mi-super-modelo

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

• Loss: 1.5146
• Accuracy: 0.38

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7601	0.0455	2	1.7148	0.3333
1.7063	0.0909	4	1.6888	0.3
1.5512	0.1364	6	1.6585	0.2933
1.5312	0.1818	8	1.6514	0.3
1.5006	0.2273	10	1.6581	0.3
1.6519	0.2727	12	1.6511	0.3067
1.6397	0.3182	14	1.6347	0.3
1.5275	0.3636	16	1.6183	0.3067
1.8253	0.4091	18	1.5949	0.3
1.7725	0.4545	20	1.5708	0.3
1.5334	0.5	22	1.5591	0.3067
1.3062	0.5455	24	1.5535	0.3133
1.4629	0.5909	26	1.5459	0.32
1.5431	0.6364	28	1.5408	0.3333
1.62	0.6818	30	1.5355	0.36
1.4165	0.7273	32	1.5299	0.36
1.6135	0.7727	34	1.5244	0.3733
1.5181	0.8182	36	1.5220	0.3733
1.3877	0.8636	38	1.5196	0.3733
1.6638	0.9091	40	1.5174	0.3733
1.4348	0.9545	42	1.5154	0.38
1.4226	1.0	44	1.5146	0.38

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.0
• Datasets 3.1.0
• Tokenizers 0.20.1