distilbert-base-uncased-finetuned-sst2

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

• Loss: 0.4654
• Accuracy: 0.8624

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: 32
• seed: 30
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	27	0.4003	0.8224
No log	2.0	54	0.3516	0.8459
No log	3.0	81	0.4151	0.8376
No log	4.0	108	0.4419	0.8635
No log	5.0	135	0.4654	0.8624

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2