freeway_resnet50_Model

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0047
• Accuracy: 1.0

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3403	0.4808	100	0.3006	0.9454
0.3093	0.9615	200	0.2498	0.9540
0.2743	1.4423	300	0.2004	0.9666
0.2375	1.9231	400	0.1552	0.9798
0.2118	2.4038	500	0.1143	0.9852
0.1953	2.8846	600	0.1095	0.9844
0.1807	3.3654	700	0.0893	0.9895
0.1623	3.8462	800	0.0682	0.9914
0.1414	4.3269	900	0.0560	0.9941
0.1296	4.8077	1000	0.0511	0.9933
0.1195	5.2885	1100	0.0344	0.9957
0.1114	5.7692	1200	0.0303	0.9984
0.1034	6.25	1300	0.0298	0.9965
0.0994	6.7308	1400	0.0257	0.9987
0.0907	7.2115	1500	0.0225	0.9992
0.0881	7.6923	1600	0.0201	0.9987
0.0801	8.1731	1700	0.0157	1.0
0.0764	8.6538	1800	0.0141	0.9995
0.0746	9.1346	1900	0.0142	0.9995
0.0715	9.6154	2000	0.0115	0.9995
0.074	10.0962	2100	0.0124	0.9992
0.0677	10.5769	2200	0.0102	0.9995
0.0679	11.0577	2300	0.0101	0.9995
0.068	11.5385	2400	0.0110	0.9992
0.0589	12.0192	2500	0.0081	0.9997
0.0581	12.5	2600	0.0090	0.9995
0.058	12.9808	2700	0.0080	0.9995
0.0559	13.4615	2800	0.0082	0.9997
0.0547	13.9423	2900	0.0062	1.0
0.0493	14.4231	3000	0.0061	1.0
0.0506	14.9038	3100	0.0054	1.0
0.0466	15.3846	3200	0.0068	0.9995
0.0506	15.8654	3300	0.0055	1.0
0.0481	16.3462	3400	0.0053	1.0
0.0523	16.8269	3500	0.0053	1.0
0.0537	17.3077	3600	0.0061	0.9995
0.0474	17.7885	3700	0.0049	1.0
0.0511	18.2692	3800	0.0054	1.0
0.0474	18.75	3900	0.0052	1.0
0.0456	19.2308	4000	0.0062	0.9997
0.0385	19.7115	4100	0.0047	1.0

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.1.1
• Datasets 2.19.2
• Tokenizers 0.19.1