End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +232 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"eval_accuracy": 0.9949238578680203,
|
| 4 |
+
"eval_loss": 0.03001626767218113,
|
| 5 |
+
"eval_runtime": 43.9787,
|
| 6 |
+
"eval_samples_per_second": 17.918,
|
| 7 |
+
"eval_steps_per_second": 0.568,
|
| 8 |
+
"train_loss": 0.0993583433330059,
|
| 9 |
+
"train_runtime": 1134.3481,
|
| 10 |
+
"train_samples_per_second": 31.234,
|
| 11 |
+
"train_steps_per_second": 0.242
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"eval_accuracy": 0.9949238578680203,
|
| 4 |
+
"eval_loss": 0.03001626767218113,
|
| 5 |
+
"eval_runtime": 43.9787,
|
| 6 |
+
"eval_samples_per_second": 17.918,
|
| 7 |
+
"eval_steps_per_second": 0.568
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"train_loss": 0.0993583433330059,
|
| 4 |
+
"train_runtime": 1134.3481,
|
| 5 |
+
"train_samples_per_second": 31.234,
|
| 6 |
+
"train_steps_per_second": 0.242
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9949238578680203,
|
| 3 |
+
"best_model_checkpoint": "neunit-ks-ertong-chengren/checkpoint-166",
|
| 4 |
+
"epoch": 4.954954954954955,
|
| 5 |
+
"global_step": 275,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.18,
|
| 12 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 13 |
+
"loss": 0.68,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.36,
|
| 18 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 19 |
+
"loss": 0.6022,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.54,
|
| 24 |
+
"learning_rate": 2.9757085020242918e-05,
|
| 25 |
+
"loss": 0.4498,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.72,
|
| 30 |
+
"learning_rate": 2.854251012145749e-05,
|
| 31 |
+
"loss": 0.2021,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.9,
|
| 36 |
+
"learning_rate": 2.7327935222672065e-05,
|
| 37 |
+
"loss": 0.1364,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.99,
|
| 42 |
+
"eval_accuracy": 0.983502538071066,
|
| 43 |
+
"eval_loss": 0.09111545979976654,
|
| 44 |
+
"eval_runtime": 46.5624,
|
| 45 |
+
"eval_samples_per_second": 16.924,
|
| 46 |
+
"eval_steps_per_second": 0.537,
|
| 47 |
+
"step": 55
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.08,
|
| 51 |
+
"learning_rate": 2.611336032388664e-05,
|
| 52 |
+
"loss": 0.0794,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.26,
|
| 57 |
+
"learning_rate": 2.4898785425101213e-05,
|
| 58 |
+
"loss": 0.0915,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.44,
|
| 63 |
+
"learning_rate": 2.368421052631579e-05,
|
| 64 |
+
"loss": 0.0662,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.62,
|
| 69 |
+
"learning_rate": 2.2469635627530364e-05,
|
| 70 |
+
"loss": 0.043,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.8,
|
| 75 |
+
"learning_rate": 2.125506072874494e-05,
|
| 76 |
+
"loss": 0.0418,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.98,
|
| 81 |
+
"learning_rate": 2.0040485829959516e-05,
|
| 82 |
+
"loss": 0.0459,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.0,
|
| 87 |
+
"eval_accuracy": 0.9847715736040609,
|
| 88 |
+
"eval_loss": 0.07142602652311325,
|
| 89 |
+
"eval_runtime": 46.0778,
|
| 90 |
+
"eval_samples_per_second": 17.101,
|
| 91 |
+
"eval_steps_per_second": 0.543,
|
| 92 |
+
"step": 111
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.16,
|
| 96 |
+
"learning_rate": 1.882591093117409e-05,
|
| 97 |
+
"loss": 0.0356,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.34,
|
| 102 |
+
"learning_rate": 1.7611336032388663e-05,
|
| 103 |
+
"loss": 0.0211,
|
| 104 |
+
"step": 130
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.52,
|
| 108 |
+
"learning_rate": 1.639676113360324e-05,
|
| 109 |
+
"loss": 0.0218,
|
| 110 |
+
"step": 140
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.7,
|
| 114 |
+
"learning_rate": 1.5182186234817814e-05,
|
| 115 |
+
"loss": 0.0276,
|
| 116 |
+
"step": 150
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.88,
|
| 120 |
+
"learning_rate": 1.396761133603239e-05,
|
| 121 |
+
"loss": 0.0285,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.99,
|
| 126 |
+
"eval_accuracy": 0.9949238578680203,
|
| 127 |
+
"eval_loss": 0.03001626767218113,
|
| 128 |
+
"eval_runtime": 45.9035,
|
| 129 |
+
"eval_samples_per_second": 17.166,
|
| 130 |
+
"eval_steps_per_second": 0.545,
|
| 131 |
+
"step": 166
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.06,
|
| 135 |
+
"learning_rate": 1.2753036437246964e-05,
|
| 136 |
+
"loss": 0.0267,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.24,
|
| 141 |
+
"learning_rate": 1.153846153846154e-05,
|
| 142 |
+
"loss": 0.0137,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.42,
|
| 147 |
+
"learning_rate": 1.0323886639676113e-05,
|
| 148 |
+
"loss": 0.0145,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.6,
|
| 153 |
+
"learning_rate": 9.109311740890687e-06,
|
| 154 |
+
"loss": 0.009,
|
| 155 |
+
"step": 200
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.78,
|
| 159 |
+
"learning_rate": 7.894736842105263e-06,
|
| 160 |
+
"loss": 0.0123,
|
| 161 |
+
"step": 210
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.96,
|
| 165 |
+
"learning_rate": 6.680161943319838e-06,
|
| 166 |
+
"loss": 0.0216,
|
| 167 |
+
"step": 220
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 4.0,
|
| 171 |
+
"eval_accuracy": 0.9682741116751269,
|
| 172 |
+
"eval_loss": 0.08131294697523117,
|
| 173 |
+
"eval_runtime": 46.1429,
|
| 174 |
+
"eval_samples_per_second": 17.077,
|
| 175 |
+
"eval_steps_per_second": 0.542,
|
| 176 |
+
"step": 222
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.14,
|
| 180 |
+
"learning_rate": 5.465587044534413e-06,
|
| 181 |
+
"loss": 0.0111,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.32,
|
| 186 |
+
"learning_rate": 4.251012145748988e-06,
|
| 187 |
+
"loss": 0.0132,
|
| 188 |
+
"step": 240
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.5,
|
| 192 |
+
"learning_rate": 3.0364372469635627e-06,
|
| 193 |
+
"loss": 0.0078,
|
| 194 |
+
"step": 250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.68,
|
| 198 |
+
"learning_rate": 1.8218623481781377e-06,
|
| 199 |
+
"loss": 0.0113,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.86,
|
| 204 |
+
"learning_rate": 6.072874493927125e-07,
|
| 205 |
+
"loss": 0.0147,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.95,
|
| 210 |
+
"eval_accuracy": 0.9631979695431472,
|
| 211 |
+
"eval_loss": 0.09215535968542099,
|
| 212 |
+
"eval_runtime": 46.0609,
|
| 213 |
+
"eval_samples_per_second": 17.108,
|
| 214 |
+
"eval_steps_per_second": 0.543,
|
| 215 |
+
"step": 275
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.95,
|
| 219 |
+
"step": 275,
|
| 220 |
+
"total_flos": 6.3782841475584e+17,
|
| 221 |
+
"train_loss": 0.0993583433330059,
|
| 222 |
+
"train_runtime": 1134.3481,
|
| 223 |
+
"train_samples_per_second": 31.234,
|
| 224 |
+
"train_steps_per_second": 0.242
|
| 225 |
+
}
|
| 226 |
+
],
|
| 227 |
+
"max_steps": 275,
|
| 228 |
+
"num_train_epochs": 5,
|
| 229 |
+
"total_flos": 6.3782841475584e+17,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|