bert-mini-domain-adapted-imdb

This model is a fine-tuned version of prajjwal1/bert-mini on imdb movie reviews dataset. It achieves the following results on the evaluation set:

• Loss: 2.7667
• Perplexity: 15.91

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: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.0658	1.0	782	2.8164
3.0034	2.0	1564	2.7746
2.9766	3.0	2346	2.7728

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2