Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d272d808c4d78c51ed882e52436b50de43238baa0b3d5032c121b862e8c95ac
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235130
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57b32ae9ee23830597b75e7a81d34670c42dbdda022ee958920c8eae3196ea94
|
| 3 |
size 440235130
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eef8c749264b26d3c435087ceac3890a08b72e1d16e09e5376d4afb6eccc0ec4
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fec4c47fe338ca1d5d1e3d6f4fe9c0141de1fee23f97edeed87e057e0266ffd9
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./iteboshi_temp/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -297,6 +297,296 @@
|
|
| 297 |
"eval_steps_per_second": 1.1,
|
| 298 |
"eval_wer": 99.67939651107967,
|
| 299 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 300 |
}
|
| 301 |
],
|
| 302 |
"logging_steps": 25,
|
|
@@ -316,7 +606,7 @@
|
|
| 316 |
"attributes": {}
|
| 317 |
}
|
| 318 |
},
|
| 319 |
-
"total_flos":
|
| 320 |
"train_batch_size": 12,
|
| 321 |
"trial_name": null,
|
| 322 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 97.35030645921735,
|
| 3 |
+
"best_model_checkpoint": "./iteboshi_temp/checkpoint-2000",
|
| 4 |
+
"epoch": 3.300578034682081,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 297 |
"eval_steps_per_second": 1.1,
|
| 298 |
"eval_wer": 99.67939651107967,
|
| 299 |
"step": 1000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.6919900908340215,
|
| 303 |
+
"grad_norm": 9.614924430847168,
|
| 304 |
+
"learning_rate": 1.889684210526316e-05,
|
| 305 |
+
"loss": 1.8351,
|
| 306 |
+
"step": 1025
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.7332782824112303,
|
| 310 |
+
"grad_norm": 9.912728309631348,
|
| 311 |
+
"learning_rate": 1.8844210526315793e-05,
|
| 312 |
+
"loss": 1.7924,
|
| 313 |
+
"step": 1050
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.7745664739884393,
|
| 317 |
+
"grad_norm": 9.571353912353516,
|
| 318 |
+
"learning_rate": 1.8791578947368423e-05,
|
| 319 |
+
"loss": 1.7655,
|
| 320 |
+
"step": 1075
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.8158546655656482,
|
| 324 |
+
"grad_norm": 9.284981727600098,
|
| 325 |
+
"learning_rate": 1.8738947368421056e-05,
|
| 326 |
+
"loss": 1.7737,
|
| 327 |
+
"step": 1100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.8571428571428572,
|
| 331 |
+
"grad_norm": 10.073586463928223,
|
| 332 |
+
"learning_rate": 1.8686315789473686e-05,
|
| 333 |
+
"loss": 1.7343,
|
| 334 |
+
"step": 1125
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.8984310487200662,
|
| 338 |
+
"grad_norm": 8.913012504577637,
|
| 339 |
+
"learning_rate": 1.8633684210526316e-05,
|
| 340 |
+
"loss": 1.6881,
|
| 341 |
+
"step": 1150
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.939719240297275,
|
| 345 |
+
"grad_norm": 9.885432243347168,
|
| 346 |
+
"learning_rate": 1.858105263157895e-05,
|
| 347 |
+
"loss": 1.6909,
|
| 348 |
+
"step": 1175
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.981007431874484,
|
| 352 |
+
"grad_norm": 9.40440559387207,
|
| 353 |
+
"learning_rate": 1.852842105263158e-05,
|
| 354 |
+
"loss": 1.6276,
|
| 355 |
+
"step": 1200
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.0214698596201486,
|
| 359 |
+
"grad_norm": 10.476126670837402,
|
| 360 |
+
"learning_rate": 1.8475789473684212e-05,
|
| 361 |
+
"loss": 1.5264,
|
| 362 |
+
"step": 1225
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.0627580511973576,
|
| 366 |
+
"grad_norm": 8.929309844970703,
|
| 367 |
+
"learning_rate": 1.8423157894736842e-05,
|
| 368 |
+
"loss": 1.4139,
|
| 369 |
+
"step": 1250
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.1040462427745665,
|
| 373 |
+
"grad_norm": 9.487678527832031,
|
| 374 |
+
"learning_rate": 1.8370526315789476e-05,
|
| 375 |
+
"loss": 1.4765,
|
| 376 |
+
"step": 1275
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.1453344343517755,
|
| 380 |
+
"grad_norm": 9.428024291992188,
|
| 381 |
+
"learning_rate": 1.831789473684211e-05,
|
| 382 |
+
"loss": 1.4275,
|
| 383 |
+
"step": 1300
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.1866226259289845,
|
| 387 |
+
"grad_norm": 9.300884246826172,
|
| 388 |
+
"learning_rate": 1.826526315789474e-05,
|
| 389 |
+
"loss": 1.4115,
|
| 390 |
+
"step": 1325
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.227910817506193,
|
| 394 |
+
"grad_norm": 9.60734748840332,
|
| 395 |
+
"learning_rate": 1.821263157894737e-05,
|
| 396 |
+
"loss": 1.4087,
|
| 397 |
+
"step": 1350
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.269199009083402,
|
| 401 |
+
"grad_norm": 8.660606384277344,
|
| 402 |
+
"learning_rate": 1.8160000000000002e-05,
|
| 403 |
+
"loss": 1.3658,
|
| 404 |
+
"step": 1375
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.310487200660611,
|
| 408 |
+
"grad_norm": 9.169739723205566,
|
| 409 |
+
"learning_rate": 1.8107368421052632e-05,
|
| 410 |
+
"loss": 1.3645,
|
| 411 |
+
"step": 1400
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.35177539223782,
|
| 415 |
+
"grad_norm": 9.20264720916748,
|
| 416 |
+
"learning_rate": 1.8054736842105266e-05,
|
| 417 |
+
"loss": 1.328,
|
| 418 |
+
"step": 1425
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.393063583815029,
|
| 422 |
+
"grad_norm": 9.625157356262207,
|
| 423 |
+
"learning_rate": 1.8002105263157896e-05,
|
| 424 |
+
"loss": 1.3095,
|
| 425 |
+
"step": 1450
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.434351775392238,
|
| 429 |
+
"grad_norm": 8.743439674377441,
|
| 430 |
+
"learning_rate": 1.794947368421053e-05,
|
| 431 |
+
"loss": 1.3244,
|
| 432 |
+
"step": 1475
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.475639966969447,
|
| 436 |
+
"grad_norm": 9.378725051879883,
|
| 437 |
+
"learning_rate": 1.789684210526316e-05,
|
| 438 |
+
"loss": 1.2695,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.516928158546656,
|
| 443 |
+
"grad_norm": 9.474600791931152,
|
| 444 |
+
"learning_rate": 1.7844210526315792e-05,
|
| 445 |
+
"loss": 1.3238,
|
| 446 |
+
"step": 1525
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.558216350123865,
|
| 450 |
+
"grad_norm": 8.615851402282715,
|
| 451 |
+
"learning_rate": 1.7791578947368422e-05,
|
| 452 |
+
"loss": 1.2829,
|
| 453 |
+
"step": 1550
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.5995045417010734,
|
| 457 |
+
"grad_norm": 8.702414512634277,
|
| 458 |
+
"learning_rate": 1.7738947368421052e-05,
|
| 459 |
+
"loss": 1.2914,
|
| 460 |
+
"step": 1575
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.6407927332782823,
|
| 464 |
+
"grad_norm": 9.374676704406738,
|
| 465 |
+
"learning_rate": 1.7686315789473685e-05,
|
| 466 |
+
"loss": 1.2769,
|
| 467 |
+
"step": 1600
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.6820809248554913,
|
| 471 |
+
"grad_norm": 8.985688209533691,
|
| 472 |
+
"learning_rate": 1.7633684210526315e-05,
|
| 473 |
+
"loss": 1.25,
|
| 474 |
+
"step": 1625
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.7233691164327003,
|
| 478 |
+
"grad_norm": 8.864657402038574,
|
| 479 |
+
"learning_rate": 1.758105263157895e-05,
|
| 480 |
+
"loss": 1.2028,
|
| 481 |
+
"step": 1650
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.7646573080099093,
|
| 485 |
+
"grad_norm": 8.514275550842285,
|
| 486 |
+
"learning_rate": 1.7528421052631582e-05,
|
| 487 |
+
"loss": 1.2477,
|
| 488 |
+
"step": 1675
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.805945499587118,
|
| 492 |
+
"grad_norm": 9.147972106933594,
|
| 493 |
+
"learning_rate": 1.7475789473684212e-05,
|
| 494 |
+
"loss": 1.2103,
|
| 495 |
+
"step": 1700
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.847233691164327,
|
| 499 |
+
"grad_norm": 9.296348571777344,
|
| 500 |
+
"learning_rate": 1.7423157894736845e-05,
|
| 501 |
+
"loss": 1.2437,
|
| 502 |
+
"step": 1725
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.8885218827415358,
|
| 506 |
+
"grad_norm": 9.178862571716309,
|
| 507 |
+
"learning_rate": 1.7370526315789475e-05,
|
| 508 |
+
"loss": 1.1999,
|
| 509 |
+
"step": 1750
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.9298100743187447,
|
| 513 |
+
"grad_norm": 8.8689603805542,
|
| 514 |
+
"learning_rate": 1.731789473684211e-05,
|
| 515 |
+
"loss": 1.167,
|
| 516 |
+
"step": 1775
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.9710982658959537,
|
| 520 |
+
"grad_norm": 8.430618286132812,
|
| 521 |
+
"learning_rate": 1.726526315789474e-05,
|
| 522 |
+
"loss": 1.1616,
|
| 523 |
+
"step": 1800
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 3.0115606936416186,
|
| 527 |
+
"grad_norm": 8.175687789916992,
|
| 528 |
+
"learning_rate": 1.721263157894737e-05,
|
| 529 |
+
"loss": 1.1536,
|
| 530 |
+
"step": 1825
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.0528488852188276,
|
| 534 |
+
"grad_norm": 8.549736022949219,
|
| 535 |
+
"learning_rate": 1.7160000000000002e-05,
|
| 536 |
+
"loss": 1.0421,
|
| 537 |
+
"step": 1850
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.094137076796036,
|
| 541 |
+
"grad_norm": 8.512212753295898,
|
| 542 |
+
"learning_rate": 1.710736842105263e-05,
|
| 543 |
+
"loss": 1.0288,
|
| 544 |
+
"step": 1875
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 3.135425268373245,
|
| 548 |
+
"grad_norm": 7.529111385345459,
|
| 549 |
+
"learning_rate": 1.7054736842105265e-05,
|
| 550 |
+
"loss": 0.9965,
|
| 551 |
+
"step": 1900
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 3.176713459950454,
|
| 555 |
+
"grad_norm": 8.706369400024414,
|
| 556 |
+
"learning_rate": 1.7002105263157895e-05,
|
| 557 |
+
"loss": 1.0262,
|
| 558 |
+
"step": 1925
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 3.218001651527663,
|
| 562 |
+
"grad_norm": 8.718097686767578,
|
| 563 |
+
"learning_rate": 1.6949473684210528e-05,
|
| 564 |
+
"loss": 1.0232,
|
| 565 |
+
"step": 1950
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 3.259289843104872,
|
| 569 |
+
"grad_norm": 9.124544143676758,
|
| 570 |
+
"learning_rate": 1.689684210526316e-05,
|
| 571 |
+
"loss": 1.0104,
|
| 572 |
+
"step": 1975
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.300578034682081,
|
| 576 |
+
"grad_norm": 7.853435039520264,
|
| 577 |
+
"learning_rate": 1.684421052631579e-05,
|
| 578 |
+
"loss": 0.9948,
|
| 579 |
+
"step": 2000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.300578034682081,
|
| 583 |
+
"eval_cer": 59.421319913335545,
|
| 584 |
+
"eval_loss": 1.2762852907180786,
|
| 585 |
+
"eval_runtime": 738.0908,
|
| 586 |
+
"eval_samples_per_second": 14.336,
|
| 587 |
+
"eval_steps_per_second": 1.195,
|
| 588 |
+
"eval_wer": 97.35030645921735,
|
| 589 |
+
"step": 2000
|
| 590 |
}
|
| 591 |
],
|
| 592 |
"logging_steps": 25,
|
|
|
|
| 606 |
"attributes": {}
|
| 607 |
}
|
| 608 |
},
|
| 609 |
+
"total_flos": 3.89856186335232e+18,
|
| 610 |
"train_batch_size": 12,
|
| 611 |
"trial_name": null,
|
| 612 |
"trial_params": null
|