<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tripadvisor-sentiment-model-test

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

• Loss: 0.6085

• Accuracy: 0.784

• Macro F1: 0.7543

• Macro Precision: 0.7539

• Macro Recall: 0.7550

• Weighted F1: 0.7857

• Weighted Precision: 0.7876

• Weighted Recall: 0.784

• Classification Report: precision recall f1-score support

       0       0.84      0.84      0.84       213
       1       0.87      0.85      0.86       269
       2       0.55      0.57      0.56       143
  

  accuracy 0.78 625 macro avg 0.75 0.76 0.75 625 weighted avg 0.79 0.78 0.79 625

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: 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: 3

Training results

       0       0.88      0.66      0.76       213
       1       0.78      0.96      0.86       269
       2       0.47      0.45      0.46       143

accuracy                           0.74       625

macro avg 0.71 0.69 0.69 625 weighted avg 0.74 0.74 0.73 625 | | 0.4981 | 2.0 | 626 | 0.6304 | 0.736 | 0.6969 | 0.7022 | 0.7044 | 0.7348 | 0.7484 | 0.736 | precision recall f1-score support

       0       0.74      0.93      0.83       213
       1       0.91      0.74      0.81       269
       2       0.45      0.45      0.45       143

accuracy                           0.74       625

macro avg 0.70 0.70 0.70 625 weighted avg 0.75 0.74 0.73 625 | | 0.356 | 3.0 | 939 | 0.6085 | 0.784 | 0.7543 | 0.7539 | 0.7550 | 0.7857 | 0.7876 | 0.784 | precision recall f1-score support

       0       0.84      0.84      0.84       213
       1       0.87      0.85      0.86       269
       2       0.55      0.57      0.56       143

accuracy                           0.78       625

macro avg 0.75 0.76 0.75 625 weighted avg 0.79 0.78 0.79 625 |

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3