Commit
•
ba4c3e9
1
Parent(s):
2a09ac6
Training in progress, step 300
Browse files- checkpoint-1400/trainer_state.json +0 -982
- {checkpoint-1400 → checkpoint-300}/config.json +2 -2
- {checkpoint-1400 → checkpoint-300}/optimizer.pt +2 -2
- {checkpoint-1400 → checkpoint-300}/preprocessor_config.json +0 -0
- {checkpoint-1400 → checkpoint-300}/pytorch_model.bin +2 -2
- {checkpoint-1400 → checkpoint-300}/rng_state.pth +1 -1
- {checkpoint-1400 → checkpoint-300}/scaler.pt +1 -1
- {checkpoint-1400 → checkpoint-300}/scheduler.pt +1 -1
- checkpoint-300/trainer_state.json +133 -0
- {checkpoint-1400 → checkpoint-300}/training_args.bin +1 -1
- pytorch_model.bin +1 -1
checkpoint-1400/trainer_state.json
DELETED
|
@@ -1,982 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.6459054209919262,
|
| 5 |
-
"global_step": 1400,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.0,
|
| 12 |
-
"learning_rate": 5.725190839694656e-06,
|
| 13 |
-
"loss": 12.7187,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.01,
|
| 18 |
-
"learning_rate": 1.1450381679389312e-05,
|
| 19 |
-
"loss": 13.2124,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.01,
|
| 24 |
-
"learning_rate": 1.6603053435114505e-05,
|
| 25 |
-
"loss": 14.1489,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.02,
|
| 30 |
-
"learning_rate": 2.1755725190839692e-05,
|
| 31 |
-
"loss": 25.9008,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.02,
|
| 36 |
-
"learning_rate": 2.6908396946564882e-05,
|
| 37 |
-
"loss": 31.3861,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.03,
|
| 42 |
-
"learning_rate": 3.263358778625954e-05,
|
| 43 |
-
"loss": 8.9557,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.03,
|
| 48 |
-
"learning_rate": 3.835877862595419e-05,
|
| 49 |
-
"loss": 5.8443,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.04,
|
| 54 |
-
"learning_rate": 4.408396946564885e-05,
|
| 55 |
-
"loss": 4.3173,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.04,
|
| 60 |
-
"learning_rate": 4.980916030534351e-05,
|
| 61 |
-
"loss": 4.7444,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.05,
|
| 66 |
-
"learning_rate": 5.49618320610687e-05,
|
| 67 |
-
"loss": 4.542,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.05,
|
| 72 |
-
"eval_loss": 3.579599618911743,
|
| 73 |
-
"eval_runtime": 132.6751,
|
| 74 |
-
"eval_samples_per_second": 34.822,
|
| 75 |
-
"eval_steps_per_second": 1.093,
|
| 76 |
-
"eval_wer": 1.0,
|
| 77 |
-
"step": 100
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 0.05,
|
| 81 |
-
"learning_rate": 6.0687022900763354e-05,
|
| 82 |
-
"loss": 3.3873,
|
| 83 |
-
"step": 110
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.06,
|
| 87 |
-
"learning_rate": 6.641221374045802e-05,
|
| 88 |
-
"loss": 3.1783,
|
| 89 |
-
"step": 120
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 0.06,
|
| 93 |
-
"learning_rate": 7.213740458015267e-05,
|
| 94 |
-
"loss": 3.1672,
|
| 95 |
-
"step": 130
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 0.06,
|
| 99 |
-
"learning_rate": 7.494113029827315e-05,
|
| 100 |
-
"loss": 3.4915,
|
| 101 |
-
"step": 140
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.07,
|
| 105 |
-
"learning_rate": 7.483516483516483e-05,
|
| 106 |
-
"loss": 3.7276,
|
| 107 |
-
"step": 150
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.07,
|
| 111 |
-
"learning_rate": 7.471742543171114e-05,
|
| 112 |
-
"loss": 3.2435,
|
| 113 |
-
"step": 160
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 0.08,
|
| 117 |
-
"learning_rate": 7.459968602825744e-05,
|
| 118 |
-
"loss": 3.0634,
|
| 119 |
-
"step": 170
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 0.08,
|
| 123 |
-
"learning_rate": 7.448194662480377e-05,
|
| 124 |
-
"loss": 3.0859,
|
| 125 |
-
"step": 180
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 0.09,
|
| 129 |
-
"learning_rate": 7.436420722135007e-05,
|
| 130 |
-
"loss": 3.3592,
|
| 131 |
-
"step": 190
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 0.09,
|
| 135 |
-
"learning_rate": 7.425824175824176e-05,
|
| 136 |
-
"loss": 3.6018,
|
| 137 |
-
"step": 200
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 0.09,
|
| 141 |
-
"eval_loss": 3.3504831790924072,
|
| 142 |
-
"eval_runtime": 130.1255,
|
| 143 |
-
"eval_samples_per_second": 35.504,
|
| 144 |
-
"eval_steps_per_second": 1.114,
|
| 145 |
-
"eval_wer": 1.0,
|
| 146 |
-
"step": 200
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.1,
|
| 150 |
-
"learning_rate": 7.414050235478806e-05,
|
| 151 |
-
"loss": 3.1612,
|
| 152 |
-
"step": 210
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.1,
|
| 156 |
-
"learning_rate": 7.402276295133437e-05,
|
| 157 |
-
"loss": 3.0375,
|
| 158 |
-
"step": 220
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.11,
|
| 162 |
-
"learning_rate": 7.390502354788069e-05,
|
| 163 |
-
"loss": 3.08,
|
| 164 |
-
"step": 230
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.11,
|
| 168 |
-
"learning_rate": 7.3787284144427e-05,
|
| 169 |
-
"loss": 3.2809,
|
| 170 |
-
"step": 240
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.12,
|
| 174 |
-
"learning_rate": 7.368131868131867e-05,
|
| 175 |
-
"loss": 3.5351,
|
| 176 |
-
"step": 250
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.12,
|
| 180 |
-
"learning_rate": 7.356357927786499e-05,
|
| 181 |
-
"loss": 3.01,
|
| 182 |
-
"step": 260
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.12,
|
| 186 |
-
"learning_rate": 7.34458398744113e-05,
|
| 187 |
-
"loss": 3.0006,
|
| 188 |
-
"step": 270
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.13,
|
| 192 |
-
"learning_rate": 7.33281004709576e-05,
|
| 193 |
-
"loss": 3.0397,
|
| 194 |
-
"step": 280
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.13,
|
| 198 |
-
"learning_rate": 7.321036106750392e-05,
|
| 199 |
-
"loss": 3.1733,
|
| 200 |
-
"step": 290
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.14,
|
| 204 |
-
"learning_rate": 7.310439560439559e-05,
|
| 205 |
-
"loss": 3.5007,
|
| 206 |
-
"step": 300
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.14,
|
| 210 |
-
"eval_loss": 3.068483591079712,
|
| 211 |
-
"eval_runtime": 129.9806,
|
| 212 |
-
"eval_samples_per_second": 35.544,
|
| 213 |
-
"eval_steps_per_second": 1.116,
|
| 214 |
-
"eval_wer": 1.0,
|
| 215 |
-
"step": 300
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 0.14,
|
| 219 |
-
"learning_rate": 7.29866562009419e-05,
|
| 220 |
-
"loss": 2.9984,
|
| 221 |
-
"step": 310
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 0.15,
|
| 225 |
-
"learning_rate": 7.286891679748822e-05,
|
| 226 |
-
"loss": 3.0006,
|
| 227 |
-
"step": 320
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.15,
|
| 231 |
-
"learning_rate": 7.275117739403453e-05,
|
| 232 |
-
"loss": 3.029,
|
| 233 |
-
"step": 330
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 0.16,
|
| 237 |
-
"learning_rate": 7.263343799058085e-05,
|
| 238 |
-
"loss": 3.158,
|
| 239 |
-
"step": 340
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 0.16,
|
| 243 |
-
"learning_rate": 7.252747252747252e-05,
|
| 244 |
-
"loss": 3.4909,
|
| 245 |
-
"step": 350
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 0.17,
|
| 249 |
-
"learning_rate": 7.240973312401883e-05,
|
| 250 |
-
"loss": 3.001,
|
| 251 |
-
"step": 360
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.17,
|
| 255 |
-
"learning_rate": 7.229199372056515e-05,
|
| 256 |
-
"loss": 2.9925,
|
| 257 |
-
"step": 370
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 0.18,
|
| 261 |
-
"learning_rate": 7.217425431711145e-05,
|
| 262 |
-
"loss": 3.0009,
|
| 263 |
-
"step": 380
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.18,
|
| 267 |
-
"learning_rate": 7.205651491365776e-05,
|
| 268 |
-
"loss": 3.1263,
|
| 269 |
-
"step": 390
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.18,
|
| 273 |
-
"learning_rate": 7.195054945054944e-05,
|
| 274 |
-
"loss": 3.421,
|
| 275 |
-
"step": 400
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 0.18,
|
| 279 |
-
"eval_loss": 3.0357792377471924,
|
| 280 |
-
"eval_runtime": 130.0328,
|
| 281 |
-
"eval_samples_per_second": 35.529,
|
| 282 |
-
"eval_steps_per_second": 1.115,
|
| 283 |
-
"eval_wer": 1.0,
|
| 284 |
-
"step": 400
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.19,
|
| 288 |
-
"learning_rate": 7.183281004709575e-05,
|
| 289 |
-
"loss": 3.0018,
|
| 290 |
-
"step": 410
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.19,
|
| 294 |
-
"learning_rate": 7.171507064364207e-05,
|
| 295 |
-
"loss": 2.9947,
|
| 296 |
-
"step": 420
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.2,
|
| 300 |
-
"learning_rate": 7.159733124018838e-05,
|
| 301 |
-
"loss": 2.9935,
|
| 302 |
-
"step": 430
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.2,
|
| 306 |
-
"learning_rate": 7.147959183673469e-05,
|
| 307 |
-
"loss": 3.0818,
|
| 308 |
-
"step": 440
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.21,
|
| 312 |
-
"learning_rate": 7.137362637362637e-05,
|
| 313 |
-
"loss": 3.3386,
|
| 314 |
-
"step": 450
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.21,
|
| 318 |
-
"learning_rate": 7.125588697017268e-05,
|
| 319 |
-
"loss": 3.0803,
|
| 320 |
-
"step": 460
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.22,
|
| 324 |
-
"learning_rate": 7.1138147566719e-05,
|
| 325 |
-
"loss": 3.1655,
|
| 326 |
-
"step": 470
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.22,
|
| 330 |
-
"learning_rate": 7.10204081632653e-05,
|
| 331 |
-
"loss": 3.0899,
|
| 332 |
-
"step": 480
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.23,
|
| 336 |
-
"learning_rate": 7.090266875981161e-05,
|
| 337 |
-
"loss": 3.1638,
|
| 338 |
-
"step": 490
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.23,
|
| 342 |
-
"learning_rate": 7.079670329670328e-05,
|
| 343 |
-
"loss": 3.3518,
|
| 344 |
-
"step": 500
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 0.23,
|
| 348 |
-
"eval_loss": 2.9412434101104736,
|
| 349 |
-
"eval_runtime": 130.1575,
|
| 350 |
-
"eval_samples_per_second": 35.495,
|
| 351 |
-
"eval_steps_per_second": 1.114,
|
| 352 |
-
"eval_wer": 1.0,
|
| 353 |
-
"step": 500
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.24,
|
| 357 |
-
"learning_rate": 7.06789638932496e-05,
|
| 358 |
-
"loss": 2.9352,
|
| 359 |
-
"step": 510
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 0.24,
|
| 363 |
-
"learning_rate": 7.056122448979591e-05,
|
| 364 |
-
"loss": 2.9405,
|
| 365 |
-
"step": 520
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 0.24,
|
| 369 |
-
"learning_rate": 7.044348508634222e-05,
|
| 370 |
-
"loss": 2.9125,
|
| 371 |
-
"step": 530
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 0.25,
|
| 375 |
-
"learning_rate": 7.032574568288854e-05,
|
| 376 |
-
"loss": 2.9401,
|
| 377 |
-
"step": 540
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 0.25,
|
| 381 |
-
"learning_rate": 7.021978021978021e-05,
|
| 382 |
-
"loss": 3.1443,
|
| 383 |
-
"step": 550
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.26,
|
| 387 |
-
"learning_rate": 7.010204081632653e-05,
|
| 388 |
-
"loss": 2.7692,
|
| 389 |
-
"step": 560
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.26,
|
| 393 |
-
"learning_rate": 6.998430141287284e-05,
|
| 394 |
-
"loss": 2.7574,
|
| 395 |
-
"step": 570
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.27,
|
| 399 |
-
"learning_rate": 6.986656200941914e-05,
|
| 400 |
-
"loss": 2.706,
|
| 401 |
-
"step": 580
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.27,
|
| 405 |
-
"learning_rate": 6.974882260596545e-05,
|
| 406 |
-
"loss": 2.7155,
|
| 407 |
-
"step": 590
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 0.28,
|
| 411 |
-
"learning_rate": 6.964285714285713e-05,
|
| 412 |
-
"loss": 2.8747,
|
| 413 |
-
"step": 600
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 0.28,
|
| 417 |
-
"eval_loss": 2.5006003379821777,
|
| 418 |
-
"eval_runtime": 129.3111,
|
| 419 |
-
"eval_samples_per_second": 35.728,
|
| 420 |
-
"eval_steps_per_second": 1.121,
|
| 421 |
-
"eval_wer": 1.0,
|
| 422 |
-
"step": 600
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.28,
|
| 426 |
-
"learning_rate": 6.952511773940345e-05,
|
| 427 |
-
"loss": 2.5368,
|
| 428 |
-
"step": 610
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 0.29,
|
| 432 |
-
"learning_rate": 6.940737833594976e-05,
|
| 433 |
-
"loss": 2.5942,
|
| 434 |
-
"step": 620
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.29,
|
| 438 |
-
"learning_rate": 6.928963893249607e-05,
|
| 439 |
-
"loss": 2.4907,
|
| 440 |
-
"step": 630
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 0.3,
|
| 444 |
-
"learning_rate": 6.917189952904238e-05,
|
| 445 |
-
"loss": 2.472,
|
| 446 |
-
"step": 640
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.3,
|
| 450 |
-
"learning_rate": 6.907770800627943e-05,
|
| 451 |
-
"loss": 2.6826,
|
| 452 |
-
"step": 650
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 0.3,
|
| 456 |
-
"learning_rate": 6.895996860282574e-05,
|
| 457 |
-
"loss": 2.3167,
|
| 458 |
-
"step": 660
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 0.31,
|
| 462 |
-
"learning_rate": 6.884222919937205e-05,
|
| 463 |
-
"loss": 2.3457,
|
| 464 |
-
"step": 670
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.31,
|
| 468 |
-
"learning_rate": 6.872448979591836e-05,
|
| 469 |
-
"loss": 2.3532,
|
| 470 |
-
"step": 680
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.32,
|
| 474 |
-
"learning_rate": 6.860675039246468e-05,
|
| 475 |
-
"loss": 2.4822,
|
| 476 |
-
"step": 690
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 0.32,
|
| 480 |
-
"learning_rate": 6.850078492935636e-05,
|
| 481 |
-
"loss": 3.1002,
|
| 482 |
-
"step": 700
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.32,
|
| 486 |
-
"eval_loss": 2.819200277328491,
|
| 487 |
-
"eval_runtime": 129.5044,
|
| 488 |
-
"eval_samples_per_second": 35.674,
|
| 489 |
-
"eval_steps_per_second": 1.12,
|
| 490 |
-
"eval_wer": 0.9999694058618369,
|
| 491 |
-
"step": 700
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 0.33,
|
| 495 |
-
"learning_rate": 6.838304552590267e-05,
|
| 496 |
-
"loss": 2.9139,
|
| 497 |
-
"step": 710
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 0.33,
|
| 501 |
-
"learning_rate": 6.826530612244897e-05,
|
| 502 |
-
"loss": 2.9957,
|
| 503 |
-
"step": 720
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 0.34,
|
| 507 |
-
"learning_rate": 6.814756671899528e-05,
|
| 508 |
-
"loss": 2.9842,
|
| 509 |
-
"step": 730
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 0.34,
|
| 513 |
-
"learning_rate": 6.802982731554159e-05,
|
| 514 |
-
"loss": 3.2804,
|
| 515 |
-
"step": 740
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 0.35,
|
| 519 |
-
"learning_rate": 6.792386185243327e-05,
|
| 520 |
-
"loss": 3.4944,
|
| 521 |
-
"step": 750
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.35,
|
| 525 |
-
"learning_rate": 6.780612244897958e-05,
|
| 526 |
-
"loss": 2.9905,
|
| 527 |
-
"step": 760
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 0.36,
|
| 531 |
-
"learning_rate": 6.768838304552589e-05,
|
| 532 |
-
"loss": 2.9692,
|
| 533 |
-
"step": 770
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 0.36,
|
| 537 |
-
"learning_rate": 6.757064364207221e-05,
|
| 538 |
-
"loss": 2.9747,
|
| 539 |
-
"step": 780
|
| 540 |
-
},
|
| 541 |
-
{
|
| 542 |
-
"epoch": 0.36,
|
| 543 |
-
"learning_rate": 6.745290423861852e-05,
|
| 544 |
-
"loss": 3.294,
|
| 545 |
-
"step": 790
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 0.37,
|
| 549 |
-
"learning_rate": 6.73469387755102e-05,
|
| 550 |
-
"loss": 3.5998,
|
| 551 |
-
"step": 800
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 0.37,
|
| 555 |
-
"eval_loss": 3.059178590774536,
|
| 556 |
-
"eval_runtime": 129.2337,
|
| 557 |
-
"eval_samples_per_second": 35.749,
|
| 558 |
-
"eval_steps_per_second": 1.122,
|
| 559 |
-
"eval_wer": 1.0,
|
| 560 |
-
"step": 800
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 0.37,
|
| 564 |
-
"learning_rate": 6.72291993720565e-05,
|
| 565 |
-
"loss": 2.9902,
|
| 566 |
-
"step": 810
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.38,
|
| 570 |
-
"learning_rate": 6.711145996860281e-05,
|
| 571 |
-
"loss": 2.9644,
|
| 572 |
-
"step": 820
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 0.38,
|
| 576 |
-
"learning_rate": 6.699372056514913e-05,
|
| 577 |
-
"loss": 2.9529,
|
| 578 |
-
"step": 830
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 0.39,
|
| 582 |
-
"learning_rate": 6.687598116169544e-05,
|
| 583 |
-
"loss": 3.2737,
|
| 584 |
-
"step": 840
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 0.39,
|
| 588 |
-
"learning_rate": 6.677001569858712e-05,
|
| 589 |
-
"loss": 3.6534,
|
| 590 |
-
"step": 850
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 0.4,
|
| 594 |
-
"learning_rate": 6.665227629513343e-05,
|
| 595 |
-
"loss": 2.9664,
|
| 596 |
-
"step": 860
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 0.4,
|
| 600 |
-
"learning_rate": 6.653453689167974e-05,
|
| 601 |
-
"loss": 2.9463,
|
| 602 |
-
"step": 870
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 0.41,
|
| 606 |
-
"learning_rate": 6.641679748822606e-05,
|
| 607 |
-
"loss": 2.9591,
|
| 608 |
-
"step": 880
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 0.41,
|
| 612 |
-
"learning_rate": 6.629905808477237e-05,
|
| 613 |
-
"loss": 3.2701,
|
| 614 |
-
"step": 890
|
| 615 |
-
},
|
| 616 |
-
{
|
| 617 |
-
"epoch": 0.42,
|
| 618 |
-
"learning_rate": 6.618131868131867e-05,
|
| 619 |
-
"loss": 3.3784,
|
| 620 |
-
"step": 900
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 0.42,
|
| 624 |
-
"eval_loss": 3.0334482192993164,
|
| 625 |
-
"eval_runtime": 129.072,
|
| 626 |
-
"eval_samples_per_second": 35.794,
|
| 627 |
-
"eval_steps_per_second": 1.123,
|
| 628 |
-
"eval_wer": 1.0,
|
| 629 |
-
"step": 900
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 0.42,
|
| 633 |
-
"learning_rate": 6.606357927786498e-05,
|
| 634 |
-
"loss": 2.9729,
|
| 635 |
-
"step": 910
|
| 636 |
-
},
|
| 637 |
-
{
|
| 638 |
-
"epoch": 0.42,
|
| 639 |
-
"learning_rate": 6.594583987441129e-05,
|
| 640 |
-
"loss": 2.9444,
|
| 641 |
-
"step": 920
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.43,
|
| 645 |
-
"learning_rate": 6.582810047095761e-05,
|
| 646 |
-
"loss": 2.9441,
|
| 647 |
-
"step": 930
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 0.43,
|
| 651 |
-
"learning_rate": 6.571036106750392e-05,
|
| 652 |
-
"loss": 3.2629,
|
| 653 |
-
"step": 940
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 0.44,
|
| 657 |
-
"learning_rate": 6.56043956043956e-05,
|
| 658 |
-
"loss": 3.6467,
|
| 659 |
-
"step": 950
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 0.44,
|
| 663 |
-
"learning_rate": 6.548665620094191e-05,
|
| 664 |
-
"loss": 2.9472,
|
| 665 |
-
"step": 960
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 0.45,
|
| 669 |
-
"learning_rate": 6.536891679748822e-05,
|
| 670 |
-
"loss": 2.9301,
|
| 671 |
-
"step": 970
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 0.45,
|
| 675 |
-
"learning_rate": 6.525117739403452e-05,
|
| 676 |
-
"loss": 2.9555,
|
| 677 |
-
"step": 980
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"epoch": 0.46,
|
| 681 |
-
"learning_rate": 6.513343799058084e-05,
|
| 682 |
-
"loss": 3.2888,
|
| 683 |
-
"step": 990
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 0.46,
|
| 687 |
-
"learning_rate": 6.502747252747253e-05,
|
| 688 |
-
"loss": 3.6354,
|
| 689 |
-
"step": 1000
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 0.46,
|
| 693 |
-
"eval_loss": 2.9995181560516357,
|
| 694 |
-
"eval_runtime": 128.998,
|
| 695 |
-
"eval_samples_per_second": 35.815,
|
| 696 |
-
"eval_steps_per_second": 1.124,
|
| 697 |
-
"eval_wer": 1.0,
|
| 698 |
-
"step": 1000
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 0.47,
|
| 702 |
-
"learning_rate": 6.490973312401883e-05,
|
| 703 |
-
"loss": 2.9439,
|
| 704 |
-
"step": 1010
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 0.47,
|
| 708 |
-
"learning_rate": 6.479199372056514e-05,
|
| 709 |
-
"loss": 2.9291,
|
| 710 |
-
"step": 1020
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 0.48,
|
| 714 |
-
"learning_rate": 6.467425431711145e-05,
|
| 715 |
-
"loss": 2.9709,
|
| 716 |
-
"step": 1030
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 0.48,
|
| 720 |
-
"learning_rate": 6.455651491365777e-05,
|
| 721 |
-
"loss": 3.3363,
|
| 722 |
-
"step": 1040
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 0.48,
|
| 726 |
-
"learning_rate": 6.443877551020408e-05,
|
| 727 |
-
"loss": 3.4812,
|
| 728 |
-
"step": 1050
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 0.49,
|
| 732 |
-
"learning_rate": 6.432103610675038e-05,
|
| 733 |
-
"loss": 2.9394,
|
| 734 |
-
"step": 1060
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 0.49,
|
| 738 |
-
"learning_rate": 6.420329670329669e-05,
|
| 739 |
-
"loss": 2.9355,
|
| 740 |
-
"step": 1070
|
| 741 |
-
},
|
| 742 |
-
{
|
| 743 |
-
"epoch": 0.5,
|
| 744 |
-
"learning_rate": 6.4085557299843e-05,
|
| 745 |
-
"loss": 2.9679,
|
| 746 |
-
"step": 1080
|
| 747 |
-
},
|
| 748 |
-
{
|
| 749 |
-
"epoch": 0.5,
|
| 750 |
-
"learning_rate": 6.396781789638932e-05,
|
| 751 |
-
"loss": 3.3439,
|
| 752 |
-
"step": 1090
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 0.51,
|
| 756 |
-
"learning_rate": 6.3861852433281e-05,
|
| 757 |
-
"loss": 3.7295,
|
| 758 |
-
"step": 1100
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 0.51,
|
| 762 |
-
"eval_loss": 2.965841054916382,
|
| 763 |
-
"eval_runtime": 129.5437,
|
| 764 |
-
"eval_samples_per_second": 35.664,
|
| 765 |
-
"eval_steps_per_second": 1.119,
|
| 766 |
-
"eval_wer": 1.0,
|
| 767 |
-
"step": 1100
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 0.51,
|
| 771 |
-
"learning_rate": 6.374411302982731e-05,
|
| 772 |
-
"loss": 2.9341,
|
| 773 |
-
"step": 1110
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 0.52,
|
| 777 |
-
"learning_rate": 6.362637362637362e-05,
|
| 778 |
-
"loss": 2.923,
|
| 779 |
-
"step": 1120
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 0.52,
|
| 783 |
-
"learning_rate": 6.350863422291993e-05,
|
| 784 |
-
"loss": 2.9708,
|
| 785 |
-
"step": 1130
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 0.53,
|
| 789 |
-
"learning_rate": 6.339089481946623e-05,
|
| 790 |
-
"loss": 3.3851,
|
| 791 |
-
"step": 1140
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 0.53,
|
| 795 |
-
"learning_rate": 6.328492935635793e-05,
|
| 796 |
-
"loss": 3.7979,
|
| 797 |
-
"step": 1150
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 0.54,
|
| 801 |
-
"learning_rate": 6.316718995290424e-05,
|
| 802 |
-
"loss": 2.9171,
|
| 803 |
-
"step": 1160
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 0.54,
|
| 807 |
-
"learning_rate": 6.304945054945054e-05,
|
| 808 |
-
"loss": 2.9222,
|
| 809 |
-
"step": 1170
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 0.54,
|
| 813 |
-
"learning_rate": 6.293171114599685e-05,
|
| 814 |
-
"loss": 2.9591,
|
| 815 |
-
"step": 1180
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 0.55,
|
| 819 |
-
"learning_rate": 6.281397174254316e-05,
|
| 820 |
-
"loss": 3.3446,
|
| 821 |
-
"step": 1190
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 0.55,
|
| 825 |
-
"learning_rate": 6.269623233908948e-05,
|
| 826 |
-
"loss": 3.5604,
|
| 827 |
-
"step": 1200
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 0.55,
|
| 831 |
-
"eval_loss": 2.9375498294830322,
|
| 832 |
-
"eval_runtime": 129.4086,
|
| 833 |
-
"eval_samples_per_second": 35.701,
|
| 834 |
-
"eval_steps_per_second": 1.12,
|
| 835 |
-
"eval_wer": 1.0,
|
| 836 |
-
"step": 1200
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 0.56,
|
| 840 |
-
"learning_rate": 6.257849293563579e-05,
|
| 841 |
-
"loss": 2.9104,
|
| 842 |
-
"step": 1210
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 0.56,
|
| 846 |
-
"learning_rate": 6.24607535321821e-05,
|
| 847 |
-
"loss": 2.9168,
|
| 848 |
-
"step": 1220
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 0.57,
|
| 852 |
-
"learning_rate": 6.23430141287284e-05,
|
| 853 |
-
"loss": 2.952,
|
| 854 |
-
"step": 1230
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 0.57,
|
| 858 |
-
"learning_rate": 6.222527472527472e-05,
|
| 859 |
-
"loss": 3.3335,
|
| 860 |
-
"step": 1240
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 0.58,
|
| 864 |
-
"learning_rate": 6.21193092621664e-05,
|
| 865 |
-
"loss": 3.7665,
|
| 866 |
-
"step": 1250
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 0.58,
|
| 870 |
-
"learning_rate": 6.200156985871271e-05,
|
| 871 |
-
"loss": 2.9118,
|
| 872 |
-
"step": 1260
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 0.59,
|
| 876 |
-
"learning_rate": 6.188383045525902e-05,
|
| 877 |
-
"loss": 2.918,
|
| 878 |
-
"step": 1270
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 0.59,
|
| 882 |
-
"learning_rate": 6.176609105180533e-05,
|
| 883 |
-
"loss": 2.9364,
|
| 884 |
-
"step": 1280
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 0.6,
|
| 888 |
-
"learning_rate": 6.164835164835164e-05,
|
| 889 |
-
"loss": 3.219,
|
| 890 |
-
"step": 1290
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 0.6,
|
| 894 |
-
"learning_rate": 6.154238618524333e-05,
|
| 895 |
-
"loss": 3.5977,
|
| 896 |
-
"step": 1300
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 0.6,
|
| 900 |
-
"eval_loss": 2.94680118560791,
|
| 901 |
-
"eval_runtime": 130.4848,
|
| 902 |
-
"eval_samples_per_second": 35.406,
|
| 903 |
-
"eval_steps_per_second": 1.111,
|
| 904 |
-
"eval_wer": 0.9999694058618369,
|
| 905 |
-
"step": 1300
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 0.6,
|
| 909 |
-
"learning_rate": 6.142464678178964e-05,
|
| 910 |
-
"loss": 2.9167,
|
| 911 |
-
"step": 1310
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 0.61,
|
| 915 |
-
"learning_rate": 6.130690737833595e-05,
|
| 916 |
-
"loss": 2.9305,
|
| 917 |
-
"step": 1320
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 0.61,
|
| 921 |
-
"learning_rate": 6.118916797488225e-05,
|
| 922 |
-
"loss": 2.9303,
|
| 923 |
-
"step": 1330
|
| 924 |
-
},
|
| 925 |
-
{
|
| 926 |
-
"epoch": 0.62,
|
| 927 |
-
"learning_rate": 6.107142857142856e-05,
|
| 928 |
-
"loss": 3.1689,
|
| 929 |
-
"step": 1340
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"epoch": 0.62,
|
| 933 |
-
"learning_rate": 6.0965463108320243e-05,
|
| 934 |
-
"loss": 3.4788,
|
| 935 |
-
"step": 1350
|
| 936 |
-
},
|
| 937 |
-
{
|
| 938 |
-
"epoch": 0.63,
|
| 939 |
-
"learning_rate": 6.084772370486656e-05,
|
| 940 |
-
"loss": 2.9461,
|
| 941 |
-
"step": 1360
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 0.63,
|
| 945 |
-
"learning_rate": 6.072998430141287e-05,
|
| 946 |
-
"loss": 2.9556,
|
| 947 |
-
"step": 1370
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 0.64,
|
| 951 |
-
"learning_rate": 6.061224489795918e-05,
|
| 952 |
-
"loss": 2.965,
|
| 953 |
-
"step": 1380
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 0.64,
|
| 957 |
-
"learning_rate": 6.0494505494505494e-05,
|
| 958 |
-
"loss": 3.1035,
|
| 959 |
-
"step": 1390
|
| 960 |
-
},
|
| 961 |
-
{
|
| 962 |
-
"epoch": 0.65,
|
| 963 |
-
"learning_rate": 6.038854003139717e-05,
|
| 964 |
-
"loss": 3.3783,
|
| 965 |
-
"step": 1400
|
| 966 |
-
},
|
| 967 |
-
{
|
| 968 |
-
"epoch": 0.65,
|
| 969 |
-
"eval_loss": 3.044978141784668,
|
| 970 |
-
"eval_runtime": 129.9307,
|
| 971 |
-
"eval_samples_per_second": 35.557,
|
| 972 |
-
"eval_steps_per_second": 1.116,
|
| 973 |
-
"eval_wer": 1.0,
|
| 974 |
-
"step": 1400
|
| 975 |
-
}
|
| 976 |
-
],
|
| 977 |
-
"max_steps": 6501,
|
| 978 |
-
"num_train_epochs": 3,
|
| 979 |
-
"total_flos": 2.64683689964352e+19,
|
| 980 |
-
"trial_name": null,
|
| 981 |
-
"trial_params": null
|
| 982 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-1400 → checkpoint-300}/config.json
RENAMED
|
@@ -84,7 +84,7 @@
|
|
| 84 |
"num_hidden_layers": 24,
|
| 85 |
"num_negatives": 100,
|
| 86 |
"output_hidden_size": 1024,
|
| 87 |
-
"pad_token_id":
|
| 88 |
"proj_codevector_dim": 768,
|
| 89 |
"tdnn_dilation": [
|
| 90 |
1,
|
|
@@ -110,6 +110,6 @@
|
|
| 110 |
"torch_dtype": "float32",
|
| 111 |
"transformers_version": "4.17.0.dev0",
|
| 112 |
"use_weighted_layer_sum": false,
|
| 113 |
-
"vocab_size":
|
| 114 |
"xvector_output_dim": 512
|
| 115 |
}
|
|
|
|
| 84 |
"num_hidden_layers": 24,
|
| 85 |
"num_negatives": 100,
|
| 86 |
"output_hidden_size": 1024,
|
| 87 |
+
"pad_token_id": 31,
|
| 88 |
"proj_codevector_dim": 768,
|
| 89 |
"tdnn_dilation": [
|
| 90 |
1,
|
|
|
|
| 110 |
"torch_dtype": "float32",
|
| 111 |
"transformers_version": "4.17.0.dev0",
|
| 112 |
"use_weighted_layer_sum": false,
|
| 113 |
+
"vocab_size": 34,
|
| 114 |
"xvector_output_dim": 512
|
| 115 |
}
|
{checkpoint-1400 → checkpoint-300}/optimizer.pt
RENAMED
|
@@ -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 sha256:954ba48542dc5c25db0f62ed2ca1ffb7186193d086c52c02beda82c672631256
|
| 3 |
+
size 2490337809
|
{checkpoint-1400 → checkpoint-300}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-1400 → checkpoint-300}/pytorch_model.bin
RENAMED
|
@@ -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:f55e8e8bba9d8a2d1a47a603e5d5fbcf58b456ccb94f34fe863a0f009e4c42c6
|
| 3 |
+
size 1262063089
|
{checkpoint-1400 → checkpoint-300}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19a51ddd1984e27cea2dbdc4f4743549c4da11e939662b7e0827dd3b81a3bc6
|
| 3 |
size 14503
|
{checkpoint-1400 → checkpoint-300}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa13e2bd87a0ced3033a2eca0d8adb438aedf0aaa809e4e8ea0cb0e64687e1d6
|
| 3 |
size 559
|
{checkpoint-1400 → checkpoint-300}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbc4c290602ec206f870d87a70c082e7f5fe8efd17cef079d20868127fa13f9
|
| 3 |
size 623
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1380738695201933,
|
| 5 |
+
"global_step": 300,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.0305343511450381e-05,
|
| 13 |
+
"loss": 13.0539,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 2.118320610687023e-05,
|
| 19 |
+
"loss": 20.9649,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 3.206106870229007e-05,
|
| 25 |
+
"loss": 21.1001,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.04,
|
| 30 |
+
"learning_rate": 4.3511450381679383e-05,
|
| 31 |
+
"loss": 5.5852,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.05,
|
| 36 |
+
"learning_rate": 5.438931297709923e-05,
|
| 37 |
+
"loss": 5.2002,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"eval_loss": 3.5950469970703125,
|
| 43 |
+
"eval_runtime": 194.8685,
|
| 44 |
+
"eval_samples_per_second": 24.853,
|
| 45 |
+
"eval_steps_per_second": 0.78,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 100
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.06,
|
| 51 |
+
"learning_rate": 6.583969465648854e-05,
|
| 52 |
+
"loss": 3.281,
|
| 53 |
+
"step": 120
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.06,
|
| 57 |
+
"learning_rate": 7.495301487862176e-05,
|
| 58 |
+
"loss": 3.3442,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07,
|
| 63 |
+
"learning_rate": 7.472983555207517e-05,
|
| 64 |
+
"loss": 3.5229,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08,
|
| 69 |
+
"learning_rate": 7.449490994518402e-05,
|
| 70 |
+
"loss": 3.089,
|
| 71 |
+
"step": 180
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.09,
|
| 75 |
+
"learning_rate": 7.427173061863743e-05,
|
| 76 |
+
"loss": 3.482,
|
| 77 |
+
"step": 200
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.09,
|
| 81 |
+
"eval_loss": 3.274627923965454,
|
| 82 |
+
"eval_runtime": 194.5649,
|
| 83 |
+
"eval_samples_per_second": 24.891,
|
| 84 |
+
"eval_steps_per_second": 0.781,
|
| 85 |
+
"eval_wer": 1.0,
|
| 86 |
+
"step": 200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 7.403680501174628e-05,
|
| 91 |
+
"loss": 3.1517,
|
| 92 |
+
"step": 220
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.11,
|
| 96 |
+
"learning_rate": 7.380187940485512e-05,
|
| 97 |
+
"loss": 3.1617,
|
| 98 |
+
"step": 240
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.12,
|
| 102 |
+
"learning_rate": 7.357870007830852e-05,
|
| 103 |
+
"loss": 3.2971,
|
| 104 |
+
"step": 260
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.13,
|
| 108 |
+
"learning_rate": 7.334377447141738e-05,
|
| 109 |
+
"loss": 3.022,
|
| 110 |
+
"step": 280
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.14,
|
| 114 |
+
"learning_rate": 7.312059514487078e-05,
|
| 115 |
+
"loss": 3.3322,
|
| 116 |
+
"step": 300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.14,
|
| 120 |
+
"eval_loss": 3.0716073513031006,
|
| 121 |
+
"eval_runtime": 196.1674,
|
| 122 |
+
"eval_samples_per_second": 24.688,
|
| 123 |
+
"eval_steps_per_second": 0.775,
|
| 124 |
+
"eval_wer": 1.0,
|
| 125 |
+
"step": 300
|
| 126 |
+
}
|
| 127 |
+
],
|
| 128 |
+
"max_steps": 6516,
|
| 129 |
+
"num_train_epochs": 3,
|
| 130 |
+
"total_flos": 5.707308532903895e+18,
|
| 131 |
+
"trial_name": null,
|
| 132 |
+
"trial_params": null
|
| 133 |
+
}
|
{checkpoint-1400 → checkpoint-300}/training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:962dbb61fb0395a025f0dae3475a50ad9719299753b3a01bede5cb391a4aca78
|
| 3 |
size 3055
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f55e8e8bba9d8a2d1a47a603e5d5fbcf58b456ccb94f34fe863a0f009e4c42c6
|
| 3 |
size 1262063089
|