bart-copy-mechanism / README.md
bashyaldhiraj2067's picture
End of training
e5bd5fc verified
metadata
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: bart-copy-mechanism
    results: []

bart-copy-mechanism

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0335

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4853 0.3658 2500 0.2050
0.1517 0.7315 5000 0.0839
0.0833 1.0973 7500 0.0652
0.0624 1.4631 10000 0.0491
0.0508 1.8288 12500 0.0441
0.0459 2.1946 15000 0.0410
0.0431 2.5604 17500 0.0387
0.0408 2.9261 20000 0.0373
0.0391 3.2919 22500 0.0361
0.0379 3.6576 25000 0.0350
0.0371 4.0234 27500 0.0343
0.0361 4.3892 30000 0.0339
0.0357 4.7549 32500 0.0335

Framework versions

  • Transformers 4.50.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1