uhlenbeckmew's picture
update model card README.md
c2dec21
|
raw
history blame
1.38 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: distilroberta-base-swift_shake
    results: []

distilroberta-base-swift_shake

This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5309

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
No log 1.0 334 2.5817
2.7363 2.0 668 2.4499
2.4584 3.0 1002 2.5309

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1