afaji's picture
afaji/summerschool-2layer-irony
f7507c1 verified
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: summerschool-2layer-irony
    results: []

summerschool-2layer-irony

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

  • Loss: 0.6777
  • Accuracy: 0.5765

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: 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
0.7183 0.2793 50 0.6864 0.5581
0.6948 0.5587 100 0.7066 0.5068
0.6915 0.8380 150 0.6904 0.5403
0.686 1.1173 200 0.6764 0.5623
0.6511 1.3966 250 0.6981 0.5623
0.6752 1.6760 300 0.7057 0.5351
0.661 1.9553 350 0.6755 0.5686
0.6343 2.2346 400 0.6735 0.5874
0.6507 2.5140 450 0.6700 0.5895
0.6408 2.7933 500 0.6734 0.5738
0.6337 3.0726 550 0.6697 0.5843
0.6013 3.3520 600 0.6694 0.5927
0.6139 3.6313 650 0.6667 0.6031
0.6037 3.9106 700 0.6676 0.6168
0.592 4.1899 750 0.6691 0.5832
0.5791 4.4693 800 0.6707 0.5864
0.5884 4.7486 850 0.6599 0.6042

Framework versions

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