spanish-attitude

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the jorgeortizfuentes/spanish_attitude_conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6388
• Affect Precision: 0.0
• Affect Recall: 0.0
• Affect F1: 0.0
• Affect Number: 61
• Appreciation Precision: 0.2208
• Appreciation Recall: 0.3401
• Appreciation F1: 0.2677
• Appreciation Number: 294
• Judgment (j1) Precision: 0.0
• Judgment (j1) Recall: 0.0
• Judgment (j1) F1: 0.0
• Judgment (j1) Number: 2
• Social esteem (j2) Precision: 0.0
• Social esteem (j2) Recall: 0.0
• Social esteem (j2) F1: 0.0
• Social esteem (j2) Number: 2
• Social sanction (j2) Precision: 0.0
• Social sanction (j2) Recall: 0.0
• Social sanction (j2) F1: 0.0
• Social sanction (j2) Number: 1
• Capacity (j3) Precision: 0.1037
• Capacity (j3) Recall: 0.1977
• Capacity (j3) F1: 0.1360
• Capacity (j3) Number: 86
• Normality (j3) Precision: 0.0
• Normality (j3) Recall: 0.0
• Normality (j3) F1: 0.0
• Normality (j3) Number: 62
• Propriety (j3) Precision: 0.1586
• Propriety (j3) Recall: 0.2791
• Propriety (j3) F1: 0.2022
• Propriety (j3) Number: 129
• Tenacity (j3) Precision: 0.0
• Tenacity (j3) Recall: 0.0
• Tenacity (j3) F1: 0.0
• Tenacity (j3) Number: 47
• Veracity (j3) Precision: 0.0
• Veracity (j3) Recall: 0.0
• Veracity (j3) F1: 0.0
• Veracity (j3) Number: 20
• Overall Precision: 0.1792
• Overall Recall: 0.2173
• Overall F1: 0.1964
• Overall Accuracy: 0.8250

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: 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: 3.0

Training results

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2