videomae-base-finetuned-judo – AI Model by adenhaus | AlphaNeural AI

You can deploy this model and start earning money today!

adenhaus/
videomae-base-finetuned-judo

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-judo

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

Loss: 0.9681
Accuracy: 0.6765

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: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.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: 1360

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3504	0.1	136	1.5076	0.2353
1.276	1.1	272	1.3571	0.4559
1.3092	2.1	408	1.3368	0.3676
1.0253	3.1	544	1.2489	0.4853
0.8738	4.1	680	1.2059	0.4559
0.8798	5.1	816	1.0972	0.5441
0.6182	6.1	952	1.0025	0.5882
0.6829	7.1	1088	1.0121	0.6176
0.387	8.1	1224	1.0217	0.6176
0.484	9.1	1360	0.9681	0.6765

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.4.0
Tokenizers 0.21.0