videomae-base-finetuned-ucf101-subset

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: 0.3992
  • Accuracy: 0.8645

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: 8
  • eval_batch_size: 8
  • 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: 148

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.1374 0.26 38 1.7413 0.5714
0.7949 1.26 76 0.7747 0.8
0.4279 2.26 114 0.4053 0.9143
0.291 3.23 148 0.3429 0.9286

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.6.1
  • Tokenizers 0.13.2
Downloads last month
29
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using sayakpaul/videomae-base-finetuned-ucf101-subset 2