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: 4.9575
• Accuracy: 0.1809

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: 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: 930

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.0695	0.1011	94	3.0774	0.1234
2.0767	1.1011	188	1.8583	0.3957
1.0461	2.1011	282	1.2327	0.5489
0.7495	3.1011	376	0.9503	0.6638
0.5326	4.1011	470	0.9549	0.7021
0.429	5.1011	564	0.6794	0.7702
0.1877	6.1011	658	0.5646	0.8383
0.1137	7.1011	752	0.4796	0.8340
0.1102	8.1011	846	0.4773	0.8638
0.0746	9.0903	930	0.4601	0.8638

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0