modelo_entrenado_02

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

• Loss: 2.9755

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-08
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	3.0764
No log	2.0	4	2.9682
No log	3.0	6	2.9192
No log	4.0	8	2.7053
No log	5.0	10	3.2641
No log	6.0	12	3.0686
No log	7.0	14	2.8964
No log	8.0	16	2.9286
No log	9.0	18	3.2297
No log	10.0	20	2.8838
No log	11.0	22	2.6667
No log	12.0	24	2.7971
No log	13.0	26	2.5930
No log	14.0	28	2.8104
No log	15.0	30	2.7695
No log	16.0	32	2.6098
No log	17.0	34	3.0375
No log	18.0	36	3.1342
No log	19.0	38	3.0716
No log	20.0	40	2.6655
No log	21.0	42	2.5342
No log	22.0	44	2.8461
No log	23.0	46	3.1634
No log	24.0	48	3.0142
No log	25.0	50	3.2181
No log	26.0	52	3.0536
No log	27.0	54	2.6519
No log	28.0	56	2.8154
No log	29.0	58	2.9385
No log	30.0	60	2.8281
No log	31.0	62	2.7531
No log	32.0	64	2.9408
No log	33.0	66	2.5850
No log	34.0	68	2.8823
No log	35.0	70	2.5177
No log	36.0	72	2.9296
No log	37.0	74	3.0441
No log	38.0	76	2.8714
No log	39.0	78	2.7857
No log	40.0	80	2.9850
No log	41.0	82	3.3792
No log	42.0	84	2.9246
No log	43.0	86	2.9392
No log	44.0	88	2.4090
No log	45.0	90	2.8323
No log	46.0	92	3.2173
No log	47.0	94	2.5451
No log	48.0	96	2.7456
No log	49.0	98	2.7570
No log	50.0	100	3.0471

Framework versions

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