videomae-base-cart-activity-v0

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: 0.2626
• Accuracy: 0.9101

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: 16
• eval_batch_size: 16
• 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: 1272

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4774	0.125	159	0.5977	0.7471
0.2843	1.125	318	0.3505	0.8835
0.2384	2.125	477	0.3886	0.8586
0.2976	3.125	636	0.3410	0.8852
0.2244	4.125	795	0.3221	0.8802
0.2358	5.125	954	0.2995	0.8935
0.2745	6.125	1113	0.2763	0.9052
0.089	7.125	1272	0.2628	0.9101

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0