Edit model card

tiny-mbart-length-96-learning_rate-2e-05-weight_decay-0.01-finetuned-en-to-ro

This model is a fine-tuned version of sshleifer/tiny-mbart on the wmt16_en_ro_pre_processed dataset. It achieves the following results on the evaluation set:

  • Loss: 8.5137
  • Bleu: 0.0
  • Gen Len: 20.0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
8.2817 1.0 76290 8.5137 0.0 20.0

Framework versions

  • Transformers 4.12.5
  • Pytorch 1.10.0+cu102
  • Datasets 1.15.1
  • Tokenizers 0.10.3
Downloads last month
12
Hosted inference API
This model can be loaded on the Inference API on-demand.

Evaluation results