---

license: apache-2.0 base_model: google/mt5-small tags:

• generated_from_keras_callback model-index:
• name: folflo/mt5-small-finetuned-HunSum-1_hvg_index_1103 results: [] datasets:
• SZTAKI-HLT/HunSum-1 metrics:
• rouge --- rouge1: 26.98 --- rouge2: 3.449 --- rougeL: 15.3615 --- rougeLsum: 20.3444

folflo/mt5-small-finetuned-HunSum-1_hvg_index_1103

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: 2.8267
• Validation Loss: 2.6510
• 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 213912, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
3.8545	2.9337	0
3.1558	2.8171	1
3.0206	2.7562	2
2.9448	2.7049	3
2.8955	2.6809	4
2.8618	2.6626	5
2.8399	2.6548	6
2.8267	2.6510	7

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1