Hugging Face's logo

yasmineee
/
NLLB-600M-FFT

Safetensors
m2m_100
Generated from Trainer
Model card Files Community
NLLB-600M-FFT / README.md
yasmineee's picture
yasmineee
NLLB-600M-FFT
17a3e2c verified
preview code
|
raw
history blame contribute delete
1.74 kB
metadata
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
  - generated_from_trainer
metrics:
  - bleu
  - rouge
model-index:
  - name: NLLB-600M-FFT
    results: []

NLLB-600M-FFT

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: 1.3513
  • Bleu: 35.7724
  • Rouge: 0.5734
  • Gen Len: 16.8375

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Rouge Gen Len
1.9858 1.0 250 1.3645 35.126 0.5746 16.7
1.1589 2.0 500 1.3468 36.7577 0.5841 17.0312
0.9961 3.0 750 1.3513 35.7724 0.5734 16.8375

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1