VideoMAE_default_fold__3__10_epoch_Aug_batch_1_4_BdSLW60

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: 0.8015
• Accuracy: 0.8715

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 9030

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
7.7232	0.1	903	1.7044	0.5940
1.6336	1.1001	1807	0.3697	0.9029
0.5047	2.1	2710	0.2068	0.9402
0.2142	3.1001	3614	0.1498	0.9664
0.2392	4.1	4517	0.0491	0.9863
0.0409	5.1001	5421	0.0544	0.9863
0.0712	6.1	6324	0.0449	0.9888
0.0478	7.1001	7228	0.0251	0.9913
0.0057	8.1	8131	0.0290	0.9925
0.013	9.0995	9030	0.0503	0.9900

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.1