bert_adaptation_referencias_de_vinos

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

• Loss: 1.7296

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
3.06	1.0	750	2.4974
2.4463	2.0	1500	2.3140
2.2515	3.0	2250	2.1646
2.0962	4.0	3000	2.0073
2.0126	5.0	3750	2.0552
1.9271	6.0	4500	1.9176
1.8427	7.0	5250	1.8497
1.8009	8.0	6000	1.8579
1.7596	9.0	6750	1.8501
1.7049	10.0	7500	1.8178
1.6992	11.0	8250	1.7969
1.67	12.0	9000	1.8254
1.6272	13.0	9750	1.7340
1.6192	14.0	10500	1.7664
1.6209	15.0	11250	1.7281

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3