End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +332 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: top_3_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_3_ranking_stackexchange
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7316
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: top_3_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_3_ranking_stackexchange
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_3_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7316
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.7316058278083801,
|
| 4 |
+
"eval_runtime": 136.9367,
|
| 5 |
+
"eval_samples_per_second": 25.187,
|
| 6 |
+
"eval_steps_per_second": 0.394,
|
| 7 |
+
"total_flos": 643004922593280.0,
|
| 8 |
+
"train_loss": 0.7199326126525799,
|
| 9 |
+
"train_runtime": 22913.1914,
|
| 10 |
+
"train_samples_per_second": 8.578,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.7316058278083801,
|
| 4 |
+
"eval_runtime": 136.9367,
|
| 5 |
+
"eval_samples_per_second": 25.187,
|
| 6 |
+
"eval_steps_per_second": 0.394
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 643004922593280.0,
|
| 4 |
+
"train_loss": 0.7199326126525799,
|
| 5 |
+
"train_runtime": 22913.1914,
|
| 6 |
+
"train_samples_per_second": 8.578,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 384,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.078125,
|
| 13 |
+
"grad_norm": 1.989229761708077,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.9586,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15625,
|
| 20 |
+
"grad_norm": 1.0355970664158494,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.8607,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.234375,
|
| 27 |
+
"grad_norm": 0.822571498397041,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.8216,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3125,
|
| 34 |
+
"grad_norm": 0.8494183855608222,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7988,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.390625,
|
| 41 |
+
"grad_norm": 1.48341908614948,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7875,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46875,
|
| 48 |
+
"grad_norm": 0.9135159144049225,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7797,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.546875,
|
| 55 |
+
"grad_norm": 0.7384014913112803,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.7835,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.625,
|
| 62 |
+
"grad_norm": 0.6786830009552288,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7683,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.703125,
|
| 69 |
+
"grad_norm": 0.5340020280887461,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7716,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.78125,
|
| 76 |
+
"grad_norm": 0.8104437121999043,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.7584,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.859375,
|
| 83 |
+
"grad_norm": 0.6685605420479616,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.7556,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9375,
|
| 90 |
+
"grad_norm": 0.5430213176403433,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.7516,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_loss": 0.7458022236824036,
|
| 98 |
+
"eval_runtime": 136.1896,
|
| 99 |
+
"eval_samples_per_second": 25.325,
|
| 100 |
+
"eval_steps_per_second": 0.397,
|
| 101 |
+
"step": 128
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.015625,
|
| 105 |
+
"grad_norm": 1.0343825556895891,
|
| 106 |
+
"learning_rate": 5e-06,
|
| 107 |
+
"loss": 0.7472,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.09375,
|
| 112 |
+
"grad_norm": 0.8070023677042268,
|
| 113 |
+
"learning_rate": 5e-06,
|
| 114 |
+
"loss": 0.7109,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.171875,
|
| 119 |
+
"grad_norm": 0.5859766931281074,
|
| 120 |
+
"learning_rate": 5e-06,
|
| 121 |
+
"loss": 0.7018,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.25,
|
| 126 |
+
"grad_norm": 1.193085087311897,
|
| 127 |
+
"learning_rate": 5e-06,
|
| 128 |
+
"loss": 0.7094,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.328125,
|
| 133 |
+
"grad_norm": 0.617743482006567,
|
| 134 |
+
"learning_rate": 5e-06,
|
| 135 |
+
"loss": 0.7051,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.40625,
|
| 140 |
+
"grad_norm": 0.5335564121403131,
|
| 141 |
+
"learning_rate": 5e-06,
|
| 142 |
+
"loss": 0.7085,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.484375,
|
| 147 |
+
"grad_norm": 0.5636751992855745,
|
| 148 |
+
"learning_rate": 5e-06,
|
| 149 |
+
"loss": 0.7066,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.5625,
|
| 154 |
+
"grad_norm": 0.6479502921398821,
|
| 155 |
+
"learning_rate": 5e-06,
|
| 156 |
+
"loss": 0.703,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.640625,
|
| 161 |
+
"grad_norm": 0.6165550855901113,
|
| 162 |
+
"learning_rate": 5e-06,
|
| 163 |
+
"loss": 0.7057,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.71875,
|
| 168 |
+
"grad_norm": 0.8274639294227366,
|
| 169 |
+
"learning_rate": 5e-06,
|
| 170 |
+
"loss": 0.7035,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.796875,
|
| 175 |
+
"grad_norm": 0.5692720532923755,
|
| 176 |
+
"learning_rate": 5e-06,
|
| 177 |
+
"loss": 0.7013,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.875,
|
| 182 |
+
"grad_norm": 0.8938353247721228,
|
| 183 |
+
"learning_rate": 5e-06,
|
| 184 |
+
"loss": 0.7012,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.953125,
|
| 189 |
+
"grad_norm": 0.9099896322293264,
|
| 190 |
+
"learning_rate": 5e-06,
|
| 191 |
+
"loss": 0.7023,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.0,
|
| 196 |
+
"eval_loss": 0.732055127620697,
|
| 197 |
+
"eval_runtime": 136.7694,
|
| 198 |
+
"eval_samples_per_second": 25.218,
|
| 199 |
+
"eval_steps_per_second": 0.395,
|
| 200 |
+
"step": 256
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.03125,
|
| 204 |
+
"grad_norm": 0.9337633437694156,
|
| 205 |
+
"learning_rate": 5e-06,
|
| 206 |
+
"loss": 0.6879,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.109375,
|
| 211 |
+
"grad_norm": 0.7120790496228945,
|
| 212 |
+
"learning_rate": 5e-06,
|
| 213 |
+
"loss": 0.6546,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.1875,
|
| 218 |
+
"grad_norm": 0.5657696216097348,
|
| 219 |
+
"learning_rate": 5e-06,
|
| 220 |
+
"loss": 0.6547,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.265625,
|
| 225 |
+
"grad_norm": 0.762365254469541,
|
| 226 |
+
"learning_rate": 5e-06,
|
| 227 |
+
"loss": 0.6556,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.34375,
|
| 232 |
+
"grad_norm": 0.5913303554281267,
|
| 233 |
+
"learning_rate": 5e-06,
|
| 234 |
+
"loss": 0.6514,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.421875,
|
| 239 |
+
"grad_norm": 0.5943753074755849,
|
| 240 |
+
"learning_rate": 5e-06,
|
| 241 |
+
"loss": 0.6553,
|
| 242 |
+
"step": 310
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.5,
|
| 246 |
+
"grad_norm": 0.5265614373912246,
|
| 247 |
+
"learning_rate": 5e-06,
|
| 248 |
+
"loss": 0.6547,
|
| 249 |
+
"step": 320
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.578125,
|
| 253 |
+
"grad_norm": 0.5306706400306282,
|
| 254 |
+
"learning_rate": 5e-06,
|
| 255 |
+
"loss": 0.6618,
|
| 256 |
+
"step": 330
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.65625,
|
| 260 |
+
"grad_norm": 0.6427024835877703,
|
| 261 |
+
"learning_rate": 5e-06,
|
| 262 |
+
"loss": 0.66,
|
| 263 |
+
"step": 340
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.734375,
|
| 267 |
+
"grad_norm": 0.874951265122395,
|
| 268 |
+
"learning_rate": 5e-06,
|
| 269 |
+
"loss": 0.6627,
|
| 270 |
+
"step": 350
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.8125,
|
| 274 |
+
"grad_norm": 0.6147127292953415,
|
| 275 |
+
"learning_rate": 5e-06,
|
| 276 |
+
"loss": 0.6586,
|
| 277 |
+
"step": 360
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.890625,
|
| 281 |
+
"grad_norm": 0.8847013098076022,
|
| 282 |
+
"learning_rate": 5e-06,
|
| 283 |
+
"loss": 0.6632,
|
| 284 |
+
"step": 370
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.96875,
|
| 288 |
+
"grad_norm": 0.5144682471063818,
|
| 289 |
+
"learning_rate": 5e-06,
|
| 290 |
+
"loss": 0.6572,
|
| 291 |
+
"step": 380
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.0,
|
| 295 |
+
"eval_loss": 0.7316058278083801,
|
| 296 |
+
"eval_runtime": 136.3333,
|
| 297 |
+
"eval_samples_per_second": 25.298,
|
| 298 |
+
"eval_steps_per_second": 0.396,
|
| 299 |
+
"step": 384
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.0,
|
| 303 |
+
"step": 384,
|
| 304 |
+
"total_flos": 643004922593280.0,
|
| 305 |
+
"train_loss": 0.7199326126525799,
|
| 306 |
+
"train_runtime": 22913.1914,
|
| 307 |
+
"train_samples_per_second": 8.578,
|
| 308 |
+
"train_steps_per_second": 0.017
|
| 309 |
+
}
|
| 310 |
+
],
|
| 311 |
+
"logging_steps": 10,
|
| 312 |
+
"max_steps": 384,
|
| 313 |
+
"num_input_tokens_seen": 0,
|
| 314 |
+
"num_train_epochs": 3,
|
| 315 |
+
"save_steps": 500,
|
| 316 |
+
"stateful_callbacks": {
|
| 317 |
+
"TrainerControl": {
|
| 318 |
+
"args": {
|
| 319 |
+
"should_epoch_stop": false,
|
| 320 |
+
"should_evaluate": false,
|
| 321 |
+
"should_log": false,
|
| 322 |
+
"should_save": true,
|
| 323 |
+
"should_training_stop": true
|
| 324 |
+
},
|
| 325 |
+
"attributes": {}
|
| 326 |
+
}
|
| 327 |
+
},
|
| 328 |
+
"total_flos": 643004922593280.0,
|
| 329 |
+
"train_batch_size": 8,
|
| 330 |
+
"trial_name": null,
|
| 331 |
+
"trial_params": null
|
| 332 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|