deberta-v3-large-fever

This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3771
• Accuracy: 0.8864

Model description

Input <= 512: [evidence_text][SEP][claim]

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2748	1.0	7134	0.3707	0.8779
0.1482	2.0	14268	0.3771	0.8864

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1
• Datasets 2.15.0
• Tokenizers 0.14.1