nllb-200-distilled-600M-finetuned_augmented_synthetic_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: 0.7501
• Bleu: 62.4193
• Gen Len: 64.586

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
1.0564	1.0	2210	1.0374	45.431	65.406
0.8998	2.0	4420	0.8975	52.6173	66.014
0.7972	3.0	6630	0.8399	55.9624	65.357
0.7451	4.0	8840	0.8021	57.3958	65.94
0.6884	5.0	11050	0.7771	59.9589	65.367
0.6742	6.0	13260	0.7648	61.0786	64.74
0.6599	7.0	15470	0.7562	61.9442	64.694
0.6168	8.0	17680	0.7530	62.0067	64.965
0.6234	9.0	19890	0.7502	62.0721	64.888
0.5948	10.0	22100	0.7501	62.4193	64.586

Framework versions

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