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
Downloads last month
105
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for KoNqUeRoR3891/HW2-reward

Finetuned
(1)
this model

Dataset used to train KoNqUeRoR3891/HW2-reward

Evaluation results