videomae-base-finetuned-kinetics-finetuned-right-hand-conflab-v9

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: 2.0098
• Accuracy: 0.6108

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: 702

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2	0.1681	118	2.0320	0.5686
0.1561	1.1681	236	1.7991	0.6127
0.1245	2.1681	354	1.9133	0.6029
0.0567	3.1681	472	1.9671	0.6275
0.0253	4.1681	590	1.9833	0.6520
0.0627	5.1595	702	2.0055	0.6324

Framework versions

• Transformers 4.41.0
• Pytorch 1.12.0+cu116
• Datasets 2.19.1
• Tokenizers 0.19.1