bert_category_prediction_amazon_book_reviews

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

• Loss: 1.3592
• Accuracy: 0.6

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	1.6152	0.6
No log	2.0	10	1.4903	0.6
No log	3.0	15	1.4141	0.6
No log	4.0	20	1.3729	0.6
No log	5.0	25	1.3592	0.6

Framework versions

• Transformers 4.28.0
• Pytorch 1.13.1
• Datasets 2.12.0
• Tokenizers 0.13.3