arize-ai/distilbert_reviews_with_context_drift

distilbert_finetuned_reviews_with_drift

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

• Loss: 0.3822
• Accuracy: 0.8548
• F1: 0.8547

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.4173	1.0	620	0.3519	0.8511	0.8511
0.259	2.0	1240	0.3822	0.8548	0.8547

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1