VideoMAE_default_fold__0__10_epoch_Aug_batch_1_4_LSA64

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: 0.1199
• Accuracy: 0.9663

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: 2880

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
15.3983	0.1	288	3.5284	0.0618
8.6438	1.1	576	1.2307	0.7104
2.2913	2.1	864	0.5788	0.8378
0.7753	3.1	1152	0.3188	0.9112
0.4337	4.1	1440	0.2272	0.9382
0.2878	5.1	1728	0.1662	0.9614
0.2576	6.1	2016	0.1262	0.9537
0.0631	7.1	2304	0.1343	0.9575
0.1669	8.1	2592	0.1011	0.9730
0.0401	9.1	2880	0.0878	0.9768

Framework versions

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