distilbert-base-uncased-finetuned-mnli

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: 0.5486
• Accuracy: 0.8244

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: 16
• eval_batch_size: 16
• 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
0.5142	1.0	24544	0.4922	0.8075
0.4089	2.0	49088	0.4865	0.8194
0.2936	3.0	73632	0.5486	0.8244

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1