VideoMAE_default_fold__0__10_epoch_bdslw60_kinetics_25_2_25

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2880
• Accuracy: 0.9436

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2264	0.1	903	0.3193	0.9502
0.2835	1.1001	1807	0.0355	0.9888
0.124	2.1	2710	0.0410	0.9913
0.0637	3.1001	3614	0.0343	0.9888
0.0062	4.1	4517	0.0191	0.9938
0.0009	5.1001	5421	0.0163	0.9950
0.0026	6.1	6324	0.0338	0.9938
0.0136	7.1001	7228	0.0064	0.9988
0.0007	8.1	8131	0.0065	0.9975
0.0002	9.0995	9030	0.0089	0.9975

Framework versions

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