vivit-vit-8-10-epochs-splited_bdd_2-1747208501.832576

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0410
• Accuracy: 0.9913

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: 8
• eval_batch_size: 8
• 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: 14940

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2705	0.1001	1495	0.1152	0.9625
0.0196	1.1001	2990	0.0991	0.9793
0.0131	2.1001	4485	0.0621	0.9846
0.0826	3.1001	5980	0.0644	0.9866
0.0304	4.1001	7475	0.0449	0.9880
0.032	5.1001	8970	0.0572	0.9886
0.115	6.1001	10465	0.0497	0.9880
0.0002	7.1001	11960	0.0667	0.9893
0.0001	8.1001	13455	0.0500	0.9920
0.0	9.0994	14940	0.0488	0.9906

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.5.1
• Tokenizers 0.21.1