videomae-base-finetuned-ucf101-subset – AI Model by hamy786 | AlphaNeural AI

You can deploy this model and start earning money today!

hamy786/
videomae-base-finetuned-ucf101-subset

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-ucf101-subset

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: 0.0503
Accuracy: 0.9857

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 1200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1866	0.06	75	2.0837	0.2286
0.898	1.06	150	0.8424	0.6429
0.4187	2.06	225	0.6812	0.7429
0.3636	3.06	300	0.5211	0.8286
0.1533	4.06	375	0.5294	0.8143
0.136	5.06	450	0.1853	0.9286
0.1537	6.06	525	0.0949	0.9714
0.0734	7.06	600	0.1561	0.9571
0.0039	8.06	675	0.1018	0.9857
0.0042	9.06	750	0.0403	0.9857
0.0028	10.06	825	0.1176	0.9714
0.0082	11.06	900	0.0272	0.9857
0.0022	12.06	975	0.0345	0.9857
0.002	13.06	1050	0.0631	0.9857
0.002	14.06	1125	0.0469	0.9714
0.0095	15.06	1200	0.0503	0.9857

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.0
Tokenizers 0.15.0