Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
|
@@ -908,6 +908,16 @@ You can finetune this model on your own dataset.
|
|
| 908 |
| 0.8 | 14056 | 0.5737 | 0.4942 | 0.5019 | 0.1500 | - |
|
| 909 |
| 0.9 | 15813 | 0.5896 | 0.4757 | 0.4804 | 0.1465 | - |
|
| 910 |
| 1.0 | 17570 | 0.5174 | 0.5253 | 0.4587 | 0.0534 | - |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 911 |
|
| 912 |
|
| 913 |
### Framework Versions
|
|
|
|
| 908 |
| 0.8 | 14056 | 0.5737 | 0.4942 | 0.5019 | 0.1500 | - |
|
| 909 |
| 0.9 | 15813 | 0.5896 | 0.4757 | 0.4804 | 0.1465 | - |
|
| 910 |
| 1.0 | 17570 | 0.5174 | 0.5253 | 0.4587 | 0.0534 | - |
|
| 911 |
+
| 1.1 | 19327 | 0.5059 | 0.5493 | 0.4587 | 0.0278 | - |
|
| 912 |
+
| 1.2 | 21084 | 0.4654 | 0.4850 | 0.4415 | 0.0517 | - |
|
| 913 |
+
| 1.3 | 22841 | 0.4224 | 0.4292 | 0.3957 | 0.0938 | - |
|
| 914 |
+
| 1.4 | 24598 | 0.4125 | 0.4624 | 0.3794 | 0.0839 | - |
|
| 915 |
+
| 1.5 | 26355 | 0.4072 | 0.4481 | 0.3878 | 0.0681 | - |
|
| 916 |
+
| 1.6 | 28112 | 0.3572 | 0.4953 | 0.3716 | 0.0674 | - |
|
| 917 |
+
| 1.7 | 29869 | 0.371 | 0.4767 | 0.3622 | 0.0600 | - |
|
| 918 |
+
| 1.8 | 31626 | 0.3332 | 0.4659 | 0.3600 | 0.0561 | - |
|
| 919 |
+
| 1.9 | 33383 | 0.3695 | 0.4604 | 0.3567 | 0.0614 | - |
|
| 920 |
+
| 2.0 | 35140 | 0.3315 | 0.4712 | 0.3597 | 0.0540 | - |
|
| 921 |
|
| 922 |
|
| 923 |
### Framework Versions
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1130520122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caaeeb3bee414e6382503e0e4566778971da5035d9883fa6c4013148b09c280c
|
| 3 |
size 1130520122
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 565251810
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d7823fbc9158972fe4a2cec91802737230154657abd47b1f0f2065b9a223127
|
| 3 |
size 565251810
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04c63c792c38c2033263ef312d4b227d8d109c687d4efdc325699d09450706d
|
| 3 |
size 14180
|
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 sha256:292a922960da915a02f1436dd2a4aea0ac1e9584691974a2c6e06cc13c6d0a3b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1757,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -317,6 +317,316 @@
|
|
| 317 |
"eval_qnli-contrastive_samples_per_second": 352.263,
|
| 318 |
"eval_qnli-contrastive_steps_per_second": 22.053,
|
| 319 |
"step": 17570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 320 |
}
|
| 321 |
],
|
| 322 |
"logging_steps": 1757,
|
|
@@ -331,7 +641,7 @@
|
|
| 331 |
"should_evaluate": false,
|
| 332 |
"should_log": false,
|
| 333 |
"should_save": true,
|
| 334 |
-
"should_training_stop":
|
| 335 |
},
|
| 336 |
"attributes": {}
|
| 337 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 1757,
|
| 6 |
+
"global_step": 35140,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 317 |
"eval_qnli-contrastive_samples_per_second": 352.263,
|
| 318 |
"eval_qnli-contrastive_steps_per_second": 22.053,
|
| 319 |
"step": 17570
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.1,
|
| 323 |
+
"grad_norm": 18.839372634887695,
|
| 324 |
+
"learning_rate": 9.75831232890717e-06,
|
| 325 |
+
"loss": 0.5059,
|
| 326 |
+
"step": 19327
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.1,
|
| 330 |
+
"eval_nli-pairs_loss": 0.45871272683143616,
|
| 331 |
+
"eval_nli-pairs_runtime": 22.8984,
|
| 332 |
+
"eval_nli-pairs_samples_per_second": 297.313,
|
| 333 |
+
"eval_nli-pairs_steps_per_second": 18.604,
|
| 334 |
+
"step": 19327
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.1,
|
| 338 |
+
"eval_scitail-pairs-pos_loss": 0.5492986440658569,
|
| 339 |
+
"eval_scitail-pairs-pos_runtime": 5.1782,
|
| 340 |
+
"eval_scitail-pairs-pos_samples_per_second": 251.824,
|
| 341 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.836,
|
| 342 |
+
"step": 19327
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.1,
|
| 346 |
+
"eval_qnli-contrastive_loss": 0.027841920033097267,
|
| 347 |
+
"eval_qnli-contrastive_runtime": 15.522,
|
| 348 |
+
"eval_qnli-contrastive_samples_per_second": 351.952,
|
| 349 |
+
"eval_qnli-contrastive_steps_per_second": 22.033,
|
| 350 |
+
"step": 19327
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.2,
|
| 354 |
+
"grad_norm": 6.800241947174072,
|
| 355 |
+
"learning_rate": 9.051905444616243e-06,
|
| 356 |
+
"loss": 0.4654,
|
| 357 |
+
"step": 21084
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.2,
|
| 361 |
+
"eval_nli-pairs_loss": 0.44151321053504944,
|
| 362 |
+
"eval_nli-pairs_runtime": 23.1311,
|
| 363 |
+
"eval_nli-pairs_samples_per_second": 294.323,
|
| 364 |
+
"eval_nli-pairs_steps_per_second": 18.417,
|
| 365 |
+
"step": 21084
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.2,
|
| 369 |
+
"eval_scitail-pairs-pos_loss": 0.4850437045097351,
|
| 370 |
+
"eval_scitail-pairs-pos_runtime": 5.2939,
|
| 371 |
+
"eval_scitail-pairs-pos_samples_per_second": 246.321,
|
| 372 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.49,
|
| 373 |
+
"step": 21084
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.2,
|
| 377 |
+
"eval_qnli-contrastive_loss": 0.05170624330639839,
|
| 378 |
+
"eval_qnli-contrastive_runtime": 15.7737,
|
| 379 |
+
"eval_qnli-contrastive_samples_per_second": 346.336,
|
| 380 |
+
"eval_qnli-contrastive_steps_per_second": 21.682,
|
| 381 |
+
"step": 21084
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3,
|
| 385 |
+
"grad_norm": 0.41899746656417847,
|
| 386 |
+
"learning_rate": 7.948320938272786e-06,
|
| 387 |
+
"loss": 0.4224,
|
| 388 |
+
"step": 22841
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3,
|
| 392 |
+
"eval_nli-pairs_loss": 0.39569494128227234,
|
| 393 |
+
"eval_nli-pairs_runtime": 23.2638,
|
| 394 |
+
"eval_nli-pairs_samples_per_second": 292.643,
|
| 395 |
+
"eval_nli-pairs_steps_per_second": 18.312,
|
| 396 |
+
"step": 22841
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3,
|
| 400 |
+
"eval_scitail-pairs-pos_loss": 0.42922988533973694,
|
| 401 |
+
"eval_scitail-pairs-pos_runtime": 5.2769,
|
| 402 |
+
"eval_scitail-pairs-pos_samples_per_second": 247.114,
|
| 403 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.539,
|
| 404 |
+
"step": 22841
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.3,
|
| 408 |
+
"eval_qnli-contrastive_loss": 0.0938122496008873,
|
| 409 |
+
"eval_qnli-contrastive_runtime": 15.6681,
|
| 410 |
+
"eval_qnli-contrastive_samples_per_second": 348.67,
|
| 411 |
+
"eval_qnli-contrastive_steps_per_second": 21.828,
|
| 412 |
+
"step": 22841
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.4,
|
| 416 |
+
"grad_norm": 3.0029168128967285,
|
| 417 |
+
"learning_rate": 6.556983832253587e-06,
|
| 418 |
+
"loss": 0.4125,
|
| 419 |
+
"step": 24598
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.4,
|
| 423 |
+
"eval_nli-pairs_loss": 0.3794442415237427,
|
| 424 |
+
"eval_nli-pairs_runtime": 23.2107,
|
| 425 |
+
"eval_nli-pairs_samples_per_second": 293.313,
|
| 426 |
+
"eval_nli-pairs_steps_per_second": 18.354,
|
| 427 |
+
"step": 24598
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.4,
|
| 431 |
+
"eval_scitail-pairs-pos_loss": 0.4623956084251404,
|
| 432 |
+
"eval_scitail-pairs-pos_runtime": 5.2884,
|
| 433 |
+
"eval_scitail-pairs-pos_samples_per_second": 246.577,
|
| 434 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.506,
|
| 435 |
+
"step": 24598
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.4,
|
| 439 |
+
"eval_qnli-contrastive_loss": 0.0838843286037445,
|
| 440 |
+
"eval_qnli-contrastive_runtime": 15.7017,
|
| 441 |
+
"eval_qnli-contrastive_samples_per_second": 347.924,
|
| 442 |
+
"eval_qnli-contrastive_steps_per_second": 21.781,
|
| 443 |
+
"step": 24598
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.5,
|
| 447 |
+
"grad_norm": 10.91913890838623,
|
| 448 |
+
"learning_rate": 5.012516292320938e-06,
|
| 449 |
+
"loss": 0.4072,
|
| 450 |
+
"step": 26355
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.5,
|
| 454 |
+
"eval_nli-pairs_loss": 0.3877629041671753,
|
| 455 |
+
"eval_nli-pairs_runtime": 23.1072,
|
| 456 |
+
"eval_nli-pairs_samples_per_second": 294.627,
|
| 457 |
+
"eval_nli-pairs_steps_per_second": 18.436,
|
| 458 |
+
"step": 26355
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.5,
|
| 462 |
+
"eval_scitail-pairs-pos_loss": 0.4480924606323242,
|
| 463 |
+
"eval_scitail-pairs-pos_runtime": 5.2741,
|
| 464 |
+
"eval_scitail-pairs-pos_samples_per_second": 247.244,
|
| 465 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.548,
|
| 466 |
+
"step": 26355
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.5,
|
| 470 |
+
"eval_qnli-contrastive_loss": 0.06811495870351791,
|
| 471 |
+
"eval_qnli-contrastive_runtime": 15.7641,
|
| 472 |
+
"eval_qnli-contrastive_samples_per_second": 346.546,
|
| 473 |
+
"eval_qnli-contrastive_steps_per_second": 21.695,
|
| 474 |
+
"step": 26355
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.6,
|
| 478 |
+
"grad_norm": 3.676146984100342,
|
| 479 |
+
"learning_rate": 3.4668235704897813e-06,
|
| 480 |
+
"loss": 0.3572,
|
| 481 |
+
"step": 28112
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.6,
|
| 485 |
+
"eval_nli-pairs_loss": 0.3715905547142029,
|
| 486 |
+
"eval_nli-pairs_runtime": 23.1744,
|
| 487 |
+
"eval_nli-pairs_samples_per_second": 293.773,
|
| 488 |
+
"eval_nli-pairs_steps_per_second": 18.382,
|
| 489 |
+
"step": 28112
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.6,
|
| 493 |
+
"eval_scitail-pairs-pos_loss": 0.49534013867378235,
|
| 494 |
+
"eval_scitail-pairs-pos_runtime": 5.2856,
|
| 495 |
+
"eval_scitail-pairs-pos_samples_per_second": 246.708,
|
| 496 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.514,
|
| 497 |
+
"step": 28112
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.6,
|
| 501 |
+
"eval_qnli-contrastive_loss": 0.06735851615667343,
|
| 502 |
+
"eval_qnli-contrastive_runtime": 15.7308,
|
| 503 |
+
"eval_qnli-contrastive_samples_per_second": 347.281,
|
| 504 |
+
"eval_qnli-contrastive_steps_per_second": 21.741,
|
| 505 |
+
"step": 28112
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.7,
|
| 509 |
+
"grad_norm": 229.6580047607422,
|
| 510 |
+
"learning_rate": 2.072658211127134e-06,
|
| 511 |
+
"loss": 0.371,
|
| 512 |
+
"step": 29869
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.7,
|
| 516 |
+
"eval_nli-pairs_loss": 0.36217835545539856,
|
| 517 |
+
"eval_nli-pairs_runtime": 23.1495,
|
| 518 |
+
"eval_nli-pairs_samples_per_second": 294.089,
|
| 519 |
+
"eval_nli-pairs_steps_per_second": 18.402,
|
| 520 |
+
"step": 29869
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.7,
|
| 524 |
+
"eval_scitail-pairs-pos_loss": 0.47673526406288147,
|
| 525 |
+
"eval_scitail-pairs-pos_runtime": 5.2158,
|
| 526 |
+
"eval_scitail-pairs-pos_samples_per_second": 250.008,
|
| 527 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.721,
|
| 528 |
+
"step": 29869
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.7,
|
| 532 |
+
"eval_qnli-contrastive_loss": 0.06000087782740593,
|
| 533 |
+
"eval_qnli-contrastive_runtime": 15.6328,
|
| 534 |
+
"eval_qnli-contrastive_samples_per_second": 349.458,
|
| 535 |
+
"eval_qnli-contrastive_steps_per_second": 21.877,
|
| 536 |
+
"step": 29869
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.8,
|
| 540 |
+
"grad_norm": 0.6022229194641113,
|
| 541 |
+
"learning_rate": 9.638670801112644e-07,
|
| 542 |
+
"loss": 0.3332,
|
| 543 |
+
"step": 31626
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.8,
|
| 547 |
+
"eval_nli-pairs_loss": 0.3600439131259918,
|
| 548 |
+
"eval_nli-pairs_runtime": 23.0874,
|
| 549 |
+
"eval_nli-pairs_samples_per_second": 294.879,
|
| 550 |
+
"eval_nli-pairs_steps_per_second": 18.452,
|
| 551 |
+
"step": 31626
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.8,
|
| 555 |
+
"eval_scitail-pairs-pos_loss": 0.465911865234375,
|
| 556 |
+
"eval_scitail-pairs-pos_runtime": 5.3369,
|
| 557 |
+
"eval_scitail-pairs-pos_samples_per_second": 244.338,
|
| 558 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.365,
|
| 559 |
+
"step": 31626
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.8,
|
| 563 |
+
"eval_qnli-contrastive_loss": 0.05613844096660614,
|
| 564 |
+
"eval_qnli-contrastive_runtime": 15.7089,
|
| 565 |
+
"eval_qnli-contrastive_samples_per_second": 347.764,
|
| 566 |
+
"eval_qnli-contrastive_steps_per_second": 21.771,
|
| 567 |
+
"step": 31626
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.9,
|
| 571 |
+
"grad_norm": 0.23106251657009125,
|
| 572 |
+
"learning_rate": 2.4943593464921476e-07,
|
| 573 |
+
"loss": 0.3695,
|
| 574 |
+
"step": 33383
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.9,
|
| 578 |
+
"eval_nli-pairs_loss": 0.35667526721954346,
|
| 579 |
+
"eval_nli-pairs_runtime": 23.1588,
|
| 580 |
+
"eval_nli-pairs_samples_per_second": 293.971,
|
| 581 |
+
"eval_nli-pairs_steps_per_second": 18.395,
|
| 582 |
+
"step": 33383
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.9,
|
| 586 |
+
"eval_scitail-pairs-pos_loss": 0.4603894352912903,
|
| 587 |
+
"eval_scitail-pairs-pos_runtime": 5.248,
|
| 588 |
+
"eval_scitail-pairs-pos_samples_per_second": 248.476,
|
| 589 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.625,
|
| 590 |
+
"step": 33383
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.9,
|
| 594 |
+
"eval_qnli-contrastive_loss": 0.06141861155629158,
|
| 595 |
+
"eval_qnli-contrastive_runtime": 15.6709,
|
| 596 |
+
"eval_qnli-contrastive_samples_per_second": 348.608,
|
| 597 |
+
"eval_qnli-contrastive_steps_per_second": 21.824,
|
| 598 |
+
"step": 33383
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.0,
|
| 602 |
+
"grad_norm": Infinity,
|
| 603 |
+
"learning_rate": 2.5896487759191624e-11,
|
| 604 |
+
"loss": 0.3315,
|
| 605 |
+
"step": 35140
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.0,
|
| 609 |
+
"eval_nli-pairs_loss": 0.3597075045108795,
|
| 610 |
+
"eval_nli-pairs_runtime": 23.1058,
|
| 611 |
+
"eval_nli-pairs_samples_per_second": 294.645,
|
| 612 |
+
"eval_nli-pairs_steps_per_second": 18.437,
|
| 613 |
+
"step": 35140
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.0,
|
| 617 |
+
"eval_scitail-pairs-pos_loss": 0.47120198607444763,
|
| 618 |
+
"eval_scitail-pairs-pos_runtime": 5.2532,
|
| 619 |
+
"eval_scitail-pairs-pos_samples_per_second": 248.23,
|
| 620 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.61,
|
| 621 |
+
"step": 35140
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.0,
|
| 625 |
+
"eval_qnli-contrastive_loss": 0.05398999899625778,
|
| 626 |
+
"eval_qnli-contrastive_runtime": 15.7099,
|
| 627 |
+
"eval_qnli-contrastive_samples_per_second": 347.743,
|
| 628 |
+
"eval_qnli-contrastive_steps_per_second": 21.77,
|
| 629 |
+
"step": 35140
|
| 630 |
}
|
| 631 |
],
|
| 632 |
"logging_steps": 1757,
|
|
|
|
| 641 |
"should_evaluate": false,
|
| 642 |
"should_log": false,
|
| 643 |
"should_save": true,
|
| 644 |
+
"should_training_stop": true
|
| 645 |
},
|
| 646 |
"attributes": {}
|
| 647 |
}
|