Training in progress, step 60000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a3559f22e44a8a648518fcea3f8d97b85f98d79f16bfe2745da3c24e542ca94
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db7a3532ebb932b79a0341be80d04d64f85c81470da944cf60a0f259b00b3e37
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4fb849fc4647980403a7edf5a9af1697f444456121347b0f9e1834ac737e420
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a97b2afb49bff977115e649631e564b8b83f6947e290d5e2212d7d11b04765d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4376,6 +4376,318 @@
|
|
| 4376 |
"eval_samples_per_second": 77.227,
|
| 4377 |
"eval_steps_per_second": 19.307,
|
| 4378 |
"step": 56000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4379 |
}
|
| 4380 |
],
|
| 4381 |
"logging_steps": 100,
|
|
@@ -4395,7 +4707,7 @@
|
|
| 4395 |
"attributes": {}
|
| 4396 |
}
|
| 4397 |
},
|
| 4398 |
-
"total_flos": 1.
|
| 4399 |
"train_batch_size": 22,
|
| 4400 |
"trial_name": null,
|
| 4401 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.21818181818181817,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 60000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4376 |
"eval_samples_per_second": 77.227,
|
| 4377 |
"eval_steps_per_second": 19.307,
|
| 4378 |
"step": 56000
|
| 4379 |
+
},
|
| 4380 |
+
{
|
| 4381 |
+
"epoch": 0.18272727272727274,
|
| 4382 |
+
"grad_norm": 0.15831124782562256,
|
| 4383 |
+
"learning_rate": 0.00048535943984463943,
|
| 4384 |
+
"loss": 2.685963134765625,
|
| 4385 |
+
"step": 56100
|
| 4386 |
+
},
|
| 4387 |
+
{
|
| 4388 |
+
"epoch": 0.18363636363636363,
|
| 4389 |
+
"grad_norm": 0.17237283289432526,
|
| 4390 |
+
"learning_rate": 0.00048393016821573625,
|
| 4391 |
+
"loss": 2.652848205566406,
|
| 4392 |
+
"step": 56200
|
| 4393 |
+
},
|
| 4394 |
+
{
|
| 4395 |
+
"epoch": 0.18454545454545454,
|
| 4396 |
+
"grad_norm": 0.172745019197464,
|
| 4397 |
+
"learning_rate": 0.00048250102802172067,
|
| 4398 |
+
"loss": 2.6385073852539063,
|
| 4399 |
+
"step": 56300
|
| 4400 |
+
},
|
| 4401 |
+
{
|
| 4402 |
+
"epoch": 0.18545454545454546,
|
| 4403 |
+
"grad_norm": 0.16651754081249237,
|
| 4404 |
+
"learning_rate": 0.00048107203095150636,
|
| 4405 |
+
"loss": 2.6532525634765625,
|
| 4406 |
+
"step": 56400
|
| 4407 |
+
},
|
| 4408 |
+
{
|
| 4409 |
+
"epoch": 0.18636363636363637,
|
| 4410 |
+
"grad_norm": 0.16987019777297974,
|
| 4411 |
+
"learning_rate": 0.00047964318869283683,
|
| 4412 |
+
"loss": 2.690726623535156,
|
| 4413 |
+
"step": 56500
|
| 4414 |
+
},
|
| 4415 |
+
{
|
| 4416 |
+
"epoch": 0.18727272727272729,
|
| 4417 |
+
"grad_norm": 0.15424904227256775,
|
| 4418 |
+
"learning_rate": 0.000478214512932189,
|
| 4419 |
+
"loss": 2.6622409057617187,
|
| 4420 |
+
"step": 56600
|
| 4421 |
+
},
|
| 4422 |
+
{
|
| 4423 |
+
"epoch": 0.18818181818181817,
|
| 4424 |
+
"grad_norm": 0.1839853674173355,
|
| 4425 |
+
"learning_rate": 0.0004767860153546783,
|
| 4426 |
+
"loss": 2.683760681152344,
|
| 4427 |
+
"step": 56700
|
| 4428 |
+
},
|
| 4429 |
+
{
|
| 4430 |
+
"epoch": 0.1890909090909091,
|
| 4431 |
+
"grad_norm": 0.15451455116271973,
|
| 4432 |
+
"learning_rate": 0.0004753577076439628,
|
| 4433 |
+
"loss": 2.6614370727539063,
|
| 4434 |
+
"step": 56800
|
| 4435 |
+
},
|
| 4436 |
+
{
|
| 4437 |
+
"epoch": 0.19,
|
| 4438 |
+
"grad_norm": 0.19505156576633453,
|
| 4439 |
+
"learning_rate": 0.0004739296014821474,
|
| 4440 |
+
"loss": 2.65382080078125,
|
| 4441 |
+
"step": 56900
|
| 4442 |
+
},
|
| 4443 |
+
{
|
| 4444 |
+
"epoch": 0.19090909090909092,
|
| 4445 |
+
"grad_norm": 0.20561884343624115,
|
| 4446 |
+
"learning_rate": 0.0004725017085496889,
|
| 4447 |
+
"loss": 2.70877685546875,
|
| 4448 |
+
"step": 57000
|
| 4449 |
+
},
|
| 4450 |
+
{
|
| 4451 |
+
"epoch": 0.19090909090909092,
|
| 4452 |
+
"eval_loss": 3.0625686645507812,
|
| 4453 |
+
"eval_runtime": 7.4104,
|
| 4454 |
+
"eval_samples_per_second": 77.728,
|
| 4455 |
+
"eval_steps_per_second": 19.432,
|
| 4456 |
+
"step": 57000
|
| 4457 |
+
},
|
| 4458 |
+
{
|
| 4459 |
+
"epoch": 0.1918181818181818,
|
| 4460 |
+
"grad_norm": 0.1769583523273468,
|
| 4461 |
+
"learning_rate": 0.00047107404052529957,
|
| 4462 |
+
"loss": 2.6674728393554688,
|
| 4463 |
+
"step": 57100
|
| 4464 |
+
},
|
| 4465 |
+
{
|
| 4466 |
+
"epoch": 0.19272727272727272,
|
| 4467 |
+
"grad_norm": 0.15023104846477509,
|
| 4468 |
+
"learning_rate": 0.0004696466090858528,
|
| 4469 |
+
"loss": 2.6564959716796874,
|
| 4470 |
+
"step": 57200
|
| 4471 |
+
},
|
| 4472 |
+
{
|
| 4473 |
+
"epoch": 0.19363636363636363,
|
| 4474 |
+
"grad_norm": 0.1738213300704956,
|
| 4475 |
+
"learning_rate": 0.00046821942590628645,
|
| 4476 |
+
"loss": 2.6518304443359373,
|
| 4477 |
+
"step": 57300
|
| 4478 |
+
},
|
| 4479 |
+
{
|
| 4480 |
+
"epoch": 0.19454545454545455,
|
| 4481 |
+
"grad_norm": 0.15652106702327728,
|
| 4482 |
+
"learning_rate": 0.00046679250265950815,
|
| 4483 |
+
"loss": 2.6429074096679686,
|
| 4484 |
+
"step": 57400
|
| 4485 |
+
},
|
| 4486 |
+
{
|
| 4487 |
+
"epoch": 0.19545454545454546,
|
| 4488 |
+
"grad_norm": 0.20546045899391174,
|
| 4489 |
+
"learning_rate": 0.00046536585101629945,
|
| 4490 |
+
"loss": 2.66235107421875,
|
| 4491 |
+
"step": 57500
|
| 4492 |
+
},
|
| 4493 |
+
{
|
| 4494 |
+
"epoch": 0.19636363636363635,
|
| 4495 |
+
"grad_norm": 0.15202665328979492,
|
| 4496 |
+
"learning_rate": 0.0004639394826452204,
|
| 4497 |
+
"loss": 2.635772399902344,
|
| 4498 |
+
"step": 57600
|
| 4499 |
+
},
|
| 4500 |
+
{
|
| 4501 |
+
"epoch": 0.19727272727272727,
|
| 4502 |
+
"grad_norm": 0.1581605225801468,
|
| 4503 |
+
"learning_rate": 0.00046251340921251436,
|
| 4504 |
+
"loss": 2.6710745239257814,
|
| 4505 |
+
"step": 57700
|
| 4506 |
+
},
|
| 4507 |
+
{
|
| 4508 |
+
"epoch": 0.19818181818181818,
|
| 4509 |
+
"grad_norm": 0.19863693416118622,
|
| 4510 |
+
"learning_rate": 0.000461087642382012,
|
| 4511 |
+
"loss": 2.645235595703125,
|
| 4512 |
+
"step": 57800
|
| 4513 |
+
},
|
| 4514 |
+
{
|
| 4515 |
+
"epoch": 0.1990909090909091,
|
| 4516 |
+
"grad_norm": 0.14989744126796722,
|
| 4517 |
+
"learning_rate": 0.00045966219381503694,
|
| 4518 |
+
"loss": 2.6374029541015624,
|
| 4519 |
+
"step": 57900
|
| 4520 |
+
},
|
| 4521 |
+
{
|
| 4522 |
+
"epoch": 0.2,
|
| 4523 |
+
"grad_norm": 0.18618331849575043,
|
| 4524 |
+
"learning_rate": 0.000458237075170309,
|
| 4525 |
+
"loss": 2.6277200317382814,
|
| 4526 |
+
"step": 58000
|
| 4527 |
+
},
|
| 4528 |
+
{
|
| 4529 |
+
"epoch": 0.2,
|
| 4530 |
+
"eval_loss": 3.0661063194274902,
|
| 4531 |
+
"eval_runtime": 7.4551,
|
| 4532 |
+
"eval_samples_per_second": 77.262,
|
| 4533 |
+
"eval_steps_per_second": 19.316,
|
| 4534 |
+
"step": 58000
|
| 4535 |
+
},
|
| 4536 |
+
{
|
| 4537 |
+
"epoch": 0.2009090909090909,
|
| 4538 |
+
"grad_norm": 0.16106659173965454,
|
| 4539 |
+
"learning_rate": 0.00045681229810385005,
|
| 4540 |
+
"loss": 2.6352557373046874,
|
| 4541 |
+
"step": 58100
|
| 4542 |
+
},
|
| 4543 |
+
{
|
| 4544 |
+
"epoch": 0.2018181818181818,
|
| 4545 |
+
"grad_norm": 0.14770276844501495,
|
| 4546 |
+
"learning_rate": 0.000455387874268888,
|
| 4547 |
+
"loss": 2.627791442871094,
|
| 4548 |
+
"step": 58200
|
| 4549 |
+
},
|
| 4550 |
+
{
|
| 4551 |
+
"epoch": 0.20272727272727273,
|
| 4552 |
+
"grad_norm": 0.17903557419776917,
|
| 4553 |
+
"learning_rate": 0.0004539638153157621,
|
| 4554 |
+
"loss": 2.638799133300781,
|
| 4555 |
+
"step": 58300
|
| 4556 |
+
},
|
| 4557 |
+
{
|
| 4558 |
+
"epoch": 0.20363636363636364,
|
| 4559 |
+
"grad_norm": 0.16185429692268372,
|
| 4560 |
+
"learning_rate": 0.0004525401328918264,
|
| 4561 |
+
"loss": 2.635686340332031,
|
| 4562 |
+
"step": 58400
|
| 4563 |
+
},
|
| 4564 |
+
{
|
| 4565 |
+
"epoch": 0.20454545454545456,
|
| 4566 |
+
"grad_norm": 0.17657916247844696,
|
| 4567 |
+
"learning_rate": 0.00045111683864135617,
|
| 4568 |
+
"loss": 2.6360543823242186,
|
| 4569 |
+
"step": 58500
|
| 4570 |
+
},
|
| 4571 |
+
{
|
| 4572 |
+
"epoch": 0.20545454545454545,
|
| 4573 |
+
"grad_norm": 0.14804042875766754,
|
| 4574 |
+
"learning_rate": 0.0004496939442054514,
|
| 4575 |
+
"loss": 2.643255310058594,
|
| 4576 |
+
"step": 58600
|
| 4577 |
+
},
|
| 4578 |
+
{
|
| 4579 |
+
"epoch": 0.20636363636363636,
|
| 4580 |
+
"grad_norm": 0.16301922500133514,
|
| 4581 |
+
"learning_rate": 0.0004482714612219419,
|
| 4582 |
+
"loss": 2.64661376953125,
|
| 4583 |
+
"step": 58700
|
| 4584 |
+
},
|
| 4585 |
+
{
|
| 4586 |
+
"epoch": 0.20727272727272728,
|
| 4587 |
+
"grad_norm": 0.1726071685552597,
|
| 4588 |
+
"learning_rate": 0.00044684940132529264,
|
| 4589 |
+
"loss": 2.6665936279296876,
|
| 4590 |
+
"step": 58800
|
| 4591 |
+
},
|
| 4592 |
+
{
|
| 4593 |
+
"epoch": 0.2081818181818182,
|
| 4594 |
+
"grad_norm": 0.16906021535396576,
|
| 4595 |
+
"learning_rate": 0.0004454277761465076,
|
| 4596 |
+
"loss": 2.65294921875,
|
| 4597 |
+
"step": 58900
|
| 4598 |
+
},
|
| 4599 |
+
{
|
| 4600 |
+
"epoch": 0.20909090909090908,
|
| 4601 |
+
"grad_norm": 0.17039760947227478,
|
| 4602 |
+
"learning_rate": 0.0004440065973130358,
|
| 4603 |
+
"loss": 2.6539688110351562,
|
| 4604 |
+
"step": 59000
|
| 4605 |
+
},
|
| 4606 |
+
{
|
| 4607 |
+
"epoch": 0.20909090909090908,
|
| 4608 |
+
"eval_loss": 3.057651996612549,
|
| 4609 |
+
"eval_runtime": 7.4341,
|
| 4610 |
+
"eval_samples_per_second": 77.481,
|
| 4611 |
+
"eval_steps_per_second": 19.37,
|
| 4612 |
+
"step": 59000
|
| 4613 |
+
},
|
| 4614 |
+
{
|
| 4615 |
+
"epoch": 0.21,
|
| 4616 |
+
"grad_norm": 0.1761595457792282,
|
| 4617 |
+
"learning_rate": 0.0004425858764486751,
|
| 4618 |
+
"loss": 2.6766180419921874,
|
| 4619 |
+
"step": 59100
|
| 4620 |
+
},
|
| 4621 |
+
{
|
| 4622 |
+
"epoch": 0.2109090909090909,
|
| 4623 |
+
"grad_norm": 0.16640876233577728,
|
| 4624 |
+
"learning_rate": 0.00044116562517347796,
|
| 4625 |
+
"loss": 2.6426458740234375,
|
| 4626 |
+
"step": 59200
|
| 4627 |
+
},
|
| 4628 |
+
{
|
| 4629 |
+
"epoch": 0.21181818181818182,
|
| 4630 |
+
"grad_norm": 0.1541028618812561,
|
| 4631 |
+
"learning_rate": 0.00043974585510365614,
|
| 4632 |
+
"loss": 2.6716134643554685,
|
| 4633 |
+
"step": 59300
|
| 4634 |
+
},
|
| 4635 |
+
{
|
| 4636 |
+
"epoch": 0.21272727272727274,
|
| 4637 |
+
"grad_norm": 0.16134560108184814,
|
| 4638 |
+
"learning_rate": 0.0004383265778514852,
|
| 4639 |
+
"loss": 2.6808517456054686,
|
| 4640 |
+
"step": 59400
|
| 4641 |
+
},
|
| 4642 |
+
{
|
| 4643 |
+
"epoch": 0.21363636363636362,
|
| 4644 |
+
"grad_norm": 0.1456531435251236,
|
| 4645 |
+
"learning_rate": 0.0004369078050252105,
|
| 4646 |
+
"loss": 2.684778747558594,
|
| 4647 |
+
"step": 59500
|
| 4648 |
+
},
|
| 4649 |
+
{
|
| 4650 |
+
"epoch": 0.21454545454545454,
|
| 4651 |
+
"grad_norm": 0.1792006641626358,
|
| 4652 |
+
"learning_rate": 0.00043548954822895117,
|
| 4653 |
+
"loss": 2.649779052734375,
|
| 4654 |
+
"step": 59600
|
| 4655 |
+
},
|
| 4656 |
+
{
|
| 4657 |
+
"epoch": 0.21545454545454545,
|
| 4658 |
+
"grad_norm": 0.18216730654239655,
|
| 4659 |
+
"learning_rate": 0.00043407181906260627,
|
| 4660 |
+
"loss": 2.677138671875,
|
| 4661 |
+
"step": 59700
|
| 4662 |
+
},
|
| 4663 |
+
{
|
| 4664 |
+
"epoch": 0.21636363636363637,
|
| 4665 |
+
"grad_norm": 0.1598980575799942,
|
| 4666 |
+
"learning_rate": 0.0004326546291217589,
|
| 4667 |
+
"loss": 2.6525616455078125,
|
| 4668 |
+
"step": 59800
|
| 4669 |
+
},
|
| 4670 |
+
{
|
| 4671 |
+
"epoch": 0.21727272727272728,
|
| 4672 |
+
"grad_norm": 0.16436710953712463,
|
| 4673 |
+
"learning_rate": 0.0004312379899975821,
|
| 4674 |
+
"loss": 2.6850616455078127,
|
| 4675 |
+
"step": 59900
|
| 4676 |
+
},
|
| 4677 |
+
{
|
| 4678 |
+
"epoch": 0.21818181818181817,
|
| 4679 |
+
"grad_norm": 0.175828754901886,
|
| 4680 |
+
"learning_rate": 0.00042982191327674404,
|
| 4681 |
+
"loss": 2.6756378173828126,
|
| 4682 |
+
"step": 60000
|
| 4683 |
+
},
|
| 4684 |
+
{
|
| 4685 |
+
"epoch": 0.21818181818181817,
|
| 4686 |
+
"eval_loss": 3.0540809631347656,
|
| 4687 |
+
"eval_runtime": 7.4118,
|
| 4688 |
+
"eval_samples_per_second": 77.714,
|
| 4689 |
+
"eval_steps_per_second": 19.429,
|
| 4690 |
+
"step": 60000
|
| 4691 |
}
|
| 4692 |
],
|
| 4693 |
"logging_steps": 100,
|
|
|
|
| 4707 |
"attributes": {}
|
| 4708 |
}
|
| 4709 |
},
|
| 4710 |
+
"total_flos": 1.49487485976576e+18,
|
| 4711 |
"train_batch_size": 22,
|
| 4712 |
"trial_name": null,
|
| 4713 |
"trial_params": null
|