Edit model card

NLP_Opt350M

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3806

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: 3.0

Training results

Training Loss Epoch Step Validation Loss
3.453 1.0 849 3.3589
2.9744 2.0 1698 3.3594
2.7146 3.0 2547 3.3806

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
5