bert_adaptation_resenas_de_vinos_2023_11_25_15_31

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: 2.6461

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.9807	1.0	250	3.0434
3.0811	2.0	500	3.1461
2.7704	3.0	750	2.9649
2.6821	4.0	1000	2.8179
2.556	5.0	1250	2.6522
2.3324	6.0	1500	2.7123
2.3137	7.0	1750	2.5994
2.2926	8.0	2000	2.6741
2.1216	9.0	2250	2.6469
2.0317	10.0	2500	2.6205
2.0053	11.0	2750	2.4237
2.0453	12.0	3000	2.5970
1.9702	13.0	3250	2.4548
1.9147	14.0	3500	2.4731
1.9143	15.0	3750	2.4431
1.7803	16.0	4000	2.4247
1.7726	17.0	4250	2.5558
1.7448	18.0	4500	2.5092
1.7008	19.0	4750	2.4883
1.769	20.0	5000	2.4471

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0