Saltar al contenido
ModelPublicadoExterno
Descargar

BxSD Finetuned Real RGBCROP 5e6 Poly

This model is a fine-tuned version of TanAlexanderlz/BxSDRGBCROPAug16F-8B16F5e6-poly on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.1354 Accuracy: 0.7712

Fuentehuggingface.co/TanAlexanderlz/BxSD-finetuned-Real_RGBCROP_5e6-poly/tree/95ac9240ef08d787feb1c73f708cb4eb7973381b
TipoOtherModelo baseTanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-polyVersiónRevision 95ac924Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
329 MB
Modelo base
TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-poly
Versión
vRevision 95ac924
Actualizado
21 sept 2026
Descargas
5
Fuente
Hugging Face

Descripción de la fuente

BxSD-finetuned-Real_RGBCROP_5e6-poly

This model is a fine-tuned version of TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-poly on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1354
  • Accuracy: 0.7712

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-06
  • 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: polynomial
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 2112

Training results

Training LossEpochStepValidation LossAccuracy
0.40470.08381770.64280.6667
0.10451.08383540.78050.7133
0.08272.08385310.97070.7133
0.01423.08387081.22230.71
0.00074.08388851.34180.7233
0.00075.083810621.45070.7333
0.00096.083812391.51950.72
0.00037.083814161.56680.7233
0.00038.083815931.56970.74
0.00049.083817701.58620.73
0.000210.083819471.60130.7233
0.000211.078121121.60330.7267

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión 95ac9240ef08d787feb1c73f708cb4eb7973381b
huggingface.co/TanAlexanderlz/BxSD-finetuned-Real_RGBCROP_5e6-poly/tree/95ac9240ef08d787feb1c73f708cb4eb7973381b

Verificado 5 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 329 MB · SHA-256 583b76b4639d…4bbd · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme5 septhuggingface.co/TanAlexanderlz/BxSD-finetuned-Real_RGBCROP_5e6-poly

--- library_name: transformers license: cc-by-nc-4.0 base_model: TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-poly tags: - generated_from_trainer metrics: - accuracy model-index: - name: BxSD-finetuned-Real_RGBCROP_5e6-poly 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. --> # BxSD-finetuned-Real_RGBCROP_5e6-poly This model is a fine-tuned version of [TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-poly](https://huggingface.co/TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F5e6-poly) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1354 - Accuracy: 0.7712 ## 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-06 - 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: polynomial - lr_scheduler_warmup_ratio: 0.1 - training_steps: 2112 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.4047 | 0.0838 | 177 | 0.6428 | 0.6667 | | 0.1045 | 1.0838 | 354 | 0.7805 | 0.7133 | | 0.0827 | 2.0838 | 531 | 0.9707 | 0.7133 | | 0.0142 | 3.0838 | 708 | 1.2223 | 0.71 | | 0.0007 | 4.0838 | 885 | 1.3418 | 0.7233 | | 0.0007 | 5.0838 | 1062 | 1.4507 | 0.7333 | | 0.0009 | 6.0838 | 1239 | 1.5195 | 0.72 | | 0.0003 | 7.0838 | 1416 | 1.5668 | 0.7233 | | 0.0003 | 8.0838 | 1593 | 1.5697 | 0.74 | | 0.0004 | 9.0838 | 1770 | 1.5862 | 0.73 | | 0.0002 | 10.0838 | 1947 | 1.6013 | 0.7233 | | 0.0002 | 11.0781 | 2112 | 1.6033 | 0.7267 | ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1

Note5 septhuggingface.co/TanAlexanderlz/BxSD-finetuned-Real_RGBCROP_5e6-poly

Source context: 5 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo TanAlexanderlz/BxSD-finetuned-Real_RGBCROP_5e6-poly