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: 0.0888
• Accuracy: 0.9857

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: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 12
• 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: 750

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.3003	0.0333	25	1.8220	0.5429
2.4578	1.0333	50	1.1173	0.6571
1.7213	2.0333	75	0.8284	0.6
1.0839	3.0333	100	0.5795	0.7571
0.6657	4.0333	125	0.2759	0.9714
0.138	5.0333	150	0.1465	0.9714
0.1764	6.0333	175	0.0888	0.9857
0.0474	7.0333	200	0.2699	0.8857
0.1228	8.0333	225	0.0644	0.9857
0.0597	9.0333	250	0.1139	0.9714

Framework versions

• Transformers 4.47.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0