Cheese_X_ray

This model is a fine-tuned version of barghavani/Cheese_xray on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1890
• Accuracy: 0.9381

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
0.5579	0.9882	63	0.5524	0.7062
0.4491	1.9922	127	0.4218	0.7062
0.3646	2.9961	191	0.3928	0.7440
0.3419	4.0	255	0.3827	0.8110
0.3546	4.9882	318	0.3530	0.8608
0.3745	5.9922	382	0.3298	0.8814
0.3323	6.9961	446	0.3022	0.8952
0.3125	8.0	510	0.2750	0.9089
0.2663	8.9882	573	0.2648	0.8883
0.2672	9.9922	637	0.2476	0.9038
0.2492	10.9961	701	0.2354	0.9278
0.2297	12.0	765	0.2272	0.9175
0.1915	12.9882	828	0.2126	0.9107
0.2071	13.9922	892	0.2006	0.9227
0.2251	14.9961	956	0.1806	0.9244
0.1979	16.0	1020	0.1900	0.9347
0.1969	16.9882	1083	0.2081	0.9192
0.2	17.9922	1147	0.2037	0.9175
0.2082	18.9961	1211	0.2108	0.9175
0.1838	19.7647	1260	0.1688	0.9330

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1