videomae-base-cart-activity-v1

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: 0.2897
• Accuracy: 0.9002

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: 2544

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5671	0.0625	159	0.6464	0.7371
0.3141	1.0625	318	0.4348	0.8403
0.3008	2.0625	477	0.4203	0.8436
0.3051	3.0625	636	0.3499	0.8735
0.2801	4.0625	795	0.3290	0.8719
0.3035	5.0625	954	0.7646	0.7787
0.3501	6.0625	1113	0.2899	0.9002
0.0959	7.0625	1272	0.2681	0.8968
0.2196	8.0625	1431	0.3333	0.8802
0.2609	9.0625	1590	0.3849	0.8769
0.1546	10.0625	1749	0.3787	0.8852
0.1834	11.0625	1908	0.4571	0.8835
0.2244	12.0625	2067	0.3221	0.8902
0.2318	13.0625	2226	0.4032	0.8819
0.2501	14.0625	2385	0.3339	0.8952
0.086	15.0625	2544	0.3323	0.8935

Framework versions

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