Aller au contenu
ModelPrésentéExterne
Télécharger

Videomae Base Finetuned Kinetics 0320 Abnormal Val02 Pretest

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3466 Accuracy: 0.9361

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest/tree/cb985b0d742aed735d8db4233c172deb3a7b7f8f
TypeOtherModèle de baseMCG-NJU/videomae-base-finetuned-kineticsVersionRevision cb985b0

Source du modèle

Type
Other
Taille du fichier
329 MB
Modèle de base
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision cb985b0
Mis à jour
18 sept. 2026
Téléchargements
6
Source
Hugging Face

Description de la source

videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3466
  • Accuracy: 0.9361

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: 0.05
  • training_steps: 71400

Training results

Training LossEpochStepValidation LossAccuracy
0.0680.01007150.32750.8850
0.021.010014300.25330.9027
0.00492.010021450.30370.8947
0.88963.010028600.27050.9148
0.58954.010035750.30390.8955
0.00075.010042900.29030.9124
0.00036.010050050.31060.9068
0.00157.010057200.31860.9027
0.00038.010064350.45630.8818
0.11859.010071500.35320.9092
0.000410.010078650.40580.9003
0.136811.010085800.31170.9220
0.001312.010092950.32170.9156
0.000113.0100100100.36350.9164
0.001714.0100107250.39650.9124
0.000215.0100114400.36490.9260
0.000616.0100121550.53600.8915
0.000117.0100128700.42250.9132
0.000118.0100135850.36390.9260
0.000119.0100143000.37820.9268
0.000220.0100150150.39940.9156
0.021.0100157300.39310.9228
0.000222.0100164450.44160.9148
0.364523.0100171600.46890.9172
0.000124.0100178750.41370.9164
0.000125.0100185900.37430.9260
0.146426.0100193050.34040.9325
0.027.0100200200.40100.9220
0.028.0100207350.40680.9196
0.000129.0100214500.35570.9317
0.000130.0100221650.38540.9268
0.043931.0100228800.41070.9236
0.000132.0100235950.36660.9309
0.033.0100243100.35880.9309
0.000134.0100250250.36350.9317
0.000135.0100257400.36910.9293
0.036.0100264550.37550.9293

Framework versions

  • Transformers 4.48.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Sources

1 source
Hugging FacePrincipalVersion cb985b0d742aed735d8db4233c172deb3a7b7f8f
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest/tree/cb985b0d742aed735d8db4233c172deb3a7b7f8f

Vérifié 18 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 329 MB · SHA-256 07749b948e18…c928 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme18 sept.huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest 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. --> # videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3466 - Accuracy: 0.9361 ## 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: 0.05 - training_steps: 71400 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 0.068 | 0.0100 | 715 | 0.3275 | 0.8850 | | 0.02 | 1.0100 | 1430 | 0.2533 | 0.9027 | | 0.0049 | 2.0100 | 2145 | 0.3037 | 0.8947 | | 0.8896 | 3.0100 | 2860 | 0.2705 | 0.9148 | | 0.5895 | 4.0100 | 3575 | 0.3039 | 0.8955 | | 0.0007 | 5.0100 | 4290 | 0.2903 | 0.9124 | | 0.0003 | 6.0100 | 5005 | 0.3106 | 0.9068 | | 0.0015 | 7.0100 | 5720 | 0.3186 | 0.9027 | | 0.0003 | 8.0100 | 6435 | 0.4563 | 0.8818 | | 0.1185 | 9.0100 | 7150 | 0.3532 | 0.9092 | | 0.0004 | 10.0100 | 7865 | 0.4058 | 0.9003 | | 0.1368 | 11.0100 | 8580 | 0.3117 | 0.9220 | | 0.0013 | 12.0100 | 9295 | 0.3217 | 0.9156 | | 0.0001 | 13.0100 | 10010 | 0.3635 | 0.9164 | | 0.0017 | 14.0100 | 10725 | 0.3965 | 0.9124 | | 0.0002 | 15.0100 | 11440 | 0.3649 | 0.9260 | | 0.0006 | 16.0100 | 12155 | 0.5360 | 0.8915 | | 0.0001 | 17.0100 | 12870 | 0.4225 | 0.9132 | | 0.0001 | 18.0100 | 13585 | 0.3639 | 0.9260 | | 0.0001 | 19.0100 | 14300 | 0.3782 | 0.9268 | | 0.00...

Note18 sept.huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest

Source context: 6 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0320-abnormal_val02_pretest