videomae-small-finetuned-kinetics-finetuned-2

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

• Loss: 0.6633
• Accuracy: 0.7652

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: 32
• eval_batch_size: 32
• 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: 2260

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9644	0.1004	227	0.9733	0.5777
0.8823	1.1004	454	0.8691	0.6676
0.826	2.1004	681	0.8010	0.7094
0.7422	3.1004	908	0.7514	0.7371
0.7206	4.1004	1135	0.7170	0.7508
0.6806	5.1004	1362	0.6924	0.7543
0.6826	6.1004	1589	0.6757	0.7585
0.6756	7.1004	1816	0.6652	0.7631
0.6964	8.1004	2043	0.6591	0.7655
0.6943	9.0960	2260	0.6571	0.7666

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0