Saltar al contenido
ModelPublicadoExterno
Descargar

Timesformer Base Finetuned K400 Finetuned Snapdata Short Classification Sample Rate32

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: 0.9266 Accuracy: 0.6862 0 Precision: 0.6305 0...

Fuentehuggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32/tree/bfa0cb9f518d5d2f8e4f6a2bffc708a5dc40ecaa
TipoOtherModelo basefacebook/timesformer-base-finetuned-k400VersiónRevision bfa0cb9Unratedcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
463 MB
Modelo base
facebook/timesformer-base-finetuned-k400
Versión
vRevision bfa0cb9
Actualizado
3 nov 2026
Descargas
3
Fuente
Hugging Face

Descripción de la fuente

timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

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: 0.9266
  • Accuracy: 0.6862
  • 0 Precision: 0.6305
  • 0 Recall: 0.7881
  • 0 F1-score: 0.7005
  • 0 Support: 1024.0
  • 1 Precision: 0.7639
  • 1 Recall: 0.5974
  • 1 F1-score: 0.6705
  • 1 Support: 1175.0
  • Accuracy F1-score: 0.6862
  • Macro avg Precision: 0.6972
  • Macro avg Recall: 0.6928
  • Macro avg F1-score: 0.6855
  • Macro avg Support: 2199.0
  • Weighted avg Precision: 0.7018
  • Weighted avg Recall: 0.6862
  • Weighted avg F1-score: 0.6845
  • Weighted avg Support: 2199.0

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: 16
  • eval_batch_size: 16
  • seed: 42
  • 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: 31000

Training results

Training LossEpochStepValidation LossAccuracy0 Precision0 Recall0 F1-score0 Support1 Precision1 Recall1 F1-score1 SupportAccuracy F1-scoreMacro avg PrecisionMacro avg RecallMacro avg F1-scoreMacro avg SupportWeighted avg PrecisionWeighted avg RecallWeighted avg F1-scoreWeighted avg Support
0.6640.02006210.64620.62710.57330.77930.66061024.00.72000.49450.58631175.00.62710.64660.63690.62342199.00.65160.62710.62092199.0
0.59171.020012420.60000.68850.66800.65820.66311024.00.70590.71490.71041175.00.68850.68690.68650.68672199.00.68820.68850.68832199.0
0.53872.020018630.59820.67580.64740.66700.65701024.00.70190.68340.69251175.00.67580.67470.67520.67482199.00.67650.67580.67602199.0
0.52983.020024840.59780.68940.71550.55270.62371024.00.67470.80850.73561175.00.68940.69510.68060.67962199.00.69370.68940.68352199.0
0.4724.020031050.67340.64570.58860.79490.67641024.00.74260.51570.60871175.00.64570.66560.65530.64252199.00.67090.64570.64022199.0
0.46215.020037260.63090.69030.68620.61720.64991024.00.69330.75400.72241175.00.69030.68970.68560.68612199.00.69000.69030.68862199.0
0.43116.020043470.63990.70580.66820.73140.69841024.00.74490.68340.71281175.00.70580.70650.70740.70562199.00.70920.70580.70612199.0
0.37477.020049680.77010.67350.69570.53120.60241024.00.66130.79740.72301175.00.67350.67850.66430.66272199.00.67730.67350.66692199.0
0.32478.020055890.75430.70030.66050.73340.69501024.00.74290.67150.70541175.00.70030.70170.70240.70022199.00.70460.70030.70062199.0
0.30229.020062100.92660.68620.63050.78810.70051024.00.76390.59740.67051175.00.68620.69720.69280.68552199.00.70180.68620.68452199.0

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.0.0+cu117
  • Datasets 3.1.0
  • Tokenizers 0.20.3

Fuentes

1 fuente
Hugging FacePrincipalVersión bfa0cb9f518d5d2f8e4f6a2bffc708a5dc40ecaa
huggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32/tree/bfa0cb9f518d5d2f8e4f6a2bffc708a5dc40ecaa

Verificado 3 nov

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · FP32 (tensor header) · 463 MB · SHA-256 33b8d9564d6a…7e83 · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme21 agohuggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

--- 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-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32 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-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32 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: 0.9266 - Accuracy: 0.6862 - 0 Precision: 0.6305 - 0 Recall: 0.7881 - 0 F1-score: 0.7005 - 0 Support: 1024.0 - 1 Precision: 0.7639 - 1 Recall: 0.5974 - 1 F1-score: 0.6705 - 1 Support: 1175.0 - Accuracy F1-score: 0.6862 - Macro avg Precision: 0.6972 - Macro avg Recall: 0.6928 - Macro avg F1-score: 0.6855 - Macro avg Support: 2199.0 - Weighted avg Precision: 0.7018 - Weighted avg Recall: 0.6862 - Weighted avg F1-score: 0.6845 - Weighted avg Support: 2199.0 ## 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: 16 - eval_batch_size: 16 - seed: 42 - 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: 31000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | 0 Precision | 0 Recall | 0 F1-score | 0 Support | 1 Precision | 1 Recall | 1 F1-score | 1 Support | Accuracy F1-score | Macro avg Precision | Macro avg Recall | Macro avg F1-score | Macro avg Support | Weighted avg Precision | Weighted avg Recall | Weighted avg F1-score | Weighted avg Support | |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:-----------------:|:-------------------:|:...

Note21 agohuggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32