serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04

This model is a fine-tuned version of serhii-korobchenko/mt5-small_poetry_test-2024-02-23-09-44-03 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 4.2334
• Validation Loss: 3.3547
• Epoch: 16

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': 2400, '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': 0.0001}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
6.6604	4.1654	0
6.0975	3.9769	1
5.7642	3.8194	2
5.5421	3.7233	3
5.5621	3.6724	4
5.2110	3.6284	5
5.0164	3.5796	6
4.9996	3.5401	7
4.8020	3.4781	8
4.7490	3.4661	9
4.6101	3.4544	10
4.4780	3.4371	11
4.4204	3.4310	12
4.3121	3.3932	13
4.2895	3.3719	14
4.2082	3.3649	15
4.2334	3.3547	16

Framework versions

• Transformers 4.37.2
• TensorFlow 2.15.0
• Datasets 2.17.1
• Tokenizers 0.15.2