lakshaywadhwa1993/mt5-small-finetuned-hindi-mt5

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: 1.4909
• Validation Loss: 1.3507
• Epoch: 7

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 41000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
3.5310	1.8341	0
2.0735	1.6193	1
1.7617	1.4672	2
1.6375	1.4271	3
1.5712	1.3720	4
1.5294	1.3656	5
1.5051	1.3531	6
1.4909	1.3507	7

Framework versions

• Transformers 4.18.0
• TensorFlow 2.6.4
• Datasets 2.1.0
• Tokenizers 0.12.1