VideoMAE_BdSLW60_SR_8_kineticsFinetuned_withoutAug

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

  • Loss: 0.2197
  • Accuracy: 0.95
  • Precision: 0.9612
  • Recall: 0.95
  • F1: 0.9458

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 18560
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
2.859 0.0501 929 0.8475 0.9183 0.9240 0.9183 0.9087
0.0555 1.0501 1858 0.3023 0.9217 0.9317 0.9217 0.9093
0.0025 2.0501 2787 0.2999 0.935 0.9378 0.935 0.9273
0.0009 3.0501 3716 0.0876 0.9767 0.9809 0.9767 0.9762
0.1355 4.0501 4645 0.2540 0.9267 0.9182 0.9267 0.9146
0.099 5.0501 5574 0.2616 0.9633 0.9570 0.9633 0.9578
0.0656 6.0501 6503 0.2061 0.9617 0.9675 0.9617 0.9598
0.0314 7.0501 7432 0.2037 0.9533 0.9624 0.9533 0.9526
0.0874 8.0501 8361 0.2197 0.95 0.9612 0.95 0.9458

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.1
Downloads last month
21
Safetensors
Model size
86.3M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Shawon16/VideoMAE_BdSLW60_SR_8_kineticsFinetuned_withoutAug

Finetuned
(98)
this model