ABL_trad_2g

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7368
• Accuracy: 0.7594
• F1: 0.7583

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-07
• 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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7967	1.0	4683	0.7805	0.6444	0.6437
0.713	2.0	9366	0.7182	0.6826	0.6809
0.6496	3.0	14049	0.6774	0.7078	0.7070
0.6205	4.0	18732	0.6500	0.7190	0.7182
0.5875	5.0	23415	0.6315	0.7304	0.7296
0.5494	6.0	28098	0.6289	0.7362	0.7351
0.5261	7.0	32781	0.6281	0.7401	0.7389
0.4968	8.0	37464	0.6281	0.7454	0.7442
0.4478	9.0	42147	0.6244	0.7477	0.7459
0.4476	10.0	46830	0.6270	0.7529	0.7516
0.4033	11.0	51513	0.6414	0.7548	0.7532
0.3984	12.0	56196	0.6558	0.7570	0.7553
0.3577	13.0	60879	0.6742	0.7593	0.7584
0.353	14.0	65562	0.6918	0.7619	0.7611
0.3261	15.0	70245	0.7103	0.7618	0.7610
0.3248	16.0	74928	0.7368	0.7594	0.7583

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1