metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-ft-imdb-sentiment-classifier
results: []
distilbert-base-uncased-ft-imdb-sentiment-classifier
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2956
- Precision: 0.9191
- Recall: 0.8852
- F1: 0.9019
- Accuracy: 0.906
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3177 | 1.0 | 313 | 0.2525 | 0.8918 | 0.9119 | 0.9017 | 0.903 |
| 0.1762 | 2.0 | 626 | 0.2694 | 0.9137 | 0.8893 | 0.9013 | 0.905 |
| 0.113 | 3.0 | 939 | 0.2956 | 0.9191 | 0.8852 | 0.9019 | 0.906 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1