hangpatrick92
commited on
Commit
•
ddf4382
1
Parent(s):
3bd837e
End of training
Browse files- README.md +2 -0
- all_results.json +10 -10
- eval_results.json +5 -5
- runs/Sep25_15-39-03_Hang-Inspiron16/events.out.tfevents.1727293662.Hang-Inspiron16.37628.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +148 -11
README.md
CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- imagefolder
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
6 |
+
- image-classification
|
7 |
+
- vision
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- imagefolder
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 1.
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8597560975609756,
|
4 |
+
"eval_loss": 0.3955613076686859,
|
5 |
+
"eval_runtime": 18.361,
|
6 |
+
"eval_samples_per_second": 8.932,
|
7 |
+
"eval_steps_per_second": 1.144,
|
8 |
+
"total_flos": 3.571605801336545e+17,
|
9 |
+
"train_loss": 0.13593495262080224,
|
10 |
+
"train_runtime": 495.489,
|
11 |
+
"train_samples_per_second": 9.334,
|
12 |
+
"train_steps_per_second": 1.171
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8597560975609756,
|
4 |
+
"eval_loss": 0.3955613076686859,
|
5 |
+
"eval_runtime": 18.361,
|
6 |
+
"eval_samples_per_second": 8.932,
|
7 |
+
"eval_steps_per_second": 1.144
|
8 |
}
|
runs/Sep25_15-39-03_Hang-Inspiron16/events.out.tfevents.1727293662.Hang-Inspiron16.37628.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08d0bd45c22d9b61fddbd990c61b4ac2afe3219f2750f47943fb4d20ec8b90d7
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"total_flos": 3.571605801336545e+17,
|
4 |
+
"train_loss": 0.13593495262080224,
|
5 |
+
"train_runtime": 495.489,
|
6 |
+
"train_samples_per_second": 9.334,
|
7 |
+
"train_steps_per_second": 1.171
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./TransparentBagClassifier/checkpoint-
|
4 |
"epoch": 5.0,
|
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,
|
@@ -340,18 +340,155 @@
|
|
340 |
"eval_steps_per_second": 1.117,
|
341 |
"step": 410
|
342 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
343 |
{
|
344 |
"epoch": 5.0,
|
345 |
-
"step":
|
346 |
-
"total_flos":
|
347 |
-
"train_loss": 0.
|
348 |
-
"train_runtime":
|
349 |
-
"train_samples_per_second":
|
350 |
-
"train_steps_per_second":
|
351 |
}
|
352 |
],
|
353 |
"logging_steps": 10,
|
354 |
-
"max_steps":
|
355 |
"num_input_tokens_seen": 0,
|
356 |
"num_train_epochs": 5,
|
357 |
"save_steps": 500,
|
@@ -367,7 +504,7 @@
|
|
367 |
"attributes": {}
|
368 |
}
|
369 |
},
|
370 |
-
"total_flos":
|
371 |
"train_batch_size": 8,
|
372 |
"trial_name": null,
|
373 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3955613076686859,
|
3 |
+
"best_model_checkpoint": "./TransparentBagClassifier/checkpoint-580",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 580,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
340 |
"eval_steps_per_second": 1.117,
|
341 |
"step": 410
|
342 |
},
|
343 |
+
{
|
344 |
+
"epoch": 3.6206896551724137,
|
345 |
+
"grad_norm": 5.8970112800598145,
|
346 |
+
"learning_rate": 5.517241379310345e-06,
|
347 |
+
"loss": 0.4971,
|
348 |
+
"step": 420
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 3.706896551724138,
|
352 |
+
"grad_norm": 3.7783031463623047,
|
353 |
+
"learning_rate": 5.172413793103449e-06,
|
354 |
+
"loss": 0.5238,
|
355 |
+
"step": 430
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 3.793103448275862,
|
359 |
+
"grad_norm": 4.057668209075928,
|
360 |
+
"learning_rate": 4.8275862068965525e-06,
|
361 |
+
"loss": 0.476,
|
362 |
+
"step": 440
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 3.8793103448275863,
|
366 |
+
"grad_norm": 4.21135950088501,
|
367 |
+
"learning_rate": 4.482758620689656e-06,
|
368 |
+
"loss": 0.487,
|
369 |
+
"step": 450
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 3.9655172413793105,
|
373 |
+
"grad_norm": 6.149752616882324,
|
374 |
+
"learning_rate": 4.137931034482759e-06,
|
375 |
+
"loss": 0.4749,
|
376 |
+
"step": 460
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 4.0,
|
380 |
+
"eval_accuracy": 0.7987804878048781,
|
381 |
+
"eval_loss": 0.45718589425086975,
|
382 |
+
"eval_runtime": 18.5139,
|
383 |
+
"eval_samples_per_second": 8.858,
|
384 |
+
"eval_steps_per_second": 1.134,
|
385 |
+
"step": 464
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 4.051724137931035,
|
389 |
+
"grad_norm": 5.206491470336914,
|
390 |
+
"learning_rate": 3.793103448275862e-06,
|
391 |
+
"loss": 0.5889,
|
392 |
+
"step": 470
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.137931034482759,
|
396 |
+
"grad_norm": 4.442436218261719,
|
397 |
+
"learning_rate": 3.448275862068966e-06,
|
398 |
+
"loss": 0.5011,
|
399 |
+
"step": 480
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 4.224137931034483,
|
403 |
+
"grad_norm": 3.270550012588501,
|
404 |
+
"learning_rate": 3.103448275862069e-06,
|
405 |
+
"loss": 0.4479,
|
406 |
+
"step": 490
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 4.310344827586207,
|
410 |
+
"grad_norm": 2.839463710784912,
|
411 |
+
"learning_rate": 2.7586206896551725e-06,
|
412 |
+
"loss": 0.4054,
|
413 |
+
"step": 500
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 4.396551724137931,
|
417 |
+
"grad_norm": 3.1818559169769287,
|
418 |
+
"learning_rate": 2.4137931034482762e-06,
|
419 |
+
"loss": 0.3631,
|
420 |
+
"step": 510
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 4.482758620689655,
|
424 |
+
"grad_norm": 7.189451217651367,
|
425 |
+
"learning_rate": 2.0689655172413796e-06,
|
426 |
+
"loss": 0.4301,
|
427 |
+
"step": 520
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 4.568965517241379,
|
431 |
+
"grad_norm": 3.522141695022583,
|
432 |
+
"learning_rate": 1.724137931034483e-06,
|
433 |
+
"loss": 0.4977,
|
434 |
+
"step": 530
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 4.655172413793103,
|
438 |
+
"grad_norm": 2.4986538887023926,
|
439 |
+
"learning_rate": 1.3793103448275862e-06,
|
440 |
+
"loss": 0.381,
|
441 |
+
"step": 540
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 4.741379310344827,
|
445 |
+
"grad_norm": 5.762561321258545,
|
446 |
+
"learning_rate": 1.0344827586206898e-06,
|
447 |
+
"loss": 0.4179,
|
448 |
+
"step": 550
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 4.827586206896552,
|
452 |
+
"grad_norm": 1.9201445579528809,
|
453 |
+
"learning_rate": 6.896551724137931e-07,
|
454 |
+
"loss": 0.4958,
|
455 |
+
"step": 560
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 4.913793103448276,
|
459 |
+
"grad_norm": 5.6399407386779785,
|
460 |
+
"learning_rate": 3.4482758620689656e-07,
|
461 |
+
"loss": 0.4647,
|
462 |
+
"step": 570
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 5.0,
|
466 |
+
"grad_norm": 5.986402988433838,
|
467 |
+
"learning_rate": 0.0,
|
468 |
+
"loss": 0.4319,
|
469 |
+
"step": 580
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 5.0,
|
473 |
+
"eval_accuracy": 0.8597560975609756,
|
474 |
+
"eval_loss": 0.3955613076686859,
|
475 |
+
"eval_runtime": 18.7383,
|
476 |
+
"eval_samples_per_second": 8.752,
|
477 |
+
"eval_steps_per_second": 1.121,
|
478 |
+
"step": 580
|
479 |
+
},
|
480 |
{
|
481 |
"epoch": 5.0,
|
482 |
+
"step": 580,
|
483 |
+
"total_flos": 3.571605801336545e+17,
|
484 |
+
"train_loss": 0.13593495262080224,
|
485 |
+
"train_runtime": 495.489,
|
486 |
+
"train_samples_per_second": 9.334,
|
487 |
+
"train_steps_per_second": 1.171
|
488 |
}
|
489 |
],
|
490 |
"logging_steps": 10,
|
491 |
+
"max_steps": 580,
|
492 |
"num_input_tokens_seen": 0,
|
493 |
"num_train_epochs": 5,
|
494 |
"save_steps": 500,
|
|
|
504 |
"attributes": {}
|
505 |
}
|
506 |
},
|
507 |
+
"total_flos": 3.571605801336545e+17,
|
508 |
"train_batch_size": 8,
|
509 |
"trial_name": null,
|
510 |
"trial_params": null
|