timesformer-base-finetuned-k400-submission

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1785
• Accuracy: 0.94

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2307	0.1667	250	0.1391	0.96
0.2739	1.1667	500	0.6467	0.88
0.0006	2.1667	750	0.1763	0.96
0.0001	3.1667	1000	0.1302	0.96
0.0002	4.1667	1250	0.1326	0.96
0.0001	5.1667	1500	0.1758	0.96

Framework versions

• Transformers 4.40.1
• Pytorch 2.1.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1