BERT_B01

This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6902
• Precision: 0.6636
• Recall: 0.6946
• F1: 0.6788
• Accuracy: 0.8776

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:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.0749	1.0	47	0.9390	0.4203	0.3480	0.3807	0.7831
0.6411	2.0	94	0.6110	0.5948	0.5392	0.5657	0.8452
0.4786	3.0	141	0.5279	0.6784	0.6121	0.6435	0.8630
0.3573	4.0	188	0.4972	0.6462	0.6382	0.6422	0.8691
0.2824	5.0	235	0.4868	0.6339	0.6479	0.6408	0.8689
0.2434	6.0	282	0.4970	0.6490	0.6561	0.6525	0.8715
0.1854	7.0	329	0.5004	0.6578	0.6795	0.6685	0.8721
0.1336	8.0	376	0.5091	0.6508	0.6768	0.6635	0.8736
0.1186	9.0	423	0.5437	0.6340	0.6768	0.6547	0.8739
0.103	10.0	470	0.5482	0.6570	0.6823	0.6694	0.8771
0.0799	11.0	517	0.5620	0.6444	0.6781	0.6609	0.8752
0.1045	12.0	564	0.5812	0.6557	0.6864	0.6707	0.8760
0.0562	13.0	611	0.6009	0.6667	0.6850	0.6757	0.8780
0.0637	14.0	658	0.5937	0.6707	0.6946	0.6824	0.8780
0.0657	15.0	705	0.6017	0.6788	0.6946	0.6866	0.8789
0.0371	16.0	752	0.6227	0.6858	0.6905	0.6881	0.8776
0.0389	17.0	799	0.6476	0.6499	0.6919	0.6702	0.8767
0.0461	18.0	846	0.6667	0.6556	0.7043	0.6790	0.8786
0.0377	19.0	893	0.6515	0.6788	0.6919	0.6853	0.8793
0.0364	20.0	940	0.6480	0.6791	0.7015	0.6901	0.8784
0.0383	21.0	987	0.6646	0.6719	0.7070	0.6890	0.8802
0.0173	22.0	1034	0.6724	0.6750	0.7029	0.6887	0.8793
0.0613	23.0	1081	0.6779	0.6580	0.6988	0.6778	0.8778
0.0578	24.0	1128	0.6847	0.6592	0.6864	0.6725	0.8767
0.0201	25.0	1175	0.6714	0.6706	0.7001	0.6851	0.8791
0.022	26.0	1222	0.6874	0.6667	0.6878	0.6770	0.8782
0.0298	27.0	1269	0.6926	0.6675	0.6960	0.6815	0.8789
0.03	28.0	1316	0.6895	0.6662	0.6974	0.6815	0.8784
0.0216	29.0	1363	0.6888	0.6636	0.6946	0.6788	0.8780
0.0236	30.0	1410	0.6902	0.6636	0.6946	0.6788	0.8776

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3