mikhail-panzo
commited on
Commit
•
a193d7d
1
Parent(s):
16b3a8c
Training in progress, step 3000, 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 sha256:170bf6c92ae110e8eb5c1a3c0f5e69f21a3de0e3e4a77fd59d30a079ac9d4811
|
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 sha256:7cb04e2f0ab69bfcb0d47f3b2af07eb3e8c2cb14295c7e2962418f07502fe274
|
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:b0bd26a66f18a63513b4644dff9bbce4420bc172da7cc36bbc9e2bbc11796d8c
|
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 sha256:1f58257cf138830d5c1b5b1b46ab56c0eb866a6a719b4e3b6cce54569429bd96
|
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_le4_s8000/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,
|
@@ -397,6 +397,84 @@
|
|
397 |
"eval_samples_per_second": 31.28,
|
398 |
"eval_steps_per_second": 3.913,
|
399 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
400 |
}
|
401 |
],
|
402 |
"logging_steps": 50,
|
@@ -416,7 +494,7 @@
|
|
416 |
"attributes": {}
|
417 |
}
|
418 |
},
|
419 |
-
"total_flos":
|
420 |
"train_batch_size": 16,
|
421 |
"trial_name": null,
|
422 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3458922803401947,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-3000",
|
4 |
+
"epoch": 5.026178010471204,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
397 |
"eval_samples_per_second": 31.28,
|
398 |
"eval_steps_per_second": 3.913,
|
399 |
"step": 2500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 4.272251308900524,
|
403 |
+
"grad_norm": 2.468984842300415,
|
404 |
+
"learning_rate": 9.451000000000002e-05,
|
405 |
+
"loss": 0.3902,
|
406 |
+
"step": 2550
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 4.356020942408377,
|
410 |
+
"grad_norm": 1.2810943126678467,
|
411 |
+
"learning_rate": 9.401e-05,
|
412 |
+
"loss": 0.386,
|
413 |
+
"step": 2600
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 4.439790575916231,
|
417 |
+
"grad_norm": 1.6781765222549438,
|
418 |
+
"learning_rate": 9.351e-05,
|
419 |
+
"loss": 0.383,
|
420 |
+
"step": 2650
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 4.523560209424084,
|
424 |
+
"grad_norm": 1.617163896560669,
|
425 |
+
"learning_rate": 9.301e-05,
|
426 |
+
"loss": 0.3849,
|
427 |
+
"step": 2700
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 4.607329842931938,
|
431 |
+
"grad_norm": 1.4169151782989502,
|
432 |
+
"learning_rate": 9.251000000000001e-05,
|
433 |
+
"loss": 0.3807,
|
434 |
+
"step": 2750
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 4.69109947643979,
|
438 |
+
"grad_norm": 1.1944037675857544,
|
439 |
+
"learning_rate": 9.201000000000001e-05,
|
440 |
+
"loss": 0.3838,
|
441 |
+
"step": 2800
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 4.774869109947644,
|
445 |
+
"grad_norm": 1.7312718629837036,
|
446 |
+
"learning_rate": 9.151000000000001e-05,
|
447 |
+
"loss": 0.3808,
|
448 |
+
"step": 2850
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 4.858638743455497,
|
452 |
+
"grad_norm": 1.357228398323059,
|
453 |
+
"learning_rate": 9.101000000000001e-05,
|
454 |
+
"loss": 0.3832,
|
455 |
+
"step": 2900
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 4.942408376963351,
|
459 |
+
"grad_norm": 1.2495553493499756,
|
460 |
+
"learning_rate": 9.051000000000001e-05,
|
461 |
+
"loss": 0.3837,
|
462 |
+
"step": 2950
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 5.026178010471204,
|
466 |
+
"grad_norm": 1.3688994646072388,
|
467 |
+
"learning_rate": 9.001e-05,
|
468 |
+
"loss": 0.3802,
|
469 |
+
"step": 3000
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 5.026178010471204,
|
473 |
+
"eval_loss": 0.3458922803401947,
|
474 |
+
"eval_runtime": 277.371,
|
475 |
+
"eval_samples_per_second": 30.605,
|
476 |
+
"eval_steps_per_second": 3.829,
|
477 |
+
"step": 3000
|
478 |
}
|
479 |
],
|
480 |
"logging_steps": 50,
|
|
|
494 |
"attributes": {}
|
495 |
}
|
496 |
},
|
497 |
+
"total_flos": 5.37491824204009e+16,
|
498 |
"train_batch_size": 16,
|
499 |
"trial_name": null,
|
500 |
"trial_params": null
|