timesformer-base-finetuned-k400-submission

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1785
  • Accuracy: 0.94

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: 4e-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: 1500

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2307 0.1667 250 0.1391 0.96
0.2739 1.1667 500 0.6467 0.88
0.0006 2.1667 750 0.1763 0.96
0.0001 3.1667 1000 0.1302 0.96
0.0002 4.1667 1250 0.1326 0.96
0.0001 5.1667 1500 0.1758 0.96

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
121M params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for JackWong0911/timesformer-base-finetuned-k400-submission

Finetuned
(46)
this model