Text2Image_PyData_23

This model is a fine-tuned version of juliensimon/autotrain-chest-xray-demo-1677859324 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3421
• Accuracy: 0.8333
• F1: [0.71584699 0.88208617]
• Precision: [0.99242424 0.79065041]
• Recall: [0.55982906 0.9974359 ]

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-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.0451	0.98	40	0.6974	0.7933	[0.62170088 0.85777288]	[0.99065421 0.75241779]	[0.45299145 0.9974359 ]
0.036	1.99	81	0.3557	0.8958	[0.84107579 0.92252682]	[0.98285714 0.86191537]	[0.73504274 0.99230769]
0.043	2.99	122	0.4253	0.9006	[0.84803922 0.92619048]	[0.99425287 0.86444444]	[0.73931624 0.9974359 ]
0.0225	4.0	163	0.8776	0.8349	[0.71934605 0.8830874 ]	[0.9924812 0.79226069]	[0.56410256 0.9974359 ]
0.0153	4.98	203	0.7095	0.8670	[0.78552972 0.90360046]	[0.99346405 0.82590234]	[0.64957265 0.9974359 ]
0.0107	5.99	244	0.8537	0.8446	[0.73994638 0.88914286]	[0.99280576 0.80206186]	[0.58974359 0.9974359 ]
0.0052	6.99	285	1.0167	0.8462	[0.74331551 0.89016018]	[0.99285714 0.80371901]	[0.59401709 0.9974359 ]
0.0049	8.0	326	1.3230	0.8045	[0.64942529 0.86444444]	[0.99122807 0.7627451 ]	[0.48290598 0.9974359 ]
0.0061	8.98	366	1.2652	0.8269	[0.70165746 0.87810384]	[0.9921875 0.78427419]	[0.54273504 0.9974359 ]
0.004	9.99	407	1.4846	0.8157	[0.67605634 0.8712206 ]	[0.99173554 0.77335984]	[0.51282051 0.9974359 ]
0.0005	10.99	448	1.5685	0.8109	[0.66477273 0.86830357]	[0.99152542 0.7687747 ]	[0.5 0.9974359]
0.0029	12.0	489	1.2547	0.8397	[0.72972973 0.88610478]	[0.99264706 0.79713115]	[0.57692308 0.9974359 ]
0.0015	12.98	529	1.4026	0.8285	[0.70523416 0.87909605]	[0.99224806 0.78585859]	[0.54700855 0.9974359 ]
0.0012	13.99	570	1.4444	0.8237	[0.69444444 0.87612613]	[0.99206349 0.7811245 ]	[0.53418803 0.9974359 ]
0.0039	14.72	600	1.3421	0.8333	[0.71584699 0.88208617]	[0.99242424 0.79065041]	[0.55982906 0.9974359 ]

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1