videomae-base-finetuned-kinetics-finetuned-round2-v2

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: 0.3887
• Accuracy: 0.8846

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: 4
• eval_batch_size: 4
• 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: 1804

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0866	0.09	165	1.3158	0.6758
0.2793	1.09	330	0.5707	0.8159
0.2073	2.09	495	0.5581	0.8269
0.0239	3.09	660	0.3737	0.8819
0.0041	4.09	825	0.4101	0.8901
0.0038	5.09	990	0.5469	0.8736
0.0022	6.09	1155	0.3599	0.9066
0.0018	7.09	1320	0.3992	0.8929
0.0012	8.09	1485	0.4096	0.8846
0.0043	9.09	1650	0.3938	0.8819
0.0014	10.09	1804	0.3887	0.8846

Framework versions

• Transformers 4.38.2
• Pytorch 1.13.1+cu117
• Datasets 2.18.0
• Tokenizers 0.15.2