2024_08_13

This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6787
• Accuracy: 0.75

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-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7191	0.992	31	0.7459	0.25
0.6894	1.984	62	0.6787	0.75
0.5993	2.976	93	0.6090	0.75
0.5858	4.0	125	0.5702	0.75
0.5407	4.992	156	0.5572	0.75
0.6552	5.984	187	0.5553	0.75
0.5562	6.976	218	0.5529	0.75
0.6054	8.0	250	0.5519	0.75
0.7563	8.992	281	0.5518	0.75
0.5174	9.984	312	0.5523	0.75
0.3765	10.9760	343	0.5514	0.75
0.5727	12.0	375	0.5507	0.75
0.5613	12.992	406	0.5510	0.75
0.568	13.984	437	0.5510	0.75
0.6655	14.9760	468	0.5514	0.75
0.4883	16.0	500	0.5522	0.75
0.5317	16.992	531	0.5518	0.75
0.4501	17.984	562	0.5520	0.75
0.4616	18.976	593	0.5519	0.75
0.4522	20.0	625	0.5510	0.75
0.6326	20.992	656	0.5507	0.75
0.3828	21.984	687	0.5508	0.75
0.4283	22.976	718	0.5509	0.75
0.6701	24.0	750	0.5506	0.75
0.6157	24.992	781	0.5503	0.75
0.5657	25.984	812	0.5503	0.75
0.5127	26.976	843	0.5503	0.75
0.6178	28.0	875	0.5503	0.75
0.5679	28.992	906	0.5502	0.75
0.6102	29.76	930	0.5502	0.75

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1