minhah's picture
End of training
2abec99 verified
metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: videomae-base-finetuned-ElderReact-anger-balancedf1
    results: []

videomae-base-finetuned-ElderReact-anger-balancedf1

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

  • Loss: 0.7424
  • F1: 0.5798

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 240

Training results

Training Loss Epoch Step Validation Loss F1
0.7339 0.1 25 0.6865 0.4463
0.7007 1.1 50 0.7107 0.0476
0.6854 2.1 75 0.6994 0.4975
0.715 3.1 100 0.7238 0.1333
0.6866 4.1 125 0.7563 0.0195
0.6564 5.1 150 0.7628 0.1564
0.5809 6.1 175 0.7543 0.3831
0.6035 7.1 200 0.7983 0.2122
0.6153 8.1 225 0.7542 0.4063
0.5099 9.06 240 0.7408 0.4526

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2