videomae-base-finetuned-ucf101-subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1066
• Accuracy: 0.9806

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: 370

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2637	0.1027	38	0.5823	0.8
0.1646	1.1027	76	0.2318	0.9571
0.1042	2.1027	114	0.3459	0.8571
0.1973	3.1027	152	0.2397	0.8714
0.0685	4.1027	190	0.1367	0.9571
0.0194	5.1027	228	0.1976	0.9286
0.0171	6.1027	266	0.1301	0.9714
0.0035	7.1027	304	0.0791	0.9714
0.0039	8.1027	342	0.0360	0.9857
0.0377	9.0757	370	0.0391	0.9857

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1