Commit ·
7460b29
1
Parent(s): be8f27c
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +412 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1847076267004013,
|
| 3 |
+
"best_model_checkpoint": "./models/results_one_liners_23/checkpoint-325",
|
| 4 |
+
"epoch": 0.9374436632413917,
|
| 5 |
+
"global_step": 325,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.000000000000001e-06,
|
| 13 |
+
"loss": 0.694,
|
| 14 |
+
"step": 8
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 8.000000000000001e-06,
|
| 19 |
+
"loss": 0.6942,
|
| 20 |
+
"step": 16
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1.2e-05,
|
| 25 |
+
"loss": 0.6865,
|
| 26 |
+
"step": 24
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"eval_accuracy": 0.4908517350157729,
|
| 31 |
+
"eval_f1": 0.6584849767245028,
|
| 32 |
+
"eval_loss": 0.6858492493629456,
|
| 33 |
+
"eval_precision": 0.4908517350157729,
|
| 34 |
+
"eval_recall": 1.0,
|
| 35 |
+
"eval_runtime": 15.5866,
|
| 36 |
+
"eval_samples_per_second": 203.38,
|
| 37 |
+
"eval_steps_per_second": 25.471,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 43 |
+
"loss": 0.6792,
|
| 44 |
+
"step": 32
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 0.6488,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.14,
|
| 54 |
+
"learning_rate": 2.4e-05,
|
| 55 |
+
"loss": 0.4778,
|
| 56 |
+
"step": 48
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"eval_accuracy": 0.8091482649842271,
|
| 61 |
+
"eval_f1": 0.8317107093184979,
|
| 62 |
+
"eval_loss": 0.4457879066467285,
|
| 63 |
+
"eval_precision": 0.73320255026974,
|
| 64 |
+
"eval_recall": 0.9607969151670951,
|
| 65 |
+
"eval_runtime": 15.5131,
|
| 66 |
+
"eval_samples_per_second": 204.343,
|
| 67 |
+
"eval_steps_per_second": 25.591,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.16,
|
| 72 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 73 |
+
"loss": 0.44,
|
| 74 |
+
"step": 56
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.18,
|
| 78 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 79 |
+
"loss": 0.3451,
|
| 80 |
+
"step": 64
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21,
|
| 84 |
+
"learning_rate": 3.6e-05,
|
| 85 |
+
"loss": 0.3646,
|
| 86 |
+
"step": 72
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22,
|
| 90 |
+
"eval_accuracy": 0.8700315457413249,
|
| 91 |
+
"eval_f1": 0.8557422969187675,
|
| 92 |
+
"eval_loss": 0.30672192573547363,
|
| 93 |
+
"eval_precision": 0.94,
|
| 94 |
+
"eval_recall": 0.7853470437017995,
|
| 95 |
+
"eval_runtime": 15.2999,
|
| 96 |
+
"eval_samples_per_second": 207.191,
|
| 97 |
+
"eval_steps_per_second": 25.948,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.23,
|
| 102 |
+
"learning_rate": 4e-05,
|
| 103 |
+
"loss": 0.3381,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.25,
|
| 108 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 109 |
+
"loss": 0.2767,
|
| 110 |
+
"step": 88
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.28,
|
| 114 |
+
"learning_rate": 4.75e-05,
|
| 115 |
+
"loss": 0.3318,
|
| 116 |
+
"step": 96
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.29,
|
| 120 |
+
"eval_accuracy": 0.9009463722397476,
|
| 121 |
+
"eval_f1": 0.9018750000000001,
|
| 122 |
+
"eval_loss": 0.2531206011772156,
|
| 123 |
+
"eval_precision": 0.8777372262773723,
|
| 124 |
+
"eval_recall": 0.9273778920308483,
|
| 125 |
+
"eval_runtime": 15.1416,
|
| 126 |
+
"eval_samples_per_second": 209.357,
|
| 127 |
+
"eval_steps_per_second": 26.219,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3,
|
| 132 |
+
"learning_rate": 4.9390243902439024e-05,
|
| 133 |
+
"loss": 0.2726,
|
| 134 |
+
"step": 104
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.32,
|
| 138 |
+
"learning_rate": 4.776422764227643e-05,
|
| 139 |
+
"loss": 0.3775,
|
| 140 |
+
"step": 112
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.35,
|
| 144 |
+
"learning_rate": 4.613821138211382e-05,
|
| 145 |
+
"loss": 0.4153,
|
| 146 |
+
"step": 120
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.36,
|
| 150 |
+
"eval_accuracy": 0.898422712933754,
|
| 151 |
+
"eval_f1": 0.9005558987029031,
|
| 152 |
+
"eval_loss": 0.258443683385849,
|
| 153 |
+
"eval_precision": 0.8668252080856124,
|
| 154 |
+
"eval_recall": 0.9370179948586118,
|
| 155 |
+
"eval_runtime": 15.1593,
|
| 156 |
+
"eval_samples_per_second": 209.112,
|
| 157 |
+
"eval_steps_per_second": 26.189,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.37,
|
| 162 |
+
"learning_rate": 4.451219512195122e-05,
|
| 163 |
+
"loss": 0.3625,
|
| 164 |
+
"step": 128
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.39,
|
| 168 |
+
"learning_rate": 4.2886178861788616e-05,
|
| 169 |
+
"loss": 0.3033,
|
| 170 |
+
"step": 136
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.42,
|
| 174 |
+
"learning_rate": 4.126016260162602e-05,
|
| 175 |
+
"loss": 0.3392,
|
| 176 |
+
"step": 144
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.43,
|
| 180 |
+
"eval_accuracy": 0.91198738170347,
|
| 181 |
+
"eval_f1": 0.9094449853943525,
|
| 182 |
+
"eval_loss": 0.22280997037887573,
|
| 183 |
+
"eval_precision": 0.9186885245901639,
|
| 184 |
+
"eval_recall": 0.9003856041131105,
|
| 185 |
+
"eval_runtime": 14.7479,
|
| 186 |
+
"eval_samples_per_second": 214.945,
|
| 187 |
+
"eval_steps_per_second": 26.919,
|
| 188 |
+
"step": 150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.44,
|
| 192 |
+
"learning_rate": 3.9634146341463416e-05,
|
| 193 |
+
"loss": 0.2677,
|
| 194 |
+
"step": 152
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46,
|
| 198 |
+
"learning_rate": 3.800813008130081e-05,
|
| 199 |
+
"loss": 0.2286,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.48,
|
| 204 |
+
"learning_rate": 3.6382113821138216e-05,
|
| 205 |
+
"loss": 0.284,
|
| 206 |
+
"step": 168
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5,
|
| 210 |
+
"eval_accuracy": 0.8958990536277602,
|
| 211 |
+
"eval_f1": 0.9009603841536614,
|
| 212 |
+
"eval_loss": 0.2512595057487488,
|
| 213 |
+
"eval_precision": 0.8451576576576577,
|
| 214 |
+
"eval_recall": 0.9646529562982005,
|
| 215 |
+
"eval_runtime": 14.9616,
|
| 216 |
+
"eval_samples_per_second": 211.876,
|
| 217 |
+
"eval_steps_per_second": 26.535,
|
| 218 |
+
"step": 175
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.51,
|
| 222 |
+
"learning_rate": 3.475609756097561e-05,
|
| 223 |
+
"loss": 0.2726,
|
| 224 |
+
"step": 176
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.53,
|
| 228 |
+
"learning_rate": 3.313008130081301e-05,
|
| 229 |
+
"loss": 0.2476,
|
| 230 |
+
"step": 184
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.55,
|
| 234 |
+
"learning_rate": 3.150406504065041e-05,
|
| 235 |
+
"loss": 0.2403,
|
| 236 |
+
"step": 192
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.58,
|
| 240 |
+
"learning_rate": 2.9878048780487805e-05,
|
| 241 |
+
"loss": 0.1909,
|
| 242 |
+
"step": 200
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.58,
|
| 246 |
+
"eval_accuracy": 0.9148264984227129,
|
| 247 |
+
"eval_f1": 0.9126778783958602,
|
| 248 |
+
"eval_loss": 0.2199183851480484,
|
| 249 |
+
"eval_precision": 0.9186197916666666,
|
| 250 |
+
"eval_recall": 0.9068123393316195,
|
| 251 |
+
"eval_runtime": 15.3053,
|
| 252 |
+
"eval_samples_per_second": 207.118,
|
| 253 |
+
"eval_steps_per_second": 25.939,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6,
|
| 258 |
+
"learning_rate": 2.8252032520325205e-05,
|
| 259 |
+
"loss": 0.214,
|
| 260 |
+
"step": 208
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.62,
|
| 264 |
+
"learning_rate": 2.66260162601626e-05,
|
| 265 |
+
"loss": 0.2807,
|
| 266 |
+
"step": 216
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.65,
|
| 270 |
+
"learning_rate": 2.5e-05,
|
| 271 |
+
"loss": 0.2116,
|
| 272 |
+
"step": 224
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.65,
|
| 276 |
+
"eval_accuracy": 0.917981072555205,
|
| 277 |
+
"eval_f1": 0.9144736842105263,
|
| 278 |
+
"eval_loss": 0.2060399204492569,
|
| 279 |
+
"eval_precision": 0.9366576819407008,
|
| 280 |
+
"eval_recall": 0.8933161953727506,
|
| 281 |
+
"eval_runtime": 15.179,
|
| 282 |
+
"eval_samples_per_second": 208.841,
|
| 283 |
+
"eval_steps_per_second": 26.155,
|
| 284 |
+
"step": 225
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.67,
|
| 288 |
+
"learning_rate": 2.3373983739837398e-05,
|
| 289 |
+
"loss": 0.2214,
|
| 290 |
+
"step": 232
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.69,
|
| 294 |
+
"learning_rate": 2.1747967479674798e-05,
|
| 295 |
+
"loss": 0.2164,
|
| 296 |
+
"step": 240
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.72,
|
| 300 |
+
"learning_rate": 2.0121951219512197e-05,
|
| 301 |
+
"loss": 0.2329,
|
| 302 |
+
"step": 248
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.72,
|
| 306 |
+
"eval_accuracy": 0.9097791798107255,
|
| 307 |
+
"eval_f1": 0.9134382566585957,
|
| 308 |
+
"eval_loss": 0.2206372767686844,
|
| 309 |
+
"eval_precision": 0.8632723112128147,
|
| 310 |
+
"eval_recall": 0.9697943444730077,
|
| 311 |
+
"eval_runtime": 14.8474,
|
| 312 |
+
"eval_samples_per_second": 213.506,
|
| 313 |
+
"eval_steps_per_second": 26.739,
|
| 314 |
+
"step": 250
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.74,
|
| 318 |
+
"learning_rate": 1.8495934959349594e-05,
|
| 319 |
+
"loss": 0.1998,
|
| 320 |
+
"step": 256
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.76,
|
| 324 |
+
"learning_rate": 1.6869918699186994e-05,
|
| 325 |
+
"loss": 0.2386,
|
| 326 |
+
"step": 264
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.78,
|
| 330 |
+
"learning_rate": 1.524390243902439e-05,
|
| 331 |
+
"loss": 0.1922,
|
| 332 |
+
"step": 272
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.79,
|
| 336 |
+
"eval_accuracy": 0.9287066246056782,
|
| 337 |
+
"eval_f1": 0.9282083862770013,
|
| 338 |
+
"eval_loss": 0.19086162745952606,
|
| 339 |
+
"eval_precision": 0.917713567839196,
|
| 340 |
+
"eval_recall": 0.9389460154241646,
|
| 341 |
+
"eval_runtime": 14.7603,
|
| 342 |
+
"eval_samples_per_second": 214.766,
|
| 343 |
+
"eval_steps_per_second": 26.896,
|
| 344 |
+
"step": 275
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.81,
|
| 348 |
+
"learning_rate": 1.3617886178861788e-05,
|
| 349 |
+
"loss": 0.1785,
|
| 350 |
+
"step": 280
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.83,
|
| 354 |
+
"learning_rate": 1.1991869918699188e-05,
|
| 355 |
+
"loss": 0.2006,
|
| 356 |
+
"step": 288
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.85,
|
| 360 |
+
"learning_rate": 1.0365853658536585e-05,
|
| 361 |
+
"loss": 0.2012,
|
| 362 |
+
"step": 296
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.87,
|
| 366 |
+
"eval_accuracy": 0.9160883280757098,
|
| 367 |
+
"eval_f1": 0.9183046683046682,
|
| 368 |
+
"eval_loss": 0.21321891248226166,
|
| 369 |
+
"eval_precision": 0.8794117647058823,
|
| 370 |
+
"eval_recall": 0.9607969151670951,
|
| 371 |
+
"eval_runtime": 14.8364,
|
| 372 |
+
"eval_samples_per_second": 213.663,
|
| 373 |
+
"eval_steps_per_second": 26.758,
|
| 374 |
+
"step": 300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.88,
|
| 378 |
+
"learning_rate": 8.739837398373985e-06,
|
| 379 |
+
"loss": 0.205,
|
| 380 |
+
"step": 304
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9,
|
| 384 |
+
"learning_rate": 7.113821138211382e-06,
|
| 385 |
+
"loss": 0.1995,
|
| 386 |
+
"step": 312
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.92,
|
| 390 |
+
"learning_rate": 5.487804878048781e-06,
|
| 391 |
+
"loss": 0.1804,
|
| 392 |
+
"step": 320
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.94,
|
| 396 |
+
"eval_accuracy": 0.9264984227129337,
|
| 397 |
+
"eval_f1": 0.9260552205649001,
|
| 398 |
+
"eval_loss": 0.1847076267004013,
|
| 399 |
+
"eval_precision": 0.9147335423197492,
|
| 400 |
+
"eval_recall": 0.9376606683804627,
|
| 401 |
+
"eval_runtime": 15.3041,
|
| 402 |
+
"eval_samples_per_second": 207.135,
|
| 403 |
+
"eval_steps_per_second": 25.941,
|
| 404 |
+
"step": 325
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"max_steps": 346,
|
| 408 |
+
"num_train_epochs": 1,
|
| 409 |
+
"total_flos": 619955424192000.0,
|
| 410 |
+
"trial_name": null,
|
| 411 |
+
"trial_params": null
|
| 412 |
+
}
|