nllb-200-distilled-600M-Mal-Tami

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7611
  • Bleu: 37.9665
  • Rouge: {'rouge1': 0.32743825959084827, 'rouge2': 0.185409074130288, 'rougeL': 0.32502232667423403, 'rougeLsum': 0.32586316574736196}

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 Rouge
1.1388 1.0 734 0.8947 33.7987 {'rouge1': 0.32849704791121687, 'rouge2': 0.18672956891173587, 'rougeL': 0.32647539033778816, 'rougeLsum': 0.32688430438771043}
0.898 2.0 1468 0.8281 35.3540 {'rouge1': 0.32674790770839823, 'rouge2': 0.18650128486750617, 'rougeL': 0.32482214840866075, 'rougeLsum': 0.32547267295223703}
0.8046 3.0 2202 0.7962 36.1416 {'rouge1': 0.32674790770839823, 'rouge2': 0.1857352651103779, 'rougeL': 0.3244104763689233, 'rougeLsum': 0.3251467537911681}
0.7448 4.0 2936 0.7805 36.7560 {'rouge1': 0.32674790770839823, 'rouge2': 0.1858005621530716, 'rougeL': 0.32443967060792683, 'rougeLsum': 0.3251613509106698}
0.6985 5.0 3670 0.7696 37.3576 {'rouge1': 0.32614806855270073, 'rouge2': 0.18527678135494344, 'rougeL': 0.32362185574038427, 'rougeLsum': 0.3242525469535007}
0.663 6.0 4404 0.7661 37.8431 {'rouge1': 0.3275909830405743, 'rouge2': 0.18575262957184815, 'rougeL': 0.32552891023599473, 'rougeLsum': 0.32626719518749486}
0.636 7.0 5138 0.7639 37.8764 {'rouge1': 0.32740041520695484, 'rouge2': 0.18505379438127528, 'rougeL': 0.3249628569281158, 'rougeLsum': 0.3257682636769831}
0.6176 8.0 5872 0.7606 37.9621 {'rouge1': 0.3274220405691797, 'rouge2': 0.18538283587780377, 'rougeL': 0.3249736696092282, 'rougeLsum': 0.3257829175063507}
0.6047 9.0 6606 0.7605 37.9538 {'rouge1': 0.32743825959084827, 'rouge2': 0.185409074130288, 'rougeL': 0.32502232667423403, 'rougeLsum': 0.32586316574736196}
0.5969 10.0 7340 0.7611 37.9665 {'rouge1': 0.32743825959084827, 'rouge2': 0.185409074130288, 'rougeL': 0.32502232667423403, 'rougeLsum': 0.32586316574736196}

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.16.0
  • Tokenizers 0.13.3
Downloads last month
7