nllb-200-distilled-600M-finetuned_augmented_MT_ar-to-en

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7204
• Bleu: 64.0069
• Gen Len: 65.416

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: 8
• eval_batch_size: 8
• 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
1.0557	1.0	2195	0.9595	49.4737	68.419
0.9159	2.0	4390	0.8377	55.3155	67.247
0.8074	3.0	6585	0.7898	58.8942	66.102
0.7441	4.0	8780	0.7559	60.8889	65.846
0.6963	5.0	10975	0.7395	61.3835	66.31
0.641	6.0	13170	0.7320	62.4226	65.985
0.6106	7.0	15365	0.7257	62.8285	65.505
0.5826	8.0	17560	0.7212	63.5372	65.474
0.5766	9.0	19755	0.7195	63.8042	65.525
0.5533	10.0	21950	0.7204	64.0069	65.416

Framework versions

• Transformers 4.31.0
• Pytorch 1.13.1
• Datasets 2.14.4
• Tokenizers 0.13.3