712303984457276,
|
| 217 |
+
"learning_rate": 2.50005531864019e-05,
|
| 218 |
+
"loss": 0.5538,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5783582089552238,
|
| 223 |
+
"grad_norm": 0.184762420461371,
|
| 224 |
+
"learning_rate": 2.362337110764688e-05,
|
| 225 |
+
"loss": 0.554,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5970149253731343,
|
| 230 |
+
"grad_norm": 0.19664805819577819,
|
| 231 |
+
"learning_rate": 2.226101039148557e-05,
|
| 232 |
+
"loss": 0.5523,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6156716417910447,
|
| 237 |
+
"grad_norm": 0.22447188807653398,
|
| 238 |
+
"learning_rate": 2.0918679697998252e-05,
|
| 239 |
+
"loss": 0.5511,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6343283582089553,
|
| 244 |
+
"grad_norm": 0.20467888538521883,
|
| 245 |
+
"learning_rate": 1.9601511107268255e-05,
|
| 246 |
+
"loss": 0.5515,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6529850746268657,
|
| 251 |
+
"grad_norm": 0.19342748814815636,
|
| 252 |
+
"learning_rate": 1.8314540498102216e-05,
|
| 253 |
+
"loss": 0.5512,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6716417910447762,
|
| 258 |
+
"grad_norm": 0.1725054123930323,
|
| 259 |
+
"learning_rate": 1.7062688294552992e-05,
|
| 260 |
+
"loss": 0.5433,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6902985074626866,
|
| 265 |
+
"grad_norm": 0.1976162986858871,
|
| 266 |
+
"learning_rate": 1.5850740653856096e-05,
|
| 267 |
+
"loss": 0.5467,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7089552238805971,
|
| 272 |
+
"grad_norm": 0.1761682060625954,
|
| 273 |
+
"learning_rate": 1.4683331167703218e-05,
|
| 274 |
+
"loss": 0.5503,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7276119402985075,
|
| 279 |
+
"grad_norm": 0.16884692132779416,
|
| 280 |
+
"learning_rate": 1.356492314681356e-05,
|
| 281 |
+
"loss": 0.553,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.746268656716418,
|
| 286 |
+
"grad_norm": 0.16201910877834105,
|
| 287 |
+
"learning_rate": 1.2499792556533716e-05,
|
| 288 |
+
"loss": 0.5474,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7649253731343284,
|
| 293 |
+
"grad_norm": 0.17760934756569263,
|
| 294 |
+
"learning_rate": 1.1492011668707753e-05,
|
| 295 |
+
"loss": 0.5449,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7835820895522388,
|
| 300 |
+
"grad_norm": 0.17435813990190582,
|
| 301 |
+
"learning_rate": 1.0545433492320603e-05,
|
| 302 |
+
"loss": 0.55,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8022388059701493,
|
| 307 |
+
"grad_norm": 0.16123671996276417,
|
| 308 |
+
"learning_rate": 9.663677042440537e-06,
|
| 309 |
+
"loss": 0.5444,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8208955223880597,
|
| 314 |
+
"grad_norm": 0.16477412019461615,
|
| 315 |
+
"learning_rate": 8.850113503781367e-06,
|
| 316 |
+
"loss": 0.5443,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8395522388059702,
|
| 321 |
+
"grad_norm": 0.14359540990221165,
|
| 322 |
+
"learning_rate": 8.107853341784671e-06,
|
| 323 |
+
"loss": 0.5506,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8582089552238806,
|
| 328 |
+
"grad_norm": 0.1584061975292916,
|
| 329 |
+
"learning_rate": 7.439734410499752e-06,
|
| 330 |
+
"loss": 0.5471,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8768656716417911,
|
| 335 |
+
"grad_norm": 0.18102782609961157,
|
| 336 |
+
"learning_rate": 6.848311102728011e-06,
|
| 337 |
+
"loss": 0.5472,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8955223880597015,
|
| 342 |
+
"grad_norm": 0.17698885969349223,
|
| 343 |
+
"learning_rate": 6.335844583913515e-06,
|
| 344 |
+
"loss": 0.5433,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.914179104477612,
|
| 349 |
+
"grad_norm": 0.14474372246173606,
|
| 350 |
+
"learning_rate": 5.904294147118193e-06,
|
| 351 |
+
"loss": 0.5471,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9328358208955224,
|
| 356 |
+
"grad_norm": 0.14861103552443383,
|
| 357 |
+
"learning_rate": 5.555309722133842e-06,
|
| 358 |
+
"loss": 0.5435,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9514925373134329,
|
| 363 |
+
"grad_norm": 0.14113545887330373,
|
| 364 |
+
"learning_rate": 5.290225567370509e-06,
|
| 365 |
+
"loss": 0.5396,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9701492537313433,
|
| 370 |
+
"grad_norm": 0.1496443792586628,
|
| 371 |
+
"learning_rate": 5.110055168638854e-06,
|
| 372 |
+
"loss": 0.5433,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9888059701492538,
|
| 377 |
+
"grad_norm": 0.14328732269485714,
|
| 378 |
+
"learning_rate": 5.0154873643297575e-06,
|
| 379 |
+
"loss": 0.547,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.0,
|
| 384 |
+
"step": 268,
|
| 385 |
+
"total_flos": 488621249396736.0,
|
| 386 |
+
"train_loss": 0.5793006446824145,
|
| 387 |
+
"train_runtime": 6368.3771,
|
| 388 |
+
"train_samples_per_second": 5.386,
|
| 389 |
+
"train_steps_per_second": 0.042
|
| 390 |
+
}
|
| 391 |
+
],
|
| 392 |
+
"logging_steps": 5,
|
| 393 |
+
"max_steps": 268,
|
| 394 |
+
"num_input_tokens_seen": 0,
|
| 395 |
+
"num_train_epochs": 1,
|
| 396 |
+
"save_steps": 100,
|
| 397 |
+
"stateful_callbacks": {
|
| 398 |
+
"TrainerControl": {
|
| 399 |
+
"args": {
|
| 400 |
+
"should_epoch_stop": false,
|
| 401 |
+
"should_evaluate": false,
|
| 402 |
+
"should_log": false,
|
| 403 |
+
"should_save": true,
|
| 404 |
+
"should_training_stop": true
|
| 405 |
+
},
|
| 406 |
+
"attributes": {}
|
| 407 |
+
}
|
| 408 |
+
},
|
| 409 |
+
"total_flos": 488621249396736.0,
|
| 410 |
+
"train_batch_size": 16,
|
| 411 |
+
"trial_name": null,
|
| 412 |
+
"trial_params": null
|
| 413 |
+
}
|