videomae-base-groub1-finetuned-SLT-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: 0.3056
  • Accuracy: 0.9767

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: 1008

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.8889 0.06 64 3.6733 0.0465
3.8474 1.06 128 3.7358 0.0698
3.7886 2.06 192 3.6336 0.0465
3.7398 3.06 256 3.5894 0.0698
3.7363 4.06 320 3.4637 0.0698
3.6345 5.06 384 3.3875 0.0698
3.2723 6.06 448 3.2156 0.1163
3.2814 7.06 512 2.7291 0.7209
2.7245 8.06 576 1.9657 0.8140
1.8616 9.06 640 1.2883 0.8837
1.3802 10.06 704 0.8116 0.9302
1.0416 11.06 768 0.5877 0.9535
0.6415 12.06 832 0.4426 0.9767
0.5546 13.06 896 0.3599 0.9767
0.4495 14.06 960 0.3212 0.9767
0.2214 15.05 1008 0.3056 0.9767

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
16
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.

Model tree for asmaa1/videomae-base-groub1-finetuned-SLT-subset

Finetuned
(421)
this model