distilbert-amazon-shoe-reviews-scaled

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1836
• Accuracy: 0.456
• F1: [0.56281407 0.31088083 0.32608696 0.32142857 0.6640625 ]
• Precision: [0.5045045 0.34090909 0.37037037 0.35064935 0.59440559]
• Recall: [0.63636364 0.28571429 0.29126214 0.2967033 0.75221239]

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: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.3447	1.0	141	1.1836	0.456	[0.56281407 0.31088083 0.32608696 0.32142857 0.6640625 ]	[0.5045045 0.34090909 0.37037037 0.35064935 0.59440559]	[0.63636364 0.28571429 0.29126214 0.2967033 0.75221239]

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3