Training in progress, step 75, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +188 -5
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9624e9a151663ac191cc4fa232c61bd9caaa5f68fc967bf4426ca5df8971d9b9
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7677e032df90eb88721c864579dca479a5b6579e09f8f42cb668edc62cbed8d
|
3 |
size 640009682
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac2a5b05f09b8564f5d7ae67ac0484834ab5096f9c2c5416efc0bd11bed918dd
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bdd58a7b31c078fa85d00c7c6485823b15270c30aba6855ca78181731d87134
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96335fae8d0428a10bf29ce620e4c16471dfc1c7bc18964f4276730c5e3fa77e
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af91e38f8ee05f8cc00ff1294dd2d779b194430a94ac4b05a2cb8d13aa0041e
|
3 |
size 15024
|
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:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -381,6 +381,189 @@
|
|
381 |
"eval_samples_per_second": 17.021,
|
382 |
"eval_steps_per_second": 4.426,
|
383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
@@ -409,7 +592,7 @@
|
|
409 |
"attributes": {}
|
410 |
}
|
411 |
},
|
412 |
-
"total_flos":
|
413 |
"train_batch_size": 1,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.623828649520874,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-75",
|
4 |
+
"epoch": 0.09725655468655023,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 75,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
381 |
"eval_samples_per_second": 17.021,
|
382 |
"eval_steps_per_second": 4.426,
|
383 |
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.06613445718685415,
|
387 |
+
"grad_norm": 11.396697044372559,
|
388 |
+
"learning_rate": 5.192909139858981e-05,
|
389 |
+
"loss": 32.6268,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.0674312112493415,
|
394 |
+
"grad_norm": 13.8756742477417,
|
395 |
+
"learning_rate": 5.0398113297608465e-05,
|
396 |
+
"loss": 30.8687,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.06872796531182883,
|
401 |
+
"grad_norm": 11.302550315856934,
|
402 |
+
"learning_rate": 4.887250079066892e-05,
|
403 |
+
"loss": 20.7947,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.07002471937431616,
|
408 |
+
"grad_norm": 8.959757804870605,
|
409 |
+
"learning_rate": 4.7354032673710005e-05,
|
410 |
+
"loss": 14.8,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.0713214734368035,
|
415 |
+
"grad_norm": 9.0787992477417,
|
416 |
+
"learning_rate": 4.584447941263149e-05,
|
417 |
+
"loss": 10.1572,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.07261822749929084,
|
422 |
+
"grad_norm": 6.953489303588867,
|
423 |
+
"learning_rate": 4.43456010790099e-05,
|
424 |
+
"loss": 6.886,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.07391498156177817,
|
429 |
+
"grad_norm": 6.784447193145752,
|
430 |
+
"learning_rate": 4.285914529793391e-05,
|
431 |
+
"loss": 10.6766,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.07521173562426552,
|
436 |
+
"grad_norm": 7.345515251159668,
|
437 |
+
"learning_rate": 4.13868452103516e-05,
|
438 |
+
"loss": 13.2427,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.07650848968675285,
|
443 |
+
"grad_norm": 10.04677963256836,
|
444 |
+
"learning_rate": 3.9930417452305626e-05,
|
445 |
+
"loss": 15.7304,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.07780524374924018,
|
450 |
+
"grad_norm": 13.683038711547852,
|
451 |
+
"learning_rate": 3.8491560153412466e-05,
|
452 |
+
"loss": 18.4109,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.07910199781172753,
|
457 |
+
"grad_norm": 12.892768859863281,
|
458 |
+
"learning_rate": 3.707195095691913e-05,
|
459 |
+
"loss": 22.273,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.08039875187421486,
|
464 |
+
"grad_norm": 17.1517391204834,
|
465 |
+
"learning_rate": 3.567324506364632e-05,
|
466 |
+
"loss": 32.1346,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.08169550593670219,
|
471 |
+
"grad_norm": 18.07764434814453,
|
472 |
+
"learning_rate": 3.4297073302098156e-05,
|
473 |
+
"loss": 39.0696,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.08299225999918954,
|
478 |
+
"grad_norm": 10.018913269042969,
|
479 |
+
"learning_rate": 3.2945040226989244e-05,
|
480 |
+
"loss": 31.6719,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.08428901406167687,
|
485 |
+
"grad_norm": 9.357498168945312,
|
486 |
+
"learning_rate": 3.16187222484055e-05,
|
487 |
+
"loss": 19.8276,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.0855857681241642,
|
492 |
+
"grad_norm": 6.495688438415527,
|
493 |
+
"learning_rate": 3.0319665793780648e-05,
|
494 |
+
"loss": 12.7109,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.08688252218665153,
|
499 |
+
"grad_norm": 6.495363712310791,
|
500 |
+
"learning_rate": 2.9049385504830985e-05,
|
501 |
+
"loss": 10.4677,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.08817927624913888,
|
506 |
+
"grad_norm": 7.190054416656494,
|
507 |
+
"learning_rate": 2.7809362471550748e-05,
|
508 |
+
"loss": 10.2256,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.08947603031162621,
|
513 |
+
"grad_norm": 7.307028293609619,
|
514 |
+
"learning_rate": 2.660104250532764e-05,
|
515 |
+
"loss": 14.0544,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.09077278437411354,
|
520 |
+
"grad_norm": 4.946413516998291,
|
521 |
+
"learning_rate": 2.5425834453191232e-05,
|
522 |
+
"loss": 5.7595,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.09206953843660089,
|
527 |
+
"grad_norm": 7.481423854827881,
|
528 |
+
"learning_rate": 2.4285108555160577e-05,
|
529 |
+
"loss": 13.2307,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.09336629249908822,
|
534 |
+
"grad_norm": 9.990346908569336,
|
535 |
+
"learning_rate": 2.3180194846605367e-05,
|
536 |
+
"loss": 19.5935,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.09466304656157555,
|
541 |
+
"grad_norm": 9.962550163269043,
|
542 |
+
"learning_rate": 2.2112381607484417e-05,
|
543 |
+
"loss": 20.8605,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.0959598006240629,
|
548 |
+
"grad_norm": 15.367573738098145,
|
549 |
+
"learning_rate": 2.1082913860268765e-05,
|
550 |
+
"loss": 32.2455,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.09725655468655023,
|
555 |
+
"grad_norm": 23.091154098510742,
|
556 |
+
"learning_rate": 2.0092991918301108e-05,
|
557 |
+
"loss": 34.7624,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.09725655468655023,
|
562 |
+
"eval_loss": 0.623828649520874,
|
563 |
+
"eval_runtime": 2.9349,
|
564 |
+
"eval_samples_per_second": 17.036,
|
565 |
+
"eval_steps_per_second": 4.429,
|
566 |
+
"step": 75
|
567 |
}
|
568 |
],
|
569 |
"logging_steps": 1,
|
|
|
592 |
"attributes": {}
|
593 |
}
|
594 |
},
|
595 |
+
"total_flos": 7.889478898365235e+17,
|
596 |
"train_batch_size": 1,
|
597 |
"trial_name": null,
|
598 |
"trial_params": null
|