videomae-base-finetuned

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: 0.9875
• Accuracy: 0.6761

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 OptimizerNames.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: 650

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6056	0.1015	66	1.5308	0.2879
1.5067	1.1015	132	1.4474	0.3636
1.1882	2.1015	198	1.1753	0.4848
1.3819	3.1015	264	0.8098	0.6364
0.8098	4.1015	330	0.7322	0.8030
0.4295	5.1015	396	0.7815	0.6970
0.5011	6.1015	462	0.4940	0.8939
0.2092	7.1015	528	0.5270	0.8182
0.1115	8.1015	594	0.5709	0.7727
0.2199	9.0862	650	0.5146	0.7727

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0