Model save
Browse files- README.md +57 -0
- all_results.json +9 -0
- generation_config.json +8 -0
- train_results.json +9 -0
- trainer_state.json +372 -0
README.md
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: AmberYifan/Gemma-2-9B-sft-ultrachat
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Gemma-2-9B-sft-ultrachat-safeRLHF
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Gemma-2-9B-sft-ultrachat-safeRLHF
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [AmberYifan/Gemma-2-9B-sft-ultrachat](https://huggingface.co/AmberYifan/Gemma-2-9B-sft-ultrachat).
|
| 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="AmberYifan/Gemma-2-9B-sft-ultrachat-safeRLHF", 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 |
+
|
| 31 |
+
|
| 32 |
+
This model was trained with SFT.
|
| 33 |
+
|
| 34 |
+
### Framework versions
|
| 35 |
+
|
| 36 |
+
- TRL: 0.12.2
|
| 37 |
+
- Transformers: 4.46.3
|
| 38 |
+
- Pytorch: 2.5.1+cu118
|
| 39 |
+
- Datasets: 3.2.0
|
| 40 |
+
- Tokenizers: 0.20.3
|
| 41 |
+
|
| 42 |
+
## Citations
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
Cite TRL as:
|
| 47 |
+
|
| 48 |
+
```bibtex
|
| 49 |
+
@misc{vonwerra2022trl,
|
| 50 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 51 |
+
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},
|
| 52 |
+
year = 2020,
|
| 53 |
+
journal = {GitHub repository},
|
| 54 |
+
publisher = {GitHub},
|
| 55 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 56 |
+
}
|
| 57 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 26794052812800.0,
|
| 4 |
+
"train_loss": 1.5483093844519722,
|
| 5 |
+
"train_runtime": 2786.619,
|
| 6 |
+
"train_samples": 50301,
|
| 7 |
+
"train_samples_per_second": 2.581,
|
| 8 |
+
"train_steps_per_second": 0.081
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.46.3"
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 26794052812800.0,
|
| 4 |
+
"train_loss": 1.5483093844519722,
|
| 5 |
+
"train_runtime": 2786.619,
|
| 6 |
+
"train_samples": 50301,
|
| 7 |
+
"train_samples_per_second": 2.581,
|
| 8 |
+
"train_steps_per_second": 0.081
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 225,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0044444444444444444,
|
| 13 |
+
"grad_norm": 8.214417146752451,
|
| 14 |
+
"learning_rate": 8.695652173913044e-07,
|
| 15 |
+
"loss": 2.0263,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022222222222222223,
|
| 20 |
+
"grad_norm": 3.6940982023267743,
|
| 21 |
+
"learning_rate": 4.347826086956522e-06,
|
| 22 |
+
"loss": 1.9582,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.044444444444444446,
|
| 27 |
+
"grad_norm": 1.8498095767085803,
|
| 28 |
+
"learning_rate": 8.695652173913044e-06,
|
| 29 |
+
"loss": 1.7626,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06666666666666667,
|
| 34 |
+
"grad_norm": 1.6070070655248392,
|
| 35 |
+
"learning_rate": 1.3043478260869566e-05,
|
| 36 |
+
"loss": 1.6818,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08888888888888889,
|
| 41 |
+
"grad_norm": 1.5319931708713932,
|
| 42 |
+
"learning_rate": 1.739130434782609e-05,
|
| 43 |
+
"loss": 1.6306,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1111111111111111,
|
| 48 |
+
"grad_norm": 1.467269040192921,
|
| 49 |
+
"learning_rate": 1.999516282291988e-05,
|
| 50 |
+
"loss": 1.6301,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13333333333333333,
|
| 55 |
+
"grad_norm": 1.4554783607714894,
|
| 56 |
+
"learning_rate": 1.9940798309400527e-05,
|
| 57 |
+
"loss": 1.6183,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.15555555555555556,
|
| 62 |
+
"grad_norm": 1.400684418666206,
|
| 63 |
+
"learning_rate": 1.982635248222264e-05,
|
| 64 |
+
"loss": 1.6312,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17777777777777778,
|
| 69 |
+
"grad_norm": 1.373530741526711,
|
| 70 |
+
"learning_rate": 1.9652517041934357e-05,
|
| 71 |
+
"loss": 1.6135,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2,
|
| 76 |
+
"grad_norm": 1.3446098817534498,
|
| 77 |
+
"learning_rate": 1.9420342634699893e-05,
|
| 78 |
+
"loss": 1.6207,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2222222222222222,
|
| 83 |
+
"grad_norm": 1.325817153627182,
|
| 84 |
+
"learning_rate": 1.913123250228619e-05,
|
| 85 |
+
"loss": 1.5728,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.24444444444444444,
|
| 90 |
+
"grad_norm": 1.3469969360424408,
|
| 91 |
+
"learning_rate": 1.878693400099269e-05,
|
| 92 |
+
"loss": 1.6118,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26666666666666666,
|
| 97 |
+
"grad_norm": 1.3917425359171944,
|
| 98 |
+
"learning_rate": 1.8389528040783014e-05,
|
| 99 |
+
"loss": 1.6024,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.28888888888888886,
|
| 104 |
+
"grad_norm": 1.4303898969445588,
|
| 105 |
+
"learning_rate": 1.7941416508447537e-05,
|
| 106 |
+
"loss": 1.5685,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3111111111111111,
|
| 111 |
+
"grad_norm": 1.3429999677825752,
|
| 112 |
+
"learning_rate": 1.7445307750810153e-05,
|
| 113 |
+
"loss": 1.5726,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3333333333333333,
|
| 118 |
+
"grad_norm": 1.2742933093395246,
|
| 119 |
+
"learning_rate": 1.690420020571747e-05,
|
| 120 |
+
"loss": 1.5603,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.35555555555555557,
|
| 125 |
+
"grad_norm": 1.3045085959219214,
|
| 126 |
+
"learning_rate": 1.6321364279743267e-05,
|
| 127 |
+
"loss": 1.5693,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.37777777777777777,
|
| 132 |
+
"grad_norm": 1.2646034578224143,
|
| 133 |
+
"learning_rate": 1.570032258213783e-05,
|
| 134 |
+
"loss": 1.537,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4,
|
| 139 |
+
"grad_norm": 1.2590924521485223,
|
| 140 |
+
"learning_rate": 1.50448286344864e-05,
|
| 141 |
+
"loss": 1.542,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4222222222222222,
|
| 146 |
+
"grad_norm": 1.259340176409621,
|
| 147 |
+
"learning_rate": 1.4358844184753713e-05,
|
| 148 |
+
"loss": 1.5492,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4444444444444444,
|
| 153 |
+
"grad_norm": 1.2705396470791088,
|
| 154 |
+
"learning_rate": 1.3646515262826551e-05,
|
| 155 |
+
"loss": 1.5322,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4666666666666667,
|
| 160 |
+
"grad_norm": 1.2638794294944307,
|
| 161 |
+
"learning_rate": 1.2912147122272523e-05,
|
| 162 |
+
"loss": 1.5427,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4888888888888889,
|
| 167 |
+
"grad_norm": 1.2424077091728765,
|
| 168 |
+
"learning_rate": 1.2160178219764838e-05,
|
| 169 |
+
"loss": 1.5283,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5111111111111111,
|
| 174 |
+
"grad_norm": 1.2329795354035313,
|
| 175 |
+
"learning_rate": 1.1395153389439232e-05,
|
| 176 |
+
"loss": 1.5173,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5333333333333333,
|
| 181 |
+
"grad_norm": 1.2371556053676906,
|
| 182 |
+
"learning_rate": 1.0621696374314807e-05,
|
| 183 |
+
"loss": 1.5307,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5555555555555556,
|
| 188 |
+
"grad_norm": 1.232712434692815,
|
| 189 |
+
"learning_rate": 9.844481880796492e-06,
|
| 190 |
+
"loss": 1.5281,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5777777777777777,
|
| 195 |
+
"grad_norm": 1.2529176937558433,
|
| 196 |
+
"learning_rate": 9.068207325159285e-06,
|
| 197 |
+
"loss": 1.5087,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6,
|
| 202 |
+
"grad_norm": 1.2996588051365014,
|
| 203 |
+
"learning_rate": 8.297564442776014e-06,
|
| 204 |
+
"loss": 1.5159,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6222222222222222,
|
| 209 |
+
"grad_norm": 1.2184035510596667,
|
| 210 |
+
"learning_rate": 7.537210931679988e-06,
|
| 211 |
+
"loss": 1.5176,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6444444444444445,
|
| 216 |
+
"grad_norm": 1.2490727423346757,
|
| 217 |
+
"learning_rate": 6.791742301846325e-06,
|
| 218 |
+
"loss": 1.4941,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6666666666666666,
|
| 223 |
+
"grad_norm": 1.2241017843446953,
|
| 224 |
+
"learning_rate": 6.065664100332478e-06,
|
| 225 |
+
"loss": 1.5191,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6888888888888889,
|
| 230 |
+
"grad_norm": 1.239277498997839,
|
| 231 |
+
"learning_rate": 5.3633646801467255e-06,
|
| 232 |
+
"loss": 1.5149,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7111111111111111,
|
| 237 |
+
"grad_norm": 1.2454092681206306,
|
| 238 |
+
"learning_rate": 4.6890886774272485e-06,
|
| 239 |
+
"loss": 1.4911,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7333333333333333,
|
| 244 |
+
"grad_norm": 1.1922483231102439,
|
| 245 |
+
"learning_rate": 4.046911357233343e-06,
|
| 246 |
+
"loss": 1.4784,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7555555555555555,
|
| 251 |
+
"grad_norm": 1.2247982014982308,
|
| 252 |
+
"learning_rate": 3.440713983000601e-06,
|
| 253 |
+
"loss": 1.4801,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7777777777777778,
|
| 258 |
+
"grad_norm": 1.239899805156239,
|
| 259 |
+
"learning_rate": 2.8741603585249312e-06,
|
| 260 |
+
"loss": 1.4583,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8,
|
| 265 |
+
"grad_norm": 1.2422952358608288,
|
| 266 |
+
"learning_rate": 2.3506746842535244e-06,
|
| 267 |
+
"loss": 1.4918,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8222222222222222,
|
| 272 |
+
"grad_norm": 1.2349149954091598,
|
| 273 |
+
"learning_rate": 1.8734208617174986e-06,
|
| 274 |
+
"loss": 1.4642,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8444444444444444,
|
| 279 |
+
"grad_norm": 1.2203735788336134,
|
| 280 |
+
"learning_rate": 1.4452833711883629e-06,
|
| 281 |
+
"loss": 1.4605,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8666666666666667,
|
| 286 |
+
"grad_norm": 1.2111942025579017,
|
| 287 |
+
"learning_rate": 1.0688498381320855e-06,
|
| 288 |
+
"loss": 1.4518,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8888888888888888,
|
| 293 |
+
"grad_norm": 1.2227205188182604,
|
| 294 |
+
"learning_rate": 7.463953938275859e-07,
|
| 295 |
+
"loss": 1.471,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9111111111111111,
|
| 300 |
+
"grad_norm": 1.2352427530088093,
|
| 301 |
+
"learning_rate": 4.798689246727006e-07,
|
| 302 |
+
"loss": 1.4786,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9333333333333333,
|
| 307 |
+
"grad_norm": 1.2107626288198272,
|
| 308 |
+
"learning_rate": 2.708812932856253e-07,
|
| 309 |
+
"loss": 1.4627,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9555555555555556,
|
| 314 |
+
"grad_norm": 1.2338739350312762,
|
| 315 |
+
"learning_rate": 1.206956025924333e-07,
|
| 316 |
+
"loss": 1.4702,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9777777777777777,
|
| 321 |
+
"grad_norm": 1.2316651082897998,
|
| 322 |
+
"learning_rate": 3.0219561743707326e-08,
|
| 323 |
+
"loss": 1.4524,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0,
|
| 328 |
+
"grad_norm": 1.379154124562403,
|
| 329 |
+
"learning_rate": 0.0,
|
| 330 |
+
"loss": 1.4667,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"eval_loss": 1.4416327476501465,
|
| 336 |
+
"eval_runtime": 82.5389,
|
| 337 |
+
"eval_samples_per_second": 14.539,
|
| 338 |
+
"eval_steps_per_second": 0.46,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.0,
|
| 343 |
+
"step": 225,
|
| 344 |
+
"total_flos": 26794052812800.0,
|
| 345 |
+
"train_loss": 1.5483093844519722,
|
| 346 |
+
"train_runtime": 2786.619,
|
| 347 |
+
"train_samples_per_second": 2.581,
|
| 348 |
+
"train_steps_per_second": 0.081
|
| 349 |
+
}
|
| 350 |
+
],
|
| 351 |
+
"logging_steps": 5,
|
| 352 |
+
"max_steps": 225,
|
| 353 |
+
"num_input_tokens_seen": 0,
|
| 354 |
+
"num_train_epochs": 1,
|
| 355 |
+
"save_steps": 500,
|
| 356 |
+
"stateful_callbacks": {
|
| 357 |
+
"TrainerControl": {
|
| 358 |
+
"args": {
|
| 359 |
+
"should_epoch_stop": false,
|
| 360 |
+
"should_evaluate": false,
|
| 361 |
+
"should_log": false,
|
| 362 |
+
"should_save": true,
|
| 363 |
+
"should_training_stop": true
|
| 364 |
+
},
|
| 365 |
+
"attributes": {}
|
| 366 |
+
}
|
| 367 |
+
},
|
| 368 |
+
"total_flos": 26794052812800.0,
|
| 369 |
+
"train_batch_size": 8,
|
| 370 |
+
"trial_name": null,
|
| 371 |
+
"trial_params": null
|
| 372 |
+
}
|