JackWong0911's picture
Model save
d15c6cb verified
|
raw
history blame
1.92 kB
metadata
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: >-
      timesformer-base-finetuned-k400-kinetic400-subset-epoch6real-num_frame_10_myViT2_more_data
    results: []

timesformer-base-finetuned-k400-kinetic400-subset-epoch6real-num_frame_10_myViT2_more_data

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: 0.1873
  • 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
0.4861 0.17 250 0.3386 0.9
0.7118 1.17 500 0.5020 0.9
0.004 2.17 750 0.1791 0.95
0.0001 3.17 1000 0.2894 0.94
0.0001 4.17 1250 0.2922 0.94
0.002 5.17 1500 0.3140 0.93

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2