paul
commited on
Commit
•
351d245
1
Parent(s):
1e9495f
End of training
Browse files- all_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Feb02_19-21-12_teesta/events.out.tfevents.1675345885.teesta.1377.0 +2 -2
- train_results.json +6 -6
- trainer_state.json +1214 -206
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 79.97,
|
| 3 |
+
"total_flos": 3.5167284631649157e+18,
|
| 4 |
+
"train_loss": 0.37728101573884487,
|
| 5 |
+
"train_runtime": 2345.4183,
|
| 6 |
+
"train_samples_per_second": 70.606,
|
| 7 |
+
"train_steps_per_second": 0.273
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94391373
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:797ad435f3e4fc6eb51fbf8fb1645d146d75605941de95af5da769f7ccd82fe7
|
| 3 |
size 94391373
|
runs/Feb02_19-21-12_teesta/events.out.tfevents.1675345885.teesta.1377.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d861004a79be1f7adec464b5a4348942865c40ac7afa2a63cfaeb1a24999eefa
|
| 3 |
+
size 51896
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 79.97,
|
| 3 |
+
"total_flos": 3.5167284631649157e+18,
|
| 4 |
+
"train_loss": 0.37728101573884487,
|
| 5 |
+
"train_runtime": 2345.4183,
|
| 6 |
+
"train_samples_per_second": 70.606,
|
| 7 |
+
"train_steps_per_second": 0.273
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,361 +1,1369 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.97,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_precision": 0.
|
| 16 |
-
"eval_recall": 0.
|
| 17 |
-
"eval_runtime": 6.
|
| 18 |
-
"eval_samples_per_second":
|
| 19 |
-
"eval_steps_per_second": 0.
|
| 20 |
"step": 8
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 1.24,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 1.97,
|
| 30 |
-
"eval_accuracy": 0.
|
| 31 |
-
"eval_f1": 0.
|
| 32 |
-
"eval_loss": 1.
|
| 33 |
-
"eval_precision": 0.
|
| 34 |
-
"eval_recall": 0.
|
| 35 |
-
"eval_runtime": 4.
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second": 0.
|
| 38 |
"step": 16
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.48,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.97,
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_f1": 0.
|
| 50 |
-
"eval_loss": 1.
|
| 51 |
-
"eval_precision": 0.
|
| 52 |
-
"eval_recall": 0.
|
| 53 |
-
"eval_runtime": 4.
|
| 54 |
-
"eval_samples_per_second":
|
| 55 |
-
"eval_steps_per_second": 0.
|
| 56 |
"step": 24
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 3.73,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 1.
|
| 62 |
"step": 30
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 3.97,
|
| 66 |
-
"eval_accuracy": 0.
|
| 67 |
-
"eval_f1": 0.
|
| 68 |
-
"eval_loss": 1.
|
| 69 |
-
"eval_precision": 0.
|
| 70 |
-
"eval_recall": 0.
|
| 71 |
-
"eval_runtime": 4.
|
| 72 |
-
"eval_samples_per_second":
|
| 73 |
-
"eval_steps_per_second": 0.
|
| 74 |
"step": 32
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 4.97,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 1.
|
| 80 |
"step": 40
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 4.97,
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 1.
|
| 87 |
-
"eval_precision": 0.
|
| 88 |
-
"eval_recall": 0.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second":
|
| 91 |
-
"eval_steps_per_second": 0.
|
| 92 |
"step": 40
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.97,
|
| 96 |
-
"eval_accuracy": 0.
|
| 97 |
-
"eval_f1": 0.
|
| 98 |
-
"eval_loss": 1.
|
| 99 |
-
"eval_precision": 0.
|
| 100 |
-
"eval_recall": 0.
|
| 101 |
-
"eval_runtime": 4.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second": 0.
|
| 104 |
"step": 48
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.24,
|
| 108 |
-
"learning_rate": 9.
|
| 109 |
-
"loss": 1.
|
| 110 |
"step": 50
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 6.97,
|
| 114 |
-
"eval_accuracy": 0.
|
| 115 |
-
"eval_f1": 0.
|
| 116 |
-
"eval_loss": 1.
|
| 117 |
-
"eval_precision": 0.
|
| 118 |
-
"eval_recall": 0.
|
| 119 |
-
"eval_runtime": 4.
|
| 120 |
-
"eval_samples_per_second":
|
| 121 |
-
"eval_steps_per_second": 0.
|
| 122 |
"step": 56
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 7.48,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 7.97,
|
| 132 |
-
"eval_accuracy": 0.
|
| 133 |
-
"eval_f1": 0.
|
| 134 |
-
"eval_loss": 1.
|
| 135 |
-
"eval_precision": 0.
|
| 136 |
-
"eval_recall": 0.
|
| 137 |
-
"eval_runtime":
|
| 138 |
-
"eval_samples_per_second":
|
| 139 |
-
"eval_steps_per_second": 0.
|
| 140 |
"step": 64
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 8.73,
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 1.
|
| 146 |
"step": 70
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 8.97,
|
| 150 |
-
"eval_accuracy": 0.
|
| 151 |
-
"eval_f1": 0.
|
| 152 |
-
"eval_loss": 1.
|
| 153 |
-
"eval_precision": 0.
|
| 154 |
-
"eval_recall": 0.
|
| 155 |
-
"eval_runtime": 4.
|
| 156 |
-
"eval_samples_per_second":
|
| 157 |
-
"eval_steps_per_second": 0.
|
| 158 |
"step": 72
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 9.97,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 1.
|
| 164 |
"step": 80
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 9.97,
|
| 168 |
-
"eval_accuracy": 0.
|
| 169 |
-
"eval_f1": 0.
|
| 170 |
-
"eval_loss": 1.
|
| 171 |
-
"eval_precision": 0.
|
| 172 |
-
"eval_recall": 0.
|
| 173 |
-
"eval_runtime": 4.
|
| 174 |
-
"eval_samples_per_second":
|
| 175 |
-
"eval_steps_per_second": 0.
|
| 176 |
"step": 80
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 10.97,
|
| 180 |
-
"eval_accuracy": 0.
|
| 181 |
-
"eval_f1": 0.
|
| 182 |
-
"eval_loss": 1.
|
| 183 |
-
"eval_precision": 0.
|
| 184 |
-
"eval_recall": 0.
|
| 185 |
-
"eval_runtime":
|
| 186 |
-
"eval_samples_per_second":
|
| 187 |
-
"eval_steps_per_second": 0.
|
| 188 |
"step": 88
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 11.24,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 1.
|
| 194 |
"step": 90
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 11.97,
|
| 198 |
-
"eval_accuracy": 0.
|
| 199 |
-
"eval_f1": 0.
|
| 200 |
-
"eval_loss":
|
| 201 |
-
"eval_precision": 0.
|
| 202 |
-
"eval_recall": 0.
|
| 203 |
-
"eval_runtime": 4.
|
| 204 |
-
"eval_samples_per_second":
|
| 205 |
-
"eval_steps_per_second": 0.
|
| 206 |
"step": 96
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 12.48,
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 100
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 12.97,
|
| 216 |
-
"eval_accuracy": 0.
|
| 217 |
-
"eval_f1": 0.
|
| 218 |
-
"eval_loss":
|
| 219 |
-
"eval_precision": 0.
|
| 220 |
-
"eval_recall": 0.
|
| 221 |
-
"eval_runtime": 4.
|
| 222 |
-
"eval_samples_per_second":
|
| 223 |
-
"eval_steps_per_second": 0.
|
| 224 |
"step": 104
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 13.73,
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss":
|
| 230 |
"step": 110
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 13.97,
|
| 234 |
-
"eval_accuracy": 0.
|
| 235 |
-
"eval_f1": 0.
|
| 236 |
-
"eval_loss":
|
| 237 |
-
"eval_precision": 0.
|
| 238 |
-
"eval_recall": 0.
|
| 239 |
-
"eval_runtime":
|
| 240 |
-
"eval_samples_per_second":
|
| 241 |
-
"eval_steps_per_second": 0.
|
| 242 |
"step": 112
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 14.97,
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss":
|
| 248 |
"step": 120
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 14.97,
|
| 252 |
-
"eval_accuracy": 0.
|
| 253 |
-
"eval_f1": 0.
|
| 254 |
-
"eval_loss":
|
| 255 |
-
"eval_precision": 0.
|
| 256 |
-
"eval_recall": 0.
|
| 257 |
-
"eval_runtime": 4.
|
| 258 |
-
"eval_samples_per_second": 26.
|
| 259 |
-
"eval_steps_per_second": 0.
|
| 260 |
"step": 120
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 15.97,
|
| 264 |
-
"eval_accuracy": 0.
|
| 265 |
-
"eval_f1": 0.
|
| 266 |
-
"eval_loss":
|
| 267 |
-
"eval_precision": 0.
|
| 268 |
-
"eval_recall": 0.
|
| 269 |
-
"eval_runtime": 4.
|
| 270 |
-
"eval_samples_per_second":
|
| 271 |
-
"eval_steps_per_second": 0.
|
| 272 |
"step": 128
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 16.24,
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss":
|
| 278 |
"step": 130
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 16.97,
|
| 282 |
-
"eval_accuracy": 0.
|
| 283 |
-
"eval_f1": 0.
|
| 284 |
-
"eval_loss":
|
| 285 |
-
"eval_precision": 0.
|
| 286 |
-
"eval_recall": 0.
|
| 287 |
-
"eval_runtime": 4.
|
| 288 |
-
"eval_samples_per_second": 26.
|
| 289 |
-
"eval_steps_per_second": 0.
|
| 290 |
"step": 136
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 17.48,
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss":
|
| 296 |
"step": 140
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 17.97,
|
| 300 |
-
"eval_accuracy": 0.
|
| 301 |
-
"eval_f1": 0.
|
| 302 |
-
"eval_loss":
|
| 303 |
-
"eval_precision": 0.
|
| 304 |
-
"eval_recall": 0.
|
| 305 |
-
"eval_runtime": 4.
|
| 306 |
-
"eval_samples_per_second":
|
| 307 |
-
"eval_steps_per_second": 0.
|
| 308 |
"step": 144
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 18.73,
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 150
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 18.97,
|
| 318 |
-
"eval_accuracy": 0.
|
| 319 |
-
"eval_f1": 0.
|
| 320 |
-
"eval_loss":
|
| 321 |
-
"eval_precision": 0.
|
| 322 |
-
"eval_recall": 0.
|
| 323 |
-
"eval_runtime": 4.
|
| 324 |
-
"eval_samples_per_second":
|
| 325 |
-
"eval_steps_per_second": 0.
|
| 326 |
"step": 152
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 19.97,
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 160
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 19.97,
|
| 336 |
-
"eval_accuracy": 0.
|
| 337 |
-
"eval_f1": 0.
|
| 338 |
-
"eval_loss":
|
| 339 |
-
"eval_precision": 0.
|
| 340 |
-
"eval_recall": 0.
|
| 341 |
-
"eval_runtime": 4.
|
| 342 |
-
"eval_samples_per_second": 25.
|
| 343 |
-
"eval_steps_per_second": 0.
|
| 344 |
"step": 160
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"
|
| 349 |
-
"
|
| 350 |
-
"
|
| 351 |
-
"
|
| 352 |
-
"
|
| 353 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
}
|
| 355 |
],
|
| 356 |
-
"max_steps":
|
| 357 |
-
"num_train_epochs":
|
| 358 |
-
"total_flos":
|
| 359 |
"trial_name": null,
|
| 360 |
"trial_params": null
|
| 361 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8440366972477065,
|
| 3 |
+
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-528",
|
| 4 |
+
"epoch": 79.96969696969697,
|
| 5 |
+
"global_step": 640,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.97,
|
| 12 |
+
"eval_accuracy": 0.22935779816513763,
|
| 13 |
+
"eval_f1": 0.21647331951741566,
|
| 14 |
+
"eval_loss": 1.3854628801345825,
|
| 15 |
+
"eval_precision": 0.2697355008315897,
|
| 16 |
+
"eval_recall": 0.22935779816513763,
|
| 17 |
+
"eval_runtime": 6.0845,
|
| 18 |
+
"eval_samples_per_second": 17.914,
|
| 19 |
+
"eval_steps_per_second": 0.329,
|
| 20 |
"step": 8
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 1.24,
|
| 24 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 25 |
+
"loss": 1.4222,
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 1.97,
|
| 30 |
+
"eval_accuracy": 0.25688073394495414,
|
| 31 |
+
"eval_f1": 0.25434987070599063,
|
| 32 |
+
"eval_loss": 1.3791918754577637,
|
| 33 |
+
"eval_precision": 0.2807708571335123,
|
| 34 |
+
"eval_recall": 0.25688073394495414,
|
| 35 |
+
"eval_runtime": 4.2925,
|
| 36 |
+
"eval_samples_per_second": 25.393,
|
| 37 |
+
"eval_steps_per_second": 0.466,
|
| 38 |
"step": 16
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.48,
|
| 42 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 43 |
+
"loss": 1.4183,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.97,
|
| 48 |
+
"eval_accuracy": 0.3853211009174312,
|
| 49 |
+
"eval_f1": 0.3511144563688655,
|
| 50 |
+
"eval_loss": 1.3646042346954346,
|
| 51 |
+
"eval_precision": 0.4102155235182758,
|
| 52 |
+
"eval_recall": 0.3853211009174312,
|
| 53 |
+
"eval_runtime": 4.3579,
|
| 54 |
+
"eval_samples_per_second": 25.012,
|
| 55 |
+
"eval_steps_per_second": 0.459,
|
| 56 |
"step": 24
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 3.73,
|
| 60 |
+
"learning_rate": 5.625e-05,
|
| 61 |
+
"loss": 1.4097,
|
| 62 |
"step": 30
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 3.97,
|
| 66 |
+
"eval_accuracy": 0.41284403669724773,
|
| 67 |
+
"eval_f1": 0.32452248836490605,
|
| 68 |
+
"eval_loss": 1.3562716245651245,
|
| 69 |
+
"eval_precision": 0.5062447369587377,
|
| 70 |
+
"eval_recall": 0.41284403669724773,
|
| 71 |
+
"eval_runtime": 4.3612,
|
| 72 |
+
"eval_samples_per_second": 24.993,
|
| 73 |
+
"eval_steps_per_second": 0.459,
|
| 74 |
"step": 32
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 4.97,
|
| 78 |
+
"learning_rate": 7.500000000000001e-05,
|
| 79 |
+
"loss": 1.3944,
|
| 80 |
"step": 40
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 4.97,
|
| 84 |
+
"eval_accuracy": 0.4036697247706422,
|
| 85 |
+
"eval_f1": 0.293905028882093,
|
| 86 |
+
"eval_loss": 1.3461558818817139,
|
| 87 |
+
"eval_precision": 0.3927443217900042,
|
| 88 |
+
"eval_recall": 0.4036697247706422,
|
| 89 |
+
"eval_runtime": 4.4159,
|
| 90 |
+
"eval_samples_per_second": 24.684,
|
| 91 |
+
"eval_steps_per_second": 0.453,
|
| 92 |
"step": 40
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.97,
|
| 96 |
+
"eval_accuracy": 0.4036697247706422,
|
| 97 |
+
"eval_f1": 0.2840541721275666,
|
| 98 |
+
"eval_loss": 1.322252631187439,
|
| 99 |
+
"eval_precision": 0.5152005756431013,
|
| 100 |
+
"eval_recall": 0.4036697247706422,
|
| 101 |
+
"eval_runtime": 4.2725,
|
| 102 |
+
"eval_samples_per_second": 25.512,
|
| 103 |
+
"eval_steps_per_second": 0.468,
|
| 104 |
"step": 48
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.24,
|
| 108 |
+
"learning_rate": 9.375e-05,
|
| 109 |
+
"loss": 1.411,
|
| 110 |
"step": 50
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 6.97,
|
| 114 |
+
"eval_accuracy": 0.41284403669724773,
|
| 115 |
+
"eval_f1": 0.29851761513413444,
|
| 116 |
+
"eval_loss": 1.304025411605835,
|
| 117 |
+
"eval_precision": 0.44039013993142434,
|
| 118 |
+
"eval_recall": 0.41284403669724773,
|
| 119 |
+
"eval_runtime": 4.4737,
|
| 120 |
+
"eval_samples_per_second": 24.365,
|
| 121 |
+
"eval_steps_per_second": 0.447,
|
| 122 |
"step": 56
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 7.48,
|
| 126 |
+
"learning_rate": 0.0001125,
|
| 127 |
+
"loss": 1.346,
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 7.97,
|
| 132 |
+
"eval_accuracy": 0.4954128440366973,
|
| 133 |
+
"eval_f1": 0.4092687533729088,
|
| 134 |
+
"eval_loss": 1.2699785232543945,
|
| 135 |
+
"eval_precision": 0.49603902723168775,
|
| 136 |
+
"eval_recall": 0.4954128440366973,
|
| 137 |
+
"eval_runtime": 4.5079,
|
| 138 |
+
"eval_samples_per_second": 24.18,
|
| 139 |
+
"eval_steps_per_second": 0.444,
|
| 140 |
"step": 64
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 8.73,
|
| 144 |
+
"learning_rate": 0.00011875000000000001,
|
| 145 |
+
"loss": 1.3031,
|
| 146 |
"step": 70
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 8.97,
|
| 150 |
+
"eval_accuracy": 0.5596330275229358,
|
| 151 |
+
"eval_f1": 0.46723852012270245,
|
| 152 |
+
"eval_loss": 1.2149937152862549,
|
| 153 |
+
"eval_precision": 0.5440134711415631,
|
| 154 |
+
"eval_recall": 0.5596330275229358,
|
| 155 |
+
"eval_runtime": 4.3712,
|
| 156 |
+
"eval_samples_per_second": 24.936,
|
| 157 |
+
"eval_steps_per_second": 0.458,
|
| 158 |
"step": 72
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 9.97,
|
| 162 |
+
"learning_rate": 0.00011666666666666667,
|
| 163 |
+
"loss": 1.2371,
|
| 164 |
"step": 80
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 9.97,
|
| 168 |
+
"eval_accuracy": 0.5963302752293578,
|
| 169 |
+
"eval_f1": 0.5100508405791544,
|
| 170 |
+
"eval_loss": 1.1580270528793335,
|
| 171 |
+
"eval_precision": 0.5659333353788879,
|
| 172 |
+
"eval_recall": 0.5963302752293578,
|
| 173 |
+
"eval_runtime": 4.2133,
|
| 174 |
+
"eval_samples_per_second": 25.87,
|
| 175 |
+
"eval_steps_per_second": 0.475,
|
| 176 |
"step": 80
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 10.97,
|
| 180 |
+
"eval_accuracy": 0.6055045871559633,
|
| 181 |
+
"eval_f1": 0.5211004609031267,
|
| 182 |
+
"eval_loss": 1.066982388496399,
|
| 183 |
+
"eval_precision": 0.7279186904119446,
|
| 184 |
+
"eval_recall": 0.6055045871559633,
|
| 185 |
+
"eval_runtime": 14.5277,
|
| 186 |
+
"eval_samples_per_second": 7.503,
|
| 187 |
+
"eval_steps_per_second": 0.138,
|
| 188 |
"step": 88
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 11.24,
|
| 192 |
+
"learning_rate": 0.00011458333333333334,
|
| 193 |
+
"loss": 1.1736,
|
| 194 |
"step": 90
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 11.97,
|
| 198 |
+
"eval_accuracy": 0.6605504587155964,
|
| 199 |
+
"eval_f1": 0.5771675777046106,
|
| 200 |
+
"eval_loss": 0.9855989813804626,
|
| 201 |
+
"eval_precision": 0.5536726213674042,
|
| 202 |
+
"eval_recall": 0.6605504587155964,
|
| 203 |
+
"eval_runtime": 4.2828,
|
| 204 |
+
"eval_samples_per_second": 25.451,
|
| 205 |
+
"eval_steps_per_second": 0.467,
|
| 206 |
"step": 96
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 12.48,
|
| 210 |
+
"learning_rate": 0.0001125,
|
| 211 |
+
"loss": 1.0457,
|
| 212 |
"step": 100
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 12.97,
|
| 216 |
+
"eval_accuracy": 0.6697247706422018,
|
| 217 |
+
"eval_f1": 0.5964926350313968,
|
| 218 |
+
"eval_loss": 0.896264374256134,
|
| 219 |
+
"eval_precision": 0.763141515721791,
|
| 220 |
+
"eval_recall": 0.6697247706422018,
|
| 221 |
+
"eval_runtime": 4.2315,
|
| 222 |
+
"eval_samples_per_second": 25.759,
|
| 223 |
+
"eval_steps_per_second": 0.473,
|
| 224 |
"step": 104
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 13.73,
|
| 228 |
+
"learning_rate": 0.00011041666666666666,
|
| 229 |
+
"loss": 0.953,
|
| 230 |
"step": 110
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 13.97,
|
| 234 |
+
"eval_accuracy": 0.6697247706422018,
|
| 235 |
+
"eval_f1": 0.6081464096911078,
|
| 236 |
+
"eval_loss": 0.8546512722969055,
|
| 237 |
+
"eval_precision": 0.6884856947005512,
|
| 238 |
+
"eval_recall": 0.6697247706422018,
|
| 239 |
+
"eval_runtime": 4.4534,
|
| 240 |
+
"eval_samples_per_second": 24.476,
|
| 241 |
+
"eval_steps_per_second": 0.449,
|
| 242 |
"step": 112
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 14.97,
|
| 246 |
+
"learning_rate": 0.00010833333333333334,
|
| 247 |
+
"loss": 0.8579,
|
| 248 |
"step": 120
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 14.97,
|
| 252 |
+
"eval_accuracy": 0.7155963302752294,
|
| 253 |
+
"eval_f1": 0.6643295304342026,
|
| 254 |
+
"eval_loss": 0.7848823070526123,
|
| 255 |
+
"eval_precision": 0.7396182317656428,
|
| 256 |
+
"eval_recall": 0.7155963302752294,
|
| 257 |
+
"eval_runtime": 4.1662,
|
| 258 |
+
"eval_samples_per_second": 26.163,
|
| 259 |
+
"eval_steps_per_second": 0.48,
|
| 260 |
"step": 120
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 15.97,
|
| 264 |
+
"eval_accuracy": 0.7431192660550459,
|
| 265 |
+
"eval_f1": 0.711852075310986,
|
| 266 |
+
"eval_loss": 0.7563745379447937,
|
| 267 |
+
"eval_precision": 0.7371817784661822,
|
| 268 |
+
"eval_recall": 0.7431192660550459,
|
| 269 |
+
"eval_runtime": 4.2674,
|
| 270 |
+
"eval_samples_per_second": 25.542,
|
| 271 |
+
"eval_steps_per_second": 0.469,
|
| 272 |
"step": 128
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 16.24,
|
| 276 |
+
"learning_rate": 0.00010625,
|
| 277 |
+
"loss": 0.8167,
|
| 278 |
"step": 130
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 16.97,
|
| 282 |
+
"eval_accuracy": 0.7614678899082569,
|
| 283 |
+
"eval_f1": 0.7210716889645992,
|
| 284 |
+
"eval_loss": 0.7132583260536194,
|
| 285 |
+
"eval_precision": 0.7506553079947577,
|
| 286 |
+
"eval_recall": 0.7614678899082569,
|
| 287 |
+
"eval_runtime": 4.1418,
|
| 288 |
+
"eval_samples_per_second": 26.317,
|
| 289 |
+
"eval_steps_per_second": 0.483,
|
| 290 |
"step": 136
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 17.48,
|
| 294 |
+
"learning_rate": 0.00010416666666666667,
|
| 295 |
+
"loss": 0.7273,
|
| 296 |
"step": 140
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 17.97,
|
| 300 |
+
"eval_accuracy": 0.7522935779816514,
|
| 301 |
+
"eval_f1": 0.7202155642522615,
|
| 302 |
+
"eval_loss": 0.6887747645378113,
|
| 303 |
+
"eval_precision": 0.7378685592291271,
|
| 304 |
+
"eval_recall": 0.7522935779816514,
|
| 305 |
+
"eval_runtime": 4.5118,
|
| 306 |
+
"eval_samples_per_second": 24.159,
|
| 307 |
+
"eval_steps_per_second": 0.443,
|
| 308 |
"step": 144
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 18.73,
|
| 312 |
+
"learning_rate": 0.00010208333333333334,
|
| 313 |
+
"loss": 0.6547,
|
| 314 |
"step": 150
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 18.97,
|
| 318 |
+
"eval_accuracy": 0.7798165137614679,
|
| 319 |
+
"eval_f1": 0.7576525411387797,
|
| 320 |
+
"eval_loss": 0.659186065196991,
|
| 321 |
+
"eval_precision": 0.7772903701802784,
|
| 322 |
+
"eval_recall": 0.7798165137614679,
|
| 323 |
+
"eval_runtime": 4.3816,
|
| 324 |
+
"eval_samples_per_second": 24.877,
|
| 325 |
+
"eval_steps_per_second": 0.456,
|
| 326 |
"step": 152
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 19.97,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 0.5963,
|
| 332 |
"step": 160
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 19.97,
|
| 336 |
+
"eval_accuracy": 0.7706422018348624,
|
| 337 |
+
"eval_f1": 0.7550663564666461,
|
| 338 |
+
"eval_loss": 0.6136144399642944,
|
| 339 |
+
"eval_precision": 0.764159781184113,
|
| 340 |
+
"eval_recall": 0.7706422018348624,
|
| 341 |
+
"eval_runtime": 4.2561,
|
| 342 |
+
"eval_samples_per_second": 25.61,
|
| 343 |
+
"eval_steps_per_second": 0.47,
|
| 344 |
"step": 160
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 20.97,
|
| 348 |
+
"eval_accuracy": 0.7889908256880734,
|
| 349 |
+
"eval_f1": 0.7786916064255194,
|
| 350 |
+
"eval_loss": 0.5723462700843811,
|
| 351 |
+
"eval_precision": 0.7801645588430826,
|
| 352 |
+
"eval_recall": 0.7889908256880734,
|
| 353 |
+
"eval_runtime": 5.2546,
|
| 354 |
+
"eval_samples_per_second": 20.744,
|
| 355 |
+
"eval_steps_per_second": 0.381,
|
| 356 |
+
"step": 168
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 21.24,
|
| 360 |
+
"learning_rate": 9.791666666666667e-05,
|
| 361 |
+
"loss": 0.551,
|
| 362 |
+
"step": 170
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 21.97,
|
| 366 |
+
"eval_accuracy": 0.7889908256880734,
|
| 367 |
+
"eval_f1": 0.7780894219567608,
|
| 368 |
+
"eval_loss": 0.5686229467391968,
|
| 369 |
+
"eval_precision": 0.776092121476891,
|
| 370 |
+
"eval_recall": 0.7889908256880734,
|
| 371 |
+
"eval_runtime": 4.3144,
|
| 372 |
+
"eval_samples_per_second": 25.264,
|
| 373 |
+
"eval_steps_per_second": 0.464,
|
| 374 |
+
"step": 176
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 22.48,
|
| 378 |
+
"learning_rate": 9.583333333333334e-05,
|
| 379 |
+
"loss": 0.4929,
|
| 380 |
+
"step": 180
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 22.97,
|
| 384 |
+
"eval_accuracy": 0.7706422018348624,
|
| 385 |
+
"eval_f1": 0.7651464296127533,
|
| 386 |
+
"eval_loss": 0.5596823692321777,
|
| 387 |
+
"eval_precision": 0.7649127896435436,
|
| 388 |
+
"eval_recall": 0.7706422018348624,
|
| 389 |
+
"eval_runtime": 4.4326,
|
| 390 |
+
"eval_samples_per_second": 24.59,
|
| 391 |
+
"eval_steps_per_second": 0.451,
|
| 392 |
+
"step": 184
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 23.73,
|
| 396 |
+
"learning_rate": 9.375e-05,
|
| 397 |
+
"loss": 0.4309,
|
| 398 |
+
"step": 190
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 23.97,
|
| 402 |
+
"eval_accuracy": 0.7889908256880734,
|
| 403 |
+
"eval_f1": 0.781022184850044,
|
| 404 |
+
"eval_loss": 0.5233965516090393,
|
| 405 |
+
"eval_precision": 0.7774110647118855,
|
| 406 |
+
"eval_recall": 0.7889908256880734,
|
| 407 |
+
"eval_runtime": 4.3167,
|
| 408 |
+
"eval_samples_per_second": 25.251,
|
| 409 |
+
"eval_steps_per_second": 0.463,
|
| 410 |
+
"step": 192
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 24.97,
|
| 414 |
+
"learning_rate": 9.166666666666667e-05,
|
| 415 |
+
"loss": 0.3945,
|
| 416 |
+
"step": 200
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 24.97,
|
| 420 |
+
"eval_accuracy": 0.7889908256880734,
|
| 421 |
+
"eval_f1": 0.7812909567496724,
|
| 422 |
+
"eval_loss": 0.5007840991020203,
|
| 423 |
+
"eval_precision": 0.7836723839914905,
|
| 424 |
+
"eval_recall": 0.7889908256880734,
|
| 425 |
+
"eval_runtime": 4.3513,
|
| 426 |
+
"eval_samples_per_second": 25.05,
|
| 427 |
+
"eval_steps_per_second": 0.46,
|
| 428 |
+
"step": 200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 25.97,
|
| 432 |
+
"eval_accuracy": 0.7522935779816514,
|
| 433 |
+
"eval_f1": 0.7528893125223401,
|
| 434 |
+
"eval_loss": 0.5289302468299866,
|
| 435 |
+
"eval_precision": 0.7537344154316632,
|
| 436 |
+
"eval_recall": 0.7522935779816514,
|
| 437 |
+
"eval_runtime": 4.3647,
|
| 438 |
+
"eval_samples_per_second": 24.973,
|
| 439 |
+
"eval_steps_per_second": 0.458,
|
| 440 |
+
"step": 208
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 26.24,
|
| 444 |
+
"learning_rate": 8.958333333333333e-05,
|
| 445 |
+
"loss": 0.3704,
|
| 446 |
+
"step": 210
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 26.97,
|
| 450 |
+
"eval_accuracy": 0.7981651376146789,
|
| 451 |
+
"eval_f1": 0.7962706746091569,
|
| 452 |
+
"eval_loss": 0.4399118423461914,
|
| 453 |
+
"eval_precision": 0.7957732392169626,
|
| 454 |
+
"eval_recall": 0.7981651376146789,
|
| 455 |
+
"eval_runtime": 4.2147,
|
| 456 |
+
"eval_samples_per_second": 25.862,
|
| 457 |
+
"eval_steps_per_second": 0.475,
|
| 458 |
+
"step": 216
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 27.48,
|
| 462 |
+
"learning_rate": 8.75e-05,
|
| 463 |
+
"loss": 0.3267,
|
| 464 |
+
"step": 220
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 27.97,
|
| 468 |
+
"eval_accuracy": 0.8073394495412844,
|
| 469 |
+
"eval_f1": 0.8005365278178692,
|
| 470 |
+
"eval_loss": 0.4539415240287781,
|
| 471 |
+
"eval_precision": 0.7983420088683247,
|
| 472 |
+
"eval_recall": 0.8073394495412844,
|
| 473 |
+
"eval_runtime": 4.2272,
|
| 474 |
+
"eval_samples_per_second": 25.785,
|
| 475 |
+
"eval_steps_per_second": 0.473,
|
| 476 |
+
"step": 224
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 28.73,
|
| 480 |
+
"learning_rate": 8.541666666666668e-05,
|
| 481 |
+
"loss": 0.2966,
|
| 482 |
+
"step": 230
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 28.97,
|
| 486 |
+
"eval_accuracy": 0.7798165137614679,
|
| 487 |
+
"eval_f1": 0.7837137974455839,
|
| 488 |
+
"eval_loss": 0.4734969735145569,
|
| 489 |
+
"eval_precision": 0.789241175758926,
|
| 490 |
+
"eval_recall": 0.7798165137614679,
|
| 491 |
+
"eval_runtime": 4.2368,
|
| 492 |
+
"eval_samples_per_second": 25.727,
|
| 493 |
+
"eval_steps_per_second": 0.472,
|
| 494 |
+
"step": 232
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 29.97,
|
| 498 |
+
"learning_rate": 8.333333333333333e-05,
|
| 499 |
+
"loss": 0.2645,
|
| 500 |
+
"step": 240
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 29.97,
|
| 504 |
+
"eval_accuracy": 0.7706422018348624,
|
| 505 |
+
"eval_f1": 0.7706422018348624,
|
| 506 |
+
"eval_loss": 0.4594463109970093,
|
| 507 |
+
"eval_precision": 0.7706422018348624,
|
| 508 |
+
"eval_recall": 0.7706422018348624,
|
| 509 |
+
"eval_runtime": 4.3943,
|
| 510 |
+
"eval_samples_per_second": 24.805,
|
| 511 |
+
"eval_steps_per_second": 0.455,
|
| 512 |
+
"step": 240
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 30.97,
|
| 516 |
+
"eval_accuracy": 0.7522935779816514,
|
| 517 |
+
"eval_f1": 0.7533140030125614,
|
| 518 |
+
"eval_loss": 0.4698648750782013,
|
| 519 |
+
"eval_precision": 0.7554437319096274,
|
| 520 |
+
"eval_recall": 0.7522935779816514,
|
| 521 |
+
"eval_runtime": 4.1296,
|
| 522 |
+
"eval_samples_per_second": 26.394,
|
| 523 |
+
"eval_steps_per_second": 0.484,
|
| 524 |
+
"step": 248
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.24,
|
| 528 |
+
"learning_rate": 8.125000000000001e-05,
|
| 529 |
+
"loss": 0.2527,
|
| 530 |
+
"step": 250
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 31.97,
|
| 534 |
+
"eval_accuracy": 0.7889908256880734,
|
| 535 |
+
"eval_f1": 0.7856523955147808,
|
| 536 |
+
"eval_loss": 0.45513755083084106,
|
| 537 |
+
"eval_precision": 0.785609816323817,
|
| 538 |
+
"eval_recall": 0.7889908256880734,
|
| 539 |
+
"eval_runtime": 4.1348,
|
| 540 |
+
"eval_samples_per_second": 26.361,
|
| 541 |
+
"eval_steps_per_second": 0.484,
|
| 542 |
+
"step": 256
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 32.48,
|
| 546 |
+
"learning_rate": 7.916666666666666e-05,
|
| 547 |
+
"loss": 0.2202,
|
| 548 |
+
"step": 260
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 32.97,
|
| 552 |
+
"eval_accuracy": 0.8165137614678899,
|
| 553 |
+
"eval_f1": 0.8170336224601304,
|
| 554 |
+
"eval_loss": 0.4457748532295227,
|
| 555 |
+
"eval_precision": 0.8197900424266599,
|
| 556 |
+
"eval_recall": 0.8165137614678899,
|
| 557 |
+
"eval_runtime": 5.1689,
|
| 558 |
+
"eval_samples_per_second": 21.087,
|
| 559 |
+
"eval_steps_per_second": 0.387,
|
| 560 |
+
"step": 264
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 33.73,
|
| 564 |
+
"learning_rate": 7.708333333333334e-05,
|
| 565 |
+
"loss": 0.2006,
|
| 566 |
+
"step": 270
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 33.97,
|
| 570 |
+
"eval_accuracy": 0.7798165137614679,
|
| 571 |
+
"eval_f1": 0.7850412357933325,
|
| 572 |
+
"eval_loss": 0.46321260929107666,
|
| 573 |
+
"eval_precision": 0.7940749153601442,
|
| 574 |
+
"eval_recall": 0.7798165137614679,
|
| 575 |
+
"eval_runtime": 4.2326,
|
| 576 |
+
"eval_samples_per_second": 25.752,
|
| 577 |
+
"eval_steps_per_second": 0.473,
|
| 578 |
+
"step": 272
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 34.97,
|
| 582 |
+
"learning_rate": 7.500000000000001e-05,
|
| 583 |
+
"loss": 0.1589,
|
| 584 |
+
"step": 280
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 34.97,
|
| 588 |
+
"eval_accuracy": 0.7889908256880734,
|
| 589 |
+
"eval_f1": 0.7925041274199247,
|
| 590 |
+
"eval_loss": 0.46511203050613403,
|
| 591 |
+
"eval_precision": 0.7993275970140749,
|
| 592 |
+
"eval_recall": 0.7889908256880734,
|
| 593 |
+
"eval_runtime": 4.1566,
|
| 594 |
+
"eval_samples_per_second": 26.223,
|
| 595 |
+
"eval_steps_per_second": 0.481,
|
| 596 |
+
"step": 280
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 35.97,
|
| 600 |
+
"eval_accuracy": 0.7798165137614679,
|
| 601 |
+
"eval_f1": 0.7803733958918072,
|
| 602 |
+
"eval_loss": 0.45948973298072815,
|
| 603 |
+
"eval_precision": 0.7823930357635982,
|
| 604 |
+
"eval_recall": 0.7798165137614679,
|
| 605 |
+
"eval_runtime": 4.3202,
|
| 606 |
+
"eval_samples_per_second": 25.23,
|
| 607 |
+
"eval_steps_per_second": 0.463,
|
| 608 |
+
"step": 288
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 36.24,
|
| 612 |
+
"learning_rate": 7.291666666666666e-05,
|
| 613 |
+
"loss": 0.153,
|
| 614 |
+
"step": 290
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 36.97,
|
| 618 |
+
"eval_accuracy": 0.7614678899082569,
|
| 619 |
+
"eval_f1": 0.7632546001327497,
|
| 620 |
+
"eval_loss": 0.458363801240921,
|
| 621 |
+
"eval_precision": 0.7690950187958565,
|
| 622 |
+
"eval_recall": 0.7614678899082569,
|
| 623 |
+
"eval_runtime": 4.4275,
|
| 624 |
+
"eval_samples_per_second": 24.619,
|
| 625 |
+
"eval_steps_per_second": 0.452,
|
| 626 |
+
"step": 296
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 37.48,
|
| 630 |
+
"learning_rate": 7.083333333333334e-05,
|
| 631 |
+
"loss": 0.1427,
|
| 632 |
+
"step": 300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 37.97,
|
| 636 |
+
"eval_accuracy": 0.7798165137614679,
|
| 637 |
+
"eval_f1": 0.7796360891921739,
|
| 638 |
+
"eval_loss": 0.46078726649284363,
|
| 639 |
+
"eval_precision": 0.782995656118911,
|
| 640 |
+
"eval_recall": 0.7798165137614679,
|
| 641 |
+
"eval_runtime": 4.4461,
|
| 642 |
+
"eval_samples_per_second": 24.516,
|
| 643 |
+
"eval_steps_per_second": 0.45,
|
| 644 |
+
"step": 304
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 38.73,
|
| 648 |
+
"learning_rate": 6.874999999999999e-05,
|
| 649 |
+
"loss": 0.113,
|
| 650 |
+
"step": 310
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 38.97,
|
| 654 |
+
"eval_accuracy": 0.7889908256880734,
|
| 655 |
+
"eval_f1": 0.7898954921921011,
|
| 656 |
+
"eval_loss": 0.45713570713996887,
|
| 657 |
+
"eval_precision": 0.7922270390160299,
|
| 658 |
+
"eval_recall": 0.7889908256880734,
|
| 659 |
+
"eval_runtime": 4.3087,
|
| 660 |
+
"eval_samples_per_second": 25.297,
|
| 661 |
+
"eval_steps_per_second": 0.464,
|
| 662 |
+
"step": 312
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 39.97,
|
| 666 |
+
"learning_rate": 6.666666666666667e-05,
|
| 667 |
+
"loss": 0.1146,
|
| 668 |
+
"step": 320
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 39.97,
|
| 672 |
+
"eval_accuracy": 0.7614678899082569,
|
| 673 |
+
"eval_f1": 0.7612891030218949,
|
| 674 |
+
"eval_loss": 0.5269873142242432,
|
| 675 |
+
"eval_precision": 0.765128347697155,
|
| 676 |
+
"eval_recall": 0.7614678899082569,
|
| 677 |
+
"eval_runtime": 4.2908,
|
| 678 |
+
"eval_samples_per_second": 25.403,
|
| 679 |
+
"eval_steps_per_second": 0.466,
|
| 680 |
+
"step": 320
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 40.97,
|
| 684 |
+
"eval_accuracy": 0.7706422018348624,
|
| 685 |
+
"eval_f1": 0.7709516996486127,
|
| 686 |
+
"eval_loss": 0.48878130316734314,
|
| 687 |
+
"eval_precision": 0.7781771515945828,
|
| 688 |
+
"eval_recall": 0.7706422018348624,
|
| 689 |
+
"eval_runtime": 4.3303,
|
| 690 |
+
"eval_samples_per_second": 25.171,
|
| 691 |
+
"eval_steps_per_second": 0.462,
|
| 692 |
+
"step": 328
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 41.24,
|
| 696 |
+
"learning_rate": 6.458333333333334e-05,
|
| 697 |
+
"loss": 0.1275,
|
| 698 |
+
"step": 330
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 41.97,
|
| 702 |
+
"eval_accuracy": 0.7889908256880734,
|
| 703 |
+
"eval_f1": 0.7836706749228535,
|
| 704 |
+
"eval_loss": 0.4523099958896637,
|
| 705 |
+
"eval_precision": 0.780905883107718,
|
| 706 |
+
"eval_recall": 0.7889908256880734,
|
| 707 |
+
"eval_runtime": 4.2033,
|
| 708 |
+
"eval_samples_per_second": 25.932,
|
| 709 |
+
"eval_steps_per_second": 0.476,
|
| 710 |
+
"step": 336
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 42.48,
|
| 714 |
+
"learning_rate": 6.25e-05,
|
| 715 |
+
"loss": 0.0959,
|
| 716 |
+
"step": 340
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 42.97,
|
| 720 |
+
"eval_accuracy": 0.7798165137614679,
|
| 721 |
+
"eval_f1": 0.7767063396275014,
|
| 722 |
+
"eval_loss": 0.46965503692626953,
|
| 723 |
+
"eval_precision": 0.7753268138589239,
|
| 724 |
+
"eval_recall": 0.7798165137614679,
|
| 725 |
+
"eval_runtime": 4.3242,
|
| 726 |
+
"eval_samples_per_second": 25.207,
|
| 727 |
+
"eval_steps_per_second": 0.463,
|
| 728 |
+
"step": 344
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 43.73,
|
| 732 |
+
"learning_rate": 6.041666666666667e-05,
|
| 733 |
+
"loss": 0.0882,
|
| 734 |
+
"step": 350
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 43.97,
|
| 738 |
+
"eval_accuracy": 0.7706422018348624,
|
| 739 |
+
"eval_f1": 0.7685729724992435,
|
| 740 |
+
"eval_loss": 0.4286104738712311,
|
| 741 |
+
"eval_precision": 0.7685932721712537,
|
| 742 |
+
"eval_recall": 0.7706422018348624,
|
| 743 |
+
"eval_runtime": 4.4175,
|
| 744 |
+
"eval_samples_per_second": 24.675,
|
| 745 |
+
"eval_steps_per_second": 0.453,
|
| 746 |
+
"step": 352
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 44.97,
|
| 750 |
+
"learning_rate": 5.833333333333333e-05,
|
| 751 |
+
"loss": 0.0847,
|
| 752 |
+
"step": 360
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 44.97,
|
| 756 |
+
"eval_accuracy": 0.7889908256880734,
|
| 757 |
+
"eval_f1": 0.7925041274199247,
|
| 758 |
+
"eval_loss": 0.5317460298538208,
|
| 759 |
+
"eval_precision": 0.7993275970140749,
|
| 760 |
+
"eval_recall": 0.7889908256880734,
|
| 761 |
+
"eval_runtime": 6.0042,
|
| 762 |
+
"eval_samples_per_second": 18.154,
|
| 763 |
+
"eval_steps_per_second": 0.333,
|
| 764 |
+
"step": 360
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 45.97,
|
| 768 |
+
"eval_accuracy": 0.7614678899082569,
|
| 769 |
+
"eval_f1": 0.7646893115457605,
|
| 770 |
+
"eval_loss": 0.5431071519851685,
|
| 771 |
+
"eval_precision": 0.7699552364490537,
|
| 772 |
+
"eval_recall": 0.7614678899082569,
|
| 773 |
+
"eval_runtime": 4.3547,
|
| 774 |
+
"eval_samples_per_second": 25.03,
|
| 775 |
+
"eval_steps_per_second": 0.459,
|
| 776 |
+
"step": 368
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 46.24,
|
| 780 |
+
"learning_rate": 5.625e-05,
|
| 781 |
+
"loss": 0.0813,
|
| 782 |
+
"step": 370
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 46.97,
|
| 786 |
+
"eval_accuracy": 0.8256880733944955,
|
| 787 |
+
"eval_f1": 0.8284158367266842,
|
| 788 |
+
"eval_loss": 0.44316479563713074,
|
| 789 |
+
"eval_precision": 0.843538901662607,
|
| 790 |
+
"eval_recall": 0.8256880733944955,
|
| 791 |
+
"eval_runtime": 4.2714,
|
| 792 |
+
"eval_samples_per_second": 25.519,
|
| 793 |
+
"eval_steps_per_second": 0.468,
|
| 794 |
+
"step": 376
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 47.48,
|
| 798 |
+
"learning_rate": 5.416666666666667e-05,
|
| 799 |
+
"loss": 0.0768,
|
| 800 |
+
"step": 380
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 47.97,
|
| 804 |
+
"eval_accuracy": 0.7981651376146789,
|
| 805 |
+
"eval_f1": 0.7955546490941502,
|
| 806 |
+
"eval_loss": 0.4885597229003906,
|
| 807 |
+
"eval_precision": 0.8005162605636117,
|
| 808 |
+
"eval_recall": 0.7981651376146789,
|
| 809 |
+
"eval_runtime": 4.2576,
|
| 810 |
+
"eval_samples_per_second": 25.602,
|
| 811 |
+
"eval_steps_per_second": 0.47,
|
| 812 |
+
"step": 384
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 48.73,
|
| 816 |
+
"learning_rate": 5.208333333333334e-05,
|
| 817 |
+
"loss": 0.0627,
|
| 818 |
+
"step": 390
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 48.97,
|
| 822 |
+
"eval_accuracy": 0.7981651376146789,
|
| 823 |
+
"eval_f1": 0.8009727230444837,
|
| 824 |
+
"eval_loss": 0.5372528433799744,
|
| 825 |
+
"eval_precision": 0.8071912929511652,
|
| 826 |
+
"eval_recall": 0.7981651376146789,
|
| 827 |
+
"eval_runtime": 4.3763,
|
| 828 |
+
"eval_samples_per_second": 24.907,
|
| 829 |
+
"eval_steps_per_second": 0.457,
|
| 830 |
+
"step": 392
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 49.97,
|
| 834 |
+
"learning_rate": 5e-05,
|
| 835 |
+
"loss": 0.0688,
|
| 836 |
+
"step": 400
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 49.97,
|
| 840 |
+
"eval_accuracy": 0.7798165137614679,
|
| 841 |
+
"eval_f1": 0.7822443312570955,
|
| 842 |
+
"eval_loss": 0.5896694660186768,
|
| 843 |
+
"eval_precision": 0.789232725399693,
|
| 844 |
+
"eval_recall": 0.7798165137614679,
|
| 845 |
+
"eval_runtime": 4.3692,
|
| 846 |
+
"eval_samples_per_second": 24.947,
|
| 847 |
+
"eval_steps_per_second": 0.458,
|
| 848 |
+
"step": 400
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 50.97,
|
| 852 |
+
"eval_accuracy": 0.7981651376146789,
|
| 853 |
+
"eval_f1": 0.7992371326578404,
|
| 854 |
+
"eval_loss": 0.5114642977714539,
|
| 855 |
+
"eval_precision": 0.8014849021031709,
|
| 856 |
+
"eval_recall": 0.7981651376146789,
|
| 857 |
+
"eval_runtime": 4.3028,
|
| 858 |
+
"eval_samples_per_second": 25.332,
|
| 859 |
+
"eval_steps_per_second": 0.465,
|
| 860 |
+
"step": 408
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 51.24,
|
| 864 |
+
"learning_rate": 4.791666666666667e-05,
|
| 865 |
+
"loss": 0.0676,
|
| 866 |
+
"step": 410
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 51.97,
|
| 870 |
+
"eval_accuracy": 0.7981651376146789,
|
| 871 |
+
"eval_f1": 0.7977993643940755,
|
| 872 |
+
"eval_loss": 0.4881470799446106,
|
| 873 |
+
"eval_precision": 0.7998301588132414,
|
| 874 |
+
"eval_recall": 0.7981651376146789,
|
| 875 |
+
"eval_runtime": 4.3212,
|
| 876 |
+
"eval_samples_per_second": 25.224,
|
| 877 |
+
"eval_steps_per_second": 0.463,
|
| 878 |
+
"step": 416
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 52.48,
|
| 882 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 883 |
+
"loss": 0.0539,
|
| 884 |
+
"step": 420
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 52.97,
|
| 888 |
+
"eval_accuracy": 0.8073394495412844,
|
| 889 |
+
"eval_f1": 0.807691055721277,
|
| 890 |
+
"eval_loss": 0.4819609224796295,
|
| 891 |
+
"eval_precision": 0.8138503399273244,
|
| 892 |
+
"eval_recall": 0.8073394495412844,
|
| 893 |
+
"eval_runtime": 4.3125,
|
| 894 |
+
"eval_samples_per_second": 25.276,
|
| 895 |
+
"eval_steps_per_second": 0.464,
|
| 896 |
+
"step": 424
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 53.73,
|
| 900 |
+
"learning_rate": 4.375e-05,
|
| 901 |
+
"loss": 0.0596,
|
| 902 |
+
"step": 430
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 53.97,
|
| 906 |
+
"eval_accuracy": 0.8256880733944955,
|
| 907 |
+
"eval_f1": 0.8244465797713664,
|
| 908 |
+
"eval_loss": 0.4449571669101715,
|
| 909 |
+
"eval_precision": 0.8245908379614004,
|
| 910 |
+
"eval_recall": 0.8256880733944955,
|
| 911 |
+
"eval_runtime": 5.8195,
|
| 912 |
+
"eval_samples_per_second": 18.73,
|
| 913 |
+
"eval_steps_per_second": 0.344,
|
| 914 |
+
"step": 432
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 54.97,
|
| 918 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 919 |
+
"loss": 0.0611,
|
| 920 |
+
"step": 440
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 54.97,
|
| 924 |
+
"eval_accuracy": 0.7889908256880734,
|
| 925 |
+
"eval_f1": 0.7924465793472197,
|
| 926 |
+
"eval_loss": 0.5057494044303894,
|
| 927 |
+
"eval_precision": 0.8008019735410222,
|
| 928 |
+
"eval_recall": 0.7889908256880734,
|
| 929 |
+
"eval_runtime": 4.6616,
|
| 930 |
+
"eval_samples_per_second": 23.383,
|
| 931 |
+
"eval_steps_per_second": 0.429,
|
| 932 |
+
"step": 440
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 55.97,
|
| 936 |
+
"eval_accuracy": 0.7981651376146789,
|
| 937 |
+
"eval_f1": 0.8008031371900772,
|
| 938 |
+
"eval_loss": 0.4918478727340698,
|
| 939 |
+
"eval_precision": 0.8056331161636306,
|
| 940 |
+
"eval_recall": 0.7981651376146789,
|
| 941 |
+
"eval_runtime": 4.8639,
|
| 942 |
+
"eval_samples_per_second": 22.41,
|
| 943 |
+
"eval_steps_per_second": 0.411,
|
| 944 |
+
"step": 448
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 56.24,
|
| 948 |
+
"learning_rate": 3.958333333333333e-05,
|
| 949 |
+
"loss": 0.0643,
|
| 950 |
+
"step": 450
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 56.97,
|
| 954 |
+
"eval_accuracy": 0.7522935779816514,
|
| 955 |
+
"eval_f1": 0.7545272459450874,
|
| 956 |
+
"eval_loss": 0.5946044325828552,
|
| 957 |
+
"eval_precision": 0.7587394976605187,
|
| 958 |
+
"eval_recall": 0.7522935779816514,
|
| 959 |
+
"eval_runtime": 4.4153,
|
| 960 |
+
"eval_samples_per_second": 24.687,
|
| 961 |
+
"eval_steps_per_second": 0.453,
|
| 962 |
+
"step": 456
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 57.48,
|
| 966 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 967 |
+
"loss": 0.0605,
|
| 968 |
+
"step": 460
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 57.97,
|
| 972 |
+
"eval_accuracy": 0.8073394495412844,
|
| 973 |
+
"eval_f1": 0.8120936083458042,
|
| 974 |
+
"eval_loss": 0.4887966513633728,
|
| 975 |
+
"eval_precision": 0.8238645162528876,
|
| 976 |
+
"eval_recall": 0.8073394495412844,
|
| 977 |
+
"eval_runtime": 6.6734,
|
| 978 |
+
"eval_samples_per_second": 16.334,
|
| 979 |
+
"eval_steps_per_second": 0.3,
|
| 980 |
+
"step": 464
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 58.73,
|
| 984 |
+
"learning_rate": 3.541666666666667e-05,
|
| 985 |
+
"loss": 0.063,
|
| 986 |
+
"step": 470
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 58.97,
|
| 990 |
+
"eval_accuracy": 0.7889908256880734,
|
| 991 |
+
"eval_f1": 0.7936673558168583,
|
| 992 |
+
"eval_loss": 0.5916518568992615,
|
| 993 |
+
"eval_precision": 0.8051419661311963,
|
| 994 |
+
"eval_recall": 0.7889908256880734,
|
| 995 |
+
"eval_runtime": 4.2726,
|
| 996 |
+
"eval_samples_per_second": 25.511,
|
| 997 |
+
"eval_steps_per_second": 0.468,
|
| 998 |
+
"step": 472
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 59.97,
|
| 1002 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1003 |
+
"loss": 0.0595,
|
| 1004 |
+
"step": 480
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 59.97,
|
| 1008 |
+
"eval_accuracy": 0.7889908256880734,
|
| 1009 |
+
"eval_f1": 0.7894285298217145,
|
| 1010 |
+
"eval_loss": 0.5117025375366211,
|
| 1011 |
+
"eval_precision": 0.7904302906815871,
|
| 1012 |
+
"eval_recall": 0.7889908256880734,
|
| 1013 |
+
"eval_runtime": 4.4288,
|
| 1014 |
+
"eval_samples_per_second": 24.612,
|
| 1015 |
+
"eval_steps_per_second": 0.452,
|
| 1016 |
+
"step": 480
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 60.97,
|
| 1020 |
+
"eval_accuracy": 0.7614678899082569,
|
| 1021 |
+
"eval_f1": 0.7635438011331693,
|
| 1022 |
+
"eval_loss": 0.549720048904419,
|
| 1023 |
+
"eval_precision": 0.769159484755815,
|
| 1024 |
+
"eval_recall": 0.7614678899082569,
|
| 1025 |
+
"eval_runtime": 4.2635,
|
| 1026 |
+
"eval_samples_per_second": 25.566,
|
| 1027 |
+
"eval_steps_per_second": 0.469,
|
| 1028 |
+
"step": 488
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 61.24,
|
| 1032 |
+
"learning_rate": 3.125e-05,
|
| 1033 |
+
"loss": 0.0554,
|
| 1034 |
+
"step": 490
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 61.97,
|
| 1038 |
+
"eval_accuracy": 0.8165137614678899,
|
| 1039 |
+
"eval_f1": 0.812552773801982,
|
| 1040 |
+
"eval_loss": 0.4742366075515747,
|
| 1041 |
+
"eval_precision": 0.8100926678908328,
|
| 1042 |
+
"eval_recall": 0.8165137614678899,
|
| 1043 |
+
"eval_runtime": 4.3801,
|
| 1044 |
+
"eval_samples_per_second": 24.885,
|
| 1045 |
+
"eval_steps_per_second": 0.457,
|
| 1046 |
+
"step": 496
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 62.48,
|
| 1050 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 1051 |
+
"loss": 0.0557,
|
| 1052 |
+
"step": 500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 62.97,
|
| 1056 |
+
"eval_accuracy": 0.7889908256880734,
|
| 1057 |
+
"eval_f1": 0.7886246853481453,
|
| 1058 |
+
"eval_loss": 0.5369319915771484,
|
| 1059 |
+
"eval_precision": 0.7886251828214332,
|
| 1060 |
+
"eval_recall": 0.7889908256880734,
|
| 1061 |
+
"eval_runtime": 4.4776,
|
| 1062 |
+
"eval_samples_per_second": 24.343,
|
| 1063 |
+
"eval_steps_per_second": 0.447,
|
| 1064 |
+
"step": 504
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 63.73,
|
| 1068 |
+
"learning_rate": 2.7083333333333335e-05,
|
| 1069 |
+
"loss": 0.0539,
|
| 1070 |
+
"step": 510
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 63.97,
|
| 1074 |
+
"eval_accuracy": 0.7889908256880734,
|
| 1075 |
+
"eval_f1": 0.7898954921921011,
|
| 1076 |
+
"eval_loss": 0.5439756512641907,
|
| 1077 |
+
"eval_precision": 0.7922270390160299,
|
| 1078 |
+
"eval_recall": 0.7889908256880734,
|
| 1079 |
+
"eval_runtime": 4.4228,
|
| 1080 |
+
"eval_samples_per_second": 24.645,
|
| 1081 |
+
"eval_steps_per_second": 0.452,
|
| 1082 |
+
"step": 512
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 64.97,
|
| 1086 |
+
"learning_rate": 2.5e-05,
|
| 1087 |
+
"loss": 0.048,
|
| 1088 |
+
"step": 520
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 64.97,
|
| 1092 |
+
"eval_accuracy": 0.7889908256880734,
|
| 1093 |
+
"eval_f1": 0.7882784673502429,
|
| 1094 |
+
"eval_loss": 0.5923751592636108,
|
| 1095 |
+
"eval_precision": 0.7878178107535906,
|
| 1096 |
+
"eval_recall": 0.7889908256880734,
|
| 1097 |
+
"eval_runtime": 5.5392,
|
| 1098 |
+
"eval_samples_per_second": 19.678,
|
| 1099 |
+
"eval_steps_per_second": 0.361,
|
| 1100 |
+
"step": 520
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 65.97,
|
| 1104 |
+
"eval_accuracy": 0.8440366972477065,
|
| 1105 |
+
"eval_f1": 0.8440366972477065,
|
| 1106 |
+
"eval_loss": 0.486260324716568,
|
| 1107 |
+
"eval_precision": 0.8440366972477065,
|
| 1108 |
+
"eval_recall": 0.8440366972477065,
|
| 1109 |
+
"eval_runtime": 4.2084,
|
| 1110 |
+
"eval_samples_per_second": 25.9,
|
| 1111 |
+
"eval_steps_per_second": 0.475,
|
| 1112 |
+
"step": 528
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 66.24,
|
| 1116 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 1117 |
+
"loss": 0.045,
|
| 1118 |
+
"step": 530
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 66.97,
|
| 1122 |
+
"eval_accuracy": 0.8073394495412844,
|
| 1123 |
+
"eval_f1": 0.8046694749207712,
|
| 1124 |
+
"eval_loss": 0.5849686861038208,
|
| 1125 |
+
"eval_precision": 0.8076432996157767,
|
| 1126 |
+
"eval_recall": 0.8073394495412844,
|
| 1127 |
+
"eval_runtime": 4.3405,
|
| 1128 |
+
"eval_samples_per_second": 25.112,
|
| 1129 |
+
"eval_steps_per_second": 0.461,
|
| 1130 |
+
"step": 536
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 67.48,
|
| 1134 |
+
"learning_rate": 2.0833333333333333e-05,
|
| 1135 |
+
"loss": 0.047,
|
| 1136 |
+
"step": 540
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 67.97,
|
| 1140 |
+
"eval_accuracy": 0.8256880733944955,
|
| 1141 |
+
"eval_f1": 0.8227139701424718,
|
| 1142 |
+
"eval_loss": 0.4938836991786957,
|
| 1143 |
+
"eval_precision": 0.8211639886949021,
|
| 1144 |
+
"eval_recall": 0.8256880733944955,
|
| 1145 |
+
"eval_runtime": 4.2943,
|
| 1146 |
+
"eval_samples_per_second": 25.382,
|
| 1147 |
+
"eval_steps_per_second": 0.466,
|
| 1148 |
+
"step": 544
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 68.73,
|
| 1152 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 1153 |
+
"loss": 0.0412,
|
| 1154 |
+
"step": 550
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 68.97,
|
| 1158 |
+
"eval_accuracy": 0.7889908256880734,
|
| 1159 |
+
"eval_f1": 0.7899819010172877,
|
| 1160 |
+
"eval_loss": 0.4850451946258545,
|
| 1161 |
+
"eval_precision": 0.7911629060252914,
|
| 1162 |
+
"eval_recall": 0.7889908256880734,
|
| 1163 |
+
"eval_runtime": 4.3733,
|
| 1164 |
+
"eval_samples_per_second": 24.924,
|
| 1165 |
+
"eval_steps_per_second": 0.457,
|
| 1166 |
+
"step": 552
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 69.97,
|
| 1170 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1171 |
+
"loss": 0.0392,
|
| 1172 |
+
"step": 560
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 69.97,
|
| 1176 |
+
"eval_accuracy": 0.8256880733944955,
|
| 1177 |
+
"eval_f1": 0.8257529642156887,
|
| 1178 |
+
"eval_loss": 0.5065794587135315,
|
| 1179 |
+
"eval_precision": 0.8264957264957264,
|
| 1180 |
+
"eval_recall": 0.8256880733944955,
|
| 1181 |
+
"eval_runtime": 4.2901,
|
| 1182 |
+
"eval_samples_per_second": 25.407,
|
| 1183 |
+
"eval_steps_per_second": 0.466,
|
| 1184 |
+
"step": 560
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 70.97,
|
| 1188 |
+
"eval_accuracy": 0.8073394495412844,
|
| 1189 |
+
"eval_f1": 0.8058135764557783,
|
| 1190 |
+
"eval_loss": 0.49649733304977417,
|
| 1191 |
+
"eval_precision": 0.8053007135575942,
|
| 1192 |
+
"eval_recall": 0.8073394495412844,
|
| 1193 |
+
"eval_runtime": 4.1424,
|
| 1194 |
+
"eval_samples_per_second": 26.313,
|
| 1195 |
+
"eval_steps_per_second": 0.483,
|
| 1196 |
+
"step": 568
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 71.24,
|
| 1200 |
+
"learning_rate": 1.4583333333333333e-05,
|
| 1201 |
+
"loss": 0.0423,
|
| 1202 |
+
"step": 570
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 71.97,
|
| 1206 |
+
"eval_accuracy": 0.8348623853211009,
|
| 1207 |
+
"eval_f1": 0.8350885030999028,
|
| 1208 |
+
"eval_loss": 0.47168704867362976,
|
| 1209 |
+
"eval_precision": 0.8376424034680915,
|
| 1210 |
+
"eval_recall": 0.8348623853211009,
|
| 1211 |
+
"eval_runtime": 4.1897,
|
| 1212 |
+
"eval_samples_per_second": 26.016,
|
| 1213 |
+
"eval_steps_per_second": 0.477,
|
| 1214 |
+
"step": 576
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 72.48,
|
| 1218 |
+
"learning_rate": 1.25e-05,
|
| 1219 |
+
"loss": 0.0471,
|
| 1220 |
+
"step": 580
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 72.97,
|
| 1224 |
+
"eval_accuracy": 0.8256880733944955,
|
| 1225 |
+
"eval_f1": 0.8295520158325865,
|
| 1226 |
+
"eval_loss": 0.48450949788093567,
|
| 1227 |
+
"eval_precision": 0.837811160528748,
|
| 1228 |
+
"eval_recall": 0.8256880733944955,
|
| 1229 |
+
"eval_runtime": 4.2446,
|
| 1230 |
+
"eval_samples_per_second": 25.68,
|
| 1231 |
+
"eval_steps_per_second": 0.471,
|
| 1232 |
+
"step": 584
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 73.73,
|
| 1236 |
+
"learning_rate": 1.0416666666666666e-05,
|
| 1237 |
+
"loss": 0.0322,
|
| 1238 |
+
"step": 590
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 73.97,
|
| 1242 |
+
"eval_accuracy": 0.7706422018348624,
|
| 1243 |
+
"eval_f1": 0.7692886041532689,
|
| 1244 |
+
"eval_loss": 0.5188109278678894,
|
| 1245 |
+
"eval_precision": 0.7689271840647987,
|
| 1246 |
+
"eval_recall": 0.7706422018348624,
|
| 1247 |
+
"eval_runtime": 4.4833,
|
| 1248 |
+
"eval_samples_per_second": 24.313,
|
| 1249 |
+
"eval_steps_per_second": 0.446,
|
| 1250 |
+
"step": 592
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 74.97,
|
| 1254 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1255 |
+
"loss": 0.042,
|
| 1256 |
+
"step": 600
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 74.97,
|
| 1260 |
+
"eval_accuracy": 0.7706422018348624,
|
| 1261 |
+
"eval_f1": 0.7700888306392893,
|
| 1262 |
+
"eval_loss": 0.5242283940315247,
|
| 1263 |
+
"eval_precision": 0.7698942959712803,
|
| 1264 |
+
"eval_recall": 0.7706422018348624,
|
| 1265 |
+
"eval_runtime": 4.4923,
|
| 1266 |
+
"eval_samples_per_second": 24.264,
|
| 1267 |
+
"eval_steps_per_second": 0.445,
|
| 1268 |
+
"step": 600
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 75.97,
|
| 1272 |
+
"eval_accuracy": 0.7798165137614679,
|
| 1273 |
+
"eval_f1": 0.7803733958918072,
|
| 1274 |
+
"eval_loss": 0.5945499539375305,
|
| 1275 |
+
"eval_precision": 0.7823930357635982,
|
| 1276 |
+
"eval_recall": 0.7798165137614679,
|
| 1277 |
+
"eval_runtime": 5.1633,
|
| 1278 |
+
"eval_samples_per_second": 21.111,
|
| 1279 |
+
"eval_steps_per_second": 0.387,
|
| 1280 |
+
"step": 608
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 76.24,
|
| 1284 |
+
"learning_rate": 6.25e-06,
|
| 1285 |
+
"loss": 0.0416,
|
| 1286 |
+
"step": 610
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 76.97,
|
| 1290 |
+
"eval_accuracy": 0.7981651376146789,
|
| 1291 |
+
"eval_f1": 0.7993445642022374,
|
| 1292 |
+
"eval_loss": 0.5432426929473877,
|
| 1293 |
+
"eval_precision": 0.8038185145085823,
|
| 1294 |
+
"eval_recall": 0.7981651376146789,
|
| 1295 |
+
"eval_runtime": 4.2234,
|
| 1296 |
+
"eval_samples_per_second": 25.809,
|
| 1297 |
+
"eval_steps_per_second": 0.474,
|
| 1298 |
+
"step": 616
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 77.48,
|
| 1302 |
+
"learning_rate": 4.166666666666667e-06,
|
| 1303 |
+
"loss": 0.0399,
|
| 1304 |
+
"step": 620
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 77.97,
|
| 1308 |
+
"eval_accuracy": 0.7981651376146789,
|
| 1309 |
+
"eval_f1": 0.7994120087594209,
|
| 1310 |
+
"eval_loss": 0.5381362438201904,
|
| 1311 |
+
"eval_precision": 0.8072242548450546,
|
| 1312 |
+
"eval_recall": 0.7981651376146789,
|
| 1313 |
+
"eval_runtime": 4.2152,
|
| 1314 |
+
"eval_samples_per_second": 25.859,
|
| 1315 |
+
"eval_steps_per_second": 0.474,
|
| 1316 |
+
"step": 624
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 78.73,
|
| 1320 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 1321 |
+
"loss": 0.0439,
|
| 1322 |
+
"step": 630
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 78.97,
|
| 1326 |
+
"eval_accuracy": 0.7798165137614679,
|
| 1327 |
+
"eval_f1": 0.7827462243679189,
|
| 1328 |
+
"eval_loss": 0.6181262135505676,
|
| 1329 |
+
"eval_precision": 0.7877941763063422,
|
| 1330 |
+
"eval_recall": 0.7798165137614679,
|
| 1331 |
+
"eval_runtime": 4.2424,
|
| 1332 |
+
"eval_samples_per_second": 25.693,
|
| 1333 |
+
"eval_steps_per_second": 0.471,
|
| 1334 |
+
"step": 632
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 79.97,
|
| 1338 |
+
"learning_rate": 0.0,
|
| 1339 |
+
"loss": 0.0462,
|
| 1340 |
+
"step": 640
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 79.97,
|
| 1344 |
+
"eval_accuracy": 0.8165137614678899,
|
| 1345 |
+
"eval_f1": 0.8172526992448356,
|
| 1346 |
+
"eval_loss": 0.48008766770362854,
|
| 1347 |
+
"eval_precision": 0.8181998512273742,
|
| 1348 |
+
"eval_recall": 0.8165137614678899,
|
| 1349 |
+
"eval_runtime": 4.18,
|
| 1350 |
+
"eval_samples_per_second": 26.076,
|
| 1351 |
+
"eval_steps_per_second": 0.478,
|
| 1352 |
+
"step": 640
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 79.97,
|
| 1356 |
+
"step": 640,
|
| 1357 |
+
"total_flos": 3.5167284631649157e+18,
|
| 1358 |
+
"train_loss": 0.37728101573884487,
|
| 1359 |
+
"train_runtime": 2345.4183,
|
| 1360 |
+
"train_samples_per_second": 70.606,
|
| 1361 |
+
"train_steps_per_second": 0.273
|
| 1362 |
}
|
| 1363 |
],
|
| 1364 |
+
"max_steps": 640,
|
| 1365 |
+
"num_train_epochs": 80,
|
| 1366 |
+
"total_flos": 3.5167284631649157e+18,
|
| 1367 |
"trial_name": null,
|
| 1368 |
"trial_params": null
|
| 1369 |
}
|