ViViT_default_fold_10_10_epoch_Aug_batch_1_4

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: 0.7226
• Accuracy: 0.8315

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 18060

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.296	0.1	1806	0.3558	0.9055
0.0725	1.1000	3613	0.0838	0.9714
0.0549	2.1000	5420	0.2072	0.9565
0.0417	3.1000	7227	0.0728	0.9813
0.0149	4.1	9033	0.0382	0.9900
0.006	5.1000	10840	0.0148	0.9938
0.0003	6.1000	12647	0.0804	0.9876
0.0002	7.1000	14454	0.0757	0.9851
0.0	8.1	16260	0.0365	0.9925
0.0	9.0996	18060	0.0245	0.9925

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 2.19.2
• Tokenizers 0.19.1