bank-categorizer

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: 1.6305
• Accuracy: 0.5

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: 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
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	15	2.7929	0.1724
No log	2.0	30	2.4526	0.3448
No log	3.0	45	2.1792	0.3621
No log	4.0	60	2.0229	0.4310
No log	5.0	75	1.9259	0.4483
No log	6.0	90	1.8270	0.4655
No log	7.0	105	1.8080	0.4655
No log	8.0	120	1.7047	0.5
No log	9.0	135	1.6910	0.5172
No log	10.0	150	1.6723	0.5
No log	11.0	165	1.7065	0.4828
No log	12.0	180	1.6203	0.5
No log	13.0	195	1.6266	0.5
No log	14.0	210	1.6286	0.5
No log	15.0	225	1.6305	0.5

Framework versions

• Transformers 5.10.2
• Pytorch 2.11.0+cu128
• Datasets 2.20.0
• Tokenizers 0.22.2