bert-base-multilingual-cased-finetuned-MeIA-AlfaSolitarioAnalisisDos

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

• Loss: 1.3851
• F1: 0.4957

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: 1e-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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
1.1756	1.0	919	1.1346	0.4528
1.0961	2.0	1838	1.1198	0.4846
1.0068	3.0	2757	1.1392	0.4780
0.8529	4.0	3676	1.1641	0.4838
0.7661	5.0	4595	1.2500	0.4849
0.8	6.0	5514	1.3851	0.4957
0.6047	7.0	6433	1.5040	0.4818
0.4928	8.0	7352	1.6488	0.4705
0.4616	9.0	8271	1.8546	0.4869
0.3593	10.0	9190	2.0165	0.4637
0.296	11.0	10109	2.1244	0.4888
0.2748	12.0	11028	2.3060	0.4648
0.2045	13.0	11947	2.3929	0.4781
0.1779	14.0	12866	2.5274	0.4770
0.1997	15.0	13785	2.5591	0.4865

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3