Training in progress, step 81, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202110330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:003736294802a15151f66f8e67f2e4706c410829601a7ecb1578474277867165
|
3 |
size 202110330
|
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 sha256:712483dcfe94bc060ec2acfd864831b36255af57775103f39f5c9eb61881b2f5
|
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 sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
|
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": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -527,6 +527,69 @@
|
|
527 |
"learning_rate": 4.095071251953399e-05,
|
528 |
"loss": 0.0,
|
529 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
530 |
}
|
531 |
],
|
532 |
"logging_steps": 1,
|
@@ -546,7 +609,7 @@
|
|
546 |
"attributes": {}
|
547 |
}
|
548 |
},
|
549 |
-
"total_flos": 6.
|
550 |
"train_batch_size": 2,
|
551 |
"trial_name": null,
|
552 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06768684389199352,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 81,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
527 |
"learning_rate": 4.095071251953399e-05,
|
528 |
"loss": 0.0,
|
529 |
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.0610017235075991,
|
533 |
+
"grad_norm": NaN,
|
534 |
+
"learning_rate": 3.83534068877284e-05,
|
535 |
+
"loss": 0.0,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.0618373635556484,
|
540 |
+
"grad_norm": NaN,
|
541 |
+
"learning_rate": 3.5812607646303834e-05,
|
542 |
+
"loss": 0.0,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.06267300360369771,
|
547 |
+
"grad_norm": NaN,
|
548 |
+
"learning_rate": 3.333223252352985e-05,
|
549 |
+
"loss": 0.0,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.06350864365174701,
|
554 |
+
"grad_norm": NaN,
|
555 |
+
"learning_rate": 3.091610607806452e-05,
|
556 |
+
"loss": 0.0,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.0643442836997963,
|
561 |
+
"grad_norm": NaN,
|
562 |
+
"learning_rate": 2.856795380176244e-05,
|
563 |
+
"loss": 0.0,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.06517992374784562,
|
568 |
+
"grad_norm": NaN,
|
569 |
+
"learning_rate": 2.6291396375236232e-05,
|
570 |
+
"loss": 0.0,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.06601556379589492,
|
575 |
+
"grad_norm": NaN,
|
576 |
+
"learning_rate": 2.4089944085029363e-05,
|
577 |
+
"loss": 0.0,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.06685120384394422,
|
582 |
+
"grad_norm": NaN,
|
583 |
+
"learning_rate": 2.1966991411008938e-05,
|
584 |
+
"loss": 0.0,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.06768684389199352,
|
589 |
+
"grad_norm": NaN,
|
590 |
+
"learning_rate": 1.99258117923236e-05,
|
591 |
+
"loss": 0.0,
|
592 |
+
"step": 81
|
593 |
}
|
594 |
],
|
595 |
"logging_steps": 1,
|
|
|
609 |
"attributes": {}
|
610 |
}
|
611 |
},
|
612 |
+
"total_flos": 6.750672775859405e+16,
|
613 |
"train_batch_size": 2,
|
614 |
"trial_name": null,
|
615 |
"trial_params": null
|