Labira/LabiraPJOK_6x_50

This model is a fine-tuned version of Labira/LabiraPJOK_5x_50 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1155
• Validation Loss: 2.1395
• Epoch: 45

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': 150, '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
2.0573	2.3329	0
1.3047	2.0503	1
1.1311	1.8969	2
0.4437	1.8286	3
0.4078	1.8199	4
0.5102	1.8192	5
0.4207	1.8550	6
0.2787	1.9171	7
0.4091	1.9373	8
0.3602	1.9061	9
0.2561	1.8889	10
0.2233	1.8902	11
0.2392	1.8824	12
0.1526	1.8853	13
0.1237	1.9106	14
0.1993	1.9339	15
0.3208	1.9720	16
0.1681	2.0189	17
0.1451	2.0625	18
0.2050	2.0801	19
0.1442	2.0687	20
0.2149	2.0457	21
0.1707	2.0365	22
0.1915	2.0288	23
0.1657	2.0256	24
0.1676	2.0323	25
0.1489	2.0413	26
0.1763	2.0559	27
0.0684	2.0698	28
0.1342	2.1025	29
0.1239	2.1459	30
0.0993	2.1898	31
0.1242	2.2285	32
0.1523	2.2495	33
0.1173	2.2643	34
0.2508	2.2549	35
0.0771	2.2329	36
0.0981	2.2178	37
0.1489	2.2089	38
0.1475	2.2051	39
0.0799	2.1896	40
0.0974	2.1739	41
0.2017	2.1636	42
0.1171	2.1517	43
0.0789	2.1435	44
0.1155	2.1395	45

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 3.0.1
• Tokenizers 0.19.1