Yelp-Review-Sentiment-Analysis

<!-- 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. -->

Yelp-Review-Sentiment-Analysis

This model was trained from the YelpReviewFull Dataset.

Model description

Fine tuned from the ElizaClaPa/SentimentAnalysis-YelpReviews-OptimizedModel

Intended uses & limitations

Sentiment analysis of Yelp Reviews.

Training and evaluation data

Trained on 101 data points from the YelpReviewFull Dataset due to computing constraints. Evaluated on 51 data points from the YelpReviewFull Dataset due to computing constraints.

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

          precision    recall  f1-score   support

       0       1.00      0.00      0.00        10
       1       0.25      0.15      0.19        13
       2       0.00      0.00      0.00         5
       3       0.17      0.18      0.17        11
       4       0.25      0.20      0.22        10
       5       0.00      1.00      0.00         0

accuracy                           0.12        49

macro avg 0.28 0.26 0.10 49 weighted avg 0.36 0.12 0.13 49

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Tokenizers 0.19.1