You can deploy this model and start earning money today!

Shawon16/
VideoMAE_Kinetics_fold1BdSLW60_SKF

Name: VideoMAE_Kinetics_fold__1__BdSLW60_SKF
Availability: InStock

Views

No views yet

VideoMAE_Kinetics_fold1BdSLW60_SKF

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
8.3842	0.1	903	0.2617	0.9601
0.3809	1.1001	1807	0.0295	0.9938
0.0785	2.1	2710	0.0575	0.9863
0.0559	3.1001	3614	0.0443	0.9888
0.0343	4.1	4517	0.0711	0.9838
0.0242	5.1001	5421	0.0213	0.9963
0.0217	6.1	6324	0.0303	0.9938
0.0056	7.1001	7228	0.0216	0.9963
0.0067	8.1	8131	0.0275	0.9963
0.001	9.0995	9030	0.0177	0.9963