Saltar al contenido
ModelPublicadoExterno
Browse files

Unlearn Ucf101 Videomae Large Salun 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: 0.4212 Accuracy: 0.9150 Test Accuracy: 0.9150 Df Accuracy: 0.9101...

Fuentehuggingface.co/jialicheng/unlearn_ucf101_videomae-large_salun_10_42/tree/558c9dd11661e7c26f3e97e50207e69d055d92c6
TipoModeloModelo baseMCG-NJU/videomae-largeVersiónRevision 558c9ddBcalidad

Fuente del modelo

Tipo
Modelo
Tamaño del archivo
1,13–2,26 GB
Modelo base
MCG-NJU/videomae-large
Versión
vRevision 558c9dd
Actualizado
30 oct 2026
Descargas
3
Fuente
Hugging Face

Descripción de la fuente

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: 0.4212
  • Accuracy: 0.9150
  • Test Accuracy: 0.9150
  • Df Accuracy: 0.9101
  • Unlearn Overall Accuracy: 0.5024
  • Unlearn Time: 15833.3814

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 log1.02980.47530.96780.47020.4702-1
No log2.05960.44160.93080.48740.4874-1
No log3.08940.42120.91010.50240.5024-1

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión 558c9dd11661e7c26f3e97e50207e69d055d92c6
huggingface.co/jialicheng/unlearn_ucf101_videomae-large_salun_10_42/tree/558c9dd11661e7c26f3e97e50207e69d055d92c6

Verificado 30 oct

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

2 artefactos

model.safetensors

safetensors · FP32 (tensor header) · 1,13 GB · SHA-256 a03d6babd789…bd8d · Hugging Face

Download file

sal_mask_with_0.5.pt

pt · 2,26 GB · SHA-256 10369bc228d2…67b2 · Hugging Face

Download file

Extractos de fuentes

3 extractos
Readme14 agohuggingface.co/jialicheng/unlearn_ucf101_videomae-large_salun_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: 0.4212 - Accuracy: 0.9150 - Test Accuracy: 0.9150 - Df Accuracy: 0.9101 - Unlearn Overall Accuracy: 0.5024 - Unlearn Time: 15833.3814 ## 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 | 1.0 | 298 | 0.4753 | 0.9678 | 0.4702 | 0.4702 | -1 | | No log | 2.0 | 596 | 0.4416 | 0.9308 | 0.4874 | 0.4874 | -1 | | No log | 3.0 | 894 | 0.4212 | 0.9101 | 0.5024 | 0.5024 | -1 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu118 - Datasets 2.18.0 - Tokenizers 0.15.2

Note30 octhuggingface.co/jialicheng/unlearn_ucf101_videomae-large_salun_10_42

Source context: 3 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_salun_10_42

Note14 agohuggingface.co/jialicheng/unlearn_ucf101_videomae-large_salun_10_42

Source context: 5 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_salun_10_42