Edit model card

videomae-base-finetuned-2

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: 0.4272
  • Accuracy: 0.9182

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: 4
  • eval_batch_size: 4
  • 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: 925

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9244 0.2011 186 0.9936 0.5818
0.3114 1.2011 372 1.0746 0.6818
0.3265 2.2011 558 0.7547 0.8364
0.1401 3.2011 744 0.5196 0.9
0.0014 4.1957 925 0.4272 0.9182

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.1.0+cpu
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
48
Safetensors
Model size
86.2M params
Tensor type
F32
Β·
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 2nzi/videomae-surf-analytics

Finetuned
(410)
this model

Spaces using 2nzi/videomae-surf-analytics 5