videomae-base-finetuned-custom-videos

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: 196.2340
• Accuracy: 0.0246

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: 12
• eval_batch_size: 12
• 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: 352

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
186.9037	0.2528	89	205.8250	0.0275
197.3661	1.2528	178	183.3524	0.0275
166.2926	2.2528	267	171.0079	0.0275
186.6101	3.2415	352	167.3370	0.0275

Framework versions

• Transformers 4.53.0.dev0
• Pytorch 2.6.0+cu118
• Datasets 2.13.2
• Tokenizers 0.21.1