metadata

license: apache-2.0
tags:
  - generated_from_keras_callback
base_model: Helsinki-NLP/opus-mt-en-fr
model-index:
  - name: marian-finetuned-kde4-english-to-french
    results: []

marian-finetuned-kde4-english-to-french

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

Train Loss: 0.6794
Validation Loss: 0.8119
Epoch: 2

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 29555, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
1.0577	0.8929	0
0.8023	0.8343	1
0.6794	0.8119	2

Framework versions

Transformers 4.30.2
TensorFlow 2.12.0
Datasets 2.13.1
Tokenizers 0.13.3