Edit model card

videomae-base-finetuned-ssv2-finetuned-on-our-dataset

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

  • Loss: 0.7609
  • Accuracy: 0.8416

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: 1
  • eval_batch_size: 1
  • 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: 374512

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.9334 0.25 93628 1.6568 0.6375
1.1377 1.25 187256 1.0517 0.7516
1.2928 2.25 280884 0.8637 0.8105
0.0011 3.25 374512 0.7609 0.8416

Framework versions

  • Transformers 4.44.0
  • Pytorch 1.13.1+cu117
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
86.3M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for virkha/videomae-base-finetuned-ssv2-finetuned-on-our-dataset

Finetuned
(7)
this model