Skip to content
ModelListedExternal
Download

Timesformer Base Finetuned K400 Finetuned Yt Short Classification Sample Rate16

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: 0.2786 Accuracy: 0.9220 0 Precision: 0.8978 0...

Sourcehuggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16/tree/f47c279e7ce83d1101f5353f0773b9d398b6c7a4
KindOtherBase modelfacebook/timesformer-base-finetuned-k400VersionRevision f47c279

Model source

Kind
Other
File size
463 MB
Base model
facebook/timesformer-base-finetuned-k400
Version
vRevision f47c279
Updated
Sep 26, 2026
Downloads
3
Source
Hugging Face

Source description

timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16

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: 0.2786
  • Accuracy: 0.9220
  • 0 Precision: 0.8978
  • 0 Recall: 0.9432
  • 0 F1-score: 0.9200
  • 0 Support: 5796.0
  • 1 Precision: 0.9460
  • 1 Recall: 0.9026
  • 1 F1-score: 0.9238
  • 1 Support: 6389.0
  • Accuracy F1-score: 0.9220
  • Macro avg Precision: 0.9219
  • Macro avg Recall: 0.9229
  • Macro avg F1-score: 0.9219
  • Macro avg Support: 12185.0
  • Weighted avg Precision: 0.9231
  • Weighted avg Recall: 0.9220
  • Weighted avg F1-score: 0.9220
  • Weighted avg Support: 12185.0

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: 8
  • eval_batch_size: 8
  • 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: 19800

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
0.60990.05019910.44270.79650.84860.69630.76505796.00.76310.88730.82056389.00.79650.80590.79180.792712185.00.80380.79650.794112185.0
0.4621.050119820.46450.78830.72500.89410.80075796.00.87810.69230.77426389.00.78830.80150.79320.787412185.00.80530.78830.786812185.0
0.34252.050129730.44530.80080.73760.90230.81175796.00.88890.70870.78866389.00.80080.81320.80550.800212185.00.81690.80080.799612185.0
0.45973.050139640.42120.81350.89650.68720.77805796.00.76580.92800.83916389.00.81350.83110.80760.808612185.00.82800.81350.810112185.0
0.344.050149550.37820.84350.86720.79230.82815796.00.82530.89000.85646389.00.84350.84620.84110.842212185.00.84520.84350.842912185.0
0.23225.050159460.37860.85070.81050.89560.85095796.00.89530.81000.85056389.00.85070.85290.85280.850712185.00.85500.85070.850712185.0
0.32786.050169370.55800.78810.69880.97460.81405796.00.96420.61890.75396389.00.78810.83150.79680.783912185.00.83790.78810.782512185.0
0.35317.050179280.40570.85160.79480.92750.85615796.00.92250.78280.84696389.00.85160.85870.85510.851512185.00.86180.85160.851312185.0
0.25138.050189190.36430.85740.80210.92960.86125796.00.92540.79200.85356389.00.85740.86380.86080.857312185.00.86680.85740.857212185.0
0.25929.050199100.28190.89680.87750.90990.89345796.00.91550.88480.89996389.00.89680.89650.89740.896712185.00.89740.89680.896812185.0
0.40510.0501109010.37550.86930.82290.92410.87055796.00.92250.81950.86806389.00.86930.87270.87180.869312185.00.87510.86930.869212185.0
0.197111.0501118920.39130.87620.81020.96620.88135796.00.96280.79460.87076389.00.87620.88650.88040.876012185.00.89020.87620.875812185.0
0.349912.0501128830.28500.89710.89390.88920.89155796.00.90000.90420.90216389.00.89710.89690.89670.896812185.00.89710.89710.897112185.0
0.155113.0501138740.29650.90040.88760.90510.89635796.00.91240.89610.90416389.00.90040.90000.90060.900212185.00.90060.90040.900412185.0
0.137914.0501148650.31750.90280.86610.94120.90215796.00.94210.86810.90366389.00.90280.90410.90460.902812185.00.90600.90280.902912185.0
0.197915.0501158560.51680.86520.78840.97930.87365796.00.97590.76160.85566389.00.86520.88220.87050.864612185.00.88670.86520.864112185.0
0.04316.0501168470.32690.90930.86760.95510.90935796.00.95520.86770.90946389.00.90930.91140.91140.909312185.00.91350.90930.909312185.0
0.07917.0501178380.29410.91560.89290.93460.91335796.00.93810.89830.91776389.00.91560.91550.91640.915512185.00.91660.91560.915612185.0
0.281818.0501188290.31270.91370.87510.95500.91335796.00.95550.87630.91426389.00.91370.91530.91570.913712185.00.91720.91370.913812185.0
0.078919.0490198000.27860.92200.89780.94320.92005796.00.94600.90260.92386389.00.92200.92190.92290.921912185.00.92310.92200.922012185.0

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion f47c279e7ce83d1101f5353f0773b9d398b6c7a4
huggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16/tree/f47c279e7ce83d1101f5353f0773b9d398b6c7a4

Verified Aug 28

Model artifacts

1 artifact

model.safetensors

safetensors · 463 MB · SHA-256 4bbb8f5a399c…98e9 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeAug 28huggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16

--- 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-yt_short_classification-sample_rate16 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-yt_short_classification-sample_rate16 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: 0.2786 - Accuracy: 0.9220 - 0 Precision: 0.8978 - 0 Recall: 0.9432 - 0 F1-score: 0.9200 - 0 Support: 5796.0 - 1 Precision: 0.9460 - 1 Recall: 0.9026 - 1 F1-score: 0.9238 - 1 Support: 6389.0 - Accuracy F1-score: 0.9220 - Macro avg Precision: 0.9219 - Macro avg Recall: 0.9229 - Macro avg F1-score: 0.9219 - Macro avg Support: 12185.0 - Weighted avg Precision: 0.9231 - Weighted avg Recall: 0.9220 - Weighted avg F1-score: 0.9220 - Weighted avg Support: 12185.0 ## 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: 8 - eval_batch_size: 8 - 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: 19800 ### 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 | |:-------------:|:-------:|:-----:|:---------------:|:--------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:-----------------:|:-------------------:|:----------...

NoteAug 28huggingface.co/Kartikeya/timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Kartikeya/timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16