aditnnda/machine_translation

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

• Train Loss: 0.2082
• Validation Loss: 1.0149
• Epoch: 24

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': 5e-05, 'decay_steps': 1500, '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
1.8561	1.6274	0
1.4184	1.4283	1
1.1634	1.2964	2
0.9729	1.2049	3
0.8390	1.1546	4
0.7333	1.1060	5
0.6449	1.0874	6
0.6032	1.0554	7
0.5251	1.0308	8
0.4711	1.0321	9
0.4255	1.0258	10
0.3880	1.0208	11
0.3622	1.0189	12
0.3337	1.0176	13
0.3107	1.0187	14
0.2922	1.0149	15
0.2718	1.0110	16
0.2594	1.0118	17
0.2460	1.0116	18
0.2334	1.0133	19
0.2279	1.0156	20
0.2210	1.0134	21
0.2130	1.0147	22
0.2085	1.0157	23
0.2082	1.0149	24

Framework versions

• Transformers 4.35.2
• TensorFlow 2.14.0
• Datasets 2.15.0
• Tokenizers 0.15.0