fine-tuned-MoritzLaurer-deberta-v3-base-zeroshot-v2.0-arceasy

This model is a fine-tuned version of MoritzLaurer/deberta-v3-base-zeroshot-v2.0 on ARC-Easy dataset. It achieves the following results on the evaluation set:

• Loss: 0.9473
• Accuracy: 0.7123

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: 1.5e-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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	71	1.0023	0.6947
No log	2.0	142	1.0230	0.6982
No log	3.0	213	0.9488	0.7053
No log	4.0	284	0.9037	0.7211
No log	5.0	355	0.9433	0.7123
No log	6.0	426	0.9473	0.7123

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1