GPT2-small-finetuned-amazon-reviews-en-classification

This model is a fine-tuned version of openai-community/gpt2 on mteb/amazon_reviews_multi dataset.

It is the result of the post Fine tunning SML

It achieves the following results on the evaluation set:

• Loss: 0.7974
• Accuracy: 0.6626

Model description

This model provides classification of reviews in english

Intended uses & limitations

Classifiction of reviews in english

Training and evaluation data

It is training on mteb/amazon_reviews_multi dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 28
• eval_batch_size: 40
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8074	1.0	7143	0.8203	0.652
0.7519	2.0	14286	0.8022	0.6546
0.7181	3.0	21429	0.8102	0.6578

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1