sentiment-analysis-imdb-distilbert

This model is a fine-tuned version of distilbert-base-uncased on IMDb dataset. It achieves the following results on the evaluation set:

• Loss: 0.2224
• Accuracy: 0.918
• F1: 0.9180

Model description

This model is a DistilBERT-based sentiment analysis model fine-tuned on the IMDb dataset. It is designed to predict sentiment labels for the texts, classifying them as either positive or negative.

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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.287	1.0	500	0.2224	0.918	0.9180

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Tokenizers 0.15.2