pr_dataset_metadata

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

• eval_loss: 0.6216
• eval_accuracy: 1.0
• eval_runtime: 0.4472
• eval_samples_per_second: 2.236
• eval_steps_per_second: 2.236
• step: 0

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: not_parallel
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.11.0+cu102
• Datasets 2.0.0
• Tokenizers 0.12.1