FNST_trad_2g

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: 0.8657
• Accuracy: 0.6837
• F1: 0.6778

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-07
• 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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9579	1.0	3125	0.9375	0.5919	0.5798
0.8774	2.0	6250	0.8804	0.6252	0.6138
0.8269	3.0	9375	0.8451	0.6401	0.6322
0.7742	4.0	12500	0.8269	0.6491	0.6427
0.7478	5.0	15625	0.8143	0.6590	0.6521
0.7171	6.0	18750	0.8046	0.6616	0.6547
0.7033	7.0	21875	0.8018	0.6662	0.6598
0.6641	8.0	25000	0.7981	0.6733	0.6651
0.655	9.0	28125	0.8056	0.6736	0.6668
0.6189	10.0	31250	0.8114	0.6751	0.6688
0.5952	11.0	34375	0.8171	0.6778	0.6718
0.5759	12.0	37500	0.8190	0.6779	0.6733
0.536	13.0	40625	0.8297	0.6815	0.6768
0.5282	14.0	43750	0.8351	0.6799	0.6733
0.5146	15.0	46875	0.8632	0.6853	0.6794
0.4846	16.0	50000	0.8657	0.6837	0.6778

Framework versions

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