output_dir2 / README.md
cifope's picture
End of training
d130c08 verified
metadata
base_model: cifope/nllb-200-en-twi-v4-1.3B
tags:
  - generated_from_trainer
model-index:
  - name: output_dir2
    results: []

output_dir2

This model is a fine-tuned version of cifope/nllb-200-en-twi-v4-1.3B on the None dataset. It achieves the following results on the evaluation set:

  • eval_rouge: 0.8878
  • eval_loss: 4.8689
  • eval_rouge1: 0.9058
  • eval_rouge2: 0.8579
  • eval_rougeL: 0.8996
  • eval_runtime: 118.7194
  • eval_samples_per_second: 6.065
  • eval_steps_per_second: 0.379
  • epoch: 0.47
  • step: 100

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2