file_classifier_v3

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

• Loss: 0.6714
• Accuracy: 0.8586

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	73	0.7821	0.7966
No log	2.0	146	0.7362	0.8103
No log	3.0	219	0.6557	0.8207
No log	4.0	292	0.7113	0.8069
No log	5.0	365	0.6241	0.8379
No log	6.0	438	0.6169	0.8448
0.206	7.0	511	0.6305	0.8345
0.206	8.0	584	0.6552	0.8621
0.206	9.0	657	0.6110	0.8724
0.206	10.0	730	0.6937	0.8552
0.206	11.0	803	0.6749	0.8552
0.206	12.0	876	0.6484	0.8690
0.206	13.0	949	0.6889	0.8586
0.0253	14.0	1022	0.6630	0.8586
0.0253	15.0	1095	0.6714	0.8586

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1