epochs_4_fold_3

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

• Loss: 0.4891

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.7377	0.2020	300	0.5840
0.574	0.4040	600	0.5354
0.5498	0.6061	900	0.5066
0.5235	0.8081	1200	0.4885
0.4919	1.0101	1500	0.4831
0.4094	1.2121	1800	0.4765
0.3969	1.4141	2100	0.4650
0.4004	1.6162	2400	0.4601
0.3805	1.8182	2700	0.4430
0.3667	2.0202	3000	0.4686
0.2865	2.2222	3300	0.4657
0.2665	2.4242	3600	0.4708
0.2826	2.6263	3900	0.4578
0.277	2.8283	4200	0.4487
0.2573	3.0303	4500	0.4659
0.1979	3.2323	4800	0.4792
0.1906	3.4343	5100	0.4979
0.182	3.6364	5400	0.4955
0.1863	3.8384	5700	0.4891

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.0