mikhail-panzo
commited on
Commit
•
fe05b9b
1
Parent(s):
bb27c7a
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 sha256:496158892ef6f1b16a4adb70da5d5ef8bea4d4e7a9f957a9a6c135da931ce57c
|
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 sha256:1023f70e0e98439d17243ec462d604fc30b3d89014f3443daadb033a23e653e2
|
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:aac92226f0d21eb319c78dbae49877455a40d317910aac9583ab04de32de7d1c
|
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 sha256:6ccd61c3eccb4c4508bcc2fc4d263b434bb910fdf4295c867e005e4b128c82ef
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-
|
4 |
-
"epoch": 5.
|
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": 33.139,
|
476 |
"eval_steps_per_second": 4.146,
|
477 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
478 |
}
|
479 |
],
|
480 |
"logging_steps": 50,
|
@@ -494,7 +572,7 @@
|
|
494 |
"attributes": {}
|
495 |
}
|
496 |
},
|
497 |
-
"total_flos":
|
498 |
"train_batch_size": 16,
|
499 |
"trial_name": null,
|
500 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.39255669713020325,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-3500",
|
4 |
+
"epoch": 5.863874345549738,
|
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": 33.139,
|
476 |
"eval_steps_per_second": 4.146,
|
477 |
"step": 3000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 5.109947643979058,
|
481 |
+
"grad_norm": 1.1454211473464966,
|
482 |
+
"learning_rate": 8.255000000000001e-06,
|
483 |
+
"loss": 0.4422,
|
484 |
+
"step": 3050
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 5.193717277486911,
|
488 |
+
"grad_norm": 1.8685294389724731,
|
489 |
+
"learning_rate": 8.171666666666668e-06,
|
490 |
+
"loss": 0.4426,
|
491 |
+
"step": 3100
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 5.277486910994765,
|
495 |
+
"grad_norm": 1.6863799095153809,
|
496 |
+
"learning_rate": 8.088333333333334e-06,
|
497 |
+
"loss": 0.4398,
|
498 |
+
"step": 3150
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 5.361256544502618,
|
502 |
+
"grad_norm": 2.249805212020874,
|
503 |
+
"learning_rate": 8.005e-06,
|
504 |
+
"loss": 0.4384,
|
505 |
+
"step": 3200
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 5.445026178010472,
|
509 |
+
"grad_norm": 2.1187326908111572,
|
510 |
+
"learning_rate": 7.921666666666667e-06,
|
511 |
+
"loss": 0.4431,
|
512 |
+
"step": 3250
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 5.528795811518324,
|
516 |
+
"grad_norm": 1.8476357460021973,
|
517 |
+
"learning_rate": 7.838333333333334e-06,
|
518 |
+
"loss": 0.4434,
|
519 |
+
"step": 3300
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 5.612565445026178,
|
523 |
+
"grad_norm": 1.6522760391235352,
|
524 |
+
"learning_rate": 7.755000000000001e-06,
|
525 |
+
"loss": 0.4343,
|
526 |
+
"step": 3350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 5.696335078534031,
|
530 |
+
"grad_norm": 1.3926664590835571,
|
531 |
+
"learning_rate": 7.671666666666668e-06,
|
532 |
+
"loss": 0.4365,
|
533 |
+
"step": 3400
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 5.780104712041885,
|
537 |
+
"grad_norm": 2.1967947483062744,
|
538 |
+
"learning_rate": 7.588333333333334e-06,
|
539 |
+
"loss": 0.4362,
|
540 |
+
"step": 3450
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 5.863874345549738,
|
544 |
+
"grad_norm": 1.5428054332733154,
|
545 |
+
"learning_rate": 7.505e-06,
|
546 |
+
"loss": 0.4337,
|
547 |
+
"step": 3500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 5.863874345549738,
|
551 |
+
"eval_loss": 0.39255669713020325,
|
552 |
+
"eval_runtime": 251.4241,
|
553 |
+
"eval_samples_per_second": 33.764,
|
554 |
+
"eval_steps_per_second": 4.224,
|
555 |
+
"step": 3500
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 50,
|
|
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
+
"total_flos": 6.269975786347891e+16,
|
576 |
"train_batch_size": 16,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|