videomae-base-finetuned-numbers – AI Model by latif98 | AlphaNeural AI

You can deploy this model and start earning money today!

latif98/
videomae-base-finetuned-numbers

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-numbers

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: 0.3433
Accuracy: 0.8222
F1: 0.8015
Precision: 0.8762
Recall: 0.8182

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: 176

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7592	0.25	44	0.6378	0.8462	0.8479	0.8758	0.8561
0.296	1.25	88	0.3027	0.8974	0.8805	0.9091	0.8864
0.2144	2.25	132	0.1289	0.9487	0.9377	0.9545	0.9394
0.1331	3.25	176	0.0958	0.9744	0.9688	0.9773	0.9697

Framework versions

Transformers 4.40.0
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.19.1