JackWong0911's picture
Model save
0c44243 verified
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-finetuned-kinetic400-subset-epoch6-num_frame_10_full_time_space
    results: []

timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_full_time_space

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: 0.4630
  • Accuracy: 0.8971

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: 300

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5915 0.17 50 0.6170 0.8611
0.2742 1.17 100 0.4572 0.8333
0.0174 2.17 150 0.3006 0.8611
0.0309 3.17 200 0.3319 0.8889
0.0006 4.17 250 0.3438 0.8889
0.0008 5.17 300 0.3266 0.8889

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Tokenizers 0.15.2