modelo_entrenado_03

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

• Loss: 2.8773

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	3.0317
No log	2.0	4	3.2466
No log	3.0	6	2.8743
No log	4.0	8	3.1765
No log	5.0	10	2.9545
No log	6.0	12	2.9224
No log	7.0	14	2.6441
No log	8.0	16	3.1026
No log	9.0	18	2.8052
No log	10.0	20	2.9207
No log	11.0	22	2.9361
No log	12.0	24	3.1022
No log	13.0	26	2.6288
No log	14.0	28	2.8037
No log	15.0	30	2.9928
No log	16.0	32	3.0567
No log	17.0	34	2.9547
No log	18.0	36	2.8910
No log	19.0	38	3.2010
No log	20.0	40	3.0122
No log	21.0	42	2.7867
No log	22.0	44	3.1202
No log	23.0	46	3.2064
No log	24.0	48	2.8428
No log	25.0	50	2.9438
No log	26.0	52	3.0401
No log	27.0	54	2.6635
No log	28.0	56	2.8430
No log	29.0	58	2.7399
No log	30.0	60	3.0186
No log	31.0	62	2.5696
No log	32.0	64	2.9357
No log	33.0	66	3.0687
No log	34.0	68	2.8788
No log	35.0	70	3.1435
No log	36.0	72	3.0425
No log	37.0	74	3.1079
No log	38.0	76	3.1720
No log	39.0	78	2.7954
No log	40.0	80	3.3530
No log	41.0	82	3.2281
No log	42.0	84	2.7445
No log	43.0	86	3.0153
No log	44.0	88	2.7714
No log	45.0	90	2.6887
No log	46.0	92	2.7577
No log	47.0	94	2.8747
No log	48.0	96	3.0094
No log	49.0	98	3.0738
No log	50.0	100	3.0079

Framework versions

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