poolformer_s12-finetuned-IDRiD

This model is a fine-tuned version of sail/poolformer_s12 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0484
• Accuracy: 0.4762

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: 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	3	1.6953	0.0238
No log	2.0	6	1.6010	0.3333
No log	3.0	9	1.5131	0.2857
1.5842	4.0	12	1.4584	0.3810
1.5842	5.0	15	1.4097	0.4286
1.5842	6.0	18	1.3579	0.4524
1.2645	7.0	21	1.3034	0.4762
1.2645	8.0	24	1.2696	0.4762
1.2645	9.0	27	1.2298	0.4524
1.1011	10.0	30	1.2088	0.4762
1.1011	11.0	33	1.1945	0.4048
1.1011	12.0	36	1.1898	0.4524
1.1011	13.0	39	1.1668	0.4524
1.0024	14.0	42	1.1484	0.4286
1.0024	15.0	45	1.1374	0.4524
1.0024	16.0	48	1.1289	0.4524
0.9111	17.0	51	1.1166	0.4524
0.9111	18.0	54	1.1081	0.4286
0.9111	19.0	57	1.1011	0.4048
0.876	20.0	60	1.1005	0.4286
0.876	21.0	63	1.0999	0.4524
0.876	22.0	66	1.0933	0.4524
0.876	23.0	69	1.0714	0.4762
0.8375	24.0	72	1.0551	0.4762
0.8375	25.0	75	1.0427	0.4762
0.8375	26.0	78	1.0386	0.4762
0.8085	27.0	81	1.0413	0.4524
0.8085	28.0	84	1.0462	0.4762
0.8085	29.0	87	1.0480	0.4762
0.8125	30.0	90	1.0484	0.4762

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3