You can deploy this model and start earning money today!

Shawon16/
VideoMAE_4_CLASS_QUALITY_CHECK

Name: VideoMAE_4_CLASS_QUALITY_CHECK
Availability: InStock

Views

No views yet

VideoMAE_4_CLASS_QUALITY_CHECK

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:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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: 0.1
training_steps: 350
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.0723	0.02	7	1.3154	0.4286
4.5479	1.0214	15	1.0319	0.8571
3.6957	2.02	22	0.6454	0.8571
1.7212	3.0214	30	0.2796	1.0
0.6321	4.02	37	0.0587	1.0
0.0861	5.0214	45	0.0120	1.0
0.0166	6.02	52	0.0029	1.0
0.0047	7.0214	60	0.0018	1.0
0.0029	8.02	67	0.0015	1.0