Training in progress, step 64000, 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 3555504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:926ed83f6e74d30dd04cd576ac59c6374f40022ad71666f1151acf89ef6a727f
|
| 3 |
size 3555504
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7141515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b80956cda8d577cf7bfd206ddcea2443accc461272fcb58c947316dd066ab0
|
| 3 |
size 7141515
|
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:c8a9e9fcdb822872caeabe3003c6e6517d9f7eeb88433b860fc3482c1c47480d
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1da3ebf38e6de5f93a849d5bb335be74fb8ae94c32eaa092e9a693e9450f5852
|
| 3 |
size 1383
|
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:f0f4b19a41457d0a78e68093b636e25cec379bf5b743c5d43b46b713a83c2f2b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 52000,
|
| 3 |
"best_metric": 0.9908199660129274,
|
| 4 |
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-52000",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 4000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4388,6 +4388,298 @@
|
|
| 4388 |
"eval_samples_per_second": 130.728,
|
| 4389 |
"eval_steps_per_second": 8.171,
|
| 4390 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4391 |
}
|
| 4392 |
],
|
| 4393 |
"logging_steps": 100,
|
|
@@ -4402,7 +4694,7 @@
|
|
| 4402 |
"early_stopping_threshold": 0.0
|
| 4403 |
},
|
| 4404 |
"attributes": {
|
| 4405 |
-
"early_stopping_patience_counter":
|
| 4406 |
}
|
| 4407 |
},
|
| 4408 |
"TrainerControl": {
|
|
@@ -4411,12 +4703,12 @@
|
|
| 4411 |
"should_evaluate": false,
|
| 4412 |
"should_log": false,
|
| 4413 |
"should_save": true,
|
| 4414 |
-
"should_training_stop":
|
| 4415 |
},
|
| 4416 |
"attributes": {}
|
| 4417 |
}
|
| 4418 |
},
|
| 4419 |
-
"total_flos": 2.
|
| 4420 |
"train_batch_size": 16,
|
| 4421 |
"trial_name": null,
|
| 4422 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 52000,
|
| 3 |
"best_metric": 0.9908199660129274,
|
| 4 |
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-52000",
|
| 5 |
+
"epoch": 2.048,
|
| 6 |
"eval_steps": 4000,
|
| 7 |
+
"global_step": 64000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4388 |
"eval_samples_per_second": 130.728,
|
| 4389 |
"eval_steps_per_second": 8.171,
|
| 4390 |
"step": 60000
|
| 4391 |
+
},
|
| 4392 |
+
{
|
| 4393 |
+
"epoch": 1.9232,
|
| 4394 |
+
"grad_norm": 0.016066577285528183,
|
| 4395 |
+
"learning_rate": 1.2346837881219905e-05,
|
| 4396 |
+
"loss": 0.0324,
|
| 4397 |
+
"step": 60100
|
| 4398 |
+
},
|
| 4399 |
+
{
|
| 4400 |
+
"epoch": 1.9264000000000001,
|
| 4401 |
+
"grad_norm": 1.0818510055541992,
|
| 4402 |
+
"learning_rate": 1.2333996789727128e-05,
|
| 4403 |
+
"loss": 0.0333,
|
| 4404 |
+
"step": 60200
|
| 4405 |
+
},
|
| 4406 |
+
{
|
| 4407 |
+
"epoch": 1.9296,
|
| 4408 |
+
"grad_norm": 1.9333336353302002,
|
| 4409 |
+
"learning_rate": 1.2321155698234351e-05,
|
| 4410 |
+
"loss": 0.0465,
|
| 4411 |
+
"step": 60300
|
| 4412 |
+
},
|
| 4413 |
+
{
|
| 4414 |
+
"epoch": 1.9327999999999999,
|
| 4415 |
+
"grad_norm": 0.015184523537755013,
|
| 4416 |
+
"learning_rate": 1.2308314606741574e-05,
|
| 4417 |
+
"loss": 0.031,
|
| 4418 |
+
"step": 60400
|
| 4419 |
+
},
|
| 4420 |
+
{
|
| 4421 |
+
"epoch": 1.936,
|
| 4422 |
+
"grad_norm": 3.1265370845794678,
|
| 4423 |
+
"learning_rate": 1.2295473515248797e-05,
|
| 4424 |
+
"loss": 0.0265,
|
| 4425 |
+
"step": 60500
|
| 4426 |
+
},
|
| 4427 |
+
{
|
| 4428 |
+
"epoch": 1.9392,
|
| 4429 |
+
"grad_norm": 0.06526759266853333,
|
| 4430 |
+
"learning_rate": 1.228263242375602e-05,
|
| 4431 |
+
"loss": 0.0396,
|
| 4432 |
+
"step": 60600
|
| 4433 |
+
},
|
| 4434 |
+
{
|
| 4435 |
+
"epoch": 1.9424000000000001,
|
| 4436 |
+
"grad_norm": 0.051179856061935425,
|
| 4437 |
+
"learning_rate": 1.2269791332263244e-05,
|
| 4438 |
+
"loss": 0.0457,
|
| 4439 |
+
"step": 60700
|
| 4440 |
+
},
|
| 4441 |
+
{
|
| 4442 |
+
"epoch": 1.9456,
|
| 4443 |
+
"grad_norm": 0.012131915427744389,
|
| 4444 |
+
"learning_rate": 1.2256950240770467e-05,
|
| 4445 |
+
"loss": 0.0377,
|
| 4446 |
+
"step": 60800
|
| 4447 |
+
},
|
| 4448 |
+
{
|
| 4449 |
+
"epoch": 1.9487999999999999,
|
| 4450 |
+
"grad_norm": 6.335480690002441,
|
| 4451 |
+
"learning_rate": 1.224410914927769e-05,
|
| 4452 |
+
"loss": 0.0378,
|
| 4453 |
+
"step": 60900
|
| 4454 |
+
},
|
| 4455 |
+
{
|
| 4456 |
+
"epoch": 1.952,
|
| 4457 |
+
"grad_norm": 0.6301658749580383,
|
| 4458 |
+
"learning_rate": 1.2231268057784913e-05,
|
| 4459 |
+
"loss": 0.0442,
|
| 4460 |
+
"step": 61000
|
| 4461 |
+
},
|
| 4462 |
+
{
|
| 4463 |
+
"epoch": 1.9552,
|
| 4464 |
+
"grad_norm": 0.3388197124004364,
|
| 4465 |
+
"learning_rate": 1.2218426966292136e-05,
|
| 4466 |
+
"loss": 0.0489,
|
| 4467 |
+
"step": 61100
|
| 4468 |
+
},
|
| 4469 |
+
{
|
| 4470 |
+
"epoch": 1.9584000000000001,
|
| 4471 |
+
"grad_norm": 0.007041617762297392,
|
| 4472 |
+
"learning_rate": 1.220558587479936e-05,
|
| 4473 |
+
"loss": 0.0384,
|
| 4474 |
+
"step": 61200
|
| 4475 |
+
},
|
| 4476 |
+
{
|
| 4477 |
+
"epoch": 1.9616,
|
| 4478 |
+
"grad_norm": 0.10959050804376602,
|
| 4479 |
+
"learning_rate": 1.2192744783306582e-05,
|
| 4480 |
+
"loss": 0.0463,
|
| 4481 |
+
"step": 61300
|
| 4482 |
+
},
|
| 4483 |
+
{
|
| 4484 |
+
"epoch": 1.9647999999999999,
|
| 4485 |
+
"grad_norm": 3.765045642852783,
|
| 4486 |
+
"learning_rate": 1.2179903691813806e-05,
|
| 4487 |
+
"loss": 0.043,
|
| 4488 |
+
"step": 61400
|
| 4489 |
+
},
|
| 4490 |
+
{
|
| 4491 |
+
"epoch": 1.968,
|
| 4492 |
+
"grad_norm": 2.442903757095337,
|
| 4493 |
+
"learning_rate": 1.2167062600321029e-05,
|
| 4494 |
+
"loss": 0.0431,
|
| 4495 |
+
"step": 61500
|
| 4496 |
+
},
|
| 4497 |
+
{
|
| 4498 |
+
"epoch": 1.9712,
|
| 4499 |
+
"grad_norm": 3.0291242599487305,
|
| 4500 |
+
"learning_rate": 1.2154221508828252e-05,
|
| 4501 |
+
"loss": 0.0439,
|
| 4502 |
+
"step": 61600
|
| 4503 |
+
},
|
| 4504 |
+
{
|
| 4505 |
+
"epoch": 1.9744000000000002,
|
| 4506 |
+
"grad_norm": 0.1264086663722992,
|
| 4507 |
+
"learning_rate": 1.2141380417335475e-05,
|
| 4508 |
+
"loss": 0.029,
|
| 4509 |
+
"step": 61700
|
| 4510 |
+
},
|
| 4511 |
+
{
|
| 4512 |
+
"epoch": 1.9776,
|
| 4513 |
+
"grad_norm": 0.09380912035703659,
|
| 4514 |
+
"learning_rate": 1.2128539325842698e-05,
|
| 4515 |
+
"loss": 0.05,
|
| 4516 |
+
"step": 61800
|
| 4517 |
+
},
|
| 4518 |
+
{
|
| 4519 |
+
"epoch": 1.9808,
|
| 4520 |
+
"grad_norm": 0.012730620801448822,
|
| 4521 |
+
"learning_rate": 1.211569823434992e-05,
|
| 4522 |
+
"loss": 0.0235,
|
| 4523 |
+
"step": 61900
|
| 4524 |
+
},
|
| 4525 |
+
{
|
| 4526 |
+
"epoch": 1.984,
|
| 4527 |
+
"grad_norm": 0.04120282083749771,
|
| 4528 |
+
"learning_rate": 1.2102857142857143e-05,
|
| 4529 |
+
"loss": 0.0342,
|
| 4530 |
+
"step": 62000
|
| 4531 |
+
},
|
| 4532 |
+
{
|
| 4533 |
+
"epoch": 1.9872,
|
| 4534 |
+
"grad_norm": 0.22701594233512878,
|
| 4535 |
+
"learning_rate": 1.2090016051364366e-05,
|
| 4536 |
+
"loss": 0.0499,
|
| 4537 |
+
"step": 62100
|
| 4538 |
+
},
|
| 4539 |
+
{
|
| 4540 |
+
"epoch": 1.9904,
|
| 4541 |
+
"grad_norm": 0.005121626891195774,
|
| 4542 |
+
"learning_rate": 1.2077174959871589e-05,
|
| 4543 |
+
"loss": 0.0223,
|
| 4544 |
+
"step": 62200
|
| 4545 |
+
},
|
| 4546 |
+
{
|
| 4547 |
+
"epoch": 1.9936,
|
| 4548 |
+
"grad_norm": 4.5423583984375,
|
| 4549 |
+
"learning_rate": 1.2064333868378812e-05,
|
| 4550 |
+
"loss": 0.0351,
|
| 4551 |
+
"step": 62300
|
| 4552 |
+
},
|
| 4553 |
+
{
|
| 4554 |
+
"epoch": 1.9968,
|
| 4555 |
+
"grad_norm": 0.6799706816673279,
|
| 4556 |
+
"learning_rate": 1.2051492776886035e-05,
|
| 4557 |
+
"loss": 0.0374,
|
| 4558 |
+
"step": 62400
|
| 4559 |
+
},
|
| 4560 |
+
{
|
| 4561 |
+
"epoch": 2.0,
|
| 4562 |
+
"grad_norm": 0.4670400023460388,
|
| 4563 |
+
"learning_rate": 1.2038651685393258e-05,
|
| 4564 |
+
"loss": 0.0389,
|
| 4565 |
+
"step": 62500
|
| 4566 |
+
},
|
| 4567 |
+
{
|
| 4568 |
+
"epoch": 2.0032,
|
| 4569 |
+
"grad_norm": 0.0014514782233163714,
|
| 4570 |
+
"learning_rate": 1.2025810593900481e-05,
|
| 4571 |
+
"loss": 0.0407,
|
| 4572 |
+
"step": 62600
|
| 4573 |
+
},
|
| 4574 |
+
{
|
| 4575 |
+
"epoch": 2.0064,
|
| 4576 |
+
"grad_norm": 10.322093963623047,
|
| 4577 |
+
"learning_rate": 1.2012969502407705e-05,
|
| 4578 |
+
"loss": 0.0364,
|
| 4579 |
+
"step": 62700
|
| 4580 |
+
},
|
| 4581 |
+
{
|
| 4582 |
+
"epoch": 2.0096,
|
| 4583 |
+
"grad_norm": 0.7346168160438538,
|
| 4584 |
+
"learning_rate": 1.2000128410914928e-05,
|
| 4585 |
+
"loss": 0.063,
|
| 4586 |
+
"step": 62800
|
| 4587 |
+
},
|
| 4588 |
+
{
|
| 4589 |
+
"epoch": 2.0128,
|
| 4590 |
+
"grad_norm": 15.471858978271484,
|
| 4591 |
+
"learning_rate": 1.1987287319422153e-05,
|
| 4592 |
+
"loss": 0.0365,
|
| 4593 |
+
"step": 62900
|
| 4594 |
+
},
|
| 4595 |
+
{
|
| 4596 |
+
"epoch": 2.016,
|
| 4597 |
+
"grad_norm": 0.22428256273269653,
|
| 4598 |
+
"learning_rate": 1.1974446227929376e-05,
|
| 4599 |
+
"loss": 0.0437,
|
| 4600 |
+
"step": 63000
|
| 4601 |
+
},
|
| 4602 |
+
{
|
| 4603 |
+
"epoch": 2.0192,
|
| 4604 |
+
"grad_norm": 5.6665849685668945,
|
| 4605 |
+
"learning_rate": 1.1961605136436599e-05,
|
| 4606 |
+
"loss": 0.0448,
|
| 4607 |
+
"step": 63100
|
| 4608 |
+
},
|
| 4609 |
+
{
|
| 4610 |
+
"epoch": 2.0224,
|
| 4611 |
+
"grad_norm": 0.011902675963938236,
|
| 4612 |
+
"learning_rate": 1.1948764044943822e-05,
|
| 4613 |
+
"loss": 0.0309,
|
| 4614 |
+
"step": 63200
|
| 4615 |
+
},
|
| 4616 |
+
{
|
| 4617 |
+
"epoch": 2.0256,
|
| 4618 |
+
"grad_norm": 0.01199142262339592,
|
| 4619 |
+
"learning_rate": 1.1935922953451045e-05,
|
| 4620 |
+
"loss": 0.0181,
|
| 4621 |
+
"step": 63300
|
| 4622 |
+
},
|
| 4623 |
+
{
|
| 4624 |
+
"epoch": 2.0288,
|
| 4625 |
+
"grad_norm": 0.2028602510690689,
|
| 4626 |
+
"learning_rate": 1.1923081861958268e-05,
|
| 4627 |
+
"loss": 0.0433,
|
| 4628 |
+
"step": 63400
|
| 4629 |
+
},
|
| 4630 |
+
{
|
| 4631 |
+
"epoch": 2.032,
|
| 4632 |
+
"grad_norm": 0.05186166614294052,
|
| 4633 |
+
"learning_rate": 1.1910240770465491e-05,
|
| 4634 |
+
"loss": 0.0349,
|
| 4635 |
+
"step": 63500
|
| 4636 |
+
},
|
| 4637 |
+
{
|
| 4638 |
+
"epoch": 2.0352,
|
| 4639 |
+
"grad_norm": 8.039327621459961,
|
| 4640 |
+
"learning_rate": 1.1897399678972715e-05,
|
| 4641 |
+
"loss": 0.0447,
|
| 4642 |
+
"step": 63600
|
| 4643 |
+
},
|
| 4644 |
+
{
|
| 4645 |
+
"epoch": 2.0384,
|
| 4646 |
+
"grad_norm": 0.013709252700209618,
|
| 4647 |
+
"learning_rate": 1.1884558587479938e-05,
|
| 4648 |
+
"loss": 0.0264,
|
| 4649 |
+
"step": 63700
|
| 4650 |
+
},
|
| 4651 |
+
{
|
| 4652 |
+
"epoch": 2.0416,
|
| 4653 |
+
"grad_norm": 0.12741540372371674,
|
| 4654 |
+
"learning_rate": 1.187171749598716e-05,
|
| 4655 |
+
"loss": 0.0285,
|
| 4656 |
+
"step": 63800
|
| 4657 |
+
},
|
| 4658 |
+
{
|
| 4659 |
+
"epoch": 2.0448,
|
| 4660 |
+
"grad_norm": 38.967525482177734,
|
| 4661 |
+
"learning_rate": 1.1858876404494384e-05,
|
| 4662 |
+
"loss": 0.0406,
|
| 4663 |
+
"step": 63900
|
| 4664 |
+
},
|
| 4665 |
+
{
|
| 4666 |
+
"epoch": 2.048,
|
| 4667 |
+
"grad_norm": 10.748799324035645,
|
| 4668 |
+
"learning_rate": 1.1846035313001607e-05,
|
| 4669 |
+
"loss": 0.0358,
|
| 4670 |
+
"step": 64000
|
| 4671 |
+
},
|
| 4672 |
+
{
|
| 4673 |
+
"epoch": 2.048,
|
| 4674 |
+
"eval_accuracy": 0.99072,
|
| 4675 |
+
"eval_f1": 0.9907211797405157,
|
| 4676 |
+
"eval_loss": 0.038402359932661057,
|
| 4677 |
+
"eval_precision": 0.990739513426471,
|
| 4678 |
+
"eval_recall": 0.99072,
|
| 4679 |
+
"eval_runtime": 764.7435,
|
| 4680 |
+
"eval_samples_per_second": 130.763,
|
| 4681 |
+
"eval_steps_per_second": 8.173,
|
| 4682 |
+
"step": 64000
|
| 4683 |
}
|
| 4684 |
],
|
| 4685 |
"logging_steps": 100,
|
|
|
|
| 4694 |
"early_stopping_threshold": 0.0
|
| 4695 |
},
|
| 4696 |
"attributes": {
|
| 4697 |
+
"early_stopping_patience_counter": 3
|
| 4698 |
}
|
| 4699 |
},
|
| 4700 |
"TrainerControl": {
|
|
|
|
| 4703 |
"should_evaluate": false,
|
| 4704 |
"should_log": false,
|
| 4705 |
"should_save": true,
|
| 4706 |
+
"should_training_stop": true
|
| 4707 |
},
|
| 4708 |
"attributes": {}
|
| 4709 |
}
|
| 4710 |
},
|
| 4711 |
+
"total_flos": 2.7177787451207846e+17,
|
| 4712 |
"train_batch_size": 16,
|
| 4713 |
"trial_name": null,
|
| 4714 |
"trial_params": null
|