Prototipo_4_EMI

This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0406
• Accuracy: 0.5567

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: 50
• eval_batch_size: 50
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3118	0.3704	200	1.2660	0.4457
1.0828	0.7407	400	1.0757	0.5203
1.0145	1.1111	600	1.0380	0.534
0.9955	1.4815	800	1.0184	0.5377
0.9449	1.8519	1000	0.9944	0.5507
0.9143	2.2222	1200	1.0077	0.5533
0.8609	2.5926	1400	1.0104	0.5473
0.882	2.9630	1600	1.0037	0.5507
0.8049	3.3333	1800	1.0202	0.5593
0.8045	3.7037	2000	1.0234	0.5503
0.78	4.0741	2200	1.0280	0.5593
0.7651	4.4444	2400	1.0411	0.5583
0.7301	4.8148	2600	1.0406	0.5567

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1