modelo_entrenado_01

This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4536

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	267	0.6835
0.9199	2.0	534	0.6370
0.9199	3.0	801	0.5897
0.6357	4.0	1068	0.5777
0.6357	5.0	1335	0.5880
0.5711	6.0	1602	0.5634
0.5711	7.0	1869	0.5716
0.5481	8.0	2136	0.5407
0.5481	9.0	2403	0.5352
0.5204	10.0	2670	0.5153
0.5204	11.0	2937	0.5037
0.492	12.0	3204	0.4821
0.492	13.0	3471	0.4890
0.4854	14.0	3738	0.4826
0.48	15.0	4005	0.4718
0.48	16.0	4272	0.4758
0.464	17.0	4539	0.4655
0.464	18.0	4806	0.4870
0.4575	19.0	5073	0.4544
0.4575	20.0	5340	0.4559
0.4484	21.0	5607	0.5187
0.4484	22.0	5874	0.4987
0.4414	23.0	6141	0.4673
0.4414	24.0	6408	0.4795
0.4323	25.0	6675	0.4692
0.4323	26.0	6942	0.4749
0.4333	27.0	7209	0.4828
0.4333	28.0	7476	0.4351
0.4313	29.0	7743	0.4405
0.4292	30.0	8010	0.4614

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1