FNST_trad_g

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: 0.8709
• Accuracy: 0.6667
• F1: 0.6510

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-06
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.1501	1.0	1000	1.0940	0.5208	0.3539
0.9834	2.0	2000	0.9339	0.5883	0.5317
0.8949	3.0	3000	0.8767	0.6233	0.6071
0.8316	4.0	4000	0.8421	0.64	0.6185
0.7873	5.0	5000	0.8242	0.645	0.6211
0.7676	6.0	6000	0.8323	0.6525	0.6356
0.7196	7.0	7000	0.8204	0.6542	0.6352
0.6937	8.0	8000	0.8229	0.6608	0.6449
0.6493	9.0	9000	0.8427	0.6617	0.6450
0.6254	10.0	10000	0.8474	0.6667	0.6502
0.5911	11.0	11000	0.8611	0.6708	0.6551
0.5732	12.0	12000	0.8709	0.6667	0.6510

Framework versions

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