Edit model card

Labira/LabiraPJOK_2_100_Full

This model is a fine-tuned version of Labira/LabiraPJOK_1_100_Full on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0293
  • Validation Loss: 0.1300
  • Epoch: 99

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 600, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
4.5209 3.3699 0
3.0253 2.2638 1
2.4401 1.5791 2
1.7668 1.1757 3
1.1708 0.9297 4
0.8116 0.9080 5
0.7249 0.8814 6
0.5783 0.8619 7
0.6304 0.8486 8
0.4778 0.7509 9
0.2941 0.7865 10
0.3170 0.7460 11
0.4126 0.6175 12
0.3620 0.6029 13
0.1818 0.6585 14
0.2768 0.6480 15
0.2536 0.5260 16
0.2123 0.4587 17
0.2634 0.4301 18
0.1602 0.4109 19
0.0932 0.4353 20
0.1643 0.4815 21
0.1566 0.4562 22
0.1502 0.4109 23
0.1226 0.3920 24
0.1434 0.3484 25
0.1087 0.3325 26
0.1222 0.3458 27
0.1464 0.3116 28
0.0992 0.3066 29
0.1061 0.2891 30
0.1433 0.2752 31
0.0631 0.2797 32
0.0411 0.3270 33
0.1420 0.3368 34
0.1089 0.3010 35
0.1200 0.2545 36
0.0783 0.2148 37
0.1737 0.2061 38
0.1382 0.2004 39
0.0655 0.2980 40
0.0930 0.2433 41
0.0628 0.2099 42
0.0819 0.1863 43
0.0670 0.2036 44
0.0692 0.2208 45
0.0712 0.1989 46
0.0552 0.1790 47
0.0593 0.1699 48
0.1086 0.1732 49
0.0655 0.1703 50
0.0448 0.2029 51
0.0449 0.2357 52
0.0486 0.2362 53
0.0432 0.1734 54
0.0471 0.1580 55
0.1355 0.1838 56
0.0690 0.3843 57
0.1021 0.3450 58
0.0422 0.1757 59
0.0434 0.1444 60
0.0612 0.1391 61
0.1042 0.1467 62
0.0445 0.1664 63
0.0454 0.1636 64
0.0485 0.1568 65
0.0361 0.1518 66
0.0365 0.1477 67
0.0444 0.1452 68
0.0399 0.1430 69
0.0396 0.1401 70
0.0133 0.1408 71
0.0388 0.1452 72
0.0442 0.1505 73
0.0394 0.1497 74
0.0370 0.1474 75
0.0428 0.1436 76
0.0378 0.1408 77
0.0363 0.1413 78
0.0390 0.1391 79
0.0456 0.1396 80
0.0405 0.1390 81
0.0316 0.1379 82
0.0366 0.1389 83
0.0339 0.1389 84
0.0380 0.1374 85
0.0406 0.1369 86
0.0306 0.1352 87
0.0319 0.1332 88
0.0383 0.1322 89
0.0356 0.1301 90
0.0376 0.1295 91
0.0450 0.1300 92
0.0336 0.1304 93
0.0286 0.1306 94
0.0277 0.1304 95
0.0290 0.1302 96
0.0142 0.1299 97
0.0334 0.1300 98
0.0293 0.1300 99

Framework versions

  • Transformers 4.44.2
  • TensorFlow 2.17.0
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
8
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Labira/LabiraPJOK_2_100_Full

Finetuned
(1)
this model
Finetunes
1 model