Ir para o conteúdo
ModelListadosExterno
Baixar

Unlearn Ucf101 Videomae Large Bad Teaching 10 42

This model is a fine-tuned version of MCG-NJU/videomae-large on the ucf101 dataset. It achieves the following results on the evaluation set: Loss: 0.7369 Accuracy: 0.884 Test Accuracy: 0.884 Df Accuracy: 0.9510...

Fontehuggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42/tree/adc772af37f24e7dfa8ea38a184ab7faf16d3af2
TipoModeloModelo baseMCG-NJU/videomae-largeVersãoRevision adc772aBnota

Fonte do modelo

Tipo
Modelo
Tamanho do arquivo
1,13 GB
Modelo base
MCG-NJU/videomae-large
Versão
vRevision adc772a
Atualizado
30 de out. de 2026
Downloads
8
Fonte
Hugging Face

Descrição da fonte

ucf101_42

This model is a fine-tuned version of MCG-NJU/videomae-large on the ucf101 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7369
  • Accuracy: 0.884
  • Test Accuracy: 0.884
  • Df Accuracy: 0.9510
  • Unlearn Overall Accuracy: 0.4665
  • Unlearn Time: 6701.2192

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: 32
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training LossEpochStepValidation LossAccuracyOverall AccuracyUnlearn Overall AccuracyTime
No log1.01640.59450.96120.46480.4648-1
No log2.011280.69800.94930.46590.4659-1
No log2.971890.73690.95100.46650.4665-1

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.2+cu118
  • Datasets 2.18.0
  • Tokenizers 0.15.2

Fontes

1 fonte
Hugging FacePrimárioVersão adc772af37f24e7dfa8ea38a184ab7faf16d3af2
huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42/tree/adc772af37f24e7dfa8ea38a184ab7faf16d3af2

Verificado 30 de out.

Download files

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · FP32 (tensor header) · 1,13 GB · SHA-256 9c4423d0b465…cbab · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme14 de ago.huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42

--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-large tags: - video-classification - generated_from_trainer metrics: - accuracy model-index: - name: ucf101_42 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # ucf101_42 This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on the ucf101 dataset. It achieves the following results on the evaluation set: - Loss: 0.7369 - Accuracy: 0.884 - Test Accuracy: 0.884 - Df Accuracy: 0.9510 - Unlearn Overall Accuracy: 0.4665 - Unlearn Time: 6701.2192 ## 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: 32 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------------:|:------------------------:|:----:| | No log | 1.01 | 64 | 0.5945 | 0.9612 | 0.4648 | 0.4648 | -1 | | No log | 2.01 | 128 | 0.6980 | 0.9493 | 0.4659 | 0.4659 | -1 | | No log | 2.97 | 189 | 0.7369 | 0.9510 | 0.4665 | 0.4665 | -1 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu118 - Datasets 2.18.0 - Tokenizers 0.15.2

Note30 de out.huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42

Source context: 8 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42

Note14 de ago.huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42

Source context: 4 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_bad_teaching_10_42