swinv2-tiny-patch4-window8-256-RD-aptos19

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 144573075075950992480149202324684800.0000
• Accuracy: 0.6739

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: 0.00015
• 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: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.86	3	144573075075950992480149202324684800.0000	0.4565
No log	2.0	7	144573075075950992480149202324684800.0000	0.4565
141735823463928302525633790371430400.0000	2.86	10	144573075075950992480149202324684800.0000	0.4565
141735823463928302525633790371430400.0000	4.0	14	144573075075950992480149202324684800.0000	0.4565
141735823463928302525633790371430400.0000	4.86	17	144573075075950992480149202324684800.0000	0.4565
148386187888478135085935683952443392.0000	6.0	21	144573075075950992480149202324684800.0000	0.4565
148386187888478135085935683952443392.0000	6.86	24	144573075075950992480149202324684800.0000	0.4783
148386187888478135085935683952443392.0000	8.0	28	144573075075950992480149202324684800.0000	0.4565
166674646480500797315403436963921920.0000	8.86	31	144573075075950992480149202324684800.0000	0.4565
166674646480500797315403436963921920.0000	10.0	35	144573075075950992480149202324684800.0000	0.4565
166674646480500797315403436963921920.0000	10.86	38	144573075075950992480149202324684800.0000	0.4565
123031678471642034838718731348082688.0000	12.0	42	144573075075950992480149202324684800.0000	0.5217
123031678471642034838718731348082688.0000	12.86	45	144573075075950992480149202324684800.0000	0.6087
123031678471642034838718731348082688.0000	14.0	49	144573075075950992480149202324684800.0000	0.5435
160439944687765812243898756589682688.0000	14.86	52	144573075075950992480149202324684800.0000	0.6522
160439944687765812243898756589682688.0000	16.0	56	144573075075950992480149202324684800.0000	0.5870
160439944687765812243898756589682688.0000	16.86	59	144573075075950992480149202324684800.0000	0.5652
151295747083019479456202288017702912.0000	18.0	63	144573075075950992480149202324684800.0000	0.6087
151295747083019479456202288017702912.0000	18.86	66	144573075075950992480149202324684800.0000	0.6304
142151454404478133240649521934893056.0000	20.0	70	144573075075950992480149202324684800.0000	0.6522
142151454404478133240649521934893056.0000	20.86	73	144573075075950992480149202324684800.0000	0.6739
142151454404478133240649521934893056.0000	22.0	77	144573075075950992480149202324684800.0000	0.6739
137163724661555136131785556085440512.0000	22.86	80	144573075075950992480149202324684800.0000	0.6304
137163724661555136131785556085440512.0000	24.0	84	144573075075950992480149202324684800.0000	0.6304
137163724661555136131785556085440512.0000	24.86	87	144573075075950992480149202324684800.0000	0.6739
137163692970290119358004074442129408.0000	26.0	91	144573075075950992480149202324684800.0000	0.6304
137163692970290119358004074442129408.0000	26.86	94	144573075075950992480149202324684800.0000	0.6522
137163692970290119358004074442129408.0000	28.0	98	144573075075950992480149202324684800.0000	0.6522
155452183253577798361253309096919040.0000	28.86	101	144573075075950992480149202324684800.0000	0.6739
155452183253577798361253309096919040.0000	30.0	105	144573075075950992480149202324684800.0000	0.6522
155452183253577798361253309096919040.0000	30.86	108	144573075075950992480149202324684800.0000	0.6522
139657557841751617912436057366855680.0000	32.0	112	144573075075950992480149202324684800.0000	0.6522
139657557841751617912436057366855680.0000	32.86	115	144573075075950992480149202324684800.0000	0.6522
139657557841751617912436057366855680.0000	34.0	119	144573075075950992480149202324684800.0000	0.6304
141735791772663285751852308728119296.0000	34.29	120	144573075075950992480149202324684800.0000	0.6304

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0