Labira/LabiraPJOK_6A_100_Full

This model is a fine-tuned version of Labira/LabiraPJOK_5A_100_Full on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0722
• Validation Loss: 0.0016
• 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 400, '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
2.0258	2.2523	0
1.2808	1.3791	1
0.9120	0.9660	2
0.6753	0.6375	3
0.4471	0.5591	4
0.3726	0.4426	5
0.2978	0.2854	6
0.2381	0.1319	7
0.2195	0.0788	8
0.1522	0.0483	9
0.1850	0.0283	10
0.0757	0.0216	11
0.0648	0.0191	12
0.1023	0.0174	13
0.1222	0.0153	14
0.0889	0.0162	15
0.0899	0.0106	16
0.0866	0.0076	17
0.0861	0.0074	18
0.0277	0.0049	19
0.1076	0.0044	20
0.0762	0.0049	21
0.1464	0.0127	22
0.1535	0.0320	23
0.1119	0.0419	24
0.2640	0.0356	25
0.2114	0.0199	26
0.0937	0.0106	27
0.1126	0.0091	28
0.1023	0.0089	29
0.0583	0.0079	30
0.0477	0.0065	31
0.0445	0.0055	32
0.0692	0.0045	33
0.0400	0.0039	34
0.0486	0.0035	35
0.0696	0.0032	36
0.0550	0.0030	37
0.0637	0.0027	38
0.0714	0.0023	39
0.0348	0.0019	40
0.0628	0.0017	41
0.0392	0.0017	42
0.0407	0.0018	43
0.0275	0.0019	44
0.0603	0.0019	45
0.0404	0.0016	46
0.0369	0.0014	47
0.0456	0.0012	48
0.0314	0.0010	49
0.0648	0.0010	50
0.0711	0.0010	51
0.0514	0.0011	52
0.0399	0.0012	53
0.0398	0.0013	54
0.0228	0.0013	55
0.0265	0.0013	56
0.0131	0.0014	57
0.0461	0.0014	58
0.0542	0.0014	59
0.0421	0.0014	60
0.0393	0.0019	61
0.0493	0.0023	62
0.0663	0.0027	63
0.0312	0.0029	64
0.0459	0.0031	65
0.0782	0.0030	66
0.0560	0.0029	67
0.0396	0.0028	68
0.0421	0.0026	69
0.0495	0.0025	70
0.0452	0.0024	71
0.0767	0.0023	72
0.0501	0.0020	73
0.0825	0.0019	74
0.0627	0.0018	75
0.0559	0.0018	76
0.0564	0.0017	77
0.0564	0.0017	78
0.0413	0.0017	79
0.0367	0.0017	80
0.0457	0.0017	81
0.0337	0.0017	82
0.0433	0.0017	83
0.0526	0.0018	84
0.0425	0.0018	85
0.0498	0.0018	86
0.0302	0.0017	87
0.0590	0.0017	88
0.0564	0.0017	89
0.0404	0.0016	90
0.0604	0.0016	91
0.0533	0.0016	92
0.0599	0.0016	93
0.0384	0.0016	94
0.0528	0.0016	95
0.0488	0.0016	96
0.0665	0.0016	97
0.0279	0.0016	98
0.0722	0.0016	99

Framework versions

• Transformers 4.45.2
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.20.1