Skip to content
ModelListedExternal
Download

ViViT BdSLW60 FrameRate Corrected With Augment 20 Epch

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.0009 Accuracy: 0.8117 Precision: 0.8529 Recall: 0.8117 F1:...

Sourcehuggingface.co/Shawon16/ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch/tree/559c73deb364d5efc71676de54a0315a8b4e7f0f
KindOtherBase modelgoogle/vivit-b-16x2-kinetics400VersionRevision 559c73d

Model source

Kind
Other
File size
338 MB
Base model
google/vivit-b-16x2-kinetics400
Version
vRevision 559c73d
Updated
Sep 18, 2026
Downloads
3
Source
Hugging Face

Source description

ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0009
  • Accuracy: 0.8117
  • Precision: 0.8529
  • Recall: 0.8117
  • F1: 0.7868

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: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use 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: 18560
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyPrecisionRecallF1
4.11330.05019291.37960.7850.79200.7850.7528
0.4571.050118580.68230.8050.80220.8050.7825
0.1272.050127870.40440.8750.90700.8750.8649
0.14073.050137160.54900.88170.90390.88170.8715
0.12464.050146450.71600.8350.86870.8350.8213
0.20275.050155740.72560.83830.87510.83830.8290
0.07326.050165030.59210.85330.85510.85330.8276
0.12277.050174320.45190.91330.93390.91330.9038
0.0088.050183610.52570.88170.89210.88170.8718
0.03059.050192900.47300.8750.90540.8750.8693
0.040810.0501102190.54180.89830.90460.89830.8842
0.145811.0501111480.41620.90830.93240.90830.9006
0.040212.0501120771.00090.81170.85290.81170.7868

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.1

Sources

1 source
Hugging FacePrimaryVersion 559c73deb364d5efc71676de54a0315a8b4e7f0f
huggingface.co/Shawon16/ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch/tree/559c73deb364d5efc71676de54a0315a8b4e7f0f

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 338 MB · SHA-256 b74fd13ae694…ff2a · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/Shawon16/ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch

--- library_name: transformers license: mit base_model: google/vivit-b-16x2-kinetics400 tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch 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. --> # ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0009 - Accuracy: 0.8117 - Precision: 0.8529 - Recall: 0.8117 - F1: 0.7868 ## 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: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use 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: 18560 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:| | 4.1133 | 0.0501 | 929 | 1.3796 | 0.785 | 0.7920 | 0.785 | 0.7528 | | 0.457 | 1.0501 | 1858 | 0.6823 | 0.805 | 0.8022 | 0.805 | 0.7825 | | 0.127 | 2.0501 | 2787 | 0.4044 | 0.875 | 0.9070 | 0.875 | 0.8649 | | 0.1407 | 3.0501 | 3716 | 0.5490 | 0.8817 | 0.9039 | 0.8817 | 0.8715 | | 0.1246 | 4.0501 | 4645 | 0.7160 | 0.835 | 0.8687 | 0.835 | 0.8213 | | 0.2027 | 5.0501 | 5574 | 0.7256 | 0.8383 | 0.8751 | 0.8383 | 0.8290 | | 0.0732 | 6.0501 | 6503 | 0.5921 | 0.8533 | 0.8551 | 0.8533 | 0.8276 | | 0.1227 | 7.0501 | 7432 | 0.4519 | 0.9133 | 0.9339 | 0.9133 | 0.9038 | | 0.008 | 8.0501 | 8361 | 0.5257 | 0.8817 | 0.8921 | 0.8817 | 0.8718 | | 0.0305 | 9.0501 | 9290 | 0.4730 | 0.875 | 0.9054 | 0.875 | 0.8693 | | 0.0408 | 10.0501 | 10219 | 0...

NoteSep 18huggingface.co/Shawon16/ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch