| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: distilbert-base-uncased |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: AnalysisSentimentsReviewFilms |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # AnalysisSentimentsReviewFilms |
|
|
| This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: |
| - Accuracy: 0.79 |
| - Loss: 0.4532 |
|
|
| ## Model description |
|
|
| This model is designed to analyze movie reviews and automatically classify the sentiment expressed in the text. It determines whether the review is positive or negative and assigns a confidence score indicating the probability of the prediction. |
| The model processes the review's text content, identifies linguistic patterns, and evaluates the overall tone to generate its classification. |
|
|
| ## Intended uses & limitations |
|
|
| Intended Uses: |
|
|
| - Automatic classification of film reviews as positive or negative. |
|
|
| - Sentiment analysis on film review platforms. |
|
|
| - Support for recommendation systems based on user reviews. |
|
|
| - Monitoring audience perception of films. |
|
|
| Limitations: |
|
|
| - The model only distinguishes between positive and negative sentiment; it does not identify more complex nuances such as neutrality or irony. |
|
|
| - It may be less accurate with ambiguous, sarcastic, or figurative language. |
|
|
| ## Training and evaluation data |
|
|
| The model was trained using a dataset of film reviews manually labeled as positive or negative. |
| The data includes texts of varying lengths and writing styles to improve the model's generalizability. |
|
|
| The dataset was divided into training, validation, and testing categories to evaluate performance and avoid overfitting. |
| The metrics used for evaluation include accuracy, accuracy by class, recall, and F1 score. |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 2 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 1 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | No log | 1.0 | 250 | 0.4532 | 0.79 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.2.0 |
| - Pytorch 2.10.0+cpu |
| - Datasets 4.6.1 |
| - Tokenizers 0.22.2 |
| |
