timesformer-base-finetuned-k400-continual-lora-ucf101-til-02-continual-lora-ucf101-til-03

This model is a fine-tuned version of NiiCole/timesformer-base-finetuned-k400-continual-lora-ucf101-til-02 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.4504
• Accuracy: 0.0

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3768

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1682	0.5	1885	2.3425	0.7215
1.785	1.5	3768	1.6384	0.7948

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3