HW2-reward

This model is a fine-tuned version of KoNqUeRoR3891/HW2-supervised on the piqa dataset. It achieves the following results on the evaluation set:

• Loss: 0.7024
• Accuracy: 0.6408

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6793	1.0	3626	0.6733	0.5782
0.6767	2.0	7252	0.6590	0.6210
0.5686	3.0	10878	0.7024	0.6408

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1