metadata

license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: opus-mt-ar-en-finetunedTanzil-v6-ar-to-en
    results: []

opus-mt-ar-en-finetunedTanzil-v6-ar-to-en

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

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
1.7341	1.4426	55.0505	31.6295	51.3925	51.8558	76.44	0
1.4329	1.2987	56.7672	33.8519	53.2796	53.6077	75.905	1
1.2849	1.2132	59.1926	36.8577	55.8615	56.2321	94.415	2
1.1854	1.1560	59.5654	36.0992	56.2438	56.6259	109.725	3
1.1092	1.1101	59.2882	36.3247	56.1751	56.6098	110.7	4
1.0478	1.0738	59.3702	35.9485	56.2157	56.6418	100.835	5
0.9957	1.0464	59.3582	35.5831	55.8989	56.3337	103.575	6
0.9503	1.0190	59.2327	35.7054	55.6769	56.0504	97.95	7
0.9099	0.9959	58.9992	34.9965	55.5582	55.8486	97.05	8
0.8735	0.9776	58.9665	35.1024	55.6433	55.8640	100.195	9
0.8405	0.9594	58.4345	34.4502	54.6634	54.9469	96.98	10