Saltar al contenido
ModelPublicadoExterno
Descargar

RALL RGBCROP Aug16F 8B16F GACWDlr

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.7229 Accuracy: 0.8373

Fuentehuggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-GACWDlr/tree/901f603663b00a73553391619ce3a412b1dd5433
TipoOtherModelo baseMCG-NJU/videomae-base-finetuned-kineticsVersiónRevision 901f603Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
329 MB
Modelo base
MCG-NJU/videomae-base-finetuned-kinetics
Versión
vRevision 901f603
Actualizado
21 sept 2026
Descargas
3
Fuente
Hugging Face

Descripción de la fuente

RALL_RGBCROP_Aug16F-8B16F-GACWDlr

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7229
  • Accuracy: 0.8373

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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.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: 3462

Training results

Training LossEpochStepValidation LossAccuracy
0.54810.04161440.60800.6789
0.24181.04162880.47810.7894
0.06552.04164320.62260.7935
0.01383.04165760.88330.8078
0.00094.04167200.99300.8057
0.00055.04168641.06400.8098
0.00036.041610081.19210.7914
0.00027.041611521.22670.7996
0.00028.041612961.27730.7914
0.00019.041614401.30200.7996

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1

Fuentes

1 fuente
Hugging FacePrincipalVersión 901f603663b00a73553391619ce3a412b1dd5433
huggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-GACWDlr/tree/901f603663b00a73553391619ce3a412b1dd5433

Verificado 5 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 329 MB · SHA-256 f7e10df722ed…a7fc · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme5 septhuggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-GACWDlr

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: RALL_RGBCROP_Aug16F-8B16F-GACWDlr 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. --> # RALL_RGBCROP_Aug16F-8B16F-GACWDlr This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7229 - Accuracy: 0.8373 ## 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: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.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: 3462 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------:| | 0.5481 | 0.0416 | 144 | 0.6080 | 0.6789 | | 0.2418 | 1.0416 | 288 | 0.4781 | 0.7894 | | 0.0655 | 2.0416 | 432 | 0.6226 | 0.7935 | | 0.0138 | 3.0416 | 576 | 0.8833 | 0.8078 | | 0.0009 | 4.0416 | 720 | 0.9930 | 0.8057 | | 0.0005 | 5.0416 | 864 | 1.0640 | 0.8098 | | 0.0003 | 6.0416 | 1008 | 1.1921 | 0.7914 | | 0.0002 | 7.0416 | 1152 | 1.2267 | 0.7996 | | 0.0002 | 8.0416 | 1296 | 1.2773 | 0.7914 | | 0.0001 | 9.0416 | 1440 | 1.3020 | 0.7996 | ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1

Note5 septhuggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-GACWDlr

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-GACWDlr