Upload 5 files
Browse files- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +328 -0
- training_args.bin +3 -0
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff36b00a002f7c9b34f802a7c7e4dcf4686750aa2509000d9129403b1acbe8c0
|
| 3 |
+
size 1676049841
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ca05be3a8e45e4f6903917e904086a733817ba4d4c32a5a34b41a3ce7f3dcc9
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97519aa695f3215852a0bd8194be02fe14096179a4483c7bb1670cea083c52a3
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,328 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7025796661608499,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-4434",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 22170,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.68,
|
| 12 |
+
"learning_rate": 2e-06,
|
| 13 |
+
"loss": 0.4736,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8308534531162268,
|
| 19 |
+
"eval_f1": 0.682141915061989,
|
| 20 |
+
"eval_loss": 0.37968066334724426,
|
| 21 |
+
"eval_precision": 0.6996753246753247,
|
| 22 |
+
"eval_recall": 0.6654657745753989,
|
| 23 |
+
"eval_runtime": 2.7102,
|
| 24 |
+
"eval_samples_per_second": 68.261,
|
| 25 |
+
"eval_steps_per_second": 68.261,
|
| 26 |
+
"step": 1478
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.35,
|
| 30 |
+
"learning_rate": 1.9055266887104394e-06,
|
| 31 |
+
"loss": 0.3656,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.826221224031443,
|
| 37 |
+
"eval_f1": 0.6371629542790153,
|
| 38 |
+
"eval_loss": 0.37435096502304077,
|
| 39 |
+
"eval_precision": 0.7399591558883595,
|
| 40 |
+
"eval_recall": 0.5594441585177561,
|
| 41 |
+
"eval_runtime": 2.6167,
|
| 42 |
+
"eval_samples_per_second": 70.701,
|
| 43 |
+
"eval_steps_per_second": 70.701,
|
| 44 |
+
"step": 2956
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.03,
|
| 48 |
+
"learning_rate": 1.8110533774208785e-06,
|
| 49 |
+
"loss": 0.3599,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.71,
|
| 54 |
+
"learning_rate": 1.716580066131318e-06,
|
| 55 |
+
"loss": 0.3458,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.8349241998877035,
|
| 61 |
+
"eval_f1": 0.7025796661608499,
|
| 62 |
+
"eval_loss": 0.36284855008125305,
|
| 63 |
+
"eval_precision": 0.6907011437095972,
|
| 64 |
+
"eval_recall": 0.7148739063304169,
|
| 65 |
+
"eval_runtime": 2.6495,
|
| 66 |
+
"eval_samples_per_second": 69.825,
|
| 67 |
+
"eval_steps_per_second": 69.825,
|
| 68 |
+
"step": 4434
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.38,
|
| 72 |
+
"learning_rate": 1.622106754841757e-06,
|
| 73 |
+
"loss": 0.337,
|
| 74 |
+
"step": 5000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"eval_accuracy": 0.8281864121280179,
|
| 79 |
+
"eval_f1": 0.651678998292544,
|
| 80 |
+
"eval_loss": 0.37390556931495667,
|
| 81 |
+
"eval_precision": 0.728835136855506,
|
| 82 |
+
"eval_recall": 0.5892949047864128,
|
| 83 |
+
"eval_runtime": 2.6125,
|
| 84 |
+
"eval_samples_per_second": 70.813,
|
| 85 |
+
"eval_steps_per_second": 70.813,
|
| 86 |
+
"step": 5912
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.06,
|
| 90 |
+
"learning_rate": 1.5276334435521965e-06,
|
| 91 |
+
"loss": 0.3239,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.74,
|
| 96 |
+
"learning_rate": 1.4331601322626356e-06,
|
| 97 |
+
"loss": 0.3015,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.0,
|
| 102 |
+
"eval_accuracy": 0.8357664233576643,
|
| 103 |
+
"eval_f1": 0.6978305785123967,
|
| 104 |
+
"eval_loss": 0.36176469922065735,
|
| 105 |
+
"eval_precision": 0.7003628823224468,
|
| 106 |
+
"eval_recall": 0.6953165208440556,
|
| 107 |
+
"eval_runtime": 2.8697,
|
| 108 |
+
"eval_samples_per_second": 64.467,
|
| 109 |
+
"eval_steps_per_second": 64.467,
|
| 110 |
+
"step": 7390
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.41,
|
| 114 |
+
"learning_rate": 1.338686820973075e-06,
|
| 115 |
+
"loss": 0.2884,
|
| 116 |
+
"step": 8000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.833941605839416,
|
| 121 |
+
"eval_f1": 0.6902330452998167,
|
| 122 |
+
"eval_loss": 0.37303170561790466,
|
| 123 |
+
"eval_precision": 0.7025586353944563,
|
| 124 |
+
"eval_recall": 0.6783324755532681,
|
| 125 |
+
"eval_runtime": 2.7072,
|
| 126 |
+
"eval_samples_per_second": 68.337,
|
| 127 |
+
"eval_steps_per_second": 68.337,
|
| 128 |
+
"step": 8868
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.09,
|
| 132 |
+
"learning_rate": 1.2442135096835144e-06,
|
| 133 |
+
"loss": 0.264,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.77,
|
| 138 |
+
"learning_rate": 1.1497401983939536e-06,
|
| 139 |
+
"loss": 0.2324,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.0,
|
| 144 |
+
"eval_accuracy": 0.8322571588994947,
|
| 145 |
+
"eval_f1": 0.6844467916556641,
|
| 146 |
+
"eval_loss": 0.3992096483707428,
|
| 147 |
+
"eval_precision": 0.702819956616052,
|
| 148 |
+
"eval_recall": 0.6670097786927431,
|
| 149 |
+
"eval_runtime": 2.6272,
|
| 150 |
+
"eval_samples_per_second": 70.416,
|
| 151 |
+
"eval_steps_per_second": 70.416,
|
| 152 |
+
"step": 10346
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 7.44,
|
| 156 |
+
"learning_rate": 1.0552668871043931e-06,
|
| 157 |
+
"loss": 0.1965,
|
| 158 |
+
"step": 11000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.0,
|
| 162 |
+
"eval_accuracy": 0.8250982594048287,
|
| 163 |
+
"eval_f1": 0.6525376464026771,
|
| 164 |
+
"eval_loss": 0.44216522574424744,
|
| 165 |
+
"eval_precision": 0.7121119902617163,
|
| 166 |
+
"eval_recall": 0.602161605764282,
|
| 167 |
+
"eval_runtime": 2.622,
|
| 168 |
+
"eval_samples_per_second": 70.557,
|
| 169 |
+
"eval_steps_per_second": 70.557,
|
| 170 |
+
"step": 11824
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.12,
|
| 174 |
+
"learning_rate": 9.607935758148322e-07,
|
| 175 |
+
"loss": 0.182,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.8,
|
| 180 |
+
"learning_rate": 8.663202645252716e-07,
|
| 181 |
+
"loss": 0.1405,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 9.0,
|
| 186 |
+
"eval_accuracy": 0.823694553621561,
|
| 187 |
+
"eval_f1": 0.6694736842105264,
|
| 188 |
+
"eval_loss": 0.49459609389305115,
|
| 189 |
+
"eval_precision": 0.6849757673667205,
|
| 190 |
+
"eval_recall": 0.6546577457539887,
|
| 191 |
+
"eval_runtime": 2.6563,
|
| 192 |
+
"eval_samples_per_second": 69.645,
|
| 193 |
+
"eval_steps_per_second": 69.645,
|
| 194 |
+
"step": 13302
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 9.47,
|
| 198 |
+
"learning_rate": 7.718469532357109e-07,
|
| 199 |
+
"loss": 0.1149,
|
| 200 |
+
"step": 14000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 10.0,
|
| 204 |
+
"eval_accuracy": 0.8238349241998877,
|
| 205 |
+
"eval_f1": 0.6766297346044834,
|
| 206 |
+
"eval_loss": 0.5486593842506409,
|
| 207 |
+
"eval_precision": 0.6775025799793601,
|
| 208 |
+
"eval_recall": 0.6757591353576943,
|
| 209 |
+
"eval_runtime": 2.6698,
|
| 210 |
+
"eval_samples_per_second": 69.293,
|
| 211 |
+
"eval_steps_per_second": 69.293,
|
| 212 |
+
"step": 14780
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 10.15,
|
| 216 |
+
"learning_rate": 6.773736419461502e-07,
|
| 217 |
+
"loss": 0.1013,
|
| 218 |
+
"step": 15000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 10.83,
|
| 222 |
+
"learning_rate": 5.829003306565895e-07,
|
| 223 |
+
"loss": 0.0808,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 11.0,
|
| 228 |
+
"eval_accuracy": 0.8252386299831556,
|
| 229 |
+
"eval_f1": 0.6767073487405868,
|
| 230 |
+
"eval_loss": 0.6354735493659973,
|
| 231 |
+
"eval_precision": 0.6829140461215933,
|
| 232 |
+
"eval_recall": 0.6706124549665465,
|
| 233 |
+
"eval_runtime": 2.7422,
|
| 234 |
+
"eval_samples_per_second": 67.465,
|
| 235 |
+
"eval_steps_per_second": 67.465,
|
| 236 |
+
"step": 16258
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 11.5,
|
| 240 |
+
"learning_rate": 4.884270193670288e-07,
|
| 241 |
+
"loss": 0.0627,
|
| 242 |
+
"step": 17000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 12.0,
|
| 246 |
+
"eval_accuracy": 0.8260808534531162,
|
| 247 |
+
"eval_f1": 0.6648634027589938,
|
| 248 |
+
"eval_loss": 0.6998042464256287,
|
| 249 |
+
"eval_precision": 0.7006841505131128,
|
| 250 |
+
"eval_recall": 0.6325270200720535,
|
| 251 |
+
"eval_runtime": 2.7874,
|
| 252 |
+
"eval_samples_per_second": 66.371,
|
| 253 |
+
"eval_steps_per_second": 66.371,
|
| 254 |
+
"step": 17736
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 12.18,
|
| 258 |
+
"learning_rate": 3.939537080774681e-07,
|
| 259 |
+
"loss": 0.0496,
|
| 260 |
+
"step": 18000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 12.86,
|
| 264 |
+
"learning_rate": 2.9948039678790744e-07,
|
| 265 |
+
"loss": 0.0399,
|
| 266 |
+
"step": 19000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 13.0,
|
| 270 |
+
"eval_accuracy": 0.8258001122964627,
|
| 271 |
+
"eval_f1": 0.6703851261620186,
|
| 272 |
+
"eval_loss": 0.7429465651512146,
|
| 273 |
+
"eval_precision": 0.6926454445664105,
|
| 274 |
+
"eval_recall": 0.649511065362841,
|
| 275 |
+
"eval_runtime": 2.7701,
|
| 276 |
+
"eval_samples_per_second": 66.784,
|
| 277 |
+
"eval_steps_per_second": 66.784,
|
| 278 |
+
"step": 19214
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 13.53,
|
| 282 |
+
"learning_rate": 2.0500708549834672e-07,
|
| 283 |
+
"loss": 0.032,
|
| 284 |
+
"step": 20000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 14.0,
|
| 288 |
+
"eval_accuracy": 0.8218697361033127,
|
| 289 |
+
"eval_f1": 0.6556309362279512,
|
| 290 |
+
"eval_loss": 0.7868731617927551,
|
| 291 |
+
"eval_precision": 0.6934557979334098,
|
| 292 |
+
"eval_recall": 0.6217189912506433,
|
| 293 |
+
"eval_runtime": 2.7709,
|
| 294 |
+
"eval_samples_per_second": 66.766,
|
| 295 |
+
"eval_steps_per_second": 66.766,
|
| 296 |
+
"step": 20692
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 14.21,
|
| 300 |
+
"learning_rate": 1.1053377420878601e-07,
|
| 301 |
+
"loss": 0.0274,
|
| 302 |
+
"step": 21000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.88,
|
| 306 |
+
"learning_rate": 1.606046291922532e-08,
|
| 307 |
+
"loss": 0.0233,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 15.0,
|
| 312 |
+
"eval_accuracy": 0.8235541830432341,
|
| 313 |
+
"eval_f1": 0.6621875839828004,
|
| 314 |
+
"eval_loss": 0.7936236262321472,
|
| 315 |
+
"eval_precision": 0.6929133858267716,
|
| 316 |
+
"eval_recall": 0.6340710241893979,
|
| 317 |
+
"eval_runtime": 2.7604,
|
| 318 |
+
"eval_samples_per_second": 67.019,
|
| 319 |
+
"eval_steps_per_second": 67.019,
|
| 320 |
+
"step": 22170
|
| 321 |
+
}
|
| 322 |
+
],
|
| 323 |
+
"max_steps": 22170,
|
| 324 |
+
"num_train_epochs": 15,
|
| 325 |
+
"total_flos": 7912225034580240.0,
|
| 326 |
+
"trial_name": null,
|
| 327 |
+
"trial_params": null
|
| 328 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a45227cf2e8bbe468c44c39efcf784a14bbc38689cd98dff0484da1c71a1ce98
|
| 3 |
+
size 2415
|