nbme-deberta-large / README.md
smeoni's picture
update model card README.md
418cca0
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: nbme-deberta-large
    results: []

nbme-deberta-large

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

  • Loss: 0.8806

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.358 1.0 1850 1.1622
1.0073 2.0 3700 0.9461
0.8837 3.0 5550 0.8806

Framework versions

  • Transformers 4.19.0.dev0
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1