Hugging Face's logo

Ahmed107
/
nllb200-ar-en_v1-qlora

Translation
PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
nllb200-ar-en_v1-qlora / README.md
Ahmed107's picture
Ahmed107
Training complete
587ee3b verified
preview code
|
raw
history blame contribute delete
1.16 kB
metadata
license: cc-by-nc-4.0
library_name: peft
tags:
  - translation
  - generated_from_trainer
base_model: Ahmed107/nllb200-ar-en_v8
model-index:
  - name: nllb200-ar-en_v1-qlora
    results: []

nllb200-ar-en_v1-qlora

This model is a fine-tuned version of Ahmed107/nllb200-ar-en_v8 on an unknown dataset.

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: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0