Ir para o conteúdo
ModelListadosExterno
Baixar

Timesformer BDSLW60 U5 20 CoR WithoutAug

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.6824 Accuracy: 0.86

Fontehuggingface.co/Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug/tree/cf930ea8c15d3e69d57e37ec85b57dd2822d4b12
TipoOtherModelo basefacebook/timesformer-base-finetuned-k400VersãoRevision cf930eaBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
463 MB
Modelo base
facebook/timesformer-base-finetuned-k400
Versão
vRevision cf930ea
Atualizado
24 de out. de 2026
Downloads
8
Fonte
Hugging Face

Descrição da fonte

Timesformer_BDSLW60_U5_20_coR_withoutAug

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6824
  • Accuracy: 0.86

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 LossAccuracy
8.93170.05019291.37300.7133
0.28761.050118580.81840.7533
0.04522.050127870.94450.77
0.08353.050137160.95430.7467
0.06834.050146451.01890.7617
0.06855.050155740.75190.8117
0.06876.050165030.96100.7933
0.05597.050174320.80730.8
0.06118.050183611.02150.815
0.02389.050192900.80730.825
0.00910.0501102190.75930.8167
0.011.0501111480.71600.8367
0.012.0501120770.70140.8483
0.013.0501130060.69600.8467
0.014.0501139350.69240.8483
0.015.0501148640.68800.855
0.016.0501157930.68720.8567
0.017.0501167220.68500.8583
0.018.0501176510.68350.86
0.019.0490185600.68240.86

Framework versions

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

Fontes

1 fonte
Hugging FacePrimárioVersão cf930ea8c15d3e69d57e37ec85b57dd2822d4b12
huggingface.co/Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug/tree/cf930ea8c15d3e69d57e37ec85b57dd2822d4b12

Verificado 24 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 463 MB · SHA-256 938921804209…bb2b · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme6 de ago.huggingface.co/Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug

--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/timesformer-base-finetuned-k400 tags: - generated_from_trainer metrics: - accuracy model-index: - name: Timesformer_BDSLW60_U5_20_coR_withoutAug 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. --> # Timesformer_BDSLW60_U5_20_coR_withoutAug This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6824 - Accuracy: 0.86 ## 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 | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 8.9317 | 0.0501 | 929 | 1.3730 | 0.7133 | | 0.2876 | 1.0501 | 1858 | 0.8184 | 0.7533 | | 0.0452 | 2.0501 | 2787 | 0.9445 | 0.77 | | 0.0835 | 3.0501 | 3716 | 0.9543 | 0.7467 | | 0.0683 | 4.0501 | 4645 | 1.0189 | 0.7617 | | 0.0685 | 5.0501 | 5574 | 0.7519 | 0.8117 | | 0.0687 | 6.0501 | 6503 | 0.9610 | 0.7933 | | 0.0559 | 7.0501 | 7432 | 0.8073 | 0.8 | | 0.0611 | 8.0501 | 8361 | 1.0215 | 0.815 | | 0.0238 | 9.0501 | 9290 | 0.8073 | 0.825 | | 0.009 | 10.0501 | 10219 | 0.7593 | 0.8167 | | 0.0 | 11.0501 | 11148 | 0.7160 | 0.8367 | | 0.0 | 12.0501 | 12077 | 0.7014 | 0.8483 | | 0.0 | 13.0501 | 13006 | 0.6960 | 0.8467 | | 0.0 | 14.0501 | 13935 | 0.6924 | 0.8483 | | 0.0 | 15.0501 | 14864 | 0.6880 | 0.855 | | 0.0 | 16.0501 | 15793 | 0.6872 | 0.8567 | | 0.0 | 17.0501 | 16722 | 0.6850 | 0.8583 | | 0.0 | 18.0501 | 17651 | 0.6835 | 0.86 | | 0.0 | 19.0490 | 18560 |...

Note24 de out.huggingface.co/Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug

Source context: 8 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug

Note6 de ago.huggingface.co/Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug

Source context: 4 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/Timesformer_BDSLW60_U5_20_coR_withoutAug