dit-base-Tobacco_Dataset_v3

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

Loss: 0.1958
Accuracy: 0.9419
F1
- Weighted: 0.9403
- Micro: 0.9419
- Macro: 0.9278

Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Document%20AI/Multiclass%20Classification/Tobacco-Related%20Documents/Tobacco%20Dataset%20%26%20DiT%20Transformer%20Project_v3.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/patrickaudriaz/tobacco3482jpg

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Weighted F1	Micro F1	Macro F1
1.9273	0.98	43	1.1368	0.5987	0.5462	0.5987	0.5175
1.0685	1.98	86	0.5244	0.8248	0.7939	0.8248	0.7670
0.7373	2.98	129	0.3631	0.8808	0.8610	0.8808	0.8318
0.641	3.98	172	0.2884	0.9045	0.8967	0.9045	0.8732
0.5579	4.98	215	0.2192	0.9361	0.9338	0.9361	0.9214
0.5279	5.98	258	0.2292	0.9289	0.9263	0.9289	0.9137
0.4918	6.98	301	0.2052	0.9368	0.9348	0.9368	0.9218
0.4723	7.98	344	0.1958	0.9419	0.9403	0.9419	0.9278

Framework versions

Transformers 4.26.1
Pytorch 1.12.1
Datasets 2.9.0
Tokenizers 0.12.1