results / README.md
afaji's picture
afaji/summerschool-2layer-distill-irony
e639254 verified
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: results
    results: []

results

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

  • Loss: 2.7225
  • Accuracy: 0.6416

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.6926 0.5587 100 2.4932 0.5508
3.4971 1.1173 200 2.1649 0.5738
2.7013 1.6760 300 2.1019 0.5801
2.0768 2.2346 400 2.4828 0.6241
1.4108 2.7933 500 2.3521 0.6471
1.0545 3.3520 600 2.5568 0.6115
0.707 3.9106 700 2.5198 0.6304
0.4998 4.4693 800 2.8322 0.6314

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1