Commit
·
a58659e
1
Parent(s):
b0f1b12
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +301 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.999384615384617,
|
| 5 |
+
"global_step": 8120,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 0.16827097535133362,
|
| 13 |
+
"eval_mse": 0.1682709902524948,
|
| 14 |
+
"eval_runtime": 6.9267,
|
| 15 |
+
"eval_samples_per_second": 72.185,
|
| 16 |
+
"eval_steps_per_second": 9.095,
|
| 17 |
+
"step": 406
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.23,
|
| 21 |
+
"learning_rate": 1.6705897491197778e-05,
|
| 22 |
+
"loss": 0.473,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_loss": 0.12349746376276016,
|
| 28 |
+
"eval_mse": 0.12349746376276016,
|
| 29 |
+
"eval_runtime": 6.9169,
|
| 30 |
+
"eval_samples_per_second": 72.287,
|
| 31 |
+
"eval_steps_per_second": 9.108,
|
| 32 |
+
"step": 812
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.46,
|
| 36 |
+
"learning_rate": 1.5609709991775352e-05,
|
| 37 |
+
"loss": 0.1309,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_loss": 0.12400069087743759,
|
| 43 |
+
"eval_mse": 0.12400069087743759,
|
| 44 |
+
"eval_runtime": 6.8578,
|
| 45 |
+
"eval_samples_per_second": 72.91,
|
| 46 |
+
"eval_steps_per_second": 9.187,
|
| 47 |
+
"step": 1218
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.69,
|
| 51 |
+
"learning_rate": 1.4513522492352923e-05,
|
| 52 |
+
"loss": 0.0981,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_loss": 0.099566251039505,
|
| 58 |
+
"eval_mse": 0.099566251039505,
|
| 59 |
+
"eval_runtime": 6.8428,
|
| 60 |
+
"eval_samples_per_second": 73.07,
|
| 61 |
+
"eval_steps_per_second": 9.207,
|
| 62 |
+
"step": 1624
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.93,
|
| 66 |
+
"learning_rate": 1.3417334992930497e-05,
|
| 67 |
+
"loss": 0.0777,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_loss": 0.09356459975242615,
|
| 73 |
+
"eval_mse": 0.09356459975242615,
|
| 74 |
+
"eval_runtime": 6.8878,
|
| 75 |
+
"eval_samples_per_second": 72.593,
|
| 76 |
+
"eval_steps_per_second": 9.147,
|
| 77 |
+
"step": 2030
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_loss": 0.08973243087530136,
|
| 82 |
+
"eval_mse": 0.08973242342472076,
|
| 83 |
+
"eval_runtime": 6.8512,
|
| 84 |
+
"eval_samples_per_second": 72.98,
|
| 85 |
+
"eval_steps_per_second": 9.196,
|
| 86 |
+
"step": 2436
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.16,
|
| 90 |
+
"learning_rate": 1.2321147493508071e-05,
|
| 91 |
+
"loss": 0.0627,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_loss": 0.09244009107351303,
|
| 97 |
+
"eval_mse": 0.09244009107351303,
|
| 98 |
+
"eval_runtime": 6.9051,
|
| 99 |
+
"eval_samples_per_second": 72.41,
|
| 100 |
+
"eval_steps_per_second": 9.124,
|
| 101 |
+
"step": 2842
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 7.39,
|
| 105 |
+
"learning_rate": 1.1224959994085646e-05,
|
| 106 |
+
"loss": 0.0543,
|
| 107 |
+
"step": 3000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_loss": 0.08615754544734955,
|
| 112 |
+
"eval_mse": 0.08615754544734955,
|
| 113 |
+
"eval_runtime": 6.8404,
|
| 114 |
+
"eval_samples_per_second": 73.095,
|
| 115 |
+
"eval_steps_per_second": 9.21,
|
| 116 |
+
"step": 3248
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.62,
|
| 120 |
+
"learning_rate": 1.012877249466322e-05,
|
| 121 |
+
"loss": 0.0452,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.0,
|
| 126 |
+
"eval_loss": 0.08058410882949829,
|
| 127 |
+
"eval_mse": 0.08058410882949829,
|
| 128 |
+
"eval_runtime": 6.8551,
|
| 129 |
+
"eval_samples_per_second": 72.938,
|
| 130 |
+
"eval_steps_per_second": 9.19,
|
| 131 |
+
"step": 3654
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 9.85,
|
| 135 |
+
"learning_rate": 9.032584995240794e-06,
|
| 136 |
+
"loss": 0.0656,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"eval_loss": 0.17249491810798645,
|
| 142 |
+
"eval_mse": 0.17249493300914764,
|
| 143 |
+
"eval_runtime": 6.8293,
|
| 144 |
+
"eval_samples_per_second": 73.214,
|
| 145 |
+
"eval_steps_per_second": 9.225,
|
| 146 |
+
"step": 4060
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.0,
|
| 150 |
+
"eval_loss": 0.12468425184488297,
|
| 151 |
+
"eval_mse": 0.12468423694372177,
|
| 152 |
+
"eval_runtime": 6.9207,
|
| 153 |
+
"eval_samples_per_second": 72.247,
|
| 154 |
+
"eval_steps_per_second": 9.103,
|
| 155 |
+
"step": 4466
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.08,
|
| 159 |
+
"learning_rate": 7.936397495818367e-06,
|
| 160 |
+
"loss": 0.0482,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 12.0,
|
| 165 |
+
"eval_loss": 0.11367713660001755,
|
| 166 |
+
"eval_mse": 0.11367714405059814,
|
| 167 |
+
"eval_runtime": 6.9089,
|
| 168 |
+
"eval_samples_per_second": 72.371,
|
| 169 |
+
"eval_steps_per_second": 9.119,
|
| 170 |
+
"step": 4872
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 12.32,
|
| 174 |
+
"learning_rate": 6.84020999639594e-06,
|
| 175 |
+
"loss": 0.0397,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_loss": 0.08477988839149475,
|
| 181 |
+
"eval_mse": 0.08477988839149475,
|
| 182 |
+
"eval_runtime": 6.9087,
|
| 183 |
+
"eval_samples_per_second": 72.372,
|
| 184 |
+
"eval_steps_per_second": 9.119,
|
| 185 |
+
"step": 5278
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 13.55,
|
| 189 |
+
"learning_rate": 5.744022496973514e-06,
|
| 190 |
+
"loss": 0.0338,
|
| 191 |
+
"step": 5500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"eval_loss": 0.099708691239357,
|
| 196 |
+
"eval_mse": 0.099708691239357,
|
| 197 |
+
"eval_runtime": 6.9177,
|
| 198 |
+
"eval_samples_per_second": 72.278,
|
| 199 |
+
"eval_steps_per_second": 9.107,
|
| 200 |
+
"step": 5684
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 14.78,
|
| 204 |
+
"learning_rate": 4.647834997551088e-06,
|
| 205 |
+
"loss": 0.0306,
|
| 206 |
+
"step": 6000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.0,
|
| 210 |
+
"eval_loss": 0.08894743025302887,
|
| 211 |
+
"eval_mse": 0.08894742280244827,
|
| 212 |
+
"eval_runtime": 6.8363,
|
| 213 |
+
"eval_samples_per_second": 73.139,
|
| 214 |
+
"eval_steps_per_second": 9.215,
|
| 215 |
+
"step": 6090
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 16.0,
|
| 219 |
+
"eval_loss": 0.09760861098766327,
|
| 220 |
+
"eval_mse": 0.09760861098766327,
|
| 221 |
+
"eval_runtime": 6.9072,
|
| 222 |
+
"eval_samples_per_second": 72.388,
|
| 223 |
+
"eval_steps_per_second": 9.121,
|
| 224 |
+
"step": 6496
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.01,
|
| 228 |
+
"learning_rate": 3.5516474981286615e-06,
|
| 229 |
+
"loss": 0.0278,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 17.0,
|
| 234 |
+
"eval_loss": 0.07102830708026886,
|
| 235 |
+
"eval_mse": 0.07102830708026886,
|
| 236 |
+
"eval_runtime": 6.8361,
|
| 237 |
+
"eval_samples_per_second": 73.141,
|
| 238 |
+
"eval_steps_per_second": 9.216,
|
| 239 |
+
"step": 6902
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.24,
|
| 243 |
+
"learning_rate": 2.455459998706235e-06,
|
| 244 |
+
"loss": 0.0256,
|
| 245 |
+
"step": 7000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 18.0,
|
| 249 |
+
"eval_loss": 0.08258407562971115,
|
| 250 |
+
"eval_mse": 0.08258406072854996,
|
| 251 |
+
"eval_runtime": 6.9004,
|
| 252 |
+
"eval_samples_per_second": 72.459,
|
| 253 |
+
"eval_steps_per_second": 9.13,
|
| 254 |
+
"step": 7308
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 18.47,
|
| 258 |
+
"learning_rate": 1.3592724992838087e-06,
|
| 259 |
+
"loss": 0.0238,
|
| 260 |
+
"step": 7500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_loss": 0.07976492494344711,
|
| 265 |
+
"eval_mse": 0.07976492494344711,
|
| 266 |
+
"eval_runtime": 6.8326,
|
| 267 |
+
"eval_samples_per_second": 73.179,
|
| 268 |
+
"eval_steps_per_second": 9.221,
|
| 269 |
+
"step": 7714
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 19.7,
|
| 273 |
+
"learning_rate": 2.630849998613823e-07,
|
| 274 |
+
"loss": 0.0223,
|
| 275 |
+
"step": 8000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"eval_loss": 0.07929830998182297,
|
| 280 |
+
"eval_mse": 0.07929830998182297,
|
| 281 |
+
"eval_runtime": 6.798,
|
| 282 |
+
"eval_samples_per_second": 73.551,
|
| 283 |
+
"eval_steps_per_second": 9.267,
|
| 284 |
+
"step": 8120
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.0,
|
| 288 |
+
"step": 8120,
|
| 289 |
+
"total_flos": 3.028673504394547e+16,
|
| 290 |
+
"train_loss": 0.07788722984896505,
|
| 291 |
+
"train_runtime": 7794.4594,
|
| 292 |
+
"train_samples_per_second": 16.679,
|
| 293 |
+
"train_steps_per_second": 1.042
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"max_steps": 8120,
|
| 297 |
+
"num_train_epochs": 20,
|
| 298 |
+
"total_flos": 3.028673504394547e+16,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": null
|
| 301 |
+
}
|