opus-mt-ar-en-finetuned_augmented_synthetic_cleaned-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:

• Loss: 0.6421
• Bleu: 64.9533
• Gen Len: 66.193

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:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.9547	1.0	1043	0.8017	56.8271	68.803
0.7598	2.0	2086	0.7281	60.44	67.238
0.672	3.0	3129	0.6984	62.5171	66.992
0.6063	4.0	4172	0.6737	63.4355	66.075
0.5641	5.0	5215	0.6607	64.2124	66.145
0.5188	6.0	6258	0.6537	64.5988	66.547
0.4934	7.0	7301	0.6467	64.7664	66.528
0.4858	8.0	8344	0.6458	64.756	66.225
0.468	9.0	9387	0.6427	64.9386	66.086
0.4474	10.0	10430	0.6421	64.9533	66.193

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3