resnet-101-finetuned-CivilEng11k-newDS

This model is a fine-tuned version of microsoft/resnet-101 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4541
• Accuracy: 0.9932

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 20
• total_train_batch_size: 640
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.54	1	1.0986	0.4136
No log	1.62	3	1.0295	0.4339
No log	2.7	5	0.8537	0.4339
No log	3.78	7	0.6785	0.4441
No log	4.86	9	0.6141	0.6576
No log	5.95	11	0.5794	0.7559
No log	6.49	12	0.5616	0.8034
No log	7.57	14	0.5304	0.8475
No log	8.65	16	0.4964	0.9492
No log	9.73	18	0.4680	0.9864
0.6919	10.81	20	0.4541	0.9932

Framework versions

• Transformers 4.37.2
• Pytorch 1.12.1
• Datasets 2.18.0
• Tokenizers 0.15.1