README.md

metadata

license: apache-2.0
base_model: Helsinki-NLP/opus-mt-id-en
tags:
  - generated_from_keras_callback
model-index:
  - name: aditnnda/machine_translation_informal2formal
    results: []

aditnnda/machine_translation_informal2formal

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: 0.0453
• Validation Loss: 1.1322
• Epoch: 37

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': 6000, '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: float32

Training results

Train Loss	Validation Loss	Epoch
3.4298	2.4070	0
2.1508	1.8031	1
1.6301	1.5249	2
1.3013	1.3417	3
1.0752	1.2465	4
0.9119	1.1651	5
0.7778	1.1213	6
0.6763	1.0813	7
0.5907	1.0542	8
0.5162	1.0289	9
0.4573	1.0265	10
0.4057	1.0115	11
0.3645	1.0096	12
0.3227	1.0037	13
0.2864	1.0016	14
0.2598	1.0121	15
0.2291	1.0079	16
0.2069	1.0199	17
0.1876	1.0247	18
0.1717	1.0199	19
0.1544	1.0283	20
0.1393	1.0416	21
0.1285	1.0370	22
0.1171	1.0430	23
0.1069	1.0593	24
0.0990	1.0670	25
0.0915	1.0655	26
0.0827	1.0818	27
0.0781	1.0903	28
0.0729	1.0998	29
0.0678	1.0932	30
0.0639	1.1051	31
0.0592	1.1125	32
0.0556	1.1240	33
0.0509	1.1177	34
0.0512	1.1355	35
0.0438	1.1405	36
0.0453	1.1322	37

Framework versions

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