pvt-small-224-ConcreteClassifier-PVT

This model is a fine-tuned version of Xrenya/pvt-small-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.9419
• Accuracy: {'accuracy': 0.17665369649805449}
• F1: {'f1': 0.04289493575207861}
• Precision: {'precision': 0.025236242356864926}
• Recall: {'recall': 0.14285714285714285}

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: 0.001
• 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: constant
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.981	1.0	1927	1.9584	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.951	2.0	3854	1.9447	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9799	3.0	5781	1.9498	{'accuracy': 0.13618677042801555}	{'f1': 0.03424657534246575}	{'precision': 0.019455252918287935}	{'recall': 0.14285714285714285}
1.9458	4.0	7708	1.9412	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9444	5.0	9635	1.9408	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9441	6.0	11562	1.9427	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9379	7.0	13489	1.9433	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9529	8.0	15416	1.9432	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9305	9.0	17343	1.9463	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.94	10.0	19270	1.9412	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.945	11.0	21197	1.9432	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9294	12.0	23124	1.9444	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9339	13.0	25051	1.9415	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.934	14.0	26978	1.9408	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9275	15.0	28905	1.9423	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9539	16.0	30832	1.9440	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9584	17.0	32759	1.9412	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9409	18.0	34686	1.9405	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9522	19.0	36613	1.9405	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9296	20.0	38540	1.9410	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9272	21.0	40467	1.9412	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9399	22.0	42394	1.9413	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9258	23.0	44321	1.9413	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9481	24.0	46248	1.9422	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.948	25.0	48175	1.9423	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.918	26.0	50102	1.9416	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.938	27.0	52029	1.9414	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9207	28.0	53956	1.9410	{'accuracy': 0.1556420233463035}	{'f1': 0.03848003848003848}	{'precision': 0.022234574763757644}	{'recall': 0.14285714285714285}
1.9472	29.0	55883	1.9404	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}
1.9355	30.0	57810	1.9419	{'accuracy': 0.17665369649805449}	{'f1': 0.04289493575207861}	{'precision': 0.025236242356864926}	{'recall': 0.14285714285714285}

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0
• Datasets 2.17.1
• Tokenizers 0.15.2