distilbert-base-uncased-finetuned-imdb

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

• Loss: 0.2776
• Accuracy: {'accuracy': 0.93192}
• F1: {'f1': 0.9319183250818663}

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.227	1.0	1563	0.2893	{'accuracy': 0.89856}	{'f1': 0.8979731717204342}
0.16	2.0	3126	0.2327	{'accuracy': 0.92876}	{'f1': 0.9287230772995674}
0.0914	3.0	4689	0.2776	{'accuracy': 0.93192}	{'f1': 0.9319183250818663}

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3