End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +5 -5
- trainer_state.json +56 -332
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples":
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 253.1309051513672,
|
| 5 |
+
"eval_runtime": 2.6357,
|
| 6 |
+
"eval_samples": 176,
|
| 7 |
+
"eval_samples_per_second": 66.774,
|
| 8 |
+
"eval_steps_per_second": 1.138,
|
| 9 |
+
"train_loss": 348.7352382114955,
|
| 10 |
+
"train_runtime": 184.625,
|
| 11 |
+
"train_samples": 877,
|
| 12 |
+
"train_samples_per_second": 14.251,
|
| 13 |
+
"train_steps_per_second": 0.455
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 253.1309051513672,
|
| 5 |
+
"eval_runtime": 2.6357,
|
| 6 |
+
"eval_samples": 176,
|
| 7 |
+
"eval_samples_per_second": 66.774,
|
| 8 |
+
"eval_steps_per_second": 1.138
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 348.7352382114955,
|
| 4 |
+
"train_runtime": 184.625,
|
| 5 |
+
"train_samples": 877,
|
| 6 |
+
"train_samples_per_second": 14.251,
|
| 7 |
+
"train_steps_per_second": 0.455
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -3,378 +3,102 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.17,
|
| 25 |
-
"learning_rate": 4.444444444444444e-06,
|
| 26 |
-
"loss": 96.9119,
|
| 27 |
-
"step": 30
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.22,
|
| 31 |
-
"learning_rate": 5.925925925925925e-06,
|
| 32 |
-
"loss": 85.8261,
|
| 33 |
-
"step": 40
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.28,
|
| 37 |
-
"learning_rate": 7.4074074074074075e-06,
|
| 38 |
-
"loss": 76.0406,
|
| 39 |
-
"step": 50
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.33,
|
| 43 |
-
"learning_rate": 7.99699181001692e-06,
|
| 44 |
-
"loss": 62.1596,
|
| 45 |
-
"step": 60
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.39,
|
| 49 |
-
"learning_rate": 7.978624809626406e-06,
|
| 50 |
-
"loss": 60.1637,
|
| 51 |
-
"step": 70
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.44,
|
| 55 |
-
"learning_rate": 7.943638653379184e-06,
|
| 56 |
-
"loss": 49.0233,
|
| 57 |
-
"step": 80
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.5,
|
| 61 |
-
"learning_rate": 7.892179482319294e-06,
|
| 62 |
-
"loss": 61.9877,
|
| 63 |
-
"step": 90
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.56,
|
| 67 |
-
"learning_rate": 7.824462247095518e-06,
|
| 68 |
-
"loss": 41.0057,
|
| 69 |
-
"step": 100
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.61,
|
| 73 |
-
"learning_rate": 7.740769810088759e-06,
|
| 74 |
-
"loss": 28.3225,
|
| 75 |
-
"step": 110
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.67,
|
| 79 |
-
"learning_rate": 7.641451763864587e-06,
|
| 80 |
-
"loss": 21.0979,
|
| 81 |
-
"step": 120
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.72,
|
| 85 |
-
"learning_rate": 7.526922970886431e-06,
|
| 86 |
-
"loss": 18.2794,
|
| 87 |
-
"step": 130
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.78,
|
| 91 |
-
"learning_rate": 7.3976618305891895e-06,
|
| 92 |
-
"loss": 9.044,
|
| 93 |
-
"step": 140
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.83,
|
| 97 |
-
"learning_rate": 7.2542082810518696e-06,
|
| 98 |
-
"loss": 6.2416,
|
| 99 |
-
"step": 150
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.89,
|
| 103 |
-
"learning_rate": 7.097161543616529e-06,
|
| 104 |
-
"loss": 2.6869,
|
| 105 |
-
"step": 160
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.94,
|
| 109 |
-
"learning_rate": 6.927177619874449e-06,
|
| 110 |
-
"loss": 1.5778,
|
| 111 |
-
"step": 170
|
| 112 |
-
},
|
| 113 |
{
|
| 114 |
"epoch": 1.0,
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
"
|
| 121 |
-
"eval_f1": 0.1941564561734213,
|
| 122 |
-
"eval_loss": 15.080679893493652,
|
| 123 |
-
"eval_runtime": 20.7366,
|
| 124 |
-
"eval_samples_per_second": 92.397,
|
| 125 |
-
"eval_steps_per_second": 1.447,
|
| 126 |
-
"step": 180
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 1.06,
|
| 130 |
-
"learning_rate": 6.551289454202823e-06,
|
| 131 |
-
"loss": 1.0316,
|
| 132 |
-
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch": 1.
|
| 136 |
-
"learning_rate": 6.
|
| 137 |
-
"loss":
|
| 138 |
-
"step":
|
| 139 |
-
},
|
| 140 |
-
{
|
| 141 |
-
"epoch": 1.17,
|
| 142 |
-
"learning_rate": 6.132817731206765e-06,
|
| 143 |
-
"loss": 0.9913,
|
| 144 |
-
"step": 210
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 1.22,
|
| 148 |
-
"learning_rate": 5.9097711081517955e-06,
|
| 149 |
-
"loss": 0.9418,
|
| 150 |
-
"step": 220
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 1.28,
|
| 154 |
-
"learning_rate": 5.678747159961716e-06,
|
| 155 |
-
"loss": 1.3579,
|
| 156 |
-
"step": 230
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 1.33,
|
| 160 |
-
"learning_rate": 5.440710899218841e-06,
|
| 161 |
-
"loss": 0.7793,
|
| 162 |
-
"step": 240
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 1.39,
|
| 166 |
-
"learning_rate": 5.196656629710567e-06,
|
| 167 |
-
"loss": 0.8691,
|
| 168 |
-
"step": 250
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 1.44,
|
| 172 |
-
"learning_rate": 4.947603793112476e-06,
|
| 173 |
-
"loss": 0.7268,
|
| 174 |
-
"step": 260
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 1.5,
|
| 178 |
-
"learning_rate": 4.694592710667722e-06,
|
| 179 |
-
"loss": 1.3357,
|
| 180 |
-
"step": 270
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 1.56,
|
| 184 |
-
"learning_rate": 4.438680237650126e-06,
|
| 185 |
-
"loss": 0.7497,
|
| 186 |
-
"step": 280
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 1.61,
|
| 190 |
-
"learning_rate": 4.180935348762825e-06,
|
| 191 |
-
"loss": 0.5343,
|
| 192 |
-
"step": 290
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 1.67,
|
| 196 |
-
"learning_rate": 3.922434672912703e-06,
|
| 197 |
-
"loss": 1.0287,
|
| 198 |
-
"step": 300
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 1.72,
|
| 202 |
-
"learning_rate": 3.664257996012372e-06,
|
| 203 |
-
"loss": 0.45,
|
| 204 |
-
"step": 310
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.78,
|
| 208 |
-
"learning_rate": 3.4074837505950056e-06,
|
| 209 |
-
"loss": 1.4606,
|
| 210 |
-
"step": 320
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 1.83,
|
| 214 |
-
"learning_rate": 3.1531845110823583e-06,
|
| 215 |
-
"loss": 0.4987,
|
| 216 |
-
"step": 330
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 1.89,
|
| 220 |
-
"learning_rate": 2.9024225135227944e-06,
|
| 221 |
-
"loss": 0.4837,
|
| 222 |
-
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch": 1.
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss":
|
| 228 |
-
"step":
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch":
|
| 232 |
-
"learning_rate":
|
| 233 |
-
"loss":
|
| 234 |
-
"step":
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 2.0,
|
| 238 |
-
"eval_f1": 0.
|
| 239 |
-
"eval_loss":
|
| 240 |
-
"eval_runtime":
|
| 241 |
-
"eval_samples_per_second":
|
| 242 |
-
"eval_steps_per_second": 1.
|
| 243 |
-
"step":
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 2.06,
|
| 247 |
-
"learning_rate": 2.181734529125998e-06,
|
| 248 |
-
"loss": 0.4364,
|
| 249 |
-
"step": 370
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 2.11,
|
| 253 |
-
"learning_rate": 1.9553832183765073e-06,
|
| 254 |
-
"loss": 0.3626,
|
| 255 |
-
"step": 380
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 2.17,
|
| 259 |
-
"learning_rate": 1.7375724980538462e-06,
|
| 260 |
-
"loss": 0.1876,
|
| 261 |
-
"step": 390
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 2.22,
|
| 265 |
-
"learning_rate": 1.529212187626172e-06,
|
| 266 |
-
"loss": 0.1443,
|
| 267 |
-
"step": 400
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 2.
|
| 271 |
-
"learning_rate": 1.
|
| 272 |
-
"loss":
|
| 273 |
-
"step":
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 2.33,
|
| 277 |
-
"learning_rate": 1.1442810617684044e-06,
|
| 278 |
-
"loss": 0.1862,
|
| 279 |
-
"step": 420
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.39,
|
| 283 |
-
"learning_rate": 9.693181462235283e-07,
|
| 284 |
-
"loss": 0.0915,
|
| 285 |
-
"step": 430
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 2.44,
|
| 289 |
-
"learning_rate": 8.070147239684279e-07,
|
| 290 |
-
"loss": 0.0219,
|
| 291 |
-
"step": 440
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 2.5,
|
| 295 |
-
"learning_rate": 6.
|
| 296 |
-
"loss":
|
| 297 |
-
"step":
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.56,
|
| 301 |
-
"learning_rate": 5.230424846934088e-07,
|
| 302 |
-
"loss": 0.0806,
|
| 303 |
-
"step": 460
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 2.61,
|
| 307 |
-
"learning_rate": 4.025598511236281e-07,
|
| 308 |
-
"loss": 0.1472,
|
| 309 |
-
"step": 470
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 2.67,
|
| 313 |
-
"learning_rate": 2.9710412292443863e-07,
|
| 314 |
-
"loss": 0.1118,
|
| 315 |
-
"step": 480
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 2.72,
|
| 319 |
-
"learning_rate": 2.071158003356941e-07,
|
| 320 |
-
"loss": 0.0869,
|
| 321 |
-
"step": 490
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.78,
|
| 325 |
-
"learning_rate": 1.3297077453335193e-07,
|
| 326 |
-
"loss": 0.1594,
|
| 327 |
-
"step": 500
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 2.83,
|
| 331 |
-
"learning_rate": 7.497875749046122e-08,
|
| 332 |
-
"loss": 0.1333,
|
| 333 |
-
"step": 510
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 2.89,
|
| 337 |
-
"learning_rate": 3.3381988275995585e-08,
|
| 338 |
-
"loss": 0.1171,
|
| 339 |
-
"step": 520
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.94,
|
| 343 |
-
"learning_rate": 8.354221195471912e-09,
|
| 344 |
-
"loss": 0.2449,
|
| 345 |
-
"step": 530
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss":
|
| 351 |
-
"step":
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 3.0,
|
| 355 |
-
"eval_f1": 0.
|
| 356 |
-
"eval_loss":
|
| 357 |
-
"eval_runtime":
|
| 358 |
-
"eval_samples_per_second":
|
| 359 |
-
"eval_steps_per_second": 1.
|
| 360 |
-
"step":
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 3.0,
|
| 364 |
-
"step":
|
| 365 |
-
"total_flos":
|
| 366 |
-
"train_loss":
|
| 367 |
-
"train_runtime":
|
| 368 |
-
"train_samples_per_second":
|
| 369 |
-
"train_steps_per_second": 0.
|
| 370 |
}
|
| 371 |
],
|
| 372 |
"logging_steps": 10,
|
| 373 |
-
"max_steps":
|
| 374 |
"num_input_tokens_seen": 0,
|
| 375 |
"num_train_epochs": 3,
|
| 376 |
"save_steps": 500,
|
| 377 |
-
"total_flos":
|
| 378 |
"train_batch_size": 4,
|
| 379 |
"trial_name": null,
|
| 380 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 84,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.36,
|
| 13 |
+
"learning_rate": 7.996491320395433e-06,
|
| 14 |
+
"loss": 459.6986,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.71,
|
| 19 |
+
"learning_rate": 7.582847040957651e-06,
|
| 20 |
+
"loss": 429.225,
|
| 21 |
"step": 20
|
| 22 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
{
|
| 24 |
"epoch": 1.0,
|
| 25 |
+
"eval_f1": 0.0,
|
| 26 |
+
"eval_loss": 329.4008483886719,
|
| 27 |
+
"eval_runtime": 2.9528,
|
| 28 |
+
"eval_samples_per_second": 59.604,
|
| 29 |
+
"eval_steps_per_second": 1.016,
|
| 30 |
+
"step": 28
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 1.07,
|
| 34 |
+
"learning_rate": 6.549695958994759e-06,
|
| 35 |
+
"loss": 361.3969,
|
| 36 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
},
|
| 38 |
{
|
| 39 |
+
"epoch": 1.43,
|
| 40 |
+
"learning_rate": 5.0756792824610625e-06,
|
| 41 |
+
"loss": 347.9836,
|
| 42 |
+
"step": 40
|
| 43 |
},
|
| 44 |
{
|
| 45 |
+
"epoch": 1.79,
|
| 46 |
+
"learning_rate": 3.415667885750354e-06,
|
| 47 |
+
"loss": 312.0525,
|
| 48 |
+
"step": 50
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 2.0,
|
| 52 |
+
"eval_f1": 0.0,
|
| 53 |
+
"eval_loss": 266.168701171875,
|
| 54 |
+
"eval_runtime": 2.5812,
|
| 55 |
+
"eval_samples_per_second": 68.187,
|
| 56 |
+
"eval_steps_per_second": 1.162,
|
| 57 |
+
"step": 56
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 2.14,
|
| 61 |
+
"learning_rate": 1.8566928200840125e-06,
|
| 62 |
+
"loss": 324.8967,
|
| 63 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 2.5,
|
| 67 |
+
"learning_rate": 6.683150371596022e-07,
|
| 68 |
+
"loss": 286.3452,
|
| 69 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 2.86,
|
| 73 |
+
"learning_rate": 5.601585171798051e-08,
|
| 74 |
+
"loss": 280.638,
|
| 75 |
+
"step": 80
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 3.0,
|
| 79 |
+
"eval_f1": 0.0,
|
| 80 |
+
"eval_loss": 253.1309051513672,
|
| 81 |
+
"eval_runtime": 2.6388,
|
| 82 |
+
"eval_samples_per_second": 66.696,
|
| 83 |
+
"eval_steps_per_second": 1.137,
|
| 84 |
+
"step": 84
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 3.0,
|
| 88 |
+
"step": 84,
|
| 89 |
+
"total_flos": 2697390194688.0,
|
| 90 |
+
"train_loss": 348.7352382114955,
|
| 91 |
+
"train_runtime": 184.625,
|
| 92 |
+
"train_samples_per_second": 14.251,
|
| 93 |
+
"train_steps_per_second": 0.455
|
| 94 |
}
|
| 95 |
],
|
| 96 |
"logging_steps": 10,
|
| 97 |
+
"max_steps": 84,
|
| 98 |
"num_input_tokens_seen": 0,
|
| 99 |
"num_train_epochs": 3,
|
| 100 |
"save_steps": 500,
|
| 101 |
+
"total_flos": 2697390194688.0,
|
| 102 |
"train_batch_size": 4,
|
| 103 |
"trial_name": null,
|
| 104 |
"trial_params": null
|