huynhdoo/distilcamembert-base-finetuned-jva-missions-report

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

• Train Loss: 0.0336
• Validation Loss: 1.1880
• Train F1: 0.0391
• Epoch: 17

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': 3000, '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	Train F1	Epoch
0.5225	0.4756	0.3575	0
0.4079	0.4294	0.2961	1
0.3439	0.5053	0.2961	2
0.2765	0.5106	0.2346	3
0.2044	0.5352	0.1788	4
0.1774	0.6706	0.1341	5
0.1690	0.8693	0.1676	6
0.1143	0.7711	0.0726	7
0.0930	0.9906	0.0950	8
0.1091	0.9093	0.1117	9
0.0576	0.8518	0.0894	10
0.0500	1.2538	0.0950	11
0.0541	0.7193	0.0838	12
0.0461	0.9906	0.0503	13
0.0359	0.9036	0.0447	14
0.0320	1.1648	0.0391	15
0.0299	1.0017	0.0279	16
0.0336	1.1880	0.0391	17

Framework versions

• Transformers 4.26.0
• TensorFlow 2.9.2
• Datasets 2.9.0
• Tokenizers 0.13.2