Timesformer_tuning_BdSLW60_divided_100epochs

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: 1.0540
• Accuracy: 0.7168

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 21900

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2101	0.0400	877	1.5081	0.5677
0.2501	1.0400	1754	1.9650	0.4586
0.1882	2.0400	2631	1.8327	0.5603
0.1689	3.0400	3508	2.1530	0.4607
0.2985	4.0400	4385	2.2342	0.4858
0.0795	5.0400	5262	2.0402	0.5100

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1