maxime7770/model

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

• Train Loss: 0.1211
• Validation Loss: 0.4812
• Epoch: 49

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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 650, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.5966	1.5898	0
1.5577	1.5576	1
1.5034	1.4761	2
1.4034	1.3538	3
1.2864	1.2163	4
1.1502	1.0980	5
1.0085	0.9988	6
0.8828	0.9130	7
0.7863	0.8445	8
0.7036	0.7871	9
0.6322	0.7399	10
0.5731	0.7030	11
0.5180	0.6714	12
0.4757	0.6432	13
0.4366	0.6204	14
0.4057	0.6006	15
0.3743	0.5827	16
0.3475	0.5689	17
0.3221	0.5577	18
0.2971	0.5467	19
0.2815	0.5372	20
0.2700	0.5297	21
0.2521	0.5225	22
0.2343	0.5168	23
0.2265	0.5117	24
0.2143	0.5074	25
0.2063	0.5038	26
0.1941	0.5001	27
0.1843	0.4976	28
0.1782	0.4949	29
0.2012	0.4938	30
0.1691	0.4930	31
0.1626	0.4910	32
0.1884	0.4886	33
0.1547	0.4870	34
0.1492	0.4858	35
0.1445	0.4850	36
0.1415	0.4842	37
0.1383	0.4836	38
0.1374	0.4832	39
0.1336	0.4826	40
0.1322	0.4823	41
0.1295	0.4820	42
0.1268	0.4818	43
0.1261	0.4816	44
0.1253	0.4815	45
0.1275	0.4814	46
0.1247	0.4812	47
0.1256	0.4812	48
0.1211	0.4812	49

Framework versions

• Transformers 4.18.0
• TensorFlow 2.8.0
• Datasets 2.1.0
• Tokenizers 0.12.1