Training in progress, step 800, checkpoint
Browse files- last-checkpoint/model-00001-of-00003.safetensors +1 -1
- last-checkpoint/model-00002-of-00003.safetensors +1 -1
- last-checkpoint/model-00003-of-00003.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +299 -3
last-checkpoint/model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4939116424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96eefb2ab4b204e9308bae75f26755bc252532bdfce90c247e78733a4199e1e2
|
| 3 |
size 4939116424
|
last-checkpoint/model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947390880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4096a8c7f67ddbd2910b504765f448908fdd008051d764d2428a8cf62c11b3d
|
| 3 |
size 4947390880
|
last-checkpoint/model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3590619888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c892e15db6ad07c12e5d0e95b0debfd095cf21e2bf401f6eca45fe7f25d85cb
|
| 3 |
size 3590619888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13688025904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ab754728a1608ca4beccfa68dff15ae8a33135223828648ca1ace40d391f5d2
|
| 3 |
size 13688025904
|
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 sha256:3c431bcafebc4c8ee346d130e382b11c81be579ca0bfd3918fae07b16e10b92f
|
| 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 sha256:40b6b717644e21f80a22ec98694b3a2fd9d62a6467e549d64314725dba905d52
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -311,6 +311,302 @@
|
|
| 311 |
"eval_samples_per_second": 13.041,
|
| 312 |
"eval_steps_per_second": 6.521,
|
| 313 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
}
|
| 315 |
],
|
| 316 |
"logging_steps": 10,
|
|
@@ -330,7 +626,7 @@
|
|
| 330 |
"attributes": {}
|
| 331 |
}
|
| 332 |
},
|
| 333 |
-
"total_flos":
|
| 334 |
"train_batch_size": 2,
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.11839573775344088,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 311 |
"eval_samples_per_second": 13.041,
|
| 312 |
"eval_steps_per_second": 6.521,
|
| 313 |
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.06067781559863845,
|
| 317 |
+
"grad_norm": 14.375,
|
| 318 |
+
"learning_rate": 0.00019297764858882514,
|
| 319 |
+
"loss": 4.2204,
|
| 320 |
+
"step": 410
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.06215776232055646,
|
| 324 |
+
"grad_norm": 17.75,
|
| 325 |
+
"learning_rate": 0.00019248258232139388,
|
| 326 |
+
"loss": 3.7817,
|
| 327 |
+
"step": 420
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.06363770904247447,
|
| 331 |
+
"grad_norm": 25.5,
|
| 332 |
+
"learning_rate": 0.00019197133427991436,
|
| 333 |
+
"loss": 3.8348,
|
| 334 |
+
"step": 430
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.06511765576439248,
|
| 338 |
+
"grad_norm": 16.375,
|
| 339 |
+
"learning_rate": 0.00019144399391799043,
|
| 340 |
+
"loss": 4.1359,
|
| 341 |
+
"step": 440
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.0665976024863105,
|
| 345 |
+
"grad_norm": 126.5,
|
| 346 |
+
"learning_rate": 0.00019090065350491626,
|
| 347 |
+
"loss": 3.8639,
|
| 348 |
+
"step": 450
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.0680775492082285,
|
| 352 |
+
"grad_norm": 10.5,
|
| 353 |
+
"learning_rate": 0.0001903414081095315,
|
| 354 |
+
"loss": 4.3344,
|
| 355 |
+
"step": 460
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.06955749593014651,
|
| 359 |
+
"grad_norm": 9.625,
|
| 360 |
+
"learning_rate": 0.00018976635558358722,
|
| 361 |
+
"loss": 3.7876,
|
| 362 |
+
"step": 470
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.07103744265206452,
|
| 366 |
+
"grad_norm": 12.75,
|
| 367 |
+
"learning_rate": 0.00018917559654462474,
|
| 368 |
+
"loss": 4.0847,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.07251738937398254,
|
| 373 |
+
"grad_norm": 56.75,
|
| 374 |
+
"learning_rate": 0.00018856923435837022,
|
| 375 |
+
"loss": 4.2232,
|
| 376 |
+
"step": 490
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.07399733609590055,
|
| 380 |
+
"grad_norm": 49.0,
|
| 381 |
+
"learning_rate": 0.0001879473751206489,
|
| 382 |
+
"loss": 4.3389,
|
| 383 |
+
"step": 500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.07547728281781856,
|
| 387 |
+
"grad_norm": 7.96875,
|
| 388 |
+
"learning_rate": 0.00018731012763882133,
|
| 389 |
+
"loss": 4.1522,
|
| 390 |
+
"step": 510
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.07695722953973656,
|
| 394 |
+
"grad_norm": 10.8125,
|
| 395 |
+
"learning_rate": 0.00018665760341274505,
|
| 396 |
+
"loss": 4.0533,
|
| 397 |
+
"step": 520
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.07843717626165458,
|
| 401 |
+
"grad_norm": 18.0,
|
| 402 |
+
"learning_rate": 0.00018598991661526572,
|
| 403 |
+
"loss": 4.0835,
|
| 404 |
+
"step": 530
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.07991712298357259,
|
| 408 |
+
"grad_norm": 34.5,
|
| 409 |
+
"learning_rate": 0.00018530718407223974,
|
| 410 |
+
"loss": 3.5388,
|
| 411 |
+
"step": 540
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.0813970697054906,
|
| 415 |
+
"grad_norm": 28.375,
|
| 416 |
+
"learning_rate": 0.00018460952524209355,
|
| 417 |
+
"loss": 4.2171,
|
| 418 |
+
"step": 550
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.08287701642740862,
|
| 422 |
+
"grad_norm": 13.125,
|
| 423 |
+
"learning_rate": 0.00018389706219492147,
|
| 424 |
+
"loss": 4.2511,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.08435696314932663,
|
| 429 |
+
"grad_norm": 13.1875,
|
| 430 |
+
"learning_rate": 0.00018316991959112716,
|
| 431 |
+
"loss": 3.9025,
|
| 432 |
+
"step": 570
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.08583690987124463,
|
| 436 |
+
"grad_norm": 15.3125,
|
| 437 |
+
"learning_rate": 0.00018242822465961176,
|
| 438 |
+
"loss": 4.0034,
|
| 439 |
+
"step": 580
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.08731685659316264,
|
| 443 |
+
"grad_norm": 33.0,
|
| 444 |
+
"learning_rate": 0.00018167210717551224,
|
| 445 |
+
"loss": 4.0514,
|
| 446 |
+
"step": 590
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.08879680331508066,
|
| 450 |
+
"grad_norm": 35.0,
|
| 451 |
+
"learning_rate": 0.00018090169943749476,
|
| 452 |
+
"loss": 4.0116,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.08879680331508066,
|
| 457 |
+
"eval_loss": 4.839527130126953,
|
| 458 |
+
"eval_runtime": 115.7002,
|
| 459 |
+
"eval_samples_per_second": 12.982,
|
| 460 |
+
"eval_steps_per_second": 6.491,
|
| 461 |
+
"step": 600
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.09027675003699867,
|
| 465 |
+
"grad_norm": 9.9375,
|
| 466 |
+
"learning_rate": 0.00018011713624460608,
|
| 467 |
+
"loss": 4.2757,
|
| 468 |
+
"step": 610
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.09175669675891668,
|
| 472 |
+
"grad_norm": 9.375,
|
| 473 |
+
"learning_rate": 0.00017931855487268782,
|
| 474 |
+
"loss": 3.9496,
|
| 475 |
+
"step": 620
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.09323664348083469,
|
| 479 |
+
"grad_norm": 17.5,
|
| 480 |
+
"learning_rate": 0.0001785060950503568,
|
| 481 |
+
"loss": 4.0227,
|
| 482 |
+
"step": 630
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.0947165902027527,
|
| 486 |
+
"grad_norm": 12.0,
|
| 487 |
+
"learning_rate": 0.00017767989893455698,
|
| 488 |
+
"loss": 4.3345,
|
| 489 |
+
"step": 640
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.09619653692467071,
|
| 493 |
+
"grad_norm": 40.75,
|
| 494 |
+
"learning_rate": 0.00017684011108568592,
|
| 495 |
+
"loss": 3.2456,
|
| 496 |
+
"step": 650
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.09767648364658872,
|
| 500 |
+
"grad_norm": 6.03125,
|
| 501 |
+
"learning_rate": 0.00017598687844230088,
|
| 502 |
+
"loss": 4.296,
|
| 503 |
+
"step": 660
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.09915643036850673,
|
| 507 |
+
"grad_norm": 10.75,
|
| 508 |
+
"learning_rate": 0.00017512035029540885,
|
| 509 |
+
"loss": 3.8307,
|
| 510 |
+
"step": 670
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.10063637709042475,
|
| 514 |
+
"grad_norm": 11.9375,
|
| 515 |
+
"learning_rate": 0.000174240678262345,
|
| 516 |
+
"loss": 3.8659,
|
| 517 |
+
"step": 680
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.10211632381234276,
|
| 521 |
+
"grad_norm": 21.75,
|
| 522 |
+
"learning_rate": 0.000173348016260244,
|
| 523 |
+
"loss": 4.0579,
|
| 524 |
+
"step": 690
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.10359627053426076,
|
| 528 |
+
"grad_norm": 29.625,
|
| 529 |
+
"learning_rate": 0.00017244252047910892,
|
| 530 |
+
"loss": 3.8463,
|
| 531 |
+
"step": 700
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.10507621725617877,
|
| 535 |
+
"grad_norm": 12.75,
|
| 536 |
+
"learning_rate": 0.00017152434935448256,
|
| 537 |
+
"loss": 4.225,
|
| 538 |
+
"step": 710
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.1065561639780968,
|
| 542 |
+
"grad_norm": 9.0625,
|
| 543 |
+
"learning_rate": 0.0001705936635397259,
|
| 544 |
+
"loss": 3.5182,
|
| 545 |
+
"step": 720
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.1080361107000148,
|
| 549 |
+
"grad_norm": 14.75,
|
| 550 |
+
"learning_rate": 0.00016965062587790823,
|
| 551 |
+
"loss": 4.0649,
|
| 552 |
+
"step": 730
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.10951605742193281,
|
| 556 |
+
"grad_norm": 19.0,
|
| 557 |
+
"learning_rate": 0.00016869540137331445,
|
| 558 |
+
"loss": 4.2849,
|
| 559 |
+
"step": 740
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.11099600414385082,
|
| 563 |
+
"grad_norm": 34.5,
|
| 564 |
+
"learning_rate": 0.00016772815716257412,
|
| 565 |
+
"loss": 3.65,
|
| 566 |
+
"step": 750
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.11247595086576884,
|
| 570 |
+
"grad_norm": 11.0,
|
| 571 |
+
"learning_rate": 0.00016674906248541726,
|
| 572 |
+
"loss": 4.1331,
|
| 573 |
+
"step": 760
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.11395589758768684,
|
| 577 |
+
"grad_norm": 38.0,
|
| 578 |
+
"learning_rate": 0.00016575828865506245,
|
| 579 |
+
"loss": 3.5679,
|
| 580 |
+
"step": 770
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.11543584430960485,
|
| 584 |
+
"grad_norm": 9.8125,
|
| 585 |
+
"learning_rate": 0.0001647560090282419,
|
| 586 |
+
"loss": 3.573,
|
| 587 |
+
"step": 780
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.11691579103152286,
|
| 591 |
+
"grad_norm": 14.0,
|
| 592 |
+
"learning_rate": 0.000163742398974869,
|
| 593 |
+
"loss": 3.9581,
|
| 594 |
+
"step": 790
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.11839573775344088,
|
| 598 |
+
"grad_norm": 20.25,
|
| 599 |
+
"learning_rate": 0.0001627176358473537,
|
| 600 |
+
"loss": 4.0812,
|
| 601 |
+
"step": 800
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.11839573775344088,
|
| 605 |
+
"eval_loss": 4.436325550079346,
|
| 606 |
+
"eval_runtime": 113.0291,
|
| 607 |
+
"eval_samples_per_second": 13.289,
|
| 608 |
+
"eval_steps_per_second": 6.644,
|
| 609 |
+
"step": 800
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 10,
|
|
|
|
| 626 |
"attributes": {}
|
| 627 |
}
|
| 628 |
},
|
| 629 |
+
"total_flos": 1.3006933354296115e+17,
|
| 630 |
"train_batch_size": 2,
|
| 631 |
"trial_name": null,
|
| 632 |
"trial_params": null
|