Hugging Face's logo

skywalker290
/
videomae-vivit-d2

Video Classification
Transformers
Safetensors
vivit
Generated from Trainer
Inference Endpoints
Model card Files Community
videomae-vivit-d2 / README.md
skywalker290's picture
skywalker290
End of training
2f41037 verified
preview code
|
raw
history blame contribute delete
2.1 kB
metadata
library_name: transformers
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: VIVIT-d2
    results: []

VIVIT-d2

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.9103
  • Accuracy: 0.4210

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: 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: 6650
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.556 0.1 665 2.3470 0.2123
2.0142 1.1 1330 2.1601 0.3180
2.122 2.1 1995 2.0851 0.4047
1.7405 3.1 2660 2.3452 0.4205
1.2998 4.1 3325 2.3814 0.4557
1.4591 5.1 3990 2.7093 0.3820
0.8984 6.1 4655 2.5562 0.3584
0.3971 7.1 5320 3.1583 0.4057
0.5996 8.1 5985 2.9134 0.4154
0.8684 9.1 6650 2.9103 0.4210

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3