NepaliGECadmodel

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.9713
• Train Accuracy: 0.5380
• Validation Loss: 0.5668
• Validation Accuracy: 0.5871
• Epoch: 2

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 4e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 0.1, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
2.4284	0.4173	0.7741	0.5720	0
1.1785	0.5198	0.6646	0.5768	1
0.9713	0.5380	0.5668	0.5871	2

Framework versions

• Transformers 4.47.0
• TensorFlow 2.17.1
• Datasets 3.2.0
• Tokenizers 0.21.0