Ir para o conteúdo
ModelListadosExterno
Baixar

Unlearn Cl Ucf101 Videomae Large Neggrad 6 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: -41.9971 Accuracy: 0.0037 Test Accuracy: 0.0037 Df Accuracy: 0.0052...

TipoOtherModelo baseMCG-NJU/videomae-largeVersãoRevision 10be654Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
1,13 GB
Modelo base
MCG-NJU/videomae-large
Versão
vRevision 10be654
Atualizado
3 de nov. de 2026
Downloads
4
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: -41.9971
  • Accuracy: 0.0037
  • Test Accuracy: 0.0037
  • Df Accuracy: 0.0052
  • Unlearn Overall Accuracy: 0.4993
  • Unlearn Time: 4400.0969

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: 4
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • 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 log1.0520-41.99710.00520.49930.4993-1
No log2.0540-44.74920.00520.49930.4993-1
No log2.8957-45.20260.00520.49930.4993-1

Framework versions

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

Fontes

1 fonte
Hugging FacePrimárioVersão 10be654748ebd00fb195db725ae4e918bd1eb199
huggingface.co/jialicheng/unlearn-cl_ucf101_videomae-large_neggrad_6_42/tree/10be654748ebd00fb195db725ae4e918bd1eb199

Verificado 3 de nov.

Download files

Artefatos de modelo

1 artefato

model.safetensors

safetensors · FP32 (unverified) · 1,13 GB · SHA-256 652254d0e9d1…038f · Hugging Face

Download file

Trechos de fonte

3 trechos

--- 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: -41.9971 - Accuracy: 0.0037 - Test Accuracy: 0.0037 - Df Accuracy: 0.0052 - Unlearn Overall Accuracy: 0.4993 - Unlearn Time: 4400.0969 ## 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: 4 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - 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 | 1.05 | 20 | -41.9971 | 0.0052 | 0.4993 | 0.4993 | -1 | | No log | 2.05 | 40 | -44.7492 | 0.0052 | 0.4993 | 0.4993 | -1 | | No log | 2.89 | 57 | -45.2026 | 0.0052 | 0.4993 | 0.4993 | -1 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu118 - Datasets 2.18.0 - Tokenizers 0.15.2

Source context: 4 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn-cl_ucf101_videomae-large_neggrad_6_42

Source context: 3 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn-cl_ucf101_videomae-large_neggrad_6_42