videomae-base-test-small-aug-finetuned-SLT-subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7786
• Accuracy: 1.0

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: 8
• eval_batch_size: 8
• 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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.12	2	1.3221	0.5
No log	1.12	4	1.1049	0.5
No log	2.12	6	0.9825	0.5
No log	3.12	8	0.8929	0.75
1.2166	4.12	10	0.8538	0.5
1.2166	5.12	12	0.8157	0.5
1.2166	6.12	14	0.7909	1.0
1.2166	7.12	16	0.7786	1.0

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0+cpu
• Datasets 2.1.0
• Tokenizers 0.13.3