Saltar al contenido
ModelPublicadoExterno
Descargar

RALL RGBCROP Aug16F 8B16F Lr1

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: 0.8799 Accuracy: 0.8534

Fuentehuggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-lr1/tree/4957f4287cba12997bd2d1d00ab2089ff26dfb02
TipoOtherModelo baseMCG-NJU/videomae-base-finetuned-kineticsVersiónRevision 4957f42Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
329 MB
Modelo base
MCG-NJU/videomae-base-finetuned-kinetics
Versión
vRevision 4957f42
Actualizado
21 sept 2026
Descargas
5
Fuente
Hugging Face

Descripción de la fuente

RALL_RGBCROP_Aug16F-8B16F-lr1

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: 0.8799
  • Accuracy: 0.8534

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
  • 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
0.32050.08352890.48270.7873
0.17781.08355780.75930.7955
0.00172.08358670.92360.7894
0.00033.083511561.09470.7935
0.00034.083514451.10130.8180
0.00015.083517341.15820.8078
0.00016.083520231.24310.7996
0.00017.083523121.19510.8241
0.00018.083526011.33490.7935
0.00019.083528901.28950.8078
0.000110.083531791.30770.8016
0.000111.081734621.31160.8016

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión 4957f4287cba12997bd2d1d00ab2089ff26dfb02
huggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-lr1/tree/4957f4287cba12997bd2d1d00ab2089ff26dfb02

Verificado 5 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 329 MB · SHA-256 5c3485cff6df…1213 · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme5 septhuggingface.co/TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-lr1

--- 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-lr1 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-lr1 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: 0.8799 - Accuracy: 0.8534 ## 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 - 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 | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.3205 | 0.0835 | 289 | 0.4827 | 0.7873 | | 0.1778 | 1.0835 | 578 | 0.7593 | 0.7955 | | 0.0017 | 2.0835 | 867 | 0.9236 | 0.7894 | | 0.0003 | 3.0835 | 1156 | 1.0947 | 0.7935 | | 0.0003 | 4.0835 | 1445 | 1.1013 | 0.8180 | | 0.0001 | 5.0835 | 1734 | 1.1582 | 0.8078 | | 0.0001 | 6.0835 | 2023 | 1.2431 | 0.7996 | | 0.0001 | 7.0835 | 2312 | 1.1951 | 0.8241 | | 0.0001 | 8.0835 | 2601 | 1.3349 | 0.7935 | | 0.0001 | 9.0835 | 2890 | 1.2895 | 0.8078 | | 0.0001 | 10.0835 | 3179 | 1.3077 | 0.8016 | | 0.0001 | 11.0817 | 3462 | 1.3116 | 0.8016 | ### 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-lr1

Source context: 5 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo TanAlexanderlz/RALL_RGBCROP_Aug16F-8B16F-lr1