mikhail-panzo
commited on
Commit
•
595650a
1
Parent(s):
1025be2
Training in progress, step 3500, 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 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7ca77c9802a04580d4e31461c12e17e933a3887576c9945c8e484919c0199d
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af00b7662d798d9ddc39cfcfb857f08567041c5b1d85350af7dc033ca6e0561
|
3 |
size 1155772233
|
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 sha256:3bf2e8e416936cf8f439e26111c4885ea7eb78961a1138cdb6b5117961ec9a25
|
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 sha256:540fdd37fedd646a830d2028d95a2e3f201d23e9e3ef83da82d08e9580c78331
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s4000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -475,6 +475,84 @@
|
|
475 |
"eval_samples_per_second": 25.553,
|
476 |
"eval_steps_per_second": 3.265,
|
477 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
478 |
}
|
479 |
],
|
480 |
"logging_steps": 50,
|
@@ -494,7 +572,7 @@
|
|
494 |
"attributes": {}
|
495 |
}
|
496 |
},
|
497 |
-
"total_flos": 3.
|
498 |
"train_batch_size": 16,
|
499 |
"trial_name": null,
|
500 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.39516589045524597,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s4000/checkpoint-3500",
|
4 |
+
"epoch": 138.6138613861386,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
475 |
"eval_samples_per_second": 25.553,
|
476 |
"eval_steps_per_second": 3.265,
|
477 |
"step": 3000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 120.79207920792079,
|
481 |
+
"grad_norm": 0.7711001634597778,
|
482 |
+
"learning_rate": 4.755e-05,
|
483 |
+
"loss": 0.3657,
|
484 |
+
"step": 3050
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 122.77227722772277,
|
488 |
+
"grad_norm": 0.9125708937644958,
|
489 |
+
"learning_rate": 4.5050000000000004e-05,
|
490 |
+
"loss": 0.3665,
|
491 |
+
"step": 3100
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 124.75247524752476,
|
495 |
+
"grad_norm": 1.138588786125183,
|
496 |
+
"learning_rate": 4.2550000000000004e-05,
|
497 |
+
"loss": 0.3714,
|
498 |
+
"step": 3150
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 126.73267326732673,
|
502 |
+
"grad_norm": 0.8590717315673828,
|
503 |
+
"learning_rate": 4.0050000000000004e-05,
|
504 |
+
"loss": 0.3696,
|
505 |
+
"step": 3200
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 128.7128712871287,
|
509 |
+
"grad_norm": 0.8743947148323059,
|
510 |
+
"learning_rate": 3.7550000000000005e-05,
|
511 |
+
"loss": 0.3652,
|
512 |
+
"step": 3250
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 130.69306930693068,
|
516 |
+
"grad_norm": 0.8117642998695374,
|
517 |
+
"learning_rate": 3.505e-05,
|
518 |
+
"loss": 0.3643,
|
519 |
+
"step": 3300
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 132.67326732673268,
|
523 |
+
"grad_norm": 0.9085512161254883,
|
524 |
+
"learning_rate": 3.2550000000000005e-05,
|
525 |
+
"loss": 0.3637,
|
526 |
+
"step": 3350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 134.65346534653466,
|
530 |
+
"grad_norm": 0.8282843232154846,
|
531 |
+
"learning_rate": 3.0050000000000002e-05,
|
532 |
+
"loss": 0.3594,
|
533 |
+
"step": 3400
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 136.63366336633663,
|
537 |
+
"grad_norm": 0.6631731390953064,
|
538 |
+
"learning_rate": 2.7550000000000002e-05,
|
539 |
+
"loss": 0.3621,
|
540 |
+
"step": 3450
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 138.6138613861386,
|
544 |
+
"grad_norm": 0.8194773197174072,
|
545 |
+
"learning_rate": 2.5050000000000002e-05,
|
546 |
+
"loss": 0.3628,
|
547 |
+
"step": 3500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 138.6138613861386,
|
551 |
+
"eval_loss": 0.39516589045524597,
|
552 |
+
"eval_runtime": 7.3015,
|
553 |
+
"eval_samples_per_second": 24.652,
|
554 |
+
"eval_steps_per_second": 3.15,
|
555 |
+
"step": 3500
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 50,
|
|
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
+
"total_flos": 3.78207684271391e+16,
|
576 |
"train_batch_size": 16,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|