lmazzon70's picture
update model card README.md
0af6f6b
metadata
license: cc-by-nc-4.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: videomae-base-short-finetuned-ssv2-finetuned-rwf2000-epochs8
    results: []

videomae-base-short-finetuned-ssv2-finetuned-rwf2000-epochs8

This model is a fine-tuned version of MCG-NJU/videomae-base-short-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3523
  • Accuracy: 0.5071

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: 2
  • eval_batch_size: 2
  • 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: 6400

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5905 0.12 800 0.6397 0.795
0.8951 1.12 1600 1.4140 0.6575
0.0121 2.12 2400 1.0683 0.7212
0.0081 3.12 3200 1.4044 0.6625
0.0531 4.12 4000 0.7906 0.8237
0.0045 5.12 4800 1.1109 0.7612
0.017 6.12 5600 1.8795 0.6462
0.6752 7.12 6400 1.0282 0.79

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2