jialicheng/unlearn_nlvr2_vilt_neggrad_4_42

42

This model is a fine-tuned version of dandelin/vilt-b32-finetuned-nlvr2 on the nlvr2 dataset. It achieves the following results on the evaluation set:

• Loss: -4.5175
• Accuracy: 0.5726
• Dt Accuracy: 0.5726
• Df Accuracy: 0.5995
• Unlearn Overall Accuracy: 0.7689
• Unlearn Time: None

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	108	-2.1890	0.7048	0.7293	0.7293	None
No log	2.0	216	-4.5175	0.5995	0.7689	0.7689	None

Framework versions

• Transformers 4.48.0
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.21.0