serhii-korobchenko/mt5-small_poetry_Helsinki-2024-02-23-17-44-34

This model is a fine-tuned version of Helsinki-NLP/opus-mt-ru-uk on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0194
• Validation Loss: 2.6788
• Epoch: 19

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-06, 'decay_steps': 2740, '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': 1e-06}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
0.0892	2.5969	0
0.0658	2.6050	1
0.0609	2.6026	2
0.0519	2.6134	3
0.0411	2.6232	4
0.0392	2.6326	5
0.0333	2.6448	6
0.0311	2.6494	7
0.0277	2.6555	8
0.0245	2.6601	9
0.0249	2.6607	10
0.0234	2.6678	11
0.0213	2.6720	12
0.0210	2.6713	13
0.0192	2.6732	14
0.0203	2.6741	15
0.0173	2.6764	16
0.0170	2.6778	17
0.0170	2.6787	18
0.0194	2.6788	19

Framework versions

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