Hugging Face's logo

williamhtan
/
nllb-200-distilled-600M_dyu-fra

Text2Text Generation
Transformers
Safetensors
m2m_100
Generated from Trainer
Model card Files Community
nllb-200-distilled-600M_dyu-fra / README.md
williamhtan's picture
williamhtan
End of training
0b7ed68 verified
preview code
|
raw
history blame
1.9 kB
metadata
base_model: facebook/nllb-200-distilled-600M
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: nllb-200-distilled-600M_dyu-fra
    results: []

Visualize in Weights & Biases

nllb-200-distilled-600M_dyu-fra

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: 2.1351
  • Bleu: 8.0857
  • Gen Len: 12.4534

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 127 2.2543 6.9492 12.5554
No log 2.0 254 2.1730 7.8245 12.363
No log 3.0 381 2.1442 8.0013 12.4174
2.4578 4.0 508 2.1351 8.0857 12.4534

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1