Skip to content
ModelListedExternal
Download

Unlearn Ucf101 Videomae Large Bad Teaching 2 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: 0.4600 Accuracy: 0.9205 Test Accuracy: 0.9205 Df Accuracy: 0.9866...

Sourcehuggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42/tree/1af79c5255e08595e17bb2000d310bd0b0dc8ce2
KindModelBase modelMCG-NJU/videomae-largeVersionRevision 1af79c5Cgrade

Model source

Kind
Model
File size
1.13 GB
Base model
MCG-NJU/videomae-large
Version
vRevision 1af79c5
Updated
Oct 30, 2026
Downloads
9
Source
Hugging Face

Source description

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: 0.4600
  • Accuracy: 0.9205
  • Test Accuracy: 0.9205
  • Df Accuracy: 0.9866
  • Unlearn Overall Accuracy: 0.4669
  • Unlearn Time: 3981.3774

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 log1.03130.44420.98490.46340.4634-1
No log2.01260.46000.98660.46690.4669-1
No log2.75360.45910.98660.46630.4663-1

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 1af79c5255e08595e17bb2000d310bd0b0dc8ce2
huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42/tree/1af79c5255e08595e17bb2000d310bd0b0dc8ce2

Verified Oct 30

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

model.safetensors

safetensors · FP32 (tensor header) · 1.13 GB · SHA-256 22ef7b578b56…2dd3 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 14huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_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: 0.4600 - Accuracy: 0.9205 - Test Accuracy: 0.9205 - Df Accuracy: 0.9866 - Unlearn Overall Accuracy: 0.4669 - Unlearn Time: 3981.3774 ## 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 | 1.03 | 13 | 0.4442 | 0.9849 | 0.4634 | 0.4634 | -1 | | No log | 2.01 | 26 | 0.4600 | 0.9866 | 0.4669 | 0.4669 | -1 | | No log | 2.75 | 36 | 0.4591 | 0.9866 | 0.4663 | 0.4663 | -1 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu118 - Datasets 2.18.0 - Tokenizers 0.15.2

NoteOct 30huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42

Source context: 9 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42

NoteAug 14huggingface.co/jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42

Source context: 2 downloads · 0 likes · Pipeline video-classification · Repo jialicheng/unlearn_ucf101_videomae-large_bad_teaching_2_42