Upload
Browse files- trainer_state.json +376 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.959878879636639,
|
| 3 |
+
"best_model_checkpoint": "trained_models/CoNLL/checkpoint-10000",
|
| 4 |
+
"epoch": 0.7121492664862555,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.821962683378436e-05,
|
| 13 |
+
"loss": 0.166,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy_score": 0.9851641291226977,
|
| 19 |
+
"eval_f1": 0.9190357439733999,
|
| 20 |
+
"eval_loss": 0.08048456907272339,
|
| 21 |
+
"eval_precision": 0.9080157687253614,
|
| 22 |
+
"eval_recall": 0.9303264893975093,
|
| 23 |
+
"eval_runtime": 27.4476,
|
| 24 |
+
"eval_samples_per_second": 118.517,
|
| 25 |
+
"eval_steps_per_second": 14.828,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 4.643925366756873e-05,
|
| 31 |
+
"loss": 0.0586,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"eval_accuracy_score": 0.9874810170943499,
|
| 37 |
+
"eval_f1": 0.9253980161707094,
|
| 38 |
+
"eval_loss": 0.061091016978025436,
|
| 39 |
+
"eval_precision": 0.9167630057803469,
|
| 40 |
+
"eval_recall": 0.9341972399865365,
|
| 41 |
+
"eval_runtime": 26.4887,
|
| 42 |
+
"eval_samples_per_second": 122.807,
|
| 43 |
+
"eval_steps_per_second": 15.365,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 4.465888050135308e-05,
|
| 49 |
+
"loss": 0.0549,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.11,
|
| 54 |
+
"eval_accuracy_score": 0.9892138156613839,
|
| 55 |
+
"eval_f1": 0.9333000665335994,
|
| 56 |
+
"eval_loss": 0.051654551178216934,
|
| 57 |
+
"eval_precision": 0.9225583689575797,
|
| 58 |
+
"eval_recall": 0.9442948502187816,
|
| 59 |
+
"eval_runtime": 27.064,
|
| 60 |
+
"eval_samples_per_second": 120.197,
|
| 61 |
+
"eval_steps_per_second": 15.038,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.14,
|
| 66 |
+
"learning_rate": 4.287850733513745e-05,
|
| 67 |
+
"loss": 0.0408,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.14,
|
| 72 |
+
"eval_accuracy_score": 0.9887660137845099,
|
| 73 |
+
"eval_f1": 0.9369867605161722,
|
| 74 |
+
"eval_loss": 0.05154793709516525,
|
| 75 |
+
"eval_precision": 0.9330774365821095,
|
| 76 |
+
"eval_recall": 0.9409289801413665,
|
| 77 |
+
"eval_runtime": 34.9374,
|
| 78 |
+
"eval_samples_per_second": 93.109,
|
| 79 |
+
"eval_steps_per_second": 11.649,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18,
|
| 84 |
+
"learning_rate": 4.109813416892181e-05,
|
| 85 |
+
"loss": 0.0313,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.18,
|
| 90 |
+
"eval_accuracy_score": 0.9901094194151319,
|
| 91 |
+
"eval_f1": 0.9437919463087249,
|
| 92 |
+
"eval_loss": 0.049433596432209015,
|
| 93 |
+
"eval_precision": 0.9409501505520241,
|
| 94 |
+
"eval_recall": 0.946650959272972,
|
| 95 |
+
"eval_runtime": 34.757,
|
| 96 |
+
"eval_samples_per_second": 93.593,
|
| 97 |
+
"eval_steps_per_second": 11.71,
|
| 98 |
+
"step": 2500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.21,
|
| 102 |
+
"learning_rate": 3.9317761002706174e-05,
|
| 103 |
+
"loss": 0.0296,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.21,
|
| 108 |
+
"eval_accuracy_score": 0.9906740391729294,
|
| 109 |
+
"eval_f1": 0.9458756398422422,
|
| 110 |
+
"eval_loss": 0.053381938487291336,
|
| 111 |
+
"eval_precision": 0.9432635983263599,
|
| 112 |
+
"eval_recall": 0.9485021878155503,
|
| 113 |
+
"eval_runtime": 36.167,
|
| 114 |
+
"eval_samples_per_second": 89.944,
|
| 115 |
+
"eval_steps_per_second": 11.253,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.25,
|
| 120 |
+
"learning_rate": 3.7537387836490526e-05,
|
| 121 |
+
"loss": 0.0293,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25,
|
| 126 |
+
"eval_accuracy_score": 0.9910634321093416,
|
| 127 |
+
"eval_f1": 0.9481096487551345,
|
| 128 |
+
"eval_loss": 0.042416807264089584,
|
| 129 |
+
"eval_precision": 0.9445465174544847,
|
| 130 |
+
"eval_recall": 0.9516997643890945,
|
| 131 |
+
"eval_runtime": 34.7402,
|
| 132 |
+
"eval_samples_per_second": 93.638,
|
| 133 |
+
"eval_steps_per_second": 11.716,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.28,
|
| 138 |
+
"learning_rate": 3.575701467027489e-05,
|
| 139 |
+
"loss": 0.0226,
|
| 140 |
+
"step": 4000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.28,
|
| 144 |
+
"eval_accuracy_score": 0.9903041158833379,
|
| 145 |
+
"eval_f1": 0.9465661641541039,
|
| 146 |
+
"eval_loss": 0.04618750512599945,
|
| 147 |
+
"eval_precision": 0.9421473824608203,
|
| 148 |
+
"eval_recall": 0.9510265903736116,
|
| 149 |
+
"eval_runtime": 28.4523,
|
| 150 |
+
"eval_samples_per_second": 114.332,
|
| 151 |
+
"eval_steps_per_second": 14.305,
|
| 152 |
+
"step": 4000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.32,
|
| 156 |
+
"learning_rate": 3.397664150405925e-05,
|
| 157 |
+
"loss": 0.0207,
|
| 158 |
+
"step": 4500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.32,
|
| 162 |
+
"eval_accuracy_score": 0.9913944161052919,
|
| 163 |
+
"eval_f1": 0.9520862948407058,
|
| 164 |
+
"eval_loss": 0.04386541247367859,
|
| 165 |
+
"eval_precision": 0.9461525677247797,
|
| 166 |
+
"eval_recall": 0.9580949175361831,
|
| 167 |
+
"eval_runtime": 25.9577,
|
| 168 |
+
"eval_samples_per_second": 125.319,
|
| 169 |
+
"eval_steps_per_second": 15.679,
|
| 170 |
+
"step": 4500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.36,
|
| 174 |
+
"learning_rate": 3.219626833784362e-05,
|
| 175 |
+
"loss": 0.0166,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.36,
|
| 180 |
+
"eval_accuracy_score": 0.9914528250457537,
|
| 181 |
+
"eval_f1": 0.9523649781952366,
|
| 182 |
+
"eval_loss": 0.044772420078516006,
|
| 183 |
+
"eval_precision": 0.949180875961217,
|
| 184 |
+
"eval_recall": 0.9555705149781218,
|
| 185 |
+
"eval_runtime": 28.1693,
|
| 186 |
+
"eval_samples_per_second": 115.48,
|
| 187 |
+
"eval_steps_per_second": 14.448,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.39,
|
| 192 |
+
"learning_rate": 3.041589517162797e-05,
|
| 193 |
+
"loss": 0.0159,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.39,
|
| 198 |
+
"eval_accuracy_score": 0.9914333553989331,
|
| 199 |
+
"eval_f1": 0.9543924604510265,
|
| 200 |
+
"eval_loss": 0.046620924025774,
|
| 201 |
+
"eval_precision": 0.9543924604510265,
|
| 202 |
+
"eval_recall": 0.9543924604510265,
|
| 203 |
+
"eval_runtime": 27.5426,
|
| 204 |
+
"eval_samples_per_second": 118.108,
|
| 205 |
+
"eval_steps_per_second": 14.777,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.43,
|
| 210 |
+
"learning_rate": 2.8635522005412335e-05,
|
| 211 |
+
"loss": 0.0124,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.43,
|
| 216 |
+
"eval_accuracy_score": 0.9917254001012422,
|
| 217 |
+
"eval_f1": 0.9533227185116904,
|
| 218 |
+
"eval_loss": 0.04490247741341591,
|
| 219 |
+
"eval_precision": 0.9494241362043064,
|
| 220 |
+
"eval_recall": 0.9572534500168294,
|
| 221 |
+
"eval_runtime": 22.1337,
|
| 222 |
+
"eval_samples_per_second": 146.971,
|
| 223 |
+
"eval_steps_per_second": 18.388,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.46,
|
| 228 |
+
"learning_rate": 2.6855148839196698e-05,
|
| 229 |
+
"loss": 0.0104,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.46,
|
| 234 |
+
"eval_accuracy_score": 0.9911607803434446,
|
| 235 |
+
"eval_f1": 0.9488426702448842,
|
| 236 |
+
"eval_loss": 0.04854311794042587,
|
| 237 |
+
"eval_precision": 0.9456703443664326,
|
| 238 |
+
"eval_recall": 0.9520363513968361,
|
| 239 |
+
"eval_runtime": 22.2143,
|
| 240 |
+
"eval_samples_per_second": 146.437,
|
| 241 |
+
"eval_steps_per_second": 18.322,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5,
|
| 246 |
+
"learning_rate": 2.507477567298106e-05,
|
| 247 |
+
"loss": 0.0116,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5,
|
| 252 |
+
"eval_accuracy_score": 0.9924652466804252,
|
| 253 |
+
"eval_f1": 0.958029655692385,
|
| 254 |
+
"eval_loss": 0.04380907490849495,
|
| 255 |
+
"eval_precision": 0.9537948290241868,
|
| 256 |
+
"eval_recall": 0.9623022551329519,
|
| 257 |
+
"eval_runtime": 22.1806,
|
| 258 |
+
"eval_samples_per_second": 146.659,
|
| 259 |
+
"eval_steps_per_second": 18.349,
|
| 260 |
+
"step": 7000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.53,
|
| 264 |
+
"learning_rate": 2.329440250676542e-05,
|
| 265 |
+
"loss": 0.008,
|
| 266 |
+
"step": 7500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.53,
|
| 270 |
+
"eval_accuracy_score": 0.9924652466804252,
|
| 271 |
+
"eval_f1": 0.9584347972121924,
|
| 272 |
+
"eval_loss": 0.046966083347797394,
|
| 273 |
+
"eval_precision": 0.9564270152505446,
|
| 274 |
+
"eval_recall": 0.9604510265903736,
|
| 275 |
+
"eval_runtime": 22.1907,
|
| 276 |
+
"eval_samples_per_second": 146.593,
|
| 277 |
+
"eval_steps_per_second": 18.341,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.57,
|
| 282 |
+
"learning_rate": 2.151402934054978e-05,
|
| 283 |
+
"loss": 0.0106,
|
| 284 |
+
"step": 8000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.57,
|
| 288 |
+
"eval_accuracy_score": 0.9920758537440131,
|
| 289 |
+
"eval_f1": 0.9552964857837792,
|
| 290 |
+
"eval_loss": 0.04950818791985512,
|
| 291 |
+
"eval_precision": 0.9521819093797024,
|
| 292 |
+
"eval_recall": 0.9584315045439246,
|
| 293 |
+
"eval_runtime": 22.1428,
|
| 294 |
+
"eval_samples_per_second": 146.91,
|
| 295 |
+
"eval_steps_per_second": 18.381,
|
| 296 |
+
"step": 8000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.61,
|
| 300 |
+
"learning_rate": 1.9733656174334143e-05,
|
| 301 |
+
"loss": 0.0089,
|
| 302 |
+
"step": 8500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.61,
|
| 306 |
+
"eval_accuracy_score": 0.9921732019781161,
|
| 307 |
+
"eval_f1": 0.9558589496607757,
|
| 308 |
+
"eval_loss": 0.04179555922746658,
|
| 309 |
+
"eval_precision": 0.9514757378689345,
|
| 310 |
+
"eval_recall": 0.9602827330865029,
|
| 311 |
+
"eval_runtime": 22.1266,
|
| 312 |
+
"eval_samples_per_second": 147.018,
|
| 313 |
+
"eval_steps_per_second": 18.394,
|
| 314 |
+
"step": 8500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.64,
|
| 318 |
+
"learning_rate": 1.7953283008118502e-05,
|
| 319 |
+
"loss": 0.0067,
|
| 320 |
+
"step": 9000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.64,
|
| 324 |
+
"eval_accuracy_score": 0.9919979751567306,
|
| 325 |
+
"eval_f1": 0.9558872861455887,
|
| 326 |
+
"eval_loss": 0.049222081899642944,
|
| 327 |
+
"eval_precision": 0.9526914075560013,
|
| 328 |
+
"eval_recall": 0.9591046785594076,
|
| 329 |
+
"eval_runtime": 22.1688,
|
| 330 |
+
"eval_samples_per_second": 146.738,
|
| 331 |
+
"eval_steps_per_second": 18.359,
|
| 332 |
+
"step": 9000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.68,
|
| 336 |
+
"learning_rate": 1.6172909841902865e-05,
|
| 337 |
+
"loss": 0.0054,
|
| 338 |
+
"step": 9500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.68,
|
| 342 |
+
"eval_accuracy_score": 0.9919979751567306,
|
| 343 |
+
"eval_f1": 0.9572004028197382,
|
| 344 |
+
"eval_loss": 0.0546395517885685,
|
| 345 |
+
"eval_precision": 0.9546367592902578,
|
| 346 |
+
"eval_recall": 0.9597778525748906,
|
| 347 |
+
"eval_runtime": 23.9981,
|
| 348 |
+
"eval_samples_per_second": 135.552,
|
| 349 |
+
"eval_steps_per_second": 16.96,
|
| 350 |
+
"step": 9500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.71,
|
| 354 |
+
"learning_rate": 1.4392536675687223e-05,
|
| 355 |
+
"loss": 0.0055,
|
| 356 |
+
"step": 10000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.71,
|
| 360 |
+
"eval_accuracy_score": 0.9924068377399634,
|
| 361 |
+
"eval_f1": 0.959878879636639,
|
| 362 |
+
"eval_loss": 0.05072605982422829,
|
| 363 |
+
"eval_precision": 0.9594753657306205,
|
| 364 |
+
"eval_recall": 0.9602827330865029,
|
| 365 |
+
"eval_runtime": 22.125,
|
| 366 |
+
"eval_samples_per_second": 147.028,
|
| 367 |
+
"eval_steps_per_second": 18.396,
|
| 368 |
+
"step": 10000
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 14042,
|
| 372 |
+
"num_train_epochs": 1,
|
| 373 |
+
"total_flos": 5226265866240000.0,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|