Training in progress, step 650, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 578859568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91ea2e833e395bd896b7338e0b159889cb0a9805a20a0ba81249634cf8be6acb
|
| 3 |
size 578859568
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 295198386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8408296ac89ee50ae11d1a24615517bae811a4a08e26902b3f91c3361afa9523
|
| 3 |
size 295198386
|
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:d04b06ab68f7f17dc4df2206cd558b4bd98d8e29313159b73014f73bdd405dcc
|
| 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 sha256:18275b6327bd0d7d1ad9ae6ef36f205b2f0d81f6499994f6ecb9553362d17a42
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6910951733589172,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-500",
|
| 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,
|
|
@@ -4311,6 +4311,364 @@
|
|
| 4311 |
"eval_samples_per_second": 11.449,
|
| 4312 |
"eval_steps_per_second": 5.734,
|
| 4313 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4314 |
}
|
| 4315 |
],
|
| 4316 |
"logging_steps": 1,
|
|
@@ -4325,7 +4683,7 @@
|
|
| 4325 |
"early_stopping_threshold": 0.0
|
| 4326 |
},
|
| 4327 |
"attributes": {
|
| 4328 |
-
"early_stopping_patience_counter":
|
| 4329 |
}
|
| 4330 |
},
|
| 4331 |
"TrainerControl": {
|
|
@@ -4334,12 +4692,12 @@
|
|
| 4334 |
"should_evaluate": false,
|
| 4335 |
"should_log": false,
|
| 4336 |
"should_save": true,
|
| 4337 |
-
"should_training_stop":
|
| 4338 |
},
|
| 4339 |
"attributes": {}
|
| 4340 |
}
|
| 4341 |
},
|
| 4342 |
-
"total_flos":
|
| 4343 |
"train_batch_size": 2,
|
| 4344 |
"trial_name": null,
|
| 4345 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6910951733589172,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-500",
|
| 4 |
+
"epoch": 0.018067977289942392,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 650,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 4311 |
"eval_samples_per_second": 11.449,
|
| 4312 |
"eval_steps_per_second": 5.734,
|
| 4313 |
"step": 600
|
| 4314 |
+
},
|
| 4315 |
+
{
|
| 4316 |
+
"epoch": 0.016705929771162118,
|
| 4317 |
+
"grad_norm": 0.11464305222034454,
|
| 4318 |
+
"learning_rate": 0.0007000509087229895,
|
| 4319 |
+
"loss": 0.9103,
|
| 4320 |
+
"step": 601
|
| 4321 |
+
},
|
| 4322 |
+
{
|
| 4323 |
+
"epoch": 0.01673372665930049,
|
| 4324 |
+
"grad_norm": 0.09989949315786362,
|
| 4325 |
+
"learning_rate": 0.0006970252132582728,
|
| 4326 |
+
"loss": 0.8176,
|
| 4327 |
+
"step": 602
|
| 4328 |
+
},
|
| 4329 |
+
{
|
| 4330 |
+
"epoch": 0.016761523547438865,
|
| 4331 |
+
"grad_norm": 0.09268354624509811,
|
| 4332 |
+
"learning_rate": 0.0006940025687462952,
|
| 4333 |
+
"loss": 0.7983,
|
| 4334 |
+
"step": 603
|
| 4335 |
+
},
|
| 4336 |
+
{
|
| 4337 |
+
"epoch": 0.016789320435577237,
|
| 4338 |
+
"grad_norm": 0.09152427315711975,
|
| 4339 |
+
"learning_rate": 0.0006909830056250527,
|
| 4340 |
+
"loss": 0.7975,
|
| 4341 |
+
"step": 604
|
| 4342 |
+
},
|
| 4343 |
+
{
|
| 4344 |
+
"epoch": 0.01681711732371561,
|
| 4345 |
+
"grad_norm": 0.09386585652828217,
|
| 4346 |
+
"learning_rate": 0.000687966554301513,
|
| 4347 |
+
"loss": 0.8584,
|
| 4348 |
+
"step": 605
|
| 4349 |
+
},
|
| 4350 |
+
{
|
| 4351 |
+
"epoch": 0.01684491421185398,
|
| 4352 |
+
"grad_norm": 0.08477571606636047,
|
| 4353 |
+
"learning_rate": 0.0006849532451513074,
|
| 4354 |
+
"loss": 0.7387,
|
| 4355 |
+
"step": 606
|
| 4356 |
+
},
|
| 4357 |
+
{
|
| 4358 |
+
"epoch": 0.016872711099992357,
|
| 4359 |
+
"grad_norm": 0.08988666534423828,
|
| 4360 |
+
"learning_rate": 0.0006819431085184251,
|
| 4361 |
+
"loss": 0.8264,
|
| 4362 |
+
"step": 607
|
| 4363 |
+
},
|
| 4364 |
+
{
|
| 4365 |
+
"epoch": 0.01690050798813073,
|
| 4366 |
+
"grad_norm": 0.09714596718549728,
|
| 4367 |
+
"learning_rate": 0.0006789361747149092,
|
| 4368 |
+
"loss": 0.9452,
|
| 4369 |
+
"step": 608
|
| 4370 |
+
},
|
| 4371 |
+
{
|
| 4372 |
+
"epoch": 0.0169283048762691,
|
| 4373 |
+
"grad_norm": 0.10461269319057465,
|
| 4374 |
+
"learning_rate": 0.0006759324740205494,
|
| 4375 |
+
"loss": 0.7174,
|
| 4376 |
+
"step": 609
|
| 4377 |
+
},
|
| 4378 |
+
{
|
| 4379 |
+
"epoch": 0.016956101764407476,
|
| 4380 |
+
"grad_norm": 0.09161835163831711,
|
| 4381 |
+
"learning_rate": 0.0006729320366825784,
|
| 4382 |
+
"loss": 0.796,
|
| 4383 |
+
"step": 610
|
| 4384 |
+
},
|
| 4385 |
+
{
|
| 4386 |
+
"epoch": 0.016983898652545848,
|
| 4387 |
+
"grad_norm": 0.0949753150343895,
|
| 4388 |
+
"learning_rate": 0.0006699348929153668,
|
| 4389 |
+
"loss": 0.975,
|
| 4390 |
+
"step": 611
|
| 4391 |
+
},
|
| 4392 |
+
{
|
| 4393 |
+
"epoch": 0.01701169554068422,
|
| 4394 |
+
"grad_norm": 0.09028909355401993,
|
| 4395 |
+
"learning_rate": 0.0006669410729001193,
|
| 4396 |
+
"loss": 0.7738,
|
| 4397 |
+
"step": 612
|
| 4398 |
+
},
|
| 4399 |
+
{
|
| 4400 |
+
"epoch": 0.017039492428822592,
|
| 4401 |
+
"grad_norm": 0.08454867452383041,
|
| 4402 |
+
"learning_rate": 0.0006639506067845697,
|
| 4403 |
+
"loss": 0.7062,
|
| 4404 |
+
"step": 613
|
| 4405 |
+
},
|
| 4406 |
+
{
|
| 4407 |
+
"epoch": 0.017067289316960967,
|
| 4408 |
+
"grad_norm": 0.10592840611934662,
|
| 4409 |
+
"learning_rate": 0.0006609635246826793,
|
| 4410 |
+
"loss": 0.7745,
|
| 4411 |
+
"step": 614
|
| 4412 |
+
},
|
| 4413 |
+
{
|
| 4414 |
+
"epoch": 0.01709508620509934,
|
| 4415 |
+
"grad_norm": 0.09267466515302658,
|
| 4416 |
+
"learning_rate": 0.0006579798566743314,
|
| 4417 |
+
"loss": 0.8491,
|
| 4418 |
+
"step": 615
|
| 4419 |
+
},
|
| 4420 |
+
{
|
| 4421 |
+
"epoch": 0.01712288309323771,
|
| 4422 |
+
"grad_norm": 0.10221099853515625,
|
| 4423 |
+
"learning_rate": 0.0006549996328050296,
|
| 4424 |
+
"loss": 0.9564,
|
| 4425 |
+
"step": 616
|
| 4426 |
+
},
|
| 4427 |
+
{
|
| 4428 |
+
"epoch": 0.017150679981376087,
|
| 4429 |
+
"grad_norm": 0.09640829265117645,
|
| 4430 |
+
"learning_rate": 0.000652022883085595,
|
| 4431 |
+
"loss": 0.6694,
|
| 4432 |
+
"step": 617
|
| 4433 |
+
},
|
| 4434 |
+
{
|
| 4435 |
+
"epoch": 0.01717847686951446,
|
| 4436 |
+
"grad_norm": 0.09555254131555557,
|
| 4437 |
+
"learning_rate": 0.0006490496374918646,
|
| 4438 |
+
"loss": 0.7825,
|
| 4439 |
+
"step": 618
|
| 4440 |
+
},
|
| 4441 |
+
{
|
| 4442 |
+
"epoch": 0.01720627375765283,
|
| 4443 |
+
"grad_norm": 0.1080060750246048,
|
| 4444 |
+
"learning_rate": 0.0006460799259643883,
|
| 4445 |
+
"loss": 0.8122,
|
| 4446 |
+
"step": 619
|
| 4447 |
+
},
|
| 4448 |
+
{
|
| 4449 |
+
"epoch": 0.017234070645791202,
|
| 4450 |
+
"grad_norm": 0.09308885037899017,
|
| 4451 |
+
"learning_rate": 0.0006431137784081283,
|
| 4452 |
+
"loss": 0.7393,
|
| 4453 |
+
"step": 620
|
| 4454 |
+
},
|
| 4455 |
+
{
|
| 4456 |
+
"epoch": 0.017261867533929578,
|
| 4457 |
+
"grad_norm": 0.10485529899597168,
|
| 4458 |
+
"learning_rate": 0.0006401512246921576,
|
| 4459 |
+
"loss": 0.7577,
|
| 4460 |
+
"step": 621
|
| 4461 |
+
},
|
| 4462 |
+
{
|
| 4463 |
+
"epoch": 0.01728966442206795,
|
| 4464 |
+
"grad_norm": 0.10300412029027939,
|
| 4465 |
+
"learning_rate": 0.0006371922946493591,
|
| 4466 |
+
"loss": 0.7016,
|
| 4467 |
+
"step": 622
|
| 4468 |
+
},
|
| 4469 |
+
{
|
| 4470 |
+
"epoch": 0.01731746131020632,
|
| 4471 |
+
"grad_norm": 0.09915035963058472,
|
| 4472 |
+
"learning_rate": 0.0006342370180761255,
|
| 4473 |
+
"loss": 0.7562,
|
| 4474 |
+
"step": 623
|
| 4475 |
+
},
|
| 4476 |
+
{
|
| 4477 |
+
"epoch": 0.017345258198344694,
|
| 4478 |
+
"grad_norm": 0.11094118654727936,
|
| 4479 |
+
"learning_rate": 0.0006312854247320594,
|
| 4480 |
+
"loss": 0.7113,
|
| 4481 |
+
"step": 624
|
| 4482 |
+
},
|
| 4483 |
+
{
|
| 4484 |
+
"epoch": 0.01737305508648307,
|
| 4485 |
+
"grad_norm": 0.09752795100212097,
|
| 4486 |
+
"learning_rate": 0.0006283375443396726,
|
| 4487 |
+
"loss": 0.7649,
|
| 4488 |
+
"step": 625
|
| 4489 |
+
},
|
| 4490 |
+
{
|
| 4491 |
+
"epoch": 0.01740085197462144,
|
| 4492 |
+
"grad_norm": 0.10030993074178696,
|
| 4493 |
+
"learning_rate": 0.0006253934065840879,
|
| 4494 |
+
"loss": 0.7446,
|
| 4495 |
+
"step": 626
|
| 4496 |
+
},
|
| 4497 |
+
{
|
| 4498 |
+
"epoch": 0.017428648862759813,
|
| 4499 |
+
"grad_norm": 0.1134578287601471,
|
| 4500 |
+
"learning_rate": 0.0006224530411127403,
|
| 4501 |
+
"loss": 0.8147,
|
| 4502 |
+
"step": 627
|
| 4503 |
+
},
|
| 4504 |
+
{
|
| 4505 |
+
"epoch": 0.01745644575089819,
|
| 4506 |
+
"grad_norm": 0.09963490813970566,
|
| 4507 |
+
"learning_rate": 0.000619516477535077,
|
| 4508 |
+
"loss": 0.6904,
|
| 4509 |
+
"step": 628
|
| 4510 |
+
},
|
| 4511 |
+
{
|
| 4512 |
+
"epoch": 0.01748424263903656,
|
| 4513 |
+
"grad_norm": 0.10086818039417267,
|
| 4514 |
+
"learning_rate": 0.0006165837454222607,
|
| 4515 |
+
"loss": 0.5791,
|
| 4516 |
+
"step": 629
|
| 4517 |
+
},
|
| 4518 |
+
{
|
| 4519 |
+
"epoch": 0.017512039527174932,
|
| 4520 |
+
"grad_norm": 0.11571143567562103,
|
| 4521 |
+
"learning_rate": 0.0006136548743068713,
|
| 4522 |
+
"loss": 0.7572,
|
| 4523 |
+
"step": 630
|
| 4524 |
+
},
|
| 4525 |
+
{
|
| 4526 |
+
"epoch": 0.017539836415313304,
|
| 4527 |
+
"grad_norm": 0.10508367419242859,
|
| 4528 |
+
"learning_rate": 0.0006107298936826086,
|
| 4529 |
+
"loss": 0.5869,
|
| 4530 |
+
"step": 631
|
| 4531 |
+
},
|
| 4532 |
+
{
|
| 4533 |
+
"epoch": 0.01756763330345168,
|
| 4534 |
+
"grad_norm": 0.1044749990105629,
|
| 4535 |
+
"learning_rate": 0.0006078088330039945,
|
| 4536 |
+
"loss": 0.595,
|
| 4537 |
+
"step": 632
|
| 4538 |
+
},
|
| 4539 |
+
{
|
| 4540 |
+
"epoch": 0.01759543019159005,
|
| 4541 |
+
"grad_norm": 0.1138482466340065,
|
| 4542 |
+
"learning_rate": 0.0006048917216860781,
|
| 4543 |
+
"loss": 0.668,
|
| 4544 |
+
"step": 633
|
| 4545 |
+
},
|
| 4546 |
+
{
|
| 4547 |
+
"epoch": 0.017623227079728424,
|
| 4548 |
+
"grad_norm": 0.10499613732099533,
|
| 4549 |
+
"learning_rate": 0.0006019785891041381,
|
| 4550 |
+
"loss": 0.6028,
|
| 4551 |
+
"step": 634
|
| 4552 |
+
},
|
| 4553 |
+
{
|
| 4554 |
+
"epoch": 0.0176510239678668,
|
| 4555 |
+
"grad_norm": 0.10078407824039459,
|
| 4556 |
+
"learning_rate": 0.0005990694645933865,
|
| 4557 |
+
"loss": 0.5796,
|
| 4558 |
+
"step": 635
|
| 4559 |
+
},
|
| 4560 |
+
{
|
| 4561 |
+
"epoch": 0.01767882085600517,
|
| 4562 |
+
"grad_norm": 0.09239528328180313,
|
| 4563 |
+
"learning_rate": 0.0005961643774486753,
|
| 4564 |
+
"loss": 0.5735,
|
| 4565 |
+
"step": 636
|
| 4566 |
+
},
|
| 4567 |
+
{
|
| 4568 |
+
"epoch": 0.017706617744143543,
|
| 4569 |
+
"grad_norm": 0.09768297523260117,
|
| 4570 |
+
"learning_rate": 0.0005932633569242,
|
| 4571 |
+
"loss": 0.5082,
|
| 4572 |
+
"step": 637
|
| 4573 |
+
},
|
| 4574 |
+
{
|
| 4575 |
+
"epoch": 0.017734414632281915,
|
| 4576 |
+
"grad_norm": 0.10613156110048294,
|
| 4577 |
+
"learning_rate": 0.0005903664322332048,
|
| 4578 |
+
"loss": 0.5554,
|
| 4579 |
+
"step": 638
|
| 4580 |
+
},
|
| 4581 |
+
{
|
| 4582 |
+
"epoch": 0.01776221152042029,
|
| 4583 |
+
"grad_norm": 0.10876414179801941,
|
| 4584 |
+
"learning_rate": 0.000587473632547689,
|
| 4585 |
+
"loss": 0.6091,
|
| 4586 |
+
"step": 639
|
| 4587 |
+
},
|
| 4588 |
+
{
|
| 4589 |
+
"epoch": 0.017790008408558662,
|
| 4590 |
+
"grad_norm": 0.10759898275136948,
|
| 4591 |
+
"learning_rate": 0.0005845849869981136,
|
| 4592 |
+
"loss": 0.5748,
|
| 4593 |
+
"step": 640
|
| 4594 |
+
},
|
| 4595 |
+
{
|
| 4596 |
+
"epoch": 0.017817805296697034,
|
| 4597 |
+
"grad_norm": 0.12154053151607513,
|
| 4598 |
+
"learning_rate": 0.0005817005246731073,
|
| 4599 |
+
"loss": 0.6063,
|
| 4600 |
+
"step": 641
|
| 4601 |
+
},
|
| 4602 |
+
{
|
| 4603 |
+
"epoch": 0.017845602184835406,
|
| 4604 |
+
"grad_norm": 0.11394521594047546,
|
| 4605 |
+
"learning_rate": 0.0005788202746191734,
|
| 4606 |
+
"loss": 0.6124,
|
| 4607 |
+
"step": 642
|
| 4608 |
+
},
|
| 4609 |
+
{
|
| 4610 |
+
"epoch": 0.01787339907297378,
|
| 4611 |
+
"grad_norm": 0.09602084010839462,
|
| 4612 |
+
"learning_rate": 0.0005759442658403985,
|
| 4613 |
+
"loss": 0.4391,
|
| 4614 |
+
"step": 643
|
| 4615 |
+
},
|
| 4616 |
+
{
|
| 4617 |
+
"epoch": 0.017901195961112153,
|
| 4618 |
+
"grad_norm": 0.12600000202655792,
|
| 4619 |
+
"learning_rate": 0.0005730725272981583,
|
| 4620 |
+
"loss": 0.6201,
|
| 4621 |
+
"step": 644
|
| 4622 |
+
},
|
| 4623 |
+
{
|
| 4624 |
+
"epoch": 0.017928992849250525,
|
| 4625 |
+
"grad_norm": 0.1129770576953888,
|
| 4626 |
+
"learning_rate": 0.0005702050879108284,
|
| 4627 |
+
"loss": 0.4814,
|
| 4628 |
+
"step": 645
|
| 4629 |
+
},
|
| 4630 |
+
{
|
| 4631 |
+
"epoch": 0.0179567897373889,
|
| 4632 |
+
"grad_norm": 0.121727854013443,
|
| 4633 |
+
"learning_rate": 0.0005673419765534915,
|
| 4634 |
+
"loss": 0.5071,
|
| 4635 |
+
"step": 646
|
| 4636 |
+
},
|
| 4637 |
+
{
|
| 4638 |
+
"epoch": 0.017984586625527273,
|
| 4639 |
+
"grad_norm": 0.11814267188310623,
|
| 4640 |
+
"learning_rate": 0.0005644832220576479,
|
| 4641 |
+
"loss": 0.5387,
|
| 4642 |
+
"step": 647
|
| 4643 |
+
},
|
| 4644 |
+
{
|
| 4645 |
+
"epoch": 0.018012383513665645,
|
| 4646 |
+
"grad_norm": 0.14177252352237701,
|
| 4647 |
+
"learning_rate": 0.0005616288532109225,
|
| 4648 |
+
"loss": 0.6006,
|
| 4649 |
+
"step": 648
|
| 4650 |
+
},
|
| 4651 |
+
{
|
| 4652 |
+
"epoch": 0.018040180401804017,
|
| 4653 |
+
"grad_norm": 0.17021676898002625,
|
| 4654 |
+
"learning_rate": 0.0005587788987567784,
|
| 4655 |
+
"loss": 0.5445,
|
| 4656 |
+
"step": 649
|
| 4657 |
+
},
|
| 4658 |
+
{
|
| 4659 |
+
"epoch": 0.018067977289942392,
|
| 4660 |
+
"grad_norm": 0.17510192096233368,
|
| 4661 |
+
"learning_rate": 0.0005559333873942258,
|
| 4662 |
+
"loss": 0.5694,
|
| 4663 |
+
"step": 650
|
| 4664 |
+
},
|
| 4665 |
+
{
|
| 4666 |
+
"epoch": 0.018067977289942392,
|
| 4667 |
+
"eval_loss": 0.7097320556640625,
|
| 4668 |
+
"eval_runtime": 50.365,
|
| 4669 |
+
"eval_samples_per_second": 11.456,
|
| 4670 |
+
"eval_steps_per_second": 5.738,
|
| 4671 |
+
"step": 650
|
| 4672 |
}
|
| 4673 |
],
|
| 4674 |
"logging_steps": 1,
|
|
|
|
| 4683 |
"early_stopping_threshold": 0.0
|
| 4684 |
},
|
| 4685 |
"attributes": {
|
| 4686 |
+
"early_stopping_patience_counter": 3
|
| 4687 |
}
|
| 4688 |
},
|
| 4689 |
"TrainerControl": {
|
|
|
|
| 4692 |
"should_evaluate": false,
|
| 4693 |
"should_log": false,
|
| 4694 |
"should_save": true,
|
| 4695 |
+
"should_training_stop": true
|
| 4696 |
},
|
| 4697 |
"attributes": {}
|
| 4698 |
}
|
| 4699 |
},
|
| 4700 |
+
"total_flos": 4.150175529644851e+16,
|
| 4701 |
"train_batch_size": 2,
|
| 4702 |
"trial_name": null,
|
| 4703 |
"trial_params": null
|