Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
videomae-huge – AI Model by Tianjiao-Yu | AlphaNeural AI
You can deploy this model and start earning money today!
Tianjiao-Yu
/
videomae-huge
like
0
transformers
tensorboard
safetensors
videomae
video-classification
generated_from_trainer
MCG-NJU/videomae-base-finetuned-kinetics
finetune
cc-by-nc-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
videomae-huge
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:
Loss: 2.0714
Accuracy: 0.4286
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: 8
eval_batch_size: 8
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: 78
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
2.6392
0.18
14
2.5780
0.25
1.994
1.18
28
2.3995
0.3929
1.6374
2.18
42
2.3010
0.3929
1.124
3.18
56
2.2242
0.3929
0.9569
4.18
70
2.1825
0.4286
0.8862
5.1
78
2.1734
0.4286
Framework versions
Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2
