Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +295 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 360,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2777777777777778,
|
| 14 |
+
"grad_norm": 1.9213794469833374,
|
| 15 |
+
"learning_rate": 5e-05,
|
| 16 |
+
"loss": 0.9704,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5555555555555556,
|
| 21 |
+
"grad_norm": 2.6781961917877197,
|
| 22 |
+
"learning_rate": 9.999789047591562e-05,
|
| 23 |
+
"loss": 0.4178,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.8333333333333334,
|
| 28 |
+
"grad_norm": 1.419345498085022,
|
| 29 |
+
"learning_rate": 9.974496289936769e-05,
|
| 30 |
+
"loss": 0.354,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.1111111111111112,
|
| 35 |
+
"grad_norm": 0.947891116142273,
|
| 36 |
+
"learning_rate": 9.90725746626209e-05,
|
| 37 |
+
"loss": 0.3275,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.3888888888888888,
|
| 42 |
+
"grad_norm": 1.2710075378417969,
|
| 43 |
+
"learning_rate": 9.798639549376945e-05,
|
| 44 |
+
"loss": 0.2647,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6666666666666665,
|
| 49 |
+
"grad_norm": 1.4519425630569458,
|
| 50 |
+
"learning_rate": 9.64955842986544e-05,
|
| 51 |
+
"loss": 0.2325,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.9444444444444444,
|
| 56 |
+
"grad_norm": 1.5266393423080444,
|
| 57 |
+
"learning_rate": 9.46127119309197e-05,
|
| 58 |
+
"loss": 0.2325,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.2222222222222223,
|
| 63 |
+
"grad_norm": 1.442086100578308,
|
| 64 |
+
"learning_rate": 9.23536551917611e-05,
|
| 65 |
+
"loss": 0.2141,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.5,
|
| 70 |
+
"grad_norm": 1.3214430809020996,
|
| 71 |
+
"learning_rate": 8.9737462953185e-05,
|
| 72 |
+
"loss": 0.1961,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.7777777777777777,
|
| 77 |
+
"grad_norm": 1.3879374265670776,
|
| 78 |
+
"learning_rate": 8.678619553365659e-05,
|
| 79 |
+
"loss": 0.1953,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.0555555555555554,
|
| 84 |
+
"grad_norm": 1.3300167322158813,
|
| 85 |
+
"learning_rate": 8.352473868055746e-05,
|
| 86 |
+
"loss": 0.1732,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.3333333333333335,
|
| 91 |
+
"grad_norm": 0.8237183690071106,
|
| 92 |
+
"learning_rate": 7.998059372799409e-05,
|
| 93 |
+
"loss": 0.1702,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.611111111111111,
|
| 98 |
+
"grad_norm": 1.216146469116211,
|
| 99 |
+
"learning_rate": 7.618364569939391e-05,
|
| 100 |
+
"loss": 0.1519,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.888888888888889,
|
| 105 |
+
"grad_norm": 0.9486384987831116,
|
| 106 |
+
"learning_rate": 7.21659113102993e-05,
|
| 107 |
+
"loss": 0.1566,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.166666666666667,
|
| 112 |
+
"grad_norm": 0.7426595687866211,
|
| 113 |
+
"learning_rate": 6.796126899625688e-05,
|
| 114 |
+
"loss": 0.1495,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.444444444444445,
|
| 119 |
+
"grad_norm": 0.8088931441307068,
|
| 120 |
+
"learning_rate": 6.360517324226676e-05,
|
| 121 |
+
"loss": 0.1478,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.722222222222222,
|
| 126 |
+
"grad_norm": 1.0129106044769287,
|
| 127 |
+
"learning_rate": 5.9134355622630356e-05,
|
| 128 |
+
"loss": 0.1327,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.0,
|
| 133 |
+
"grad_norm": 0.8650373220443726,
|
| 134 |
+
"learning_rate": 5.458651507209518e-05,
|
| 135 |
+
"loss": 0.1381,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 5.277777777777778,
|
| 140 |
+
"grad_norm": 0.7770701050758362,
|
| 141 |
+
"learning_rate": 5e-05,
|
| 142 |
+
"loss": 0.1403,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.555555555555555,
|
| 147 |
+
"grad_norm": 0.7225720286369324,
|
| 148 |
+
"learning_rate": 4.541348492790482e-05,
|
| 149 |
+
"loss": 0.1359,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.833333333333333,
|
| 154 |
+
"grad_norm": 1.0390045642852783,
|
| 155 |
+
"learning_rate": 4.086564437736966e-05,
|
| 156 |
+
"loss": 0.1274,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 6.111111111111111,
|
| 161 |
+
"grad_norm": 1.121009349822998,
|
| 162 |
+
"learning_rate": 3.639482675773324e-05,
|
| 163 |
+
"loss": 0.1117,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.388888888888889,
|
| 168 |
+
"grad_norm": 0.7137916088104248,
|
| 169 |
+
"learning_rate": 3.203873100374314e-05,
|
| 170 |
+
"loss": 0.1101,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.666666666666667,
|
| 175 |
+
"grad_norm": 0.5132378935813904,
|
| 176 |
+
"learning_rate": 2.783408868970071e-05,
|
| 177 |
+
"loss": 0.1157,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 6.944444444444445,
|
| 182 |
+
"grad_norm": 0.5895885229110718,
|
| 183 |
+
"learning_rate": 2.381635430060611e-05,
|
| 184 |
+
"loss": 0.1041,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.222222222222222,
|
| 189 |
+
"grad_norm": 0.5823981165885925,
|
| 190 |
+
"learning_rate": 2.0019406272005915e-05,
|
| 191 |
+
"loss": 0.1066,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 7.5,
|
| 196 |
+
"grad_norm": 0.6076810359954834,
|
| 197 |
+
"learning_rate": 1.6475261319442553e-05,
|
| 198 |
+
"loss": 0.1131,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.777777777777778,
|
| 203 |
+
"grad_norm": 0.5810424089431763,
|
| 204 |
+
"learning_rate": 1.3213804466343421e-05,
|
| 205 |
+
"loss": 0.0964,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.055555555555555,
|
| 210 |
+
"grad_norm": 0.5393444299697876,
|
| 211 |
+
"learning_rate": 1.0262537046815018e-05,
|
| 212 |
+
"loss": 0.0971,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.333333333333334,
|
| 217 |
+
"grad_norm": 0.5941327214241028,
|
| 218 |
+
"learning_rate": 7.646344808238903e-06,
|
| 219 |
+
"loss": 0.0933,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 8.61111111111111,
|
| 224 |
+
"grad_norm": 0.4310052692890167,
|
| 225 |
+
"learning_rate": 5.387288069080299e-06,
|
| 226 |
+
"loss": 0.1067,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 8.88888888888889,
|
| 231 |
+
"grad_norm": 0.4362979233264923,
|
| 232 |
+
"learning_rate": 3.504415701345615e-06,
|
| 233 |
+
"loss": 0.0891,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 9.166666666666666,
|
| 238 |
+
"grad_norm": 0.46284258365631104,
|
| 239 |
+
"learning_rate": 2.013604506230554e-06,
|
| 240 |
+
"loss": 0.1027,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 9.444444444444445,
|
| 245 |
+
"grad_norm": 0.5020444393157959,
|
| 246 |
+
"learning_rate": 9.274253373791064e-07,
|
| 247 |
+
"loss": 0.0852,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 9.722222222222221,
|
| 252 |
+
"grad_norm": 0.5854896903038025,
|
| 253 |
+
"learning_rate": 2.55037100632316e-07,
|
| 254 |
+
"loss": 0.0919,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 10.0,
|
| 259 |
+
"grad_norm": 0.7395591735839844,
|
| 260 |
+
"learning_rate": 2.109524084381587e-09,
|
| 261 |
+
"loss": 0.0918,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 10.0,
|
| 266 |
+
"step": 360,
|
| 267 |
+
"total_flos": 0.0,
|
| 268 |
+
"train_loss": 0.1817794324623214,
|
| 269 |
+
"train_runtime": 394.9899,
|
| 270 |
+
"train_samples_per_second": 44.432,
|
| 271 |
+
"train_steps_per_second": 0.911
|
| 272 |
+
}
|
| 273 |
+
],
|
| 274 |
+
"logging_steps": 10,
|
| 275 |
+
"max_steps": 360,
|
| 276 |
+
"num_input_tokens_seen": 0,
|
| 277 |
+
"num_train_epochs": 10,
|
| 278 |
+
"save_steps": 3000,
|
| 279 |
+
"stateful_callbacks": {
|
| 280 |
+
"TrainerControl": {
|
| 281 |
+
"args": {
|
| 282 |
+
"should_epoch_stop": false,
|
| 283 |
+
"should_evaluate": false,
|
| 284 |
+
"should_log": false,
|
| 285 |
+
"should_save": true,
|
| 286 |
+
"should_training_stop": true
|
| 287 |
+
},
|
| 288 |
+
"attributes": {}
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"total_flos": 0.0,
|
| 292 |
+
"train_batch_size": 49,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|