Commit
·
c86eaec
1
Parent(s):
a269dad
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +292 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18770882487297058,
|
| 3 |
+
"best_model_checkpoint": "./models/results_one_liners_453/checkpoint-225",
|
| 4 |
+
"epoch": 0.6489994591671173,
|
| 5 |
+
"global_step": 225,
|
| 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": 0.6902,
|
| 14 |
+
"step": 8
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 8.000000000000001e-06,
|
| 19 |
+
"loss": 0.6955,
|
| 20 |
+
"step": 16
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1.2e-05,
|
| 25 |
+
"loss": 0.6911,
|
| 26 |
+
"step": 24
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"eval_accuracy": 0.49842271293375395,
|
| 31 |
+
"eval_f1": 0.6618460229689495,
|
| 32 |
+
"eval_loss": 0.6824508309364319,
|
| 33 |
+
"eval_precision": 0.494596312778131,
|
| 34 |
+
"eval_recall": 1.0,
|
| 35 |
+
"eval_runtime": 18.4237,
|
| 36 |
+
"eval_samples_per_second": 172.061,
|
| 37 |
+
"eval_steps_per_second": 21.548,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 43 |
+
"loss": 0.674,
|
| 44 |
+
"step": 32
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 0.611,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.14,
|
| 54 |
+
"learning_rate": 2.4e-05,
|
| 55 |
+
"loss": 0.4327,
|
| 56 |
+
"step": 48
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"eval_accuracy": 0.8712933753943217,
|
| 61 |
+
"eval_f1": 0.8696485623003196,
|
| 62 |
+
"eval_loss": 0.31961607933044434,
|
| 63 |
+
"eval_precision": 0.8646759847522236,
|
| 64 |
+
"eval_recall": 0.8746786632390745,
|
| 65 |
+
"eval_runtime": 18.2327,
|
| 66 |
+
"eval_samples_per_second": 173.864,
|
| 67 |
+
"eval_steps_per_second": 21.774,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.16,
|
| 72 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 73 |
+
"loss": 0.3598,
|
| 74 |
+
"step": 56
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.18,
|
| 78 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 79 |
+
"loss": 0.392,
|
| 80 |
+
"step": 64
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21,
|
| 84 |
+
"learning_rate": 3.6e-05,
|
| 85 |
+
"loss": 0.3812,
|
| 86 |
+
"step": 72
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22,
|
| 90 |
+
"eval_accuracy": 0.8914826498422713,
|
| 91 |
+
"eval_f1": 0.8940234134319162,
|
| 92 |
+
"eval_loss": 0.2683391869068146,
|
| 93 |
+
"eval_precision": 0.8585798816568048,
|
| 94 |
+
"eval_recall": 0.9325192802056556,
|
| 95 |
+
"eval_runtime": 18.1749,
|
| 96 |
+
"eval_samples_per_second": 174.416,
|
| 97 |
+
"eval_steps_per_second": 21.843,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.23,
|
| 102 |
+
"learning_rate": 4e-05,
|
| 103 |
+
"loss": 0.3055,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.25,
|
| 108 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 109 |
+
"loss": 0.3159,
|
| 110 |
+
"step": 88
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.28,
|
| 114 |
+
"learning_rate": 4.8e-05,
|
| 115 |
+
"loss": 0.3093,
|
| 116 |
+
"step": 96
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.29,
|
| 120 |
+
"eval_accuracy": 0.9025236593059937,
|
| 121 |
+
"eval_f1": 0.896551724137931,
|
| 122 |
+
"eval_loss": 0.26234087347984314,
|
| 123 |
+
"eval_precision": 0.9357092941998603,
|
| 124 |
+
"eval_recall": 0.8605398457583547,
|
| 125 |
+
"eval_runtime": 18.2515,
|
| 126 |
+
"eval_samples_per_second": 173.684,
|
| 127 |
+
"eval_steps_per_second": 21.752,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3,
|
| 132 |
+
"learning_rate": 4.9186991869918704e-05,
|
| 133 |
+
"loss": 0.3469,
|
| 134 |
+
"step": 104
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.32,
|
| 138 |
+
"learning_rate": 4.75609756097561e-05,
|
| 139 |
+
"loss": 0.3545,
|
| 140 |
+
"step": 112
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.35,
|
| 144 |
+
"learning_rate": 4.613821138211382e-05,
|
| 145 |
+
"loss": 0.3241,
|
| 146 |
+
"step": 120
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.36,
|
| 150 |
+
"eval_accuracy": 0.8858044164037855,
|
| 151 |
+
"eval_f1": 0.8927725118483413,
|
| 152 |
+
"eval_loss": 0.30523255467414856,
|
| 153 |
+
"eval_precision": 0.828021978021978,
|
| 154 |
+
"eval_recall": 0.968508997429306,
|
| 155 |
+
"eval_runtime": 18.1682,
|
| 156 |
+
"eval_samples_per_second": 174.481,
|
| 157 |
+
"eval_steps_per_second": 21.851,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.37,
|
| 162 |
+
"learning_rate": 4.451219512195122e-05,
|
| 163 |
+
"loss": 0.2721,
|
| 164 |
+
"step": 128
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.39,
|
| 168 |
+
"learning_rate": 4.2886178861788616e-05,
|
| 169 |
+
"loss": 0.3343,
|
| 170 |
+
"step": 136
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.42,
|
| 174 |
+
"learning_rate": 4.126016260162602e-05,
|
| 175 |
+
"loss": 0.3455,
|
| 176 |
+
"step": 144
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.43,
|
| 180 |
+
"eval_accuracy": 0.9141955835962146,
|
| 181 |
+
"eval_f1": 0.9128205128205129,
|
| 182 |
+
"eval_loss": 0.22679537534713745,
|
| 183 |
+
"eval_precision": 0.9104859335038363,
|
| 184 |
+
"eval_recall": 0.9151670951156813,
|
| 185 |
+
"eval_runtime": 18.2508,
|
| 186 |
+
"eval_samples_per_second": 173.691,
|
| 187 |
+
"eval_steps_per_second": 21.752,
|
| 188 |
+
"step": 150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.44,
|
| 192 |
+
"learning_rate": 3.9634146341463416e-05,
|
| 193 |
+
"loss": 0.2462,
|
| 194 |
+
"step": 152
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46,
|
| 198 |
+
"learning_rate": 3.800813008130081e-05,
|
| 199 |
+
"loss": 0.2843,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.48,
|
| 204 |
+
"learning_rate": 3.6382113821138216e-05,
|
| 205 |
+
"loss": 0.1991,
|
| 206 |
+
"step": 168
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5,
|
| 210 |
+
"eval_accuracy": 0.9170347003154574,
|
| 211 |
+
"eval_f1": 0.9147487844408428,
|
| 212 |
+
"eval_loss": 0.20860691368579865,
|
| 213 |
+
"eval_precision": 0.9228253760627861,
|
| 214 |
+
"eval_recall": 0.9068123393316195,
|
| 215 |
+
"eval_runtime": 18.2871,
|
| 216 |
+
"eval_samples_per_second": 173.346,
|
| 217 |
+
"eval_steps_per_second": 21.709,
|
| 218 |
+
"step": 175
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.51,
|
| 222 |
+
"learning_rate": 3.475609756097561e-05,
|
| 223 |
+
"loss": 0.276,
|
| 224 |
+
"step": 176
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.53,
|
| 228 |
+
"learning_rate": 3.313008130081301e-05,
|
| 229 |
+
"loss": 0.2483,
|
| 230 |
+
"step": 184
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.55,
|
| 234 |
+
"learning_rate": 3.150406504065041e-05,
|
| 235 |
+
"loss": 0.2568,
|
| 236 |
+
"step": 192
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.58,
|
| 240 |
+
"learning_rate": 2.9878048780487805e-05,
|
| 241 |
+
"loss": 0.227,
|
| 242 |
+
"step": 200
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.58,
|
| 246 |
+
"eval_accuracy": 0.9198738170347003,
|
| 247 |
+
"eval_f1": 0.9166666666666666,
|
| 248 |
+
"eval_loss": 0.20122328400611877,
|
| 249 |
+
"eval_precision": 0.9363270777479893,
|
| 250 |
+
"eval_recall": 0.8978149100257069,
|
| 251 |
+
"eval_runtime": 18.2795,
|
| 252 |
+
"eval_samples_per_second": 173.418,
|
| 253 |
+
"eval_steps_per_second": 21.718,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6,
|
| 258 |
+
"learning_rate": 2.8252032520325205e-05,
|
| 259 |
+
"loss": 0.2167,
|
| 260 |
+
"step": 208
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.62,
|
| 264 |
+
"learning_rate": 2.66260162601626e-05,
|
| 265 |
+
"loss": 0.2033,
|
| 266 |
+
"step": 216
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.65,
|
| 270 |
+
"learning_rate": 2.5e-05,
|
| 271 |
+
"loss": 0.2357,
|
| 272 |
+
"step": 224
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.65,
|
| 276 |
+
"eval_accuracy": 0.9261829652996846,
|
| 277 |
+
"eval_f1": 0.9254302103250478,
|
| 278 |
+
"eval_loss": 0.18770882487297058,
|
| 279 |
+
"eval_precision": 0.9178255372945638,
|
| 280 |
+
"eval_recall": 0.9331619537275064,
|
| 281 |
+
"eval_runtime": 18.2243,
|
| 282 |
+
"eval_samples_per_second": 173.943,
|
| 283 |
+
"eval_steps_per_second": 21.784,
|
| 284 |
+
"step": 225
|
| 285 |
+
}
|
| 286 |
+
],
|
| 287 |
+
"max_steps": 346,
|
| 288 |
+
"num_train_epochs": 1,
|
| 289 |
+
"total_flos": 429199909056000.0,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|