distilbert-base-finetuned-sentiment

This model is a fine-tuned version of lyrisha/distilbert-base-finetuned-imdb-sentiment on an imdb and GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3579
• Accuracy: 0.9128

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1715	1.0	2105	0.2463	0.9106
0.1114	2.0	4210	0.3239	0.9037
0.0755	3.0	6315	0.3579	0.9128

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1