Training in progress, step 70, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 125048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55b3090f899b46d492f32633e4515d9d6ae108238f6d47c3e88688671dccb48c
|
3 |
size 125048
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 162868
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2046aeb674d75035e95a8d14adfeee0462127d510df5daeba02a5d1eab404340
|
3 |
size 162868
|
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 sha256:670916a94714b472f443269033bde75c99b199370216d2fe1fb8611619905402
|
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 sha256:1074437c4c638775a20a86de2e689d1a14d0ff4e4137df2ddeb45e94a776caef
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 11.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -531,6 +531,92 @@
|
|
531 |
"eval_samples_per_second": 52.863,
|
532 |
"eval_steps_per_second": 26.435,
|
533 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
534 |
}
|
535 |
],
|
536 |
"logging_steps": 1,
|
@@ -559,7 +645,7 @@
|
|
559 |
"attributes": {}
|
560 |
}
|
561 |
},
|
562 |
-
"total_flos":
|
563 |
"train_batch_size": 2,
|
564 |
"trial_name": null,
|
565 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 11.046669960021973,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-70",
|
4 |
+
"epoch": 0.003163770310275474,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 70,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
531 |
"eval_samples_per_second": 52.863,
|
532 |
"eval_steps_per_second": 26.435,
|
533 |
"step": 60
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.0027569998418114847,
|
537 |
+
"grad_norm": 0.8553807735443115,
|
538 |
+
"learning_rate": 0.00019470159657616215,
|
539 |
+
"loss": 44.2439,
|
540 |
+
"step": 61
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.0028021965605297054,
|
544 |
+
"grad_norm": 0.7586395740509033,
|
545 |
+
"learning_rate": 0.00019449372563954293,
|
546 |
+
"loss": 44.1943,
|
547 |
+
"step": 62
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.0028473932792479266,
|
551 |
+
"grad_norm": 0.7628232836723328,
|
552 |
+
"learning_rate": 0.0001942819704359693,
|
553 |
+
"loss": 44.2594,
|
554 |
+
"step": 63
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.0028925899979661478,
|
558 |
+
"grad_norm": 0.718551754951477,
|
559 |
+
"learning_rate": 0.00019406633966986828,
|
560 |
+
"loss": 44.2302,
|
561 |
+
"step": 64
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.002937786716684369,
|
565 |
+
"grad_norm": 0.7625423073768616,
|
566 |
+
"learning_rate": 0.00019384684220497605,
|
567 |
+
"loss": 44.1989,
|
568 |
+
"step": 65
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.002937786716684369,
|
572 |
+
"eval_loss": 11.051901817321777,
|
573 |
+
"eval_runtime": 176.1759,
|
574 |
+
"eval_samples_per_second": 52.885,
|
575 |
+
"eval_steps_per_second": 26.445,
|
576 |
+
"step": 65
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.0029829834354025897,
|
580 |
+
"grad_norm": 0.7891851663589478,
|
581 |
+
"learning_rate": 0.00019362348706397373,
|
582 |
+
"loss": 44.2199,
|
583 |
+
"step": 66
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.003028180154120811,
|
587 |
+
"grad_norm": 0.6770808100700378,
|
588 |
+
"learning_rate": 0.00019339628342811632,
|
589 |
+
"loss": 44.1689,
|
590 |
+
"step": 67
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.003073376872839032,
|
594 |
+
"grad_norm": 0.7498692870140076,
|
595 |
+
"learning_rate": 0.0001931652406368554,
|
596 |
+
"loss": 44.1741,
|
597 |
+
"step": 68
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.0031185735915572528,
|
601 |
+
"grad_norm": 0.7661782503128052,
|
602 |
+
"learning_rate": 0.0001929303681874552,
|
603 |
+
"loss": 44.2123,
|
604 |
+
"step": 69
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.003163770310275474,
|
608 |
+
"grad_norm": 0.6438837647438049,
|
609 |
+
"learning_rate": 0.0001926916757346022,
|
610 |
+
"loss": 44.1718,
|
611 |
+
"step": 70
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.003163770310275474,
|
615 |
+
"eval_loss": 11.046669960021973,
|
616 |
+
"eval_runtime": 176.3634,
|
617 |
+
"eval_samples_per_second": 52.828,
|
618 |
+
"eval_steps_per_second": 26.417,
|
619 |
+
"step": 70
|
620 |
}
|
621 |
],
|
622 |
"logging_steps": 1,
|
|
|
645 |
"attributes": {}
|
646 |
}
|
647 |
},
|
648 |
+
"total_flos": 735471206400.0,
|
649 |
"train_batch_size": 2,
|
650 |
"trial_name": null,
|
651 |
"trial_params": null
|