Toprak1yu/distilbert-imdb-classification

results

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

• Loss: 0.3647
• Accuracy: 0.9205

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3138	1.0	1250	0.3044	0.905
0.1932	2.0	2500	0.3246	0.9195
0.0970	3.0	3750	0.3647	0.9205

Framework versions

• Transformers 5.14.1
• Pytorch 2.13.0+cu130
• Datasets 5.0.1
• Tokenizers 0.22.2