Aller au contenu
ModelPrésentéExterne
Télécharger

Timesformer Base Finetuned K400 Snapdata Classification Sample Rate16 Freeze Last2blocks

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: 0.6734 Accuracy: 0.6421 0 Precision: 0.6913 0...

Sourcehuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks/tree/4b274113c5d8dd82fd504302e8527e7d6a3630ff
TypeOtherModèle de basefacebook/timesformer-base-finetuned-k400VersionRevision 4b27411BClasse

Source du modèle

Type
Other
Taille du fichier
463 MB
Modèle de base
facebook/timesformer-base-finetuned-k400
Version
vRevision 4b27411
Mis à jour
2 oct. 2026
Téléchargements
3
Source
Hugging Face

Description de la source

timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

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: 0.6734
  • Accuracy: 0.6421
  • 0 Precision: 0.6913
  • 0 Recall: 0.4116
  • 0 F1-score: 0.5160
  • 0 Support: 2002.0
  • 1 Precision: 0.6234
  • 1 Recall: 0.8412
  • 1 F1-score: 0.7161
  • 1 Support: 2318.0
  • Accuracy F1-score: 0.6421
  • Macro avg Precision: 0.6573
  • Macro avg Recall: 0.6264
  • Macro avg F1-score: 0.6160
  • Macro avg Support: 4320.0
  • Weighted avg Precision: 0.6549
  • Weighted avg Recall: 0.6421
  • Weighted avg F1-score: 0.6234
  • Weighted avg Support: 4320.0

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: 8e-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: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 62000
  • label_smoothing_factor: 0.1

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
0.7250.0002100.76110.49050.45520.50450.47862002.00.52780.47840.50192318.00.49050.49150.49150.49024320.00.49420.49050.49114320.0
0.740.0003200.76090.49140.45600.50450.47902002.00.52870.48020.50332318.00.49140.49240.49230.49114320.00.49500.49140.49204320.0
0.73860.0005300.76070.49190.45640.50400.47902002.00.52920.48140.50422318.00.49190.49280.49270.49164320.00.49540.49190.49254320.0
0.81120.0006400.76050.49210.45650.50300.47862002.00.52930.48270.50502318.00.49210.49290.49290.49184320.00.49560.49210.49284320.0
0.80340.0008500.76010.49140.45550.49900.47632002.00.52840.48490.50572318.00.49140.49200.49200.49104320.00.49470.49140.49214320.0
0.7840.0010600.75960.49190.45570.49550.47482002.00.52870.48880.50802318.00.49190.49220.49210.49144320.00.49490.49190.49264320.0
0.81480.0011700.75890.49280.45620.49150.47322002.00.52940.49400.51102318.00.49280.49280.49270.49214320.00.49540.49280.49354320.0
0.80310.0013800.75800.49440.45750.48950.47302002.00.53080.49870.51422318.00.49440.49410.49410.49364320.00.49680.49440.49514320.0
0.81940.0015900.75710.49490.45750.48400.47042002.00.53090.50430.51732318.00.49490.49420.49420.49384320.00.49690.49490.49554320.0
0.78050.00161000.75610.49610.45830.48050.46922002.00.53170.50950.52042318.00.49610.49500.49500.49484320.00.49770.49610.49664320.0
0.73310.00181100.75500.49610.45780.47450.46602002.00.53140.51470.52292318.00.49610.49460.49460.49454320.00.49730.49610.49654320.0
0.71070.00191200.75420.49860.46020.47400.46702002.00.53370.51980.52672318.00.49860.49690.49690.49684320.00.49960.49860.49904320.0
0.80210.00211300.75300.49790.45890.46600.46252002.00.53260.52550.52902318.00.49790.49580.49570.49574320.00.49840.49790.49824320.0
0.75220.00231400.75150.50070.46100.45800.45952002.00.53450.53750.53602318.00.50070.49780.49780.49784320.00.50050.50070.50064320.0
0.71870.00241500.75010.50370.46400.45750.46082002.00.53710.54360.54032318.00.50370.50060.50060.50054320.00.50320.50370.50344320.0
0.87220.00261600.74830.50300.46270.44960.45602002.00.5360.54920.54252318.00.50300.49940.49940.49934320.00.50200.50300.50244320.0
0.8410.00271700.74660.50600.46600.45200.45892002.00.53870.55260.54562318.00.50600.50240.50230.50224320.00.50500.50600.50544320.0
0.76590.00291800.74550.50690.46680.44960.45802002.00.53930.55650.54782318.00.50690.50310.50300.50294320.00.50570.50690.50624320.0
0.76390.00311900.74420.50900.46890.44760.45802002.00.54090.56210.55132318.00.50900.50490.50480.50464320.00.50750.50900.50804320.0
0.78890.00322000.74330.51040.47060.45100.46062002.00.54230.56170.55182318.00.51040.50640.50640.50624320.00.50900.51040.50954320.0
0.7380.00342100.74230.51110.47130.45050.46072002.00.54280.56340.55292318.00.51110.50700.50700.50684320.00.50970.51110.51024320.0
0.73250.00352200.74160.51270.47310.45300.46292002.00.54430.56430.55412318.00.51270.50870.50870.50854320.00.51130.51270.51184320.0
0.73530.00372300.74080.51300.47380.46150.46762002.00.54510.55740.55122318.00.51300.50950.50950.50944320.00.51210.51300.51254320.0
0.7890.00392400.74070.51370.47540.47700.47622002.00.54690.54530.54612318.00.51370.51120.51120.51124320.00.51380.51370.51374320.0
0.710.00402500.73940.51550.47720.47650.47692002.00.54850.54920.54882318.00.51550.51290.51290.51294320.00.51550.51550.51554320.0
0.78020.00422600.73780.51780.47930.46850.47392002.00.54970.56040.55502318.00.51780.51450.51450.51444320.00.51710.51780.51744320.0
0.73680.00442700.73650.51900.4804...

Sources

1 source
Hugging FacePrincipalVersion 4b274113c5d8dd82fd504302e8527e7d6a3630ff
huggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks/tree/4b274113c5d8dd82fd504302e8527e7d6a3630ff

Vérifié 21 août

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 463 MB · SHA-256 3b6ee7e59dd7…bf97 · Hugging Face

Download file

Extraits de sources

2 extraits
Readme21 aoûthuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

--- 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-snapdata_classification-sample_rate16_freeze_last2blocks 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-snapdata_classification-sample_rate16_freeze_last2blocks 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: 0.6734 - Accuracy: 0.6421 - 0 Precision: 0.6913 - 0 Recall: 0.4116 - 0 F1-score: 0.5160 - 0 Support: 2002.0 - 1 Precision: 0.6234 - 1 Recall: 0.8412 - 1 F1-score: 0.7161 - 1 Support: 2318.0 - Accuracy F1-score: 0.6421 - Macro avg Precision: 0.6573 - Macro avg Recall: 0.6264 - Macro avg F1-score: 0.6160 - Macro avg Support: 4320.0 - Weighted avg Precision: 0.6549 - Weighted avg Recall: 0.6421 - Weighted avg F1-score: 0.6234 - Weighted avg Support: 4320.0 ## 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: 8e-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: cosine - lr_scheduler_warmup_ratio: 0.1 - training_steps: 62000 - label_smoothing_factor: 0.1 ### 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 aoûthuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks