paul commited on
Commit ·
81ba73a
1
Parent(s): 709b223
End of training
Browse files- all_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Jan23_23-43-30_teesta/events.out.tfevents.1674497615.teesta.22953.2 +2 -2
- train_results.json +6 -6
- trainer_state.json +1758 -198
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": 119.89,
|
| 3 |
+
"total_flos": 2.909790831021355e+18,
|
| 4 |
+
"train_loss": 1.1563791312277316,
|
| 5 |
+
"train_runtime": 2067.6252,
|
| 6 |
+
"train_samples_per_second": 100.289,
|
| 7 |
+
"train_steps_per_second": 0.348
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94555277
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fffb5d3aa1db439a2b09778eccf2c0f1f0c692878c5ede28726f33faee6556b2
|
| 3 |
size 94555277
|
runs/Jan23_23-43-30_teesta/events.out.tfevents.1674497615.teesta.22953.2
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 sha256:78eaac3478fbaeda48df7f712f3a1677080815c8e0afdff7ddb848284e8e7b1a
|
| 3 |
+
size 73092
|
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": 119.89,
|
| 3 |
+
"total_flos": 2.909790831021355e+18,
|
| 4 |
+
"train_loss": 1.1563791312277316,
|
| 5 |
+
"train_runtime": 2067.6252,
|
| 6 |
+
"train_samples_per_second": 100.289,
|
| 7 |
+
"train_steps_per_second": 0.348
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,337 +1,1897 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "microsoft-resnet-50-cartoon-face-recognition/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": 0.89,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 3.
|
| 15 |
-
"eval_precision": 0.
|
| 16 |
-
"eval_recall": 0.
|
| 17 |
-
"eval_runtime": 6.
|
| 18 |
-
"eval_samples_per_second":
|
| 19 |
-
"eval_steps_per_second": 1.
|
| 20 |
"step": 6
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 1.59,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 3.
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 1.89,
|
| 30 |
-
"eval_accuracy": 0.
|
| 31 |
-
"eval_f1": 0.
|
| 32 |
-
"eval_loss": 3.
|
| 33 |
-
"eval_precision": 0.
|
| 34 |
-
"eval_recall": 0.
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second": 1.
|
| 38 |
"step": 12
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.89,
|
| 42 |
-
"eval_accuracy": 0.
|
| 43 |
-
"eval_f1": 0.
|
| 44 |
-
"eval_loss": 3.
|
| 45 |
-
"eval_precision": 0.
|
| 46 |
-
"eval_recall": 0.
|
| 47 |
-
"eval_runtime": 5.
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second": 1.
|
| 50 |
"step": 18
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.3,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 3.
|
| 56 |
"step": 20
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 3.89,
|
| 60 |
-
"eval_accuracy": 0.
|
| 61 |
-
"eval_f1": 0.
|
| 62 |
-
"eval_loss": 3.
|
| 63 |
-
"eval_precision": 0.
|
| 64 |
-
"eval_recall": 0.
|
| 65 |
-
"eval_runtime": 5.
|
| 66 |
-
"eval_samples_per_second":
|
| 67 |
-
"eval_steps_per_second": 1.
|
| 68 |
"step": 24
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 4.89,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 3.
|
| 74 |
"step": 30
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 4.89,
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_f1": 0.
|
| 80 |
-
"eval_loss": 3.
|
| 81 |
-
"eval_precision": 0.
|
| 82 |
-
"eval_recall": 0.
|
| 83 |
-
"eval_runtime": 5.
|
| 84 |
-
"eval_samples_per_second":
|
| 85 |
-
"eval_steps_per_second": 1.
|
| 86 |
"step": 30
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 5.89,
|
| 90 |
-
"eval_accuracy": 0.
|
| 91 |
-
"eval_f1": 0.
|
| 92 |
-
"eval_loss": 3.
|
| 93 |
-
"eval_precision": 0.
|
| 94 |
-
"eval_recall": 0.
|
| 95 |
-
"eval_runtime": 5.
|
| 96 |
-
"eval_samples_per_second":
|
| 97 |
-
"eval_steps_per_second": 1.
|
| 98 |
"step": 36
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 6.59,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 3.
|
| 104 |
"step": 40
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.89,
|
| 108 |
-
"eval_accuracy": 0.
|
| 109 |
-
"eval_f1": 0.
|
| 110 |
-
"eval_loss":
|
| 111 |
-
"eval_precision": 0.
|
| 112 |
-
"eval_recall": 0.
|
| 113 |
-
"eval_runtime": 5.
|
| 114 |
-
"eval_samples_per_second":
|
| 115 |
-
"eval_steps_per_second": 1.
|
| 116 |
"step": 42
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 7.89,
|
| 120 |
-
"eval_accuracy": 0.
|
| 121 |
-
"eval_f1": 0.
|
| 122 |
-
"eval_loss":
|
| 123 |
-
"eval_precision": 0.
|
| 124 |
-
"eval_recall": 0.
|
| 125 |
-
"eval_runtime": 5.
|
| 126 |
-
"eval_samples_per_second":
|
| 127 |
-
"eval_steps_per_second": 1.
|
| 128 |
"step": 48
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 8.3,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 3.
|
| 134 |
"step": 50
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 8.89,
|
| 138 |
-
"eval_accuracy": 0.
|
| 139 |
-
"eval_f1": 0.
|
| 140 |
-
"eval_loss":
|
| 141 |
-
"eval_precision": 0.
|
| 142 |
-
"eval_recall": 0.
|
| 143 |
-
"eval_runtime":
|
| 144 |
-
"eval_samples_per_second":
|
| 145 |
-
"eval_steps_per_second": 1.
|
| 146 |
"step": 54
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 9.89,
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 3.
|
| 152 |
"step": 60
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 9.89,
|
| 156 |
-
"eval_accuracy": 0.
|
| 157 |
-
"eval_f1": 0.
|
| 158 |
-
"eval_loss":
|
| 159 |
-
"eval_precision": 0.
|
| 160 |
-
"eval_recall": 0.
|
| 161 |
-
"eval_runtime": 5.
|
| 162 |
-
"eval_samples_per_second":
|
| 163 |
-
"eval_steps_per_second": 1.
|
| 164 |
"step": 60
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 10.89,
|
| 168 |
-
"eval_accuracy": 0.
|
| 169 |
-
"eval_f1": 0.
|
| 170 |
-
"eval_loss":
|
| 171 |
-
"eval_precision": 0.
|
| 172 |
-
"eval_recall": 0.
|
| 173 |
-
"eval_runtime": 5.
|
| 174 |
-
"eval_samples_per_second":
|
| 175 |
-
"eval_steps_per_second": 1.
|
| 176 |
"step": 66
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 11.59,
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 3.
|
| 182 |
"step": 70
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 11.89,
|
| 186 |
-
"eval_accuracy": 0.
|
| 187 |
-
"eval_f1": 0.
|
| 188 |
-
"eval_loss": 2.
|
| 189 |
-
"eval_precision": 0.
|
| 190 |
-
"eval_recall": 0.
|
| 191 |
-
"eval_runtime": 5.
|
| 192 |
-
"eval_samples_per_second":
|
| 193 |
-
"eval_steps_per_second": 1.
|
| 194 |
"step": 72
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 12.89,
|
| 198 |
-
"eval_accuracy": 0.
|
| 199 |
-
"eval_f1": 0.
|
| 200 |
-
"eval_loss": 2.
|
| 201 |
-
"eval_precision": 0.
|
| 202 |
-
"eval_recall": 0.
|
| 203 |
-
"eval_runtime":
|
| 204 |
-
"eval_samples_per_second":
|
| 205 |
-
"eval_steps_per_second": 1.
|
| 206 |
"step": 78
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 13.3,
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 3.
|
| 212 |
"step": 80
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 13.89,
|
| 216 |
-
"eval_accuracy": 0.
|
| 217 |
-
"eval_f1": 0.
|
| 218 |
-
"eval_loss": 2.
|
| 219 |
-
"eval_precision": 0.
|
| 220 |
-
"eval_recall": 0.
|
| 221 |
-
"eval_runtime": 5.
|
| 222 |
-
"eval_samples_per_second":
|
| 223 |
-
"eval_steps_per_second": 1.
|
| 224 |
"step": 84
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 14.89,
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 3.
|
| 230 |
"step": 90
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 14.89,
|
| 234 |
-
"eval_accuracy": 0.
|
| 235 |
-
"eval_f1": 0.
|
| 236 |
-
"eval_loss": 2.
|
| 237 |
-
"eval_precision": 0.
|
| 238 |
-
"eval_recall": 0.
|
| 239 |
-
"eval_runtime": 5.
|
| 240 |
-
"eval_samples_per_second":
|
| 241 |
-
"eval_steps_per_second": 1.
|
| 242 |
"step": 90
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 15.89,
|
| 246 |
-
"eval_accuracy": 0.
|
| 247 |
-
"eval_f1": 0.
|
| 248 |
-
"eval_loss": 2.
|
| 249 |
-
"eval_precision": 0.
|
| 250 |
-
"eval_recall": 0.
|
| 251 |
-
"eval_runtime": 5.
|
| 252 |
-
"eval_samples_per_second":
|
| 253 |
-
"eval_steps_per_second": 1.
|
| 254 |
"step": 96
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 16.59,
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss": 3.
|
| 260 |
"step": 100
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 16.89,
|
| 264 |
-
"eval_accuracy": 0.
|
| 265 |
-
"eval_f1": 0.
|
| 266 |
-
"eval_loss": 2.
|
| 267 |
-
"eval_precision": 0.
|
| 268 |
-
"eval_recall": 0.
|
| 269 |
-
"eval_runtime": 5.
|
| 270 |
-
"eval_samples_per_second":
|
| 271 |
-
"eval_steps_per_second": 1.
|
| 272 |
"step": 102
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 17.89,
|
| 276 |
-
"eval_accuracy": 0.
|
| 277 |
-
"eval_f1": 0.
|
| 278 |
-
"eval_loss": 2.
|
| 279 |
-
"eval_precision": 0.
|
| 280 |
-
"eval_recall": 0.
|
| 281 |
-
"eval_runtime": 5.
|
| 282 |
-
"eval_samples_per_second":
|
| 283 |
-
"eval_steps_per_second": 1.
|
| 284 |
"step": 108
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 18.3,
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 3.
|
| 290 |
"step": 110
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 18.89,
|
| 294 |
-
"eval_accuracy": 0.
|
| 295 |
-
"eval_f1": 0.
|
| 296 |
-
"eval_loss": 2.
|
| 297 |
-
"eval_precision": 0.
|
| 298 |
-
"eval_recall": 0.
|
| 299 |
-
"eval_runtime":
|
| 300 |
-
"eval_samples_per_second":
|
| 301 |
-
"eval_steps_per_second": 1.
|
| 302 |
"step": 114
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 19.89,
|
| 306 |
-
"learning_rate": 0.
|
| 307 |
-
"loss": 2.
|
| 308 |
"step": 120
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 19.89,
|
| 312 |
-
"eval_accuracy": 0.
|
| 313 |
-
"eval_f1": 0.
|
| 314 |
-
"eval_loss": 2.
|
| 315 |
-
"eval_precision": 0.
|
| 316 |
-
"eval_recall": 0.
|
| 317 |
-
"eval_runtime": 5.
|
| 318 |
-
"eval_samples_per_second":
|
| 319 |
-
"eval_steps_per_second": 1.
|
| 320 |
"step": 120
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch":
|
| 324 |
-
"
|
| 325 |
-
"
|
| 326 |
-
"
|
| 327 |
-
"
|
| 328 |
-
"
|
| 329 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 330 |
}
|
| 331 |
],
|
| 332 |
-
"max_steps":
|
| 333 |
-
"num_train_epochs":
|
| 334 |
-
"total_flos":
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
| 337 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7847222222222222,
|
| 3 |
+
"best_model_checkpoint": "microsoft-resnet-50-cartoon-face-recognition/checkpoint-690",
|
| 4 |
+
"epoch": 119.88888888888889,
|
| 5 |
+
"global_step": 720,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.89,
|
| 12 |
+
"eval_accuracy": 0.037037037037037035,
|
| 13 |
+
"eval_f1": 0.009802215531382198,
|
| 14 |
+
"eval_loss": 3.177427053451538,
|
| 15 |
+
"eval_precision": 0.006871793330126662,
|
| 16 |
+
"eval_recall": 0.037037037037037035,
|
| 17 |
+
"eval_runtime": 6.7511,
|
| 18 |
+
"eval_samples_per_second": 63.989,
|
| 19 |
+
"eval_steps_per_second": 1.037,
|
| 20 |
"step": 6
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 1.59,
|
| 24 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 25 |
+
"loss": 3.4185,
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 1.89,
|
| 30 |
+
"eval_accuracy": 0.03009259259259259,
|
| 31 |
+
"eval_f1": 0.012595532039976485,
|
| 32 |
+
"eval_loss": 3.173919677734375,
|
| 33 |
+
"eval_precision": 0.009991865408265568,
|
| 34 |
+
"eval_recall": 0.03009259259259259,
|
| 35 |
+
"eval_runtime": 5.4893,
|
| 36 |
+
"eval_samples_per_second": 78.698,
|
| 37 |
+
"eval_steps_per_second": 1.275,
|
| 38 |
"step": 12
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.89,
|
| 42 |
+
"eval_accuracy": 0.04398148148148148,
|
| 43 |
+
"eval_f1": 0.03396177939075919,
|
| 44 |
+
"eval_loss": 3.1668288707733154,
|
| 45 |
+
"eval_precision": 0.08045697418202408,
|
| 46 |
+
"eval_recall": 0.04398148148148148,
|
| 47 |
+
"eval_runtime": 5.6812,
|
| 48 |
+
"eval_samples_per_second": 76.04,
|
| 49 |
+
"eval_steps_per_second": 1.232,
|
| 50 |
"step": 18
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.3,
|
| 54 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 55 |
+
"loss": 3.6463,
|
| 56 |
"step": 20
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 3.89,
|
| 60 |
+
"eval_accuracy": 0.037037037037037035,
|
| 61 |
+
"eval_f1": 0.015118236629864536,
|
| 62 |
+
"eval_loss": 3.158271312713623,
|
| 63 |
+
"eval_precision": 0.018042564247921392,
|
| 64 |
+
"eval_recall": 0.037037037037037035,
|
| 65 |
+
"eval_runtime": 5.1688,
|
| 66 |
+
"eval_samples_per_second": 83.579,
|
| 67 |
+
"eval_steps_per_second": 1.354,
|
| 68 |
"step": 24
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 4.89,
|
| 72 |
+
"learning_rate": 5e-05,
|
| 73 |
+
"loss": 3.3899,
|
| 74 |
"step": 30
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 4.89,
|
| 78 |
+
"eval_accuracy": 0.07407407407407407,
|
| 79 |
+
"eval_f1": 0.04528877134769999,
|
| 80 |
+
"eval_loss": 3.142496109008789,
|
| 81 |
+
"eval_precision": 0.06098814150284739,
|
| 82 |
+
"eval_recall": 0.07407407407407407,
|
| 83 |
+
"eval_runtime": 5.4398,
|
| 84 |
+
"eval_samples_per_second": 79.415,
|
| 85 |
+
"eval_steps_per_second": 1.287,
|
| 86 |
"step": 30
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 5.89,
|
| 90 |
+
"eval_accuracy": 0.08564814814814815,
|
| 91 |
+
"eval_f1": 0.040453657257170324,
|
| 92 |
+
"eval_loss": 3.1262054443359375,
|
| 93 |
+
"eval_precision": 0.03336711386173307,
|
| 94 |
+
"eval_recall": 0.08564814814814815,
|
| 95 |
+
"eval_runtime": 5.1611,
|
| 96 |
+
"eval_samples_per_second": 83.702,
|
| 97 |
+
"eval_steps_per_second": 1.356,
|
| 98 |
"step": 36
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 6.59,
|
| 102 |
+
"learning_rate": 6.666666666666667e-05,
|
| 103 |
+
"loss": 3.5947,
|
| 104 |
"step": 40
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.89,
|
| 108 |
+
"eval_accuracy": 0.10185185185185185,
|
| 109 |
+
"eval_f1": 0.04813087748076705,
|
| 110 |
+
"eval_loss": 3.105499744415283,
|
| 111 |
+
"eval_precision": 0.07837275882119042,
|
| 112 |
+
"eval_recall": 0.10185185185185185,
|
| 113 |
+
"eval_runtime": 5.3163,
|
| 114 |
+
"eval_samples_per_second": 81.26,
|
| 115 |
+
"eval_steps_per_second": 1.317,
|
| 116 |
"step": 42
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 7.89,
|
| 120 |
+
"eval_accuracy": 0.11805555555555555,
|
| 121 |
+
"eval_f1": 0.05001316779776901,
|
| 122 |
+
"eval_loss": 3.0840911865234375,
|
| 123 |
+
"eval_precision": 0.10709469464505224,
|
| 124 |
+
"eval_recall": 0.11805555555555555,
|
| 125 |
+
"eval_runtime": 5.3088,
|
| 126 |
+
"eval_samples_per_second": 81.374,
|
| 127 |
+
"eval_steps_per_second": 1.319,
|
| 128 |
"step": 48
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 8.3,
|
| 132 |
+
"learning_rate": 8.333333333333333e-05,
|
| 133 |
+
"loss": 3.5553,
|
| 134 |
"step": 50
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 8.89,
|
| 138 |
+
"eval_accuracy": 0.10648148148148148,
|
| 139 |
+
"eval_f1": 0.034321942911473204,
|
| 140 |
+
"eval_loss": 3.0650484561920166,
|
| 141 |
+
"eval_precision": 0.021575460554167175,
|
| 142 |
+
"eval_recall": 0.10648148148148148,
|
| 143 |
+
"eval_runtime": 5.2915,
|
| 144 |
+
"eval_samples_per_second": 81.641,
|
| 145 |
+
"eval_steps_per_second": 1.323,
|
| 146 |
"step": 54
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 9.89,
|
| 150 |
+
"learning_rate": 0.0001,
|
| 151 |
+
"loss": 3.2713,
|
| 152 |
"step": 60
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 9.89,
|
| 156 |
+
"eval_accuracy": 0.12731481481481483,
|
| 157 |
+
"eval_f1": 0.04184436999619006,
|
| 158 |
+
"eval_loss": 3.0350887775421143,
|
| 159 |
+
"eval_precision": 0.03231738683127571,
|
| 160 |
+
"eval_recall": 0.12731481481481483,
|
| 161 |
+
"eval_runtime": 5.315,
|
| 162 |
+
"eval_samples_per_second": 81.279,
|
| 163 |
+
"eval_steps_per_second": 1.317,
|
| 164 |
"step": 60
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 10.89,
|
| 168 |
+
"eval_accuracy": 0.12268518518518519,
|
| 169 |
+
"eval_f1": 0.03896546460633453,
|
| 170 |
+
"eval_loss": 3.006906747817993,
|
| 171 |
+
"eval_precision": 0.031055780240739028,
|
| 172 |
+
"eval_recall": 0.12268518518518519,
|
| 173 |
+
"eval_runtime": 5.3282,
|
| 174 |
+
"eval_samples_per_second": 81.078,
|
| 175 |
+
"eval_steps_per_second": 1.314,
|
| 176 |
"step": 66
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 11.59,
|
| 180 |
+
"learning_rate": 0.00011666666666666667,
|
| 181 |
+
"loss": 3.4382,
|
| 182 |
"step": 70
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 11.89,
|
| 186 |
+
"eval_accuracy": 0.12037037037037036,
|
| 187 |
+
"eval_f1": 0.03664636838867146,
|
| 188 |
+
"eval_loss": 2.9754226207733154,
|
| 189 |
+
"eval_precision": 0.035322359396433474,
|
| 190 |
+
"eval_recall": 0.12037037037037036,
|
| 191 |
+
"eval_runtime": 5.2664,
|
| 192 |
+
"eval_samples_per_second": 82.029,
|
| 193 |
+
"eval_steps_per_second": 1.329,
|
| 194 |
"step": 72
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 12.89,
|
| 198 |
+
"eval_accuracy": 0.12268518518518519,
|
| 199 |
+
"eval_f1": 0.03383682152179769,
|
| 200 |
+
"eval_loss": 2.945517063140869,
|
| 201 |
+
"eval_precision": 0.022390870365422862,
|
| 202 |
+
"eval_recall": 0.12268518518518519,
|
| 203 |
+
"eval_runtime": 5.4645,
|
| 204 |
+
"eval_samples_per_second": 79.056,
|
| 205 |
+
"eval_steps_per_second": 1.281,
|
| 206 |
"step": 78
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 13.3,
|
| 210 |
+
"learning_rate": 0.00011851851851851852,
|
| 211 |
+
"loss": 3.3573,
|
| 212 |
"step": 80
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 13.89,
|
| 216 |
+
"eval_accuracy": 0.12037037037037036,
|
| 217 |
+
"eval_f1": 0.03316178047360843,
|
| 218 |
+
"eval_loss": 2.9167439937591553,
|
| 219 |
+
"eval_precision": 0.021296296296296296,
|
| 220 |
+
"eval_recall": 0.12037037037037036,
|
| 221 |
+
"eval_runtime": 5.6677,
|
| 222 |
+
"eval_samples_per_second": 76.222,
|
| 223 |
+
"eval_steps_per_second": 1.235,
|
| 224 |
"step": 84
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 14.89,
|
| 228 |
+
"learning_rate": 0.00011666666666666667,
|
| 229 |
+
"loss": 3.0549,
|
| 230 |
"step": 90
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 14.89,
|
| 234 |
+
"eval_accuracy": 0.12268518518518519,
|
| 235 |
+
"eval_f1": 0.04084263761775177,
|
| 236 |
+
"eval_loss": 2.884087562561035,
|
| 237 |
+
"eval_precision": 0.047443229428523546,
|
| 238 |
+
"eval_recall": 0.12268518518518519,
|
| 239 |
+
"eval_runtime": 5.2214,
|
| 240 |
+
"eval_samples_per_second": 82.737,
|
| 241 |
+
"eval_steps_per_second": 1.341,
|
| 242 |
"step": 90
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 15.89,
|
| 246 |
+
"eval_accuracy": 0.1412037037037037,
|
| 247 |
+
"eval_f1": 0.05401596739565727,
|
| 248 |
+
"eval_loss": 2.8534481525421143,
|
| 249 |
+
"eval_precision": 0.11735631001371744,
|
| 250 |
+
"eval_recall": 0.1412037037037037,
|
| 251 |
+
"eval_runtime": 5.2992,
|
| 252 |
+
"eval_samples_per_second": 81.521,
|
| 253 |
+
"eval_steps_per_second": 1.321,
|
| 254 |
"step": 96
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 16.59,
|
| 258 |
+
"learning_rate": 0.00011481481481481482,
|
| 259 |
+
"loss": 3.1853,
|
| 260 |
"step": 100
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 16.89,
|
| 264 |
+
"eval_accuracy": 0.15046296296296297,
|
| 265 |
+
"eval_f1": 0.0666910894416082,
|
| 266 |
+
"eval_loss": 2.814347743988037,
|
| 267 |
+
"eval_precision": 0.15945772593650578,
|
| 268 |
+
"eval_recall": 0.15046296296296297,
|
| 269 |
+
"eval_runtime": 5.2953,
|
| 270 |
+
"eval_samples_per_second": 81.581,
|
| 271 |
+
"eval_steps_per_second": 1.322,
|
| 272 |
"step": 102
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 17.89,
|
| 276 |
+
"eval_accuracy": 0.16666666666666666,
|
| 277 |
+
"eval_f1": 0.07186374965273062,
|
| 278 |
+
"eval_loss": 2.777080774307251,
|
| 279 |
+
"eval_precision": 0.16930278149907305,
|
| 280 |
+
"eval_recall": 0.16666666666666666,
|
| 281 |
+
"eval_runtime": 5.5347,
|
| 282 |
+
"eval_samples_per_second": 78.053,
|
| 283 |
+
"eval_steps_per_second": 1.265,
|
| 284 |
"step": 108
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 18.3,
|
| 288 |
+
"learning_rate": 0.00011296296296296296,
|
| 289 |
+
"loss": 3.0871,
|
| 290 |
"step": 110
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 18.89,
|
| 294 |
+
"eval_accuracy": 0.17592592592592593,
|
| 295 |
+
"eval_f1": 0.08963216187544253,
|
| 296 |
+
"eval_loss": 2.7399983406066895,
|
| 297 |
+
"eval_precision": 0.14542306534176452,
|
| 298 |
+
"eval_recall": 0.17592592592592593,
|
| 299 |
+
"eval_runtime": 6.4855,
|
| 300 |
+
"eval_samples_per_second": 66.61,
|
| 301 |
+
"eval_steps_per_second": 1.079,
|
| 302 |
"step": 114
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 19.89,
|
| 306 |
+
"learning_rate": 0.00011111111111111112,
|
| 307 |
+
"loss": 2.7666,
|
| 308 |
"step": 120
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 19.89,
|
| 312 |
+
"eval_accuracy": 0.2013888888888889,
|
| 313 |
+
"eval_f1": 0.10508380061910785,
|
| 314 |
+
"eval_loss": 2.7047784328460693,
|
| 315 |
+
"eval_precision": 0.0926529909484455,
|
| 316 |
+
"eval_recall": 0.2013888888888889,
|
| 317 |
+
"eval_runtime": 5.1825,
|
| 318 |
+
"eval_samples_per_second": 83.357,
|
| 319 |
+
"eval_steps_per_second": 1.351,
|
| 320 |
"step": 120
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 20.89,
|
| 324 |
+
"eval_accuracy": 0.23148148148148148,
|
| 325 |
+
"eval_f1": 0.1249680097404455,
|
| 326 |
+
"eval_loss": 2.6457977294921875,
|
| 327 |
+
"eval_precision": 0.16220180035223264,
|
| 328 |
+
"eval_recall": 0.23148148148148148,
|
| 329 |
+
"eval_runtime": 5.3605,
|
| 330 |
+
"eval_samples_per_second": 80.59,
|
| 331 |
+
"eval_steps_per_second": 1.306,
|
| 332 |
+
"step": 126
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 21.59,
|
| 336 |
+
"learning_rate": 0.00010925925925925926,
|
| 337 |
+
"loss": 2.846,
|
| 338 |
+
"step": 130
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 21.89,
|
| 342 |
+
"eval_accuracy": 0.2569444444444444,
|
| 343 |
+
"eval_f1": 0.14696483781924097,
|
| 344 |
+
"eval_loss": 2.5803465843200684,
|
| 345 |
+
"eval_precision": 0.23855676187019514,
|
| 346 |
+
"eval_recall": 0.2569444444444444,
|
| 347 |
+
"eval_runtime": 5.1688,
|
| 348 |
+
"eval_samples_per_second": 83.579,
|
| 349 |
+
"eval_steps_per_second": 1.354,
|
| 350 |
+
"step": 132
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 22.89,
|
| 354 |
+
"eval_accuracy": 0.2638888888888889,
|
| 355 |
+
"eval_f1": 0.15231614141660005,
|
| 356 |
+
"eval_loss": 2.529054641723633,
|
| 357 |
+
"eval_precision": 0.2724892697099823,
|
| 358 |
+
"eval_recall": 0.2638888888888889,
|
| 359 |
+
"eval_runtime": 5.3151,
|
| 360 |
+
"eval_samples_per_second": 81.279,
|
| 361 |
+
"eval_steps_per_second": 1.317,
|
| 362 |
+
"step": 138
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 23.3,
|
| 366 |
+
"learning_rate": 0.00010740740740740741,
|
| 367 |
+
"loss": 2.7428,
|
| 368 |
+
"step": 140
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.89,
|
| 372 |
+
"eval_accuracy": 0.28703703703703703,
|
| 373 |
+
"eval_f1": 0.18105006076248228,
|
| 374 |
+
"eval_loss": 2.491586685180664,
|
| 375 |
+
"eval_precision": 0.211443025358476,
|
| 376 |
+
"eval_recall": 0.28703703703703703,
|
| 377 |
+
"eval_runtime": 5.2796,
|
| 378 |
+
"eval_samples_per_second": 81.825,
|
| 379 |
+
"eval_steps_per_second": 1.326,
|
| 380 |
+
"step": 144
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 24.89,
|
| 384 |
+
"learning_rate": 0.00010555555555555557,
|
| 385 |
+
"loss": 2.4183,
|
| 386 |
+
"step": 150
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 24.89,
|
| 390 |
+
"eval_accuracy": 0.30787037037037035,
|
| 391 |
+
"eval_f1": 0.20479489700821343,
|
| 392 |
+
"eval_loss": 2.427311658859253,
|
| 393 |
+
"eval_precision": 0.23219427179632832,
|
| 394 |
+
"eval_recall": 0.30787037037037035,
|
| 395 |
+
"eval_runtime": 5.439,
|
| 396 |
+
"eval_samples_per_second": 79.426,
|
| 397 |
+
"eval_steps_per_second": 1.287,
|
| 398 |
+
"step": 150
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 25.89,
|
| 402 |
+
"eval_accuracy": 0.3194444444444444,
|
| 403 |
+
"eval_f1": 0.22377035813767307,
|
| 404 |
+
"eval_loss": 2.392331838607788,
|
| 405 |
+
"eval_precision": 0.2936854089800938,
|
| 406 |
+
"eval_recall": 0.3194444444444444,
|
| 407 |
+
"eval_runtime": 5.5411,
|
| 408 |
+
"eval_samples_per_second": 77.962,
|
| 409 |
+
"eval_steps_per_second": 1.263,
|
| 410 |
+
"step": 156
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 26.59,
|
| 414 |
+
"learning_rate": 0.0001037037037037037,
|
| 415 |
+
"loss": 2.5064,
|
| 416 |
+
"step": 160
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.89,
|
| 420 |
+
"eval_accuracy": 0.3402777777777778,
|
| 421 |
+
"eval_f1": 0.24941517503564606,
|
| 422 |
+
"eval_loss": 2.334895133972168,
|
| 423 |
+
"eval_precision": 0.3182802115296284,
|
| 424 |
+
"eval_recall": 0.3402777777777778,
|
| 425 |
+
"eval_runtime": 5.4141,
|
| 426 |
+
"eval_samples_per_second": 79.791,
|
| 427 |
+
"eval_steps_per_second": 1.293,
|
| 428 |
+
"step": 162
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 27.89,
|
| 432 |
+
"eval_accuracy": 0.3541666666666667,
|
| 433 |
+
"eval_f1": 0.2663498097031901,
|
| 434 |
+
"eval_loss": 2.297736167907715,
|
| 435 |
+
"eval_precision": 0.3553616134289536,
|
| 436 |
+
"eval_recall": 0.3541666666666667,
|
| 437 |
+
"eval_runtime": 6.6536,
|
| 438 |
+
"eval_samples_per_second": 64.927,
|
| 439 |
+
"eval_steps_per_second": 1.052,
|
| 440 |
+
"step": 168
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 28.3,
|
| 444 |
+
"learning_rate": 0.00010185185185185186,
|
| 445 |
+
"loss": 2.4046,
|
| 446 |
+
"step": 170
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 28.89,
|
| 450 |
+
"eval_accuracy": 0.3773148148148148,
|
| 451 |
+
"eval_f1": 0.2980587048254368,
|
| 452 |
+
"eval_loss": 2.236337661743164,
|
| 453 |
+
"eval_precision": 0.3214024127386118,
|
| 454 |
+
"eval_recall": 0.3773148148148148,
|
| 455 |
+
"eval_runtime": 5.4904,
|
| 456 |
+
"eval_samples_per_second": 78.683,
|
| 457 |
+
"eval_steps_per_second": 1.275,
|
| 458 |
+
"step": 174
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 29.89,
|
| 462 |
+
"learning_rate": 0.0001,
|
| 463 |
+
"loss": 2.1201,
|
| 464 |
+
"step": 180
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 29.89,
|
| 468 |
+
"eval_accuracy": 0.3888888888888889,
|
| 469 |
+
"eval_f1": 0.31791564865485733,
|
| 470 |
+
"eval_loss": 2.179067611694336,
|
| 471 |
+
"eval_precision": 0.40240237475373924,
|
| 472 |
+
"eval_recall": 0.3888888888888889,
|
| 473 |
+
"eval_runtime": 5.3714,
|
| 474 |
+
"eval_samples_per_second": 80.425,
|
| 475 |
+
"eval_steps_per_second": 1.303,
|
| 476 |
+
"step": 180
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 30.89,
|
| 480 |
+
"eval_accuracy": 0.41435185185185186,
|
| 481 |
+
"eval_f1": 0.34551235135842745,
|
| 482 |
+
"eval_loss": 2.1447603702545166,
|
| 483 |
+
"eval_precision": 0.4079261289461761,
|
| 484 |
+
"eval_recall": 0.41435185185185186,
|
| 485 |
+
"eval_runtime": 5.3344,
|
| 486 |
+
"eval_samples_per_second": 80.984,
|
| 487 |
+
"eval_steps_per_second": 1.312,
|
| 488 |
+
"step": 186
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 31.59,
|
| 492 |
+
"learning_rate": 9.814814814814815e-05,
|
| 493 |
+
"loss": 2.1705,
|
| 494 |
+
"step": 190
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 31.89,
|
| 498 |
+
"eval_accuracy": 0.4305555555555556,
|
| 499 |
+
"eval_f1": 0.3583236278769072,
|
| 500 |
+
"eval_loss": 2.0968592166900635,
|
| 501 |
+
"eval_precision": 0.42138862813145966,
|
| 502 |
+
"eval_recall": 0.4305555555555556,
|
| 503 |
+
"eval_runtime": 5.2736,
|
| 504 |
+
"eval_samples_per_second": 81.918,
|
| 505 |
+
"eval_steps_per_second": 1.327,
|
| 506 |
+
"step": 192
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 32.89,
|
| 510 |
+
"eval_accuracy": 0.44675925925925924,
|
| 511 |
+
"eval_f1": 0.3796832086663997,
|
| 512 |
+
"eval_loss": 2.0535407066345215,
|
| 513 |
+
"eval_precision": 0.44476509568042505,
|
| 514 |
+
"eval_recall": 0.44675925925925924,
|
| 515 |
+
"eval_runtime": 5.5334,
|
| 516 |
+
"eval_samples_per_second": 78.071,
|
| 517 |
+
"eval_steps_per_second": 1.265,
|
| 518 |
+
"step": 198
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 33.3,
|
| 522 |
+
"learning_rate": 9.62962962962963e-05,
|
| 523 |
+
"loss": 2.0295,
|
| 524 |
+
"step": 200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 33.89,
|
| 528 |
+
"eval_accuracy": 0.47453703703703703,
|
| 529 |
+
"eval_f1": 0.41326930710155785,
|
| 530 |
+
"eval_loss": 1.9940098524093628,
|
| 531 |
+
"eval_precision": 0.487688116532901,
|
| 532 |
+
"eval_recall": 0.47453703703703703,
|
| 533 |
+
"eval_runtime": 5.2418,
|
| 534 |
+
"eval_samples_per_second": 82.414,
|
| 535 |
+
"eval_steps_per_second": 1.335,
|
| 536 |
+
"step": 204
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 34.89,
|
| 540 |
+
"learning_rate": 9.444444444444446e-05,
|
| 541 |
+
"loss": 1.8114,
|
| 542 |
+
"step": 210
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 34.89,
|
| 546 |
+
"eval_accuracy": 0.4861111111111111,
|
| 547 |
+
"eval_f1": 0.4260885563604569,
|
| 548 |
+
"eval_loss": 1.9467288255691528,
|
| 549 |
+
"eval_precision": 0.4952086854944768,
|
| 550 |
+
"eval_recall": 0.4861111111111111,
|
| 551 |
+
"eval_runtime": 6.2488,
|
| 552 |
+
"eval_samples_per_second": 69.134,
|
| 553 |
+
"eval_steps_per_second": 1.12,
|
| 554 |
+
"step": 210
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 35.89,
|
| 558 |
+
"eval_accuracy": 0.4930555555555556,
|
| 559 |
+
"eval_f1": 0.43212988067709945,
|
| 560 |
+
"eval_loss": 1.8896209001541138,
|
| 561 |
+
"eval_precision": 0.4509807456365427,
|
| 562 |
+
"eval_recall": 0.4930555555555556,
|
| 563 |
+
"eval_runtime": 6.1753,
|
| 564 |
+
"eval_samples_per_second": 69.957,
|
| 565 |
+
"eval_steps_per_second": 1.134,
|
| 566 |
+
"step": 216
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 36.59,
|
| 570 |
+
"learning_rate": 9.259259259259259e-05,
|
| 571 |
+
"loss": 1.8048,
|
| 572 |
+
"step": 220
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 36.89,
|
| 576 |
+
"eval_accuracy": 0.5046296296296297,
|
| 577 |
+
"eval_f1": 0.4507112029285062,
|
| 578 |
+
"eval_loss": 1.8403947353363037,
|
| 579 |
+
"eval_precision": 0.4858612126346595,
|
| 580 |
+
"eval_recall": 0.5046296296296297,
|
| 581 |
+
"eval_runtime": 5.4983,
|
| 582 |
+
"eval_samples_per_second": 78.57,
|
| 583 |
+
"eval_steps_per_second": 1.273,
|
| 584 |
+
"step": 222
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 37.89,
|
| 588 |
+
"eval_accuracy": 0.5277777777777778,
|
| 589 |
+
"eval_f1": 0.48163822225958186,
|
| 590 |
+
"eval_loss": 1.7998918294906616,
|
| 591 |
+
"eval_precision": 0.5142116902603466,
|
| 592 |
+
"eval_recall": 0.5277777777777778,
|
| 593 |
+
"eval_runtime": 5.2197,
|
| 594 |
+
"eval_samples_per_second": 82.764,
|
| 595 |
+
"eval_steps_per_second": 1.341,
|
| 596 |
+
"step": 228
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 38.3,
|
| 600 |
+
"learning_rate": 9.074074074074075e-05,
|
| 601 |
+
"loss": 1.6862,
|
| 602 |
+
"step": 230
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 38.89,
|
| 606 |
+
"eval_accuracy": 0.5324074074074074,
|
| 607 |
+
"eval_f1": 0.48444518889171245,
|
| 608 |
+
"eval_loss": 1.7363009452819824,
|
| 609 |
+
"eval_precision": 0.5169324177278161,
|
| 610 |
+
"eval_recall": 0.5324074074074074,
|
| 611 |
+
"eval_runtime": 5.3984,
|
| 612 |
+
"eval_samples_per_second": 80.023,
|
| 613 |
+
"eval_steps_per_second": 1.297,
|
| 614 |
+
"step": 234
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 39.89,
|
| 618 |
+
"learning_rate": 8.888888888888888e-05,
|
| 619 |
+
"loss": 1.4545,
|
| 620 |
+
"step": 240
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 39.89,
|
| 624 |
+
"eval_accuracy": 0.5439814814814815,
|
| 625 |
+
"eval_f1": 0.4970594159719364,
|
| 626 |
+
"eval_loss": 1.7104405164718628,
|
| 627 |
+
"eval_precision": 0.5100423891967305,
|
| 628 |
+
"eval_recall": 0.5439814814814815,
|
| 629 |
+
"eval_runtime": 5.3694,
|
| 630 |
+
"eval_samples_per_second": 80.456,
|
| 631 |
+
"eval_steps_per_second": 1.304,
|
| 632 |
+
"step": 240
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 40.89,
|
| 636 |
+
"eval_accuracy": 0.5648148148148148,
|
| 637 |
+
"eval_f1": 0.5137970884972636,
|
| 638 |
+
"eval_loss": 1.6491522789001465,
|
| 639 |
+
"eval_precision": 0.523917294193656,
|
| 640 |
+
"eval_recall": 0.5648148148148148,
|
| 641 |
+
"eval_runtime": 5.3928,
|
| 642 |
+
"eval_samples_per_second": 80.107,
|
| 643 |
+
"eval_steps_per_second": 1.298,
|
| 644 |
+
"step": 246
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 41.59,
|
| 648 |
+
"learning_rate": 8.703703703703704e-05,
|
| 649 |
+
"loss": 1.4444,
|
| 650 |
+
"step": 250
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 41.89,
|
| 654 |
+
"eval_accuracy": 0.5671296296296297,
|
| 655 |
+
"eval_f1": 0.5260280139698915,
|
| 656 |
+
"eval_loss": 1.6076487302780151,
|
| 657 |
+
"eval_precision": 0.5329085789061826,
|
| 658 |
+
"eval_recall": 0.5671296296296297,
|
| 659 |
+
"eval_runtime": 5.3158,
|
| 660 |
+
"eval_samples_per_second": 81.268,
|
| 661 |
+
"eval_steps_per_second": 1.317,
|
| 662 |
+
"step": 252
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 42.89,
|
| 666 |
+
"eval_accuracy": 0.5740740740740741,
|
| 667 |
+
"eval_f1": 0.5423804527832623,
|
| 668 |
+
"eval_loss": 1.5784292221069336,
|
| 669 |
+
"eval_precision": 0.5708459252154017,
|
| 670 |
+
"eval_recall": 0.5740740740740741,
|
| 671 |
+
"eval_runtime": 5.2241,
|
| 672 |
+
"eval_samples_per_second": 82.694,
|
| 673 |
+
"eval_steps_per_second": 1.34,
|
| 674 |
+
"step": 258
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 43.3,
|
| 678 |
+
"learning_rate": 8.51851851851852e-05,
|
| 679 |
+
"loss": 1.3124,
|
| 680 |
+
"step": 260
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 43.89,
|
| 684 |
+
"eval_accuracy": 0.6018518518518519,
|
| 685 |
+
"eval_f1": 0.5618867514921587,
|
| 686 |
+
"eval_loss": 1.5258712768554688,
|
| 687 |
+
"eval_precision": 0.5977120457097308,
|
| 688 |
+
"eval_recall": 0.6018518518518519,
|
| 689 |
+
"eval_runtime": 5.4521,
|
| 690 |
+
"eval_samples_per_second": 79.236,
|
| 691 |
+
"eval_steps_per_second": 1.284,
|
| 692 |
+
"step": 264
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 44.89,
|
| 696 |
+
"learning_rate": 8.333333333333333e-05,
|
| 697 |
+
"loss": 1.1645,
|
| 698 |
+
"step": 270
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 44.89,
|
| 702 |
+
"eval_accuracy": 0.6180555555555556,
|
| 703 |
+
"eval_f1": 0.587977803961619,
|
| 704 |
+
"eval_loss": 1.481404423713684,
|
| 705 |
+
"eval_precision": 0.6033401199444866,
|
| 706 |
+
"eval_recall": 0.6180555555555556,
|
| 707 |
+
"eval_runtime": 5.2922,
|
| 708 |
+
"eval_samples_per_second": 81.629,
|
| 709 |
+
"eval_steps_per_second": 1.323,
|
| 710 |
+
"step": 270
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 45.89,
|
| 714 |
+
"eval_accuracy": 0.6087962962962963,
|
| 715 |
+
"eval_f1": 0.5803382659924391,
|
| 716 |
+
"eval_loss": 1.469708800315857,
|
| 717 |
+
"eval_precision": 0.6033107779207628,
|
| 718 |
+
"eval_recall": 0.6087962962962963,
|
| 719 |
+
"eval_runtime": 5.3039,
|
| 720 |
+
"eval_samples_per_second": 81.449,
|
| 721 |
+
"eval_steps_per_second": 1.32,
|
| 722 |
+
"step": 276
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 46.59,
|
| 726 |
+
"learning_rate": 8.148148148148149e-05,
|
| 727 |
+
"loss": 1.1307,
|
| 728 |
+
"step": 280
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 46.89,
|
| 732 |
+
"eval_accuracy": 0.6087962962962963,
|
| 733 |
+
"eval_f1": 0.5768532160244407,
|
| 734 |
+
"eval_loss": 1.4379969835281372,
|
| 735 |
+
"eval_precision": 0.6014549575028018,
|
| 736 |
+
"eval_recall": 0.6087962962962963,
|
| 737 |
+
"eval_runtime": 5.4401,
|
| 738 |
+
"eval_samples_per_second": 79.41,
|
| 739 |
+
"eval_steps_per_second": 1.287,
|
| 740 |
+
"step": 282
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 47.89,
|
| 744 |
+
"eval_accuracy": 0.6226851851851852,
|
| 745 |
+
"eval_f1": 0.5916934301381287,
|
| 746 |
+
"eval_loss": 1.3872352838516235,
|
| 747 |
+
"eval_precision": 0.6084938497179186,
|
| 748 |
+
"eval_recall": 0.6226851851851852,
|
| 749 |
+
"eval_runtime": 5.7913,
|
| 750 |
+
"eval_samples_per_second": 74.594,
|
| 751 |
+
"eval_steps_per_second": 1.209,
|
| 752 |
+
"step": 288
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 48.3,
|
| 756 |
+
"learning_rate": 7.962962962962962e-05,
|
| 757 |
+
"loss": 1.0347,
|
| 758 |
+
"step": 290
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 48.89,
|
| 762 |
+
"eval_accuracy": 0.6157407407407407,
|
| 763 |
+
"eval_f1": 0.5880203126612452,
|
| 764 |
+
"eval_loss": 1.3708983659744263,
|
| 765 |
+
"eval_precision": 0.6039183905119778,
|
| 766 |
+
"eval_recall": 0.6157407407407407,
|
| 767 |
+
"eval_runtime": 5.2614,
|
| 768 |
+
"eval_samples_per_second": 82.107,
|
| 769 |
+
"eval_steps_per_second": 1.33,
|
| 770 |
+
"step": 294
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 49.89,
|
| 774 |
+
"learning_rate": 7.777777777777778e-05,
|
| 775 |
+
"loss": 0.8962,
|
| 776 |
+
"step": 300
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 49.89,
|
| 780 |
+
"eval_accuracy": 0.6296296296296297,
|
| 781 |
+
"eval_f1": 0.605687298694788,
|
| 782 |
+
"eval_loss": 1.341522455215454,
|
| 783 |
+
"eval_precision": 0.612048881556709,
|
| 784 |
+
"eval_recall": 0.6296296296296297,
|
| 785 |
+
"eval_runtime": 5.311,
|
| 786 |
+
"eval_samples_per_second": 81.34,
|
| 787 |
+
"eval_steps_per_second": 1.318,
|
| 788 |
+
"step": 300
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 50.89,
|
| 792 |
+
"eval_accuracy": 0.6388888888888888,
|
| 793 |
+
"eval_f1": 0.613426108384686,
|
| 794 |
+
"eval_loss": 1.3290259838104248,
|
| 795 |
+
"eval_precision": 0.6327490606701418,
|
| 796 |
+
"eval_recall": 0.6388888888888888,
|
| 797 |
+
"eval_runtime": 5.2871,
|
| 798 |
+
"eval_samples_per_second": 81.708,
|
| 799 |
+
"eval_steps_per_second": 1.324,
|
| 800 |
+
"step": 306
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 51.59,
|
| 804 |
+
"learning_rate": 7.592592592592593e-05,
|
| 805 |
+
"loss": 0.8898,
|
| 806 |
+
"step": 310
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 51.89,
|
| 810 |
+
"eval_accuracy": 0.6388888888888888,
|
| 811 |
+
"eval_f1": 0.6119123977370672,
|
| 812 |
+
"eval_loss": 1.2836151123046875,
|
| 813 |
+
"eval_precision": 0.6191504139826349,
|
| 814 |
+
"eval_recall": 0.6388888888888888,
|
| 815 |
+
"eval_runtime": 5.3703,
|
| 816 |
+
"eval_samples_per_second": 80.442,
|
| 817 |
+
"eval_steps_per_second": 1.303,
|
| 818 |
+
"step": 312
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 52.89,
|
| 822 |
+
"eval_accuracy": 0.6412037037037037,
|
| 823 |
+
"eval_f1": 0.6162189940531424,
|
| 824 |
+
"eval_loss": 1.2664588689804077,
|
| 825 |
+
"eval_precision": 0.6185599459790397,
|
| 826 |
+
"eval_recall": 0.6412037037037037,
|
| 827 |
+
"eval_runtime": 5.3255,
|
| 828 |
+
"eval_samples_per_second": 81.119,
|
| 829 |
+
"eval_steps_per_second": 1.314,
|
| 830 |
+
"step": 318
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 53.3,
|
| 834 |
+
"learning_rate": 7.407407407407407e-05,
|
| 835 |
+
"loss": 0.7886,
|
| 836 |
+
"step": 320
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 53.89,
|
| 840 |
+
"eval_accuracy": 0.6550925925925926,
|
| 841 |
+
"eval_f1": 0.6318769738810363,
|
| 842 |
+
"eval_loss": 1.2272124290466309,
|
| 843 |
+
"eval_precision": 0.6430932223319198,
|
| 844 |
+
"eval_recall": 0.6550925925925926,
|
| 845 |
+
"eval_runtime": 6.4776,
|
| 846 |
+
"eval_samples_per_second": 66.692,
|
| 847 |
+
"eval_steps_per_second": 1.081,
|
| 848 |
+
"step": 324
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 54.89,
|
| 852 |
+
"learning_rate": 7.222222222222222e-05,
|
| 853 |
+
"loss": 0.6794,
|
| 854 |
+
"step": 330
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 54.89,
|
| 858 |
+
"eval_accuracy": 0.6805555555555556,
|
| 859 |
+
"eval_f1": 0.6628815346611416,
|
| 860 |
+
"eval_loss": 1.2144430875778198,
|
| 861 |
+
"eval_precision": 0.6643161507927962,
|
| 862 |
+
"eval_recall": 0.6805555555555556,
|
| 863 |
+
"eval_runtime": 5.3789,
|
| 864 |
+
"eval_samples_per_second": 80.314,
|
| 865 |
+
"eval_steps_per_second": 1.301,
|
| 866 |
+
"step": 330
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 55.89,
|
| 870 |
+
"eval_accuracy": 0.6805555555555556,
|
| 871 |
+
"eval_f1": 0.6641541104251447,
|
| 872 |
+
"eval_loss": 1.1816602945327759,
|
| 873 |
+
"eval_precision": 0.6665719090253448,
|
| 874 |
+
"eval_recall": 0.6805555555555556,
|
| 875 |
+
"eval_runtime": 5.3081,
|
| 876 |
+
"eval_samples_per_second": 81.385,
|
| 877 |
+
"eval_steps_per_second": 1.319,
|
| 878 |
+
"step": 336
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 56.59,
|
| 882 |
+
"learning_rate": 7.037037037037038e-05,
|
| 883 |
+
"loss": 0.6459,
|
| 884 |
+
"step": 340
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 56.89,
|
| 888 |
+
"eval_accuracy": 0.6782407407407407,
|
| 889 |
+
"eval_f1": 0.6573948843052861,
|
| 890 |
+
"eval_loss": 1.1702219247817993,
|
| 891 |
+
"eval_precision": 0.6591247168593658,
|
| 892 |
+
"eval_recall": 0.6782407407407407,
|
| 893 |
+
"eval_runtime": 5.3756,
|
| 894 |
+
"eval_samples_per_second": 80.363,
|
| 895 |
+
"eval_steps_per_second": 1.302,
|
| 896 |
+
"step": 342
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 57.89,
|
| 900 |
+
"eval_accuracy": 0.7037037037037037,
|
| 901 |
+
"eval_f1": 0.6882802756329267,
|
| 902 |
+
"eval_loss": 1.0946831703186035,
|
| 903 |
+
"eval_precision": 0.686333931300664,
|
| 904 |
+
"eval_recall": 0.7037037037037037,
|
| 905 |
+
"eval_runtime": 5.4261,
|
| 906 |
+
"eval_samples_per_second": 79.615,
|
| 907 |
+
"eval_steps_per_second": 1.29,
|
| 908 |
+
"step": 348
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 58.3,
|
| 912 |
+
"learning_rate": 6.851851851851852e-05,
|
| 913 |
+
"loss": 0.6075,
|
| 914 |
+
"step": 350
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 58.89,
|
| 918 |
+
"eval_accuracy": 0.7037037037037037,
|
| 919 |
+
"eval_f1": 0.6867332708223882,
|
| 920 |
+
"eval_loss": 1.1226900815963745,
|
| 921 |
+
"eval_precision": 0.6874024894506818,
|
| 922 |
+
"eval_recall": 0.7037037037037037,
|
| 923 |
+
"eval_runtime": 5.4706,
|
| 924 |
+
"eval_samples_per_second": 78.968,
|
| 925 |
+
"eval_steps_per_second": 1.28,
|
| 926 |
+
"step": 354
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 59.89,
|
| 930 |
+
"learning_rate": 6.666666666666667e-05,
|
| 931 |
+
"loss": 0.4979,
|
| 932 |
+
"step": 360
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 59.89,
|
| 936 |
+
"eval_accuracy": 0.7083333333333334,
|
| 937 |
+
"eval_f1": 0.6895357100839747,
|
| 938 |
+
"eval_loss": 1.0848513841629028,
|
| 939 |
+
"eval_precision": 0.6813335838104505,
|
| 940 |
+
"eval_recall": 0.7083333333333334,
|
| 941 |
+
"eval_runtime": 5.4609,
|
| 942 |
+
"eval_samples_per_second": 79.108,
|
| 943 |
+
"eval_steps_per_second": 1.282,
|
| 944 |
+
"step": 360
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 60.89,
|
| 948 |
+
"eval_accuracy": 0.7152777777777778,
|
| 949 |
+
"eval_f1": 0.6976241288914542,
|
| 950 |
+
"eval_loss": 1.0742223262786865,
|
| 951 |
+
"eval_precision": 0.6924067070864097,
|
| 952 |
+
"eval_recall": 0.7152777777777778,
|
| 953 |
+
"eval_runtime": 5.4024,
|
| 954 |
+
"eval_samples_per_second": 79.964,
|
| 955 |
+
"eval_steps_per_second": 1.296,
|
| 956 |
+
"step": 366
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 61.59,
|
| 960 |
+
"learning_rate": 6.481481481481482e-05,
|
| 961 |
+
"loss": 0.4895,
|
| 962 |
+
"step": 370
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 61.89,
|
| 966 |
+
"eval_accuracy": 0.7245370370370371,
|
| 967 |
+
"eval_f1": 0.7056673305111377,
|
| 968 |
+
"eval_loss": 1.0452089309692383,
|
| 969 |
+
"eval_precision": 0.7020110351433776,
|
| 970 |
+
"eval_recall": 0.7245370370370371,
|
| 971 |
+
"eval_runtime": 5.2426,
|
| 972 |
+
"eval_samples_per_second": 82.401,
|
| 973 |
+
"eval_steps_per_second": 1.335,
|
| 974 |
+
"step": 372
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 62.89,
|
| 978 |
+
"eval_accuracy": 0.7361111111111112,
|
| 979 |
+
"eval_f1": 0.7235022517584233,
|
| 980 |
+
"eval_loss": 1.0434988737106323,
|
| 981 |
+
"eval_precision": 0.7315692329774679,
|
| 982 |
+
"eval_recall": 0.7361111111111112,
|
| 983 |
+
"eval_runtime": 5.6115,
|
| 984 |
+
"eval_samples_per_second": 76.984,
|
| 985 |
+
"eval_steps_per_second": 1.247,
|
| 986 |
+
"step": 378
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 63.3,
|
| 990 |
+
"learning_rate": 6.296296296296296e-05,
|
| 991 |
+
"loss": 0.456,
|
| 992 |
+
"step": 380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 63.89,
|
| 996 |
+
"eval_accuracy": 0.6921296296296297,
|
| 997 |
+
"eval_f1": 0.6782660667203742,
|
| 998 |
+
"eval_loss": 1.0698424577713013,
|
| 999 |
+
"eval_precision": 0.6835014015139541,
|
| 1000 |
+
"eval_recall": 0.6921296296296297,
|
| 1001 |
+
"eval_runtime": 5.1579,
|
| 1002 |
+
"eval_samples_per_second": 83.755,
|
| 1003 |
+
"eval_steps_per_second": 1.357,
|
| 1004 |
+
"step": 384
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 64.89,
|
| 1008 |
+
"learning_rate": 6.111111111111112e-05,
|
| 1009 |
+
"loss": 0.3816,
|
| 1010 |
+
"step": 390
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 64.89,
|
| 1014 |
+
"eval_accuracy": 0.7222222222222222,
|
| 1015 |
+
"eval_f1": 0.7090977646443078,
|
| 1016 |
+
"eval_loss": 1.012607455253601,
|
| 1017 |
+
"eval_precision": 0.7063543756769308,
|
| 1018 |
+
"eval_recall": 0.7222222222222222,
|
| 1019 |
+
"eval_runtime": 5.3628,
|
| 1020 |
+
"eval_samples_per_second": 80.554,
|
| 1021 |
+
"eval_steps_per_second": 1.305,
|
| 1022 |
+
"step": 390
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 65.89,
|
| 1026 |
+
"eval_accuracy": 0.7361111111111112,
|
| 1027 |
+
"eval_f1": 0.7204764875345293,
|
| 1028 |
+
"eval_loss": 0.993401825428009,
|
| 1029 |
+
"eval_precision": 0.724681390825583,
|
| 1030 |
+
"eval_recall": 0.7361111111111112,
|
| 1031 |
+
"eval_runtime": 5.6989,
|
| 1032 |
+
"eval_samples_per_second": 75.804,
|
| 1033 |
+
"eval_steps_per_second": 1.228,
|
| 1034 |
+
"step": 396
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 66.59,
|
| 1038 |
+
"learning_rate": 5.925925925925926e-05,
|
| 1039 |
+
"loss": 0.3599,
|
| 1040 |
+
"step": 400
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 66.89,
|
| 1044 |
+
"eval_accuracy": 0.7291666666666666,
|
| 1045 |
+
"eval_f1": 0.7170196751234628,
|
| 1046 |
+
"eval_loss": 0.9959847927093506,
|
| 1047 |
+
"eval_precision": 0.7213039734393419,
|
| 1048 |
+
"eval_recall": 0.7291666666666666,
|
| 1049 |
+
"eval_runtime": 5.2019,
|
| 1050 |
+
"eval_samples_per_second": 83.046,
|
| 1051 |
+
"eval_steps_per_second": 1.346,
|
| 1052 |
+
"step": 402
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 67.89,
|
| 1056 |
+
"eval_accuracy": 0.7222222222222222,
|
| 1057 |
+
"eval_f1": 0.7086739406130538,
|
| 1058 |
+
"eval_loss": 1.0140923261642456,
|
| 1059 |
+
"eval_precision": 0.714832297403849,
|
| 1060 |
+
"eval_recall": 0.7222222222222222,
|
| 1061 |
+
"eval_runtime": 5.4428,
|
| 1062 |
+
"eval_samples_per_second": 79.371,
|
| 1063 |
+
"eval_steps_per_second": 1.286,
|
| 1064 |
+
"step": 408
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 68.3,
|
| 1068 |
+
"learning_rate": 5.740740740740741e-05,
|
| 1069 |
+
"loss": 0.3484,
|
| 1070 |
+
"step": 410
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 68.89,
|
| 1074 |
+
"eval_accuracy": 0.7222222222222222,
|
| 1075 |
+
"eval_f1": 0.7106977986015407,
|
| 1076 |
+
"eval_loss": 0.9933716058731079,
|
| 1077 |
+
"eval_precision": 0.7124795295102475,
|
| 1078 |
+
"eval_recall": 0.7222222222222222,
|
| 1079 |
+
"eval_runtime": 5.4357,
|
| 1080 |
+
"eval_samples_per_second": 79.474,
|
| 1081 |
+
"eval_steps_per_second": 1.288,
|
| 1082 |
+
"step": 414
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 69.89,
|
| 1086 |
+
"learning_rate": 5.555555555555556e-05,
|
| 1087 |
+
"loss": 0.2939,
|
| 1088 |
+
"step": 420
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 69.89,
|
| 1092 |
+
"eval_accuracy": 0.7430555555555556,
|
| 1093 |
+
"eval_f1": 0.7348772075580454,
|
| 1094 |
+
"eval_loss": 0.9834648370742798,
|
| 1095 |
+
"eval_precision": 0.7417468353179321,
|
| 1096 |
+
"eval_recall": 0.7430555555555556,
|
| 1097 |
+
"eval_runtime": 5.6077,
|
| 1098 |
+
"eval_samples_per_second": 77.037,
|
| 1099 |
+
"eval_steps_per_second": 1.248,
|
| 1100 |
+
"step": 420
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 70.89,
|
| 1104 |
+
"eval_accuracy": 0.7314814814814815,
|
| 1105 |
+
"eval_f1": 0.7216822341228574,
|
| 1106 |
+
"eval_loss": 0.9870407581329346,
|
| 1107 |
+
"eval_precision": 0.7274511197247954,
|
| 1108 |
+
"eval_recall": 0.7314814814814815,
|
| 1109 |
+
"eval_runtime": 5.4574,
|
| 1110 |
+
"eval_samples_per_second": 79.159,
|
| 1111 |
+
"eval_steps_per_second": 1.283,
|
| 1112 |
+
"step": 426
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 71.59,
|
| 1116 |
+
"learning_rate": 5.3703703703703704e-05,
|
| 1117 |
+
"loss": 0.285,
|
| 1118 |
+
"step": 430
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 71.89,
|
| 1122 |
+
"eval_accuracy": 0.7430555555555556,
|
| 1123 |
+
"eval_f1": 0.733989971528034,
|
| 1124 |
+
"eval_loss": 0.9656376242637634,
|
| 1125 |
+
"eval_precision": 0.741147872977627,
|
| 1126 |
+
"eval_recall": 0.7430555555555556,
|
| 1127 |
+
"eval_runtime": 5.203,
|
| 1128 |
+
"eval_samples_per_second": 83.03,
|
| 1129 |
+
"eval_steps_per_second": 1.345,
|
| 1130 |
+
"step": 432
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 72.89,
|
| 1134 |
+
"eval_accuracy": 0.7337962962962963,
|
| 1135 |
+
"eval_f1": 0.7266736305881797,
|
| 1136 |
+
"eval_loss": 0.9461933970451355,
|
| 1137 |
+
"eval_precision": 0.7320442158992043,
|
| 1138 |
+
"eval_recall": 0.7337962962962963,
|
| 1139 |
+
"eval_runtime": 8.4768,
|
| 1140 |
+
"eval_samples_per_second": 50.963,
|
| 1141 |
+
"eval_steps_per_second": 0.826,
|
| 1142 |
+
"step": 438
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 73.3,
|
| 1146 |
+
"learning_rate": 5.185185185185185e-05,
|
| 1147 |
+
"loss": 0.2463,
|
| 1148 |
+
"step": 440
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 73.89,
|
| 1152 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1153 |
+
"eval_f1": 0.7384341548610988,
|
| 1154 |
+
"eval_loss": 0.9513481855392456,
|
| 1155 |
+
"eval_precision": 0.7467304556246889,
|
| 1156 |
+
"eval_recall": 0.7453703703703703,
|
| 1157 |
+
"eval_runtime": 5.2401,
|
| 1158 |
+
"eval_samples_per_second": 82.442,
|
| 1159 |
+
"eval_steps_per_second": 1.336,
|
| 1160 |
+
"step": 444
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 74.89,
|
| 1164 |
+
"learning_rate": 5e-05,
|
| 1165 |
+
"loss": 0.2328,
|
| 1166 |
+
"step": 450
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 74.89,
|
| 1170 |
+
"eval_accuracy": 0.7361111111111112,
|
| 1171 |
+
"eval_f1": 0.7285971835253146,
|
| 1172 |
+
"eval_loss": 0.9334164261817932,
|
| 1173 |
+
"eval_precision": 0.7389054794152377,
|
| 1174 |
+
"eval_recall": 0.7361111111111112,
|
| 1175 |
+
"eval_runtime": 5.3561,
|
| 1176 |
+
"eval_samples_per_second": 80.656,
|
| 1177 |
+
"eval_steps_per_second": 1.307,
|
| 1178 |
+
"step": 450
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 75.89,
|
| 1182 |
+
"eval_accuracy": 0.7384259259259259,
|
| 1183 |
+
"eval_f1": 0.7291154917372571,
|
| 1184 |
+
"eval_loss": 0.9375342130661011,
|
| 1185 |
+
"eval_precision": 0.7278364301205459,
|
| 1186 |
+
"eval_recall": 0.7384259259259259,
|
| 1187 |
+
"eval_runtime": 5.6458,
|
| 1188 |
+
"eval_samples_per_second": 76.516,
|
| 1189 |
+
"eval_steps_per_second": 1.24,
|
| 1190 |
+
"step": 456
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 76.59,
|
| 1194 |
+
"learning_rate": 4.814814814814815e-05,
|
| 1195 |
+
"loss": 0.2208,
|
| 1196 |
+
"step": 460
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 76.89,
|
| 1200 |
+
"eval_accuracy": 0.7407407407407407,
|
| 1201 |
+
"eval_f1": 0.7321580282679521,
|
| 1202 |
+
"eval_loss": 0.9331722855567932,
|
| 1203 |
+
"eval_precision": 0.7356617662856251,
|
| 1204 |
+
"eval_recall": 0.7407407407407407,
|
| 1205 |
+
"eval_runtime": 5.6602,
|
| 1206 |
+
"eval_samples_per_second": 76.322,
|
| 1207 |
+
"eval_steps_per_second": 1.237,
|
| 1208 |
+
"step": 462
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 77.89,
|
| 1212 |
+
"eval_accuracy": 0.7384259259259259,
|
| 1213 |
+
"eval_f1": 0.7345507865669115,
|
| 1214 |
+
"eval_loss": 0.9407795071601868,
|
| 1215 |
+
"eval_precision": 0.740572946269861,
|
| 1216 |
+
"eval_recall": 0.7384259259259259,
|
| 1217 |
+
"eval_runtime": 6.1079,
|
| 1218 |
+
"eval_samples_per_second": 70.728,
|
| 1219 |
+
"eval_steps_per_second": 1.146,
|
| 1220 |
+
"step": 468
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 78.3,
|
| 1224 |
+
"learning_rate": 4.6296296296296294e-05,
|
| 1225 |
+
"loss": 0.2177,
|
| 1226 |
+
"step": 470
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 78.89,
|
| 1230 |
+
"eval_accuracy": 0.7222222222222222,
|
| 1231 |
+
"eval_f1": 0.713643812457414,
|
| 1232 |
+
"eval_loss": 0.9059470891952515,
|
| 1233 |
+
"eval_precision": 0.7182721947191242,
|
| 1234 |
+
"eval_recall": 0.7222222222222222,
|
| 1235 |
+
"eval_runtime": 5.5576,
|
| 1236 |
+
"eval_samples_per_second": 77.731,
|
| 1237 |
+
"eval_steps_per_second": 1.26,
|
| 1238 |
+
"step": 474
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 79.89,
|
| 1242 |
+
"learning_rate": 4.444444444444444e-05,
|
| 1243 |
+
"loss": 0.1734,
|
| 1244 |
+
"step": 480
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 79.89,
|
| 1248 |
+
"eval_accuracy": 0.7314814814814815,
|
| 1249 |
+
"eval_f1": 0.7256550902066806,
|
| 1250 |
+
"eval_loss": 0.9517382383346558,
|
| 1251 |
+
"eval_precision": 0.7371182560572754,
|
| 1252 |
+
"eval_recall": 0.7314814814814815,
|
| 1253 |
+
"eval_runtime": 5.7365,
|
| 1254 |
+
"eval_samples_per_second": 75.308,
|
| 1255 |
+
"eval_steps_per_second": 1.22,
|
| 1256 |
+
"step": 480
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 80.89,
|
| 1260 |
+
"eval_accuracy": 0.7523148148148148,
|
| 1261 |
+
"eval_f1": 0.7423879522381177,
|
| 1262 |
+
"eval_loss": 0.9062556624412537,
|
| 1263 |
+
"eval_precision": 0.7462328400927609,
|
| 1264 |
+
"eval_recall": 0.7523148148148148,
|
| 1265 |
+
"eval_runtime": 5.6093,
|
| 1266 |
+
"eval_samples_per_second": 77.015,
|
| 1267 |
+
"eval_steps_per_second": 1.248,
|
| 1268 |
+
"step": 486
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 81.59,
|
| 1272 |
+
"learning_rate": 4.25925925925926e-05,
|
| 1273 |
+
"loss": 0.1791,
|
| 1274 |
+
"step": 490
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 81.89,
|
| 1278 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1279 |
+
"eval_f1": 0.7386111806656375,
|
| 1280 |
+
"eval_loss": 0.9171371459960938,
|
| 1281 |
+
"eval_precision": 0.7460586842065221,
|
| 1282 |
+
"eval_recall": 0.7453703703703703,
|
| 1283 |
+
"eval_runtime": 6.3994,
|
| 1284 |
+
"eval_samples_per_second": 67.506,
|
| 1285 |
+
"eval_steps_per_second": 1.094,
|
| 1286 |
+
"step": 492
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 82.89,
|
| 1290 |
+
"eval_accuracy": 0.7523148148148148,
|
| 1291 |
+
"eval_f1": 0.7485400201597975,
|
| 1292 |
+
"eval_loss": 0.8845748901367188,
|
| 1293 |
+
"eval_precision": 0.7561086436421744,
|
| 1294 |
+
"eval_recall": 0.7523148148148148,
|
| 1295 |
+
"eval_runtime": 5.4558,
|
| 1296 |
+
"eval_samples_per_second": 79.181,
|
| 1297 |
+
"eval_steps_per_second": 1.283,
|
| 1298 |
+
"step": 498
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 83.3,
|
| 1302 |
+
"learning_rate": 4.0740740740740745e-05,
|
| 1303 |
+
"loss": 0.1681,
|
| 1304 |
+
"step": 500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 83.89,
|
| 1308 |
+
"eval_accuracy": 0.7384259259259259,
|
| 1309 |
+
"eval_f1": 0.732043113565851,
|
| 1310 |
+
"eval_loss": 0.8870928883552551,
|
| 1311 |
+
"eval_precision": 0.743089114195319,
|
| 1312 |
+
"eval_recall": 0.7384259259259259,
|
| 1313 |
+
"eval_runtime": 5.6826,
|
| 1314 |
+
"eval_samples_per_second": 76.021,
|
| 1315 |
+
"eval_steps_per_second": 1.232,
|
| 1316 |
+
"step": 504
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 84.89,
|
| 1320 |
+
"learning_rate": 3.888888888888889e-05,
|
| 1321 |
+
"loss": 0.1573,
|
| 1322 |
+
"step": 510
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 84.89,
|
| 1326 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1327 |
+
"eval_f1": 0.7394662768116576,
|
| 1328 |
+
"eval_loss": 0.9117562174797058,
|
| 1329 |
+
"eval_precision": 0.7473985610054007,
|
| 1330 |
+
"eval_recall": 0.7453703703703703,
|
| 1331 |
+
"eval_runtime": 5.7055,
|
| 1332 |
+
"eval_samples_per_second": 75.717,
|
| 1333 |
+
"eval_steps_per_second": 1.227,
|
| 1334 |
+
"step": 510
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 85.89,
|
| 1338 |
+
"eval_accuracy": 0.7407407407407407,
|
| 1339 |
+
"eval_f1": 0.7365532820392154,
|
| 1340 |
+
"eval_loss": 0.9005970358848572,
|
| 1341 |
+
"eval_precision": 0.7431722449551572,
|
| 1342 |
+
"eval_recall": 0.7407407407407407,
|
| 1343 |
+
"eval_runtime": 5.5008,
|
| 1344 |
+
"eval_samples_per_second": 78.534,
|
| 1345 |
+
"eval_steps_per_second": 1.273,
|
| 1346 |
+
"step": 516
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 86.59,
|
| 1350 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 1351 |
+
"loss": 0.1439,
|
| 1352 |
+
"step": 520
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 86.89,
|
| 1356 |
+
"eval_accuracy": 0.7615740740740741,
|
| 1357 |
+
"eval_f1": 0.7579475458895545,
|
| 1358 |
+
"eval_loss": 0.8702595829963684,
|
| 1359 |
+
"eval_precision": 0.7692736377187624,
|
| 1360 |
+
"eval_recall": 0.7615740740740741,
|
| 1361 |
+
"eval_runtime": 5.4161,
|
| 1362 |
+
"eval_samples_per_second": 79.762,
|
| 1363 |
+
"eval_steps_per_second": 1.292,
|
| 1364 |
+
"step": 522
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 87.89,
|
| 1368 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1369 |
+
"eval_f1": 0.7400568258235957,
|
| 1370 |
+
"eval_loss": 0.8988061547279358,
|
| 1371 |
+
"eval_precision": 0.756961704237031,
|
| 1372 |
+
"eval_recall": 0.7453703703703703,
|
| 1373 |
+
"eval_runtime": 6.1896,
|
| 1374 |
+
"eval_samples_per_second": 69.795,
|
| 1375 |
+
"eval_steps_per_second": 1.131,
|
| 1376 |
+
"step": 528
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 88.3,
|
| 1380 |
+
"learning_rate": 3.518518518518519e-05,
|
| 1381 |
+
"loss": 0.1362,
|
| 1382 |
+
"step": 530
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 88.89,
|
| 1386 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1387 |
+
"eval_f1": 0.7395910859987699,
|
| 1388 |
+
"eval_loss": 0.9234440326690674,
|
| 1389 |
+
"eval_precision": 0.7476805026036663,
|
| 1390 |
+
"eval_recall": 0.7453703703703703,
|
| 1391 |
+
"eval_runtime": 5.5214,
|
| 1392 |
+
"eval_samples_per_second": 78.241,
|
| 1393 |
+
"eval_steps_per_second": 1.268,
|
| 1394 |
+
"step": 534
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 89.89,
|
| 1398 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1399 |
+
"loss": 0.1249,
|
| 1400 |
+
"step": 540
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 89.89,
|
| 1404 |
+
"eval_accuracy": 0.75,
|
| 1405 |
+
"eval_f1": 0.7425364320908299,
|
| 1406 |
+
"eval_loss": 0.8859997391700745,
|
| 1407 |
+
"eval_precision": 0.7472920891857668,
|
| 1408 |
+
"eval_recall": 0.75,
|
| 1409 |
+
"eval_runtime": 5.5446,
|
| 1410 |
+
"eval_samples_per_second": 77.914,
|
| 1411 |
+
"eval_steps_per_second": 1.262,
|
| 1412 |
+
"step": 540
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 90.89,
|
| 1416 |
+
"eval_accuracy": 0.7546296296296297,
|
| 1417 |
+
"eval_f1": 0.7513210643679686,
|
| 1418 |
+
"eval_loss": 0.8607540726661682,
|
| 1419 |
+
"eval_precision": 0.7600931860627275,
|
| 1420 |
+
"eval_recall": 0.7546296296296297,
|
| 1421 |
+
"eval_runtime": 5.3436,
|
| 1422 |
+
"eval_samples_per_second": 80.844,
|
| 1423 |
+
"eval_steps_per_second": 1.31,
|
| 1424 |
+
"step": 546
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 91.59,
|
| 1428 |
+
"learning_rate": 3.148148148148148e-05,
|
| 1429 |
+
"loss": 0.1264,
|
| 1430 |
+
"step": 550
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 91.89,
|
| 1434 |
+
"eval_accuracy": 0.7592592592592593,
|
| 1435 |
+
"eval_f1": 0.755976727084107,
|
| 1436 |
+
"eval_loss": 0.8870556950569153,
|
| 1437 |
+
"eval_precision": 0.7639504307480309,
|
| 1438 |
+
"eval_recall": 0.7592592592592593,
|
| 1439 |
+
"eval_runtime": 5.4043,
|
| 1440 |
+
"eval_samples_per_second": 79.937,
|
| 1441 |
+
"eval_steps_per_second": 1.295,
|
| 1442 |
+
"step": 552
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 92.89,
|
| 1446 |
+
"eval_accuracy": 0.7638888888888888,
|
| 1447 |
+
"eval_f1": 0.7599096471224447,
|
| 1448 |
+
"eval_loss": 0.8431653380393982,
|
| 1449 |
+
"eval_precision": 0.7726915475071081,
|
| 1450 |
+
"eval_recall": 0.7638888888888888,
|
| 1451 |
+
"eval_runtime": 5.4755,
|
| 1452 |
+
"eval_samples_per_second": 78.897,
|
| 1453 |
+
"eval_steps_per_second": 1.278,
|
| 1454 |
+
"step": 558
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 93.3,
|
| 1458 |
+
"learning_rate": 2.962962962962963e-05,
|
| 1459 |
+
"loss": 0.1201,
|
| 1460 |
+
"step": 560
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 93.89,
|
| 1464 |
+
"eval_accuracy": 0.7638888888888888,
|
| 1465 |
+
"eval_f1": 0.7568888380506066,
|
| 1466 |
+
"eval_loss": 0.8654246926307678,
|
| 1467 |
+
"eval_precision": 0.7697564792814707,
|
| 1468 |
+
"eval_recall": 0.7638888888888888,
|
| 1469 |
+
"eval_runtime": 6.2851,
|
| 1470 |
+
"eval_samples_per_second": 68.734,
|
| 1471 |
+
"eval_steps_per_second": 1.114,
|
| 1472 |
+
"step": 564
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 94.89,
|
| 1476 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1477 |
+
"loss": 0.1117,
|
| 1478 |
+
"step": 570
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 94.89,
|
| 1482 |
+
"eval_accuracy": 0.7453703703703703,
|
| 1483 |
+
"eval_f1": 0.741519942517561,
|
| 1484 |
+
"eval_loss": 0.8856301307678223,
|
| 1485 |
+
"eval_precision": 0.7568693783641538,
|
| 1486 |
+
"eval_recall": 0.7453703703703703,
|
| 1487 |
+
"eval_runtime": 5.3442,
|
| 1488 |
+
"eval_samples_per_second": 80.835,
|
| 1489 |
+
"eval_steps_per_second": 1.31,
|
| 1490 |
+
"step": 570
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 95.89,
|
| 1494 |
+
"eval_accuracy": 0.7546296296296297,
|
| 1495 |
+
"eval_f1": 0.7535192525414777,
|
| 1496 |
+
"eval_loss": 0.8668476939201355,
|
| 1497 |
+
"eval_precision": 0.7686452769477832,
|
| 1498 |
+
"eval_recall": 0.7546296296296297,
|
| 1499 |
+
"eval_runtime": 5.3944,
|
| 1500 |
+
"eval_samples_per_second": 80.082,
|
| 1501 |
+
"eval_steps_per_second": 1.298,
|
| 1502 |
+
"step": 576
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 96.59,
|
| 1506 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 1507 |
+
"loss": 0.1128,
|
| 1508 |
+
"step": 580
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 96.89,
|
| 1512 |
+
"eval_accuracy": 0.7662037037037037,
|
| 1513 |
+
"eval_f1": 0.7618510413877603,
|
| 1514 |
+
"eval_loss": 0.8629916310310364,
|
| 1515 |
+
"eval_precision": 0.7697577256793718,
|
| 1516 |
+
"eval_recall": 0.7662037037037037,
|
| 1517 |
+
"eval_runtime": 5.4335,
|
| 1518 |
+
"eval_samples_per_second": 79.506,
|
| 1519 |
+
"eval_steps_per_second": 1.288,
|
| 1520 |
+
"step": 582
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 97.89,
|
| 1524 |
+
"eval_accuracy": 0.7731481481481481,
|
| 1525 |
+
"eval_f1": 0.7696239297314015,
|
| 1526 |
+
"eval_loss": 0.8551383018493652,
|
| 1527 |
+
"eval_precision": 0.7826245726036102,
|
| 1528 |
+
"eval_recall": 0.7731481481481481,
|
| 1529 |
+
"eval_runtime": 5.1954,
|
| 1530 |
+
"eval_samples_per_second": 83.151,
|
| 1531 |
+
"eval_steps_per_second": 1.347,
|
| 1532 |
+
"step": 588
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 98.3,
|
| 1536 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 1537 |
+
"loss": 0.1155,
|
| 1538 |
+
"step": 590
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 98.89,
|
| 1542 |
+
"eval_accuracy": 0.7708333333333334,
|
| 1543 |
+
"eval_f1": 0.7643091084212846,
|
| 1544 |
+
"eval_loss": 0.8697354793548584,
|
| 1545 |
+
"eval_precision": 0.7738208157556675,
|
| 1546 |
+
"eval_recall": 0.7708333333333334,
|
| 1547 |
+
"eval_runtime": 5.3875,
|
| 1548 |
+
"eval_samples_per_second": 80.186,
|
| 1549 |
+
"eval_steps_per_second": 1.299,
|
| 1550 |
+
"step": 594
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 99.89,
|
| 1554 |
+
"learning_rate": 2.222222222222222e-05,
|
| 1555 |
+
"loss": 0.0987,
|
| 1556 |
+
"step": 600
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 99.89,
|
| 1560 |
+
"eval_accuracy": 0.7546296296296297,
|
| 1561 |
+
"eval_f1": 0.7483805060483262,
|
| 1562 |
+
"eval_loss": 0.8613447546958923,
|
| 1563 |
+
"eval_precision": 0.7517944160282697,
|
| 1564 |
+
"eval_recall": 0.7546296296296297,
|
| 1565 |
+
"eval_runtime": 5.9006,
|
| 1566 |
+
"eval_samples_per_second": 73.213,
|
| 1567 |
+
"eval_steps_per_second": 1.186,
|
| 1568 |
+
"step": 600
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 100.89,
|
| 1572 |
+
"eval_accuracy": 0.7569444444444444,
|
| 1573 |
+
"eval_f1": 0.7524452878233941,
|
| 1574 |
+
"eval_loss": 0.8742324113845825,
|
| 1575 |
+
"eval_precision": 0.7596693467798895,
|
| 1576 |
+
"eval_recall": 0.7569444444444444,
|
| 1577 |
+
"eval_runtime": 5.41,
|
| 1578 |
+
"eval_samples_per_second": 79.853,
|
| 1579 |
+
"eval_steps_per_second": 1.294,
|
| 1580 |
+
"step": 606
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 101.59,
|
| 1584 |
+
"learning_rate": 2.0370370370370372e-05,
|
| 1585 |
+
"loss": 0.1063,
|
| 1586 |
+
"step": 610
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 101.89,
|
| 1590 |
+
"eval_accuracy": 0.7754629629629629,
|
| 1591 |
+
"eval_f1": 0.771150415023082,
|
| 1592 |
+
"eval_loss": 0.8497992157936096,
|
| 1593 |
+
"eval_precision": 0.7807047130932955,
|
| 1594 |
+
"eval_recall": 0.7754629629629629,
|
| 1595 |
+
"eval_runtime": 5.3692,
|
| 1596 |
+
"eval_samples_per_second": 80.459,
|
| 1597 |
+
"eval_steps_per_second": 1.304,
|
| 1598 |
+
"step": 612
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 102.89,
|
| 1602 |
+
"eval_accuracy": 0.7708333333333334,
|
| 1603 |
+
"eval_f1": 0.765482842949022,
|
| 1604 |
+
"eval_loss": 0.8556762933731079,
|
| 1605 |
+
"eval_precision": 0.7749402393139675,
|
| 1606 |
+
"eval_recall": 0.7708333333333334,
|
| 1607 |
+
"eval_runtime": 5.3853,
|
| 1608 |
+
"eval_samples_per_second": 80.218,
|
| 1609 |
+
"eval_steps_per_second": 1.3,
|
| 1610 |
+
"step": 618
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 103.3,
|
| 1614 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1615 |
+
"loss": 0.097,
|
| 1616 |
+
"step": 620
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 103.89,
|
| 1620 |
+
"eval_accuracy": 0.7546296296296297,
|
| 1621 |
+
"eval_f1": 0.7526752444102988,
|
| 1622 |
+
"eval_loss": 0.8763903975486755,
|
| 1623 |
+
"eval_precision": 0.7633836255286668,
|
| 1624 |
+
"eval_recall": 0.7546296296296297,
|
| 1625 |
+
"eval_runtime": 5.3868,
|
| 1626 |
+
"eval_samples_per_second": 80.196,
|
| 1627 |
+
"eval_steps_per_second": 1.299,
|
| 1628 |
+
"step": 624
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 104.89,
|
| 1632 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1633 |
+
"loss": 0.0947,
|
| 1634 |
+
"step": 630
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 104.89,
|
| 1638 |
+
"eval_accuracy": 0.7615740740740741,
|
| 1639 |
+
"eval_f1": 0.7572102102626569,
|
| 1640 |
+
"eval_loss": 0.8676894903182983,
|
| 1641 |
+
"eval_precision": 0.7628127026058086,
|
| 1642 |
+
"eval_recall": 0.7615740740740741,
|
| 1643 |
+
"eval_runtime": 5.3643,
|
| 1644 |
+
"eval_samples_per_second": 80.532,
|
| 1645 |
+
"eval_steps_per_second": 1.305,
|
| 1646 |
+
"step": 630
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 105.89,
|
| 1650 |
+
"eval_accuracy": 0.75,
|
| 1651 |
+
"eval_f1": 0.7468928854511258,
|
| 1652 |
+
"eval_loss": 0.8909400701522827,
|
| 1653 |
+
"eval_precision": 0.7614134069792408,
|
| 1654 |
+
"eval_recall": 0.75,
|
| 1655 |
+
"eval_runtime": 5.5853,
|
| 1656 |
+
"eval_samples_per_second": 77.345,
|
| 1657 |
+
"eval_steps_per_second": 1.253,
|
| 1658 |
+
"step": 636
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 106.59,
|
| 1662 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1663 |
+
"loss": 0.1013,
|
| 1664 |
+
"step": 640
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 106.89,
|
| 1668 |
+
"eval_accuracy": 0.7638888888888888,
|
| 1669 |
+
"eval_f1": 0.7580224420360193,
|
| 1670 |
+
"eval_loss": 0.8282936811447144,
|
| 1671 |
+
"eval_precision": 0.7620546282752422,
|
| 1672 |
+
"eval_recall": 0.7638888888888888,
|
| 1673 |
+
"eval_runtime": 5.2557,
|
| 1674 |
+
"eval_samples_per_second": 82.196,
|
| 1675 |
+
"eval_steps_per_second": 1.332,
|
| 1676 |
+
"step": 642
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 107.89,
|
| 1680 |
+
"eval_accuracy": 0.7662037037037037,
|
| 1681 |
+
"eval_f1": 0.7651182502225393,
|
| 1682 |
+
"eval_loss": 0.8471357822418213,
|
| 1683 |
+
"eval_precision": 0.7863882995143683,
|
| 1684 |
+
"eval_recall": 0.7662037037037037,
|
| 1685 |
+
"eval_runtime": 5.3523,
|
| 1686 |
+
"eval_samples_per_second": 80.713,
|
| 1687 |
+
"eval_steps_per_second": 1.308,
|
| 1688 |
+
"step": 648
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 108.3,
|
| 1692 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1693 |
+
"loss": 0.0963,
|
| 1694 |
+
"step": 650
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 108.89,
|
| 1698 |
+
"eval_accuracy": 0.7592592592592593,
|
| 1699 |
+
"eval_f1": 0.755842788877039,
|
| 1700 |
+
"eval_loss": 0.8653424382209778,
|
| 1701 |
+
"eval_precision": 0.7701441521884681,
|
| 1702 |
+
"eval_recall": 0.7592592592592593,
|
| 1703 |
+
"eval_runtime": 5.2145,
|
| 1704 |
+
"eval_samples_per_second": 82.846,
|
| 1705 |
+
"eval_steps_per_second": 1.342,
|
| 1706 |
+
"step": 654
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 109.89,
|
| 1710 |
+
"learning_rate": 1.111111111111111e-05,
|
| 1711 |
+
"loss": 0.0874,
|
| 1712 |
+
"step": 660
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 109.89,
|
| 1716 |
+
"eval_accuracy": 0.7731481481481481,
|
| 1717 |
+
"eval_f1": 0.7691684134995852,
|
| 1718 |
+
"eval_loss": 0.8479176759719849,
|
| 1719 |
+
"eval_precision": 0.7834307987925804,
|
| 1720 |
+
"eval_recall": 0.7731481481481481,
|
| 1721 |
+
"eval_runtime": 5.3059,
|
| 1722 |
+
"eval_samples_per_second": 81.418,
|
| 1723 |
+
"eval_steps_per_second": 1.319,
|
| 1724 |
+
"step": 660
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 110.89,
|
| 1728 |
+
"eval_accuracy": 0.7638888888888888,
|
| 1729 |
+
"eval_f1": 0.7620275713301728,
|
| 1730 |
+
"eval_loss": 0.858402669429779,
|
| 1731 |
+
"eval_precision": 0.7719082893052805,
|
| 1732 |
+
"eval_recall": 0.7638888888888888,
|
| 1733 |
+
"eval_runtime": 6.7662,
|
| 1734 |
+
"eval_samples_per_second": 63.847,
|
| 1735 |
+
"eval_steps_per_second": 1.035,
|
| 1736 |
+
"step": 666
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 111.59,
|
| 1740 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1741 |
+
"loss": 0.0876,
|
| 1742 |
+
"step": 670
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 111.89,
|
| 1746 |
+
"eval_accuracy": 0.7615740740740741,
|
| 1747 |
+
"eval_f1": 0.7550117078450348,
|
| 1748 |
+
"eval_loss": 0.8713568449020386,
|
| 1749 |
+
"eval_precision": 0.7600458540847742,
|
| 1750 |
+
"eval_recall": 0.7615740740740741,
|
| 1751 |
+
"eval_runtime": 5.3309,
|
| 1752 |
+
"eval_samples_per_second": 81.037,
|
| 1753 |
+
"eval_steps_per_second": 1.313,
|
| 1754 |
+
"step": 672
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 112.89,
|
| 1758 |
+
"eval_accuracy": 0.7731481481481481,
|
| 1759 |
+
"eval_f1": 0.77268516651141,
|
| 1760 |
+
"eval_loss": 0.8509048223495483,
|
| 1761 |
+
"eval_precision": 0.784707905641461,
|
| 1762 |
+
"eval_recall": 0.7731481481481481,
|
| 1763 |
+
"eval_runtime": 5.3741,
|
| 1764 |
+
"eval_samples_per_second": 80.385,
|
| 1765 |
+
"eval_steps_per_second": 1.303,
|
| 1766 |
+
"step": 678
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 113.3,
|
| 1770 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 1771 |
+
"loss": 0.0974,
|
| 1772 |
+
"step": 680
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 113.89,
|
| 1776 |
+
"eval_accuracy": 0.7685185185185185,
|
| 1777 |
+
"eval_f1": 0.7647850826351645,
|
| 1778 |
+
"eval_loss": 0.8688226342201233,
|
| 1779 |
+
"eval_precision": 0.7741100821185434,
|
| 1780 |
+
"eval_recall": 0.7685185185185185,
|
| 1781 |
+
"eval_runtime": 5.3672,
|
| 1782 |
+
"eval_samples_per_second": 80.49,
|
| 1783 |
+
"eval_steps_per_second": 1.304,
|
| 1784 |
+
"step": 684
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 114.89,
|
| 1788 |
+
"learning_rate": 5.555555555555555e-06,
|
| 1789 |
+
"loss": 0.0869,
|
| 1790 |
+
"step": 690
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 114.89,
|
| 1794 |
+
"eval_accuracy": 0.7847222222222222,
|
| 1795 |
+
"eval_f1": 0.7793954933888979,
|
| 1796 |
+
"eval_loss": 0.8590295314788818,
|
| 1797 |
+
"eval_precision": 0.7931805357527522,
|
| 1798 |
+
"eval_recall": 0.7847222222222222,
|
| 1799 |
+
"eval_runtime": 5.2639,
|
| 1800 |
+
"eval_samples_per_second": 82.069,
|
| 1801 |
+
"eval_steps_per_second": 1.33,
|
| 1802 |
+
"step": 690
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 115.89,
|
| 1806 |
+
"eval_accuracy": 0.7592592592592593,
|
| 1807 |
+
"eval_f1": 0.7578890504066979,
|
| 1808 |
+
"eval_loss": 0.8686888217926025,
|
| 1809 |
+
"eval_precision": 0.7702857997814966,
|
| 1810 |
+
"eval_recall": 0.7592592592592593,
|
| 1811 |
+
"eval_runtime": 5.3584,
|
| 1812 |
+
"eval_samples_per_second": 80.621,
|
| 1813 |
+
"eval_steps_per_second": 1.306,
|
| 1814 |
+
"step": 696
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 116.59,
|
| 1818 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1819 |
+
"loss": 0.0877,
|
| 1820 |
+
"step": 700
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 116.89,
|
| 1824 |
+
"eval_accuracy": 0.7592592592592593,
|
| 1825 |
+
"eval_f1": 0.7554023755308449,
|
| 1826 |
+
"eval_loss": 0.8734990358352661,
|
| 1827 |
+
"eval_precision": 0.7698092065289778,
|
| 1828 |
+
"eval_recall": 0.7592592592592593,
|
| 1829 |
+
"eval_runtime": 5.4003,
|
| 1830 |
+
"eval_samples_per_second": 79.996,
|
| 1831 |
+
"eval_steps_per_second": 1.296,
|
| 1832 |
+
"step": 702
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 117.89,
|
| 1836 |
+
"eval_accuracy": 0.7546296296296297,
|
| 1837 |
+
"eval_f1": 0.7517939196845534,
|
| 1838 |
+
"eval_loss": 0.8566460609436035,
|
| 1839 |
+
"eval_precision": 0.7732181508714738,
|
| 1840 |
+
"eval_recall": 0.7546296296296297,
|
| 1841 |
+
"eval_runtime": 5.657,
|
| 1842 |
+
"eval_samples_per_second": 76.365,
|
| 1843 |
+
"eval_steps_per_second": 1.237,
|
| 1844 |
+
"step": 708
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 118.3,
|
| 1848 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 1849 |
+
"loss": 0.0883,
|
| 1850 |
+
"step": 710
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 118.89,
|
| 1854 |
+
"eval_accuracy": 0.7569444444444444,
|
| 1855 |
+
"eval_f1": 0.7525041374626477,
|
| 1856 |
+
"eval_loss": 0.8681396245956421,
|
| 1857 |
+
"eval_precision": 0.759078097897646,
|
| 1858 |
+
"eval_recall": 0.7569444444444444,
|
| 1859 |
+
"eval_runtime": 5.3224,
|
| 1860 |
+
"eval_samples_per_second": 81.166,
|
| 1861 |
+
"eval_steps_per_second": 1.315,
|
| 1862 |
+
"step": 714
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 119.89,
|
| 1866 |
+
"learning_rate": 0.0,
|
| 1867 |
+
"loss": 0.0762,
|
| 1868 |
+
"step": 720
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 119.89,
|
| 1872 |
+
"eval_accuracy": 0.7754629629629629,
|
| 1873 |
+
"eval_f1": 0.7676128880040883,
|
| 1874 |
+
"eval_loss": 0.8507534265518188,
|
| 1875 |
+
"eval_precision": 0.7715337787579363,
|
| 1876 |
+
"eval_recall": 0.7754629629629629,
|
| 1877 |
+
"eval_runtime": 5.389,
|
| 1878 |
+
"eval_samples_per_second": 80.163,
|
| 1879 |
+
"eval_steps_per_second": 1.299,
|
| 1880 |
+
"step": 720
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 119.89,
|
| 1884 |
+
"step": 720,
|
| 1885 |
+
"total_flos": 2.909790831021355e+18,
|
| 1886 |
+
"train_loss": 1.1563791312277316,
|
| 1887 |
+
"train_runtime": 2067.6252,
|
| 1888 |
+
"train_samples_per_second": 100.289,
|
| 1889 |
+
"train_steps_per_second": 0.348
|
| 1890 |
}
|
| 1891 |
],
|
| 1892 |
+
"max_steps": 720,
|
| 1893 |
+
"num_train_epochs": 120,
|
| 1894 |
+
"total_flos": 2.909790831021355e+18,
|
| 1895 |
"trial_name": null,
|
| 1896 |
"trial_params": null
|
| 1897 |
}
|