deberta-finetuned-answer-polarity-7e

This model is a fine-tuned version of microsoft/deberta-large on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.2369
• Accuracy: 0.9585

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: 7e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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
0.4752	1.0	944	0.3648	0.9140
0.5769	2.0	1888	0.3024	0.9402
0.1312	3.0	2832	0.2369	0.9585

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3