beto-ner-prostata-bs32

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

• Loss: 0.0640
• F1: 0.9584
• Precision: 0.9534
• Recall: 0.9635

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
No log	1.0	49	0.5442	0.6332	0.6263	0.6401
No log	2.0	98	0.1904	0.8651	0.8487	0.8822
No log	3.0	147	0.1017	0.9249	0.9098	0.9405
No log	4.0	196	0.0749	0.9511	0.9399	0.9625
No log	5.0	245	0.0514	0.9598	0.9545	0.9650
No log	6.0	294	0.0531	0.9715	0.9715	0.9715
No log	7.0	343	0.0532	0.9731	0.9728	0.9735
No log	8.0	392	0.0511	0.9748	0.9741	0.9754
No log	9.0	441	0.0505	0.9760	0.9767	0.9754
No log	10.0	490	0.0511	0.9757	0.9760	0.9754

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2