clasificador-tweets2

This model is a fine-tuned version of somosnlp-hackathon-2022/biomedtra-small-es-squad2-es on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5948
• Accuracy: 0.4894

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: 8
• eval_batch_size: 8
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	23	2.0204	0.3404
No log	2.0	46	1.9668	0.3404
No log	3.0	69	1.9234	0.3404
No log	4.0	92	1.8778	0.3404
No log	5.0	115	1.8512	0.3404
No log	6.0	138	1.8098	0.3404
No log	7.0	161	1.7683	0.3617
No log	8.0	184	1.7476	0.3404
No log	9.0	207	1.6983	0.3404
No log	10.0	230	1.6630	0.4043
No log	11.0	253	1.6474	0.4468
No log	12.0	276	1.6140	0.4468
No log	13.0	299	1.6116	0.4468
No log	14.0	322	1.5956	0.4894
No log	15.0	345	1.5948	0.4894

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0