You can deploy this model and start earning money today!

Shawon16/
videoMAE_kinetics_wlasl2000_coR_20ep

Name: videoMAE_kinetics_wlasl2000_coR_20ep
Availability: InStock

Views

No views yet

videoMAE_kinetics_wlasl2000_coR_20ep

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: 35720
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
30.4455	0.05	1786	7.5864	0.0010
29.1368	1.0500	3572	6.7872	0.0194
24.787	2.0500	5358	5.8083	0.0884
20.299	3.0500	7145	4.9645	0.1619
16.1178	4.05	8931	4.2633	0.2370
12.3227	5.0500	10717	3.6600	0.3029
9.1282	6.0500	12503	3.2388	0.3460
6.5449	7.0500	14290	2.9354	0.3897
4.6097	8.05	16076	2.7435	0.4014
3.2081	9.0500	17862	2.6247	0.4139
2.2446	10.0500	19648	2.5707	0.4247
1.6181	11.0500	21435	2.4944	0.4313
1.2196	12.05	23221	2.4961	0.4318
0.9689	13.0500	25007	2.4889	0.4339
0.802	14.0500	26793	2.4977	0.4408
0.67	15.0500	28580	2.4818	0.4346
0.5845	16.05	30366	2.4801	0.4443
0.5119	17.0500	32152	2.4924	0.4395
0.4504	18.0500	33938	2.4930	0.4454
0.3911	19.0499	35720	2.4903	0.4454