vit-model

This model is a fine-tuned version of on the preprocessed1024_config dataset. It achieves the following results on the evaluation set:

• Loss: 1.1353
• Accuracy: {'accuracy': 0.6011306532663316}
• F1: {'f1': 0.5956396413406886}

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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.224	1.0	796	0.9884	{'accuracy': 0.5276381909547738}	{'f1': 0.40344173017767304}
0.96	2.0	1592	0.9255	{'accuracy': 0.5621859296482412}	{'f1': 0.5134011716404221}
0.8878	3.0	2388	0.9308	{'accuracy': 0.574748743718593}	{'f1': 0.46867195041352344}
0.809	4.0	3184	0.8904	{'accuracy': 0.6067839195979899}	{'f1': 0.5799288651427482}
0.7541	5.0	3980	0.8936	{'accuracy': 0.5954773869346733}	{'f1': 0.5938876317530138}
0.6904	6.0	4776	0.8760	{'accuracy': 0.6118090452261307}	{'f1': 0.6023012293668115}
0.6195	7.0	5572	1.0032	{'accuracy': 0.5917085427135679}	{'f1': 0.5834559014249068}
0.5766	8.0	6368	1.0268	{'accuracy': 0.6023869346733668}	{'f1': 0.5779800559497847}
0.4963	9.0	7164	1.0460	{'accuracy': 0.5992462311557789}	{'f1': 0.5875334711293277}
0.4323	10.0	7960	1.1353	{'accuracy': 0.6011306532663316}	{'f1': 0.5956396413406886}

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0
• Datasets 2.1.0
• Tokenizers 0.12.1