Labira/LabiraPJOK_5x_50

This model is a fine-tuned version of Labira/LabiraPJOK_3x_50 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0274
• Validation Loss: 3.1328
• Epoch: 44

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
3.2696	2.9298	0
1.9565	2.6626	1
1.6690	2.7837	2
1.1679	2.9196	3
1.0975	2.8046	4
0.8930	2.6822	5
0.6527	2.6118	6
0.5637	2.5444	7
0.4854	2.5175	8
0.4389	2.5464	9
0.3206	2.5893	10
0.3225	2.6538	11
0.1880	2.7504	12
0.1288	2.8371	13
0.1381	2.9128	14
0.0994	2.9468	15
0.1544	2.9312	16
0.0978	2.9279	17
0.0492	2.9426	18
0.0612	2.9733	19
0.1016	3.0228	20
0.0554	3.0772	21
0.0768	3.1331	22
0.0277	3.1720	23
0.0403	3.1906	24
0.0730	3.1962	25
0.0204	3.1958	26
0.0731	3.1981	27
0.0414	3.1874	28
0.0316	3.1657	29
0.0324	3.1507	30
0.0526	3.1275	31
0.0369	3.1141	32
0.0406	3.1091	33
0.0214	3.1127	34
0.0209	3.1207	35
0.0139	3.1172	36
0.0215	3.1166	37
0.0140	3.1168	38
0.0277	3.1187	39
0.0131	3.1214	40
0.0184	3.1226	41
0.0286	3.1256	42
0.0144	3.1297	43
0.0274	3.1328	44

Framework versions

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