Labira/LabiraPJOK_2x_50

This model is a fine-tuned version of Labira/LabiraPJOK_1_50 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0131
• Validation Loss: 4.2318
• 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': 250, '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
4.4264	3.9800	0
3.0757	3.5083	1
2.2362	3.1869	2
1.5246	2.7953	3
0.9065	2.8214	4
0.7330	3.3041	5
0.6050	3.4187	6
0.5238	3.4963	7
0.3471	3.4544	8
0.2836	3.1970	9
0.4074	3.1324	10
0.1832	3.2997	11
0.1899	3.5169	12
0.0939	3.5228	13
0.1638	3.3909	14
0.1055	3.4798	15
0.0827	3.6602	16
0.1070	3.7096	17
0.0751	3.7451	18
0.0449	3.7821	19
0.0299	3.8203	20
0.0505	3.8744	21
0.0247	3.9163	22
0.0534	3.9760	23
0.0442	4.0388	24
0.0211	4.0753	25
0.0216	4.0966	26
0.0219	4.1131	27
0.0234	4.1117	28
0.0255	4.1391	29
0.0199	4.1682	30
0.0196	4.1973	31
0.0317	4.2302	32
0.0263	4.2538	33
0.0322	4.2648	34
0.0171	4.2541	35
0.0200	4.2429	36
0.0201	4.2240	37
0.0331	4.1675	38
0.0220	4.1519	39
0.0158	4.1661	40
0.0131	4.1824	41
0.0174	4.2002	42
0.0170	4.2208	43
0.0131	4.2318	44

Framework versions

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