You can deploy this model and start earning money today!

Shawon16/
VideoMAE_default_fold410_epoch_bdslw60_kinetics_25_2_25

Name: VideoMAE_default_fold__4__10_epoch_bdslw60_kinetics_25_2_25
Availability: InStock

Views

No views yet

VideoMAE_default_fold410_epoch_bdslw60_kinetics_25_2_25

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: 9030
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2953	0.1	903	0.3316	0.9390
0.103	1.1001	1807	0.0787	0.9826
0.1454	2.1	2710	0.0586	0.9900
0.071	3.1001	3614	0.0360	0.9938
0.0189	4.1	4517	0.0416	0.9913
0.0155	5.1001	5421	0.0561	0.9900
0.0217	6.1	6324	0.0430	0.9900
0.001	7.1001	7228	0.0188	0.9975
0.0002	8.1	8131	0.0214	0.9950
0.0002	9.0995	9030	0.0229	0.9950