videomae-base-finetuned-ucf-crimev3 – AI Model by shahadalll | AlphaNeural AI

You can deploy this model and start earning money today!

shahadalll/
videomae-base-finetuned-ucf-crimev3

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-ucf-crimev3

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: 2.2215
Accuracy: 0.3545

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: 3e-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_steps: 500
training_steps: 1230

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2429	1.0	42	1.8114	0.3091
1.2691	2.0	84	1.8293	0.3273
0.9197	3.0	126	1.8547	0.3364
0.9611	4.0	168	1.8772	0.3455
0.848	5.0	210	1.8690	0.3636
1.0474	6.0	252	1.8581	0.3636
0.7281	7.0	294	1.9003	0.3909
0.6033	8.0	336	2.0023	0.3364
0.3703	9.0	378	2.1459	0.3364
0.4539	10.0	420	2.2215	0.3545

Framework versions

Transformers 4.47.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3