distilbert-amazon-shoe-reviews_ubuntu

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: 0.9573
• Accuracy: 0.5726
• F1: [0.62998761 0.45096564 0.49037037 0.55640244 0.73547094]
• Precision: [0.62334478 0.45704118 0.47534706 0.5858748 0.72102161]
• Recall: [0.63677355 0.4450495 0.5063743 0.52975327 0.75051125]

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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.9617	1.0	2813	0.9573	0.5726	[0.62998761 0.45096564 0.49037037 0.55640244 0.73547094]	[0.62334478 0.45704118 0.47534706 0.5858748 0.72102161]	[0.63677355 0.4450495 0.5063743 0.52975327 0.75051125]

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1+cu102
• Datasets 2.4.0
• Tokenizers 0.12.1