image_classification

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0002
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: 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	1.0978	0.5
No log	2.0	2	1.0528	0.5833
No log	3.0	3	0.9606	0.625
No log	4.0	4	0.8337	0.7083
No log	5.0	5	0.6860	0.75
No log	6.0	6	0.5366	0.9167
No log	7.0	7	0.3971	0.9583
No log	8.0	8	0.2704	1.0
No log	9.0	9	0.1702	1.0
0.1887	10.0	10	0.1046	1.0
0.1887	11.0	11	0.0633	1.0
0.1887	12.0	12	0.0420	1.0
0.1887	13.0	13	0.0324	1.0
0.1887	14.0	14	0.0298	1.0
0.1887	15.0	15	0.0260	1.0
0.1887	16.0	16	0.0229	1.0
0.1887	17.0	17	0.0180	1.0
0.1887	18.0	18	0.0119	1.0
0.1887	19.0	19	0.0072	1.0
0.0083	20.0	20	0.0045	1.0
0.0083	21.0	21	0.0022	1.0
0.0083	22.0	22	0.0012	1.0
0.0083	23.0	23	0.0007	1.0
0.0083	24.0	24	0.0005	1.0
0.0083	25.0	25	0.0004	1.0
0.0083	26.0	26	0.0003	1.0
0.0083	27.0	27	0.0003	1.0
0.0083	28.0	28	0.0002	1.0
0.0083	29.0	29	0.0002	1.0
0.0009	30.0	30	0.0002	1.0
0.0009	31.0	31	0.0002	1.0
0.0009	32.0	32	0.0002	1.0
0.0009	33.0	33	0.0002	1.0
0.0009	34.0	34	0.0002	1.0
0.0009	35.0	35	0.0002	1.0
0.0009	36.0	36	0.0002	1.0
0.0009	37.0	37	0.0002	1.0
0.0009	38.0	38	0.0002	1.0
0.0009	39.0	39	0.0002	1.0
0.0003	40.0	40	0.0002	1.0
0.0003	41.0	41	0.0002	1.0
0.0003	42.0	42	0.0002	1.0
0.0003	43.0	43	0.0002	1.0
0.0003	44.0	44	0.0002	1.0
0.0003	45.0	45	0.0002	1.0
0.0003	46.0	46	0.0002	1.0
0.0003	47.0	47	0.0002	1.0
0.0003	48.0	48	0.0002	1.0
0.0003	49.0	49	0.0002	1.0
0.0002	50.0	50	0.0002	1.0

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

Loading…

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	1.0978	0.5
No log	2.0	2	1.0528	0.5833
No log	3.0	3	0.9606	0.625
No log	4.0	4	0.8337	0.7083
No log	5.0	5	0.6860	0.75
No log	6.0	6	0.5366	0.9167
No log	7.0	7	0.3971	0.9583
No log	8.0	8	0.2704	1.0
No log	9.0	9	0.1702	1.0
0.1887	10.0	10	0.1046	1.0
0.1887	11.0	11	0.0633	1.0
0.1887	12.0	12	0.0420	1.0
0.1887	13.0	13	0.0324	1.0
0.1887	14.0	14	0.0298	1.0
0.1887	15.0	15	0.0260	1.0
0.1887	16.0	16	0.0229	1.0
0.1887	17.0	17	0.0180	1.0
0.1887	18.0	18	0.0119	1.0
0.1887	19.0	19	0.0072	1.0
0.0083	20.0	20	0.0045	1.0
0.0083	21.0	21	0.0022	1.0
0.0083	22.0	22	0.0012	1.0
0.0083	23.0	23	0.0007	1.0
0.0083	24.0	24	0.0005	1.0
0.0083	25.0	25	0.0004	1.0
0.0083	26.0	26	0.0003	1.0
0.0083	27.0	27	0.0003	1.0
0.0083	28.0	28	0.0002	1.0
0.0083	29.0	29	0.0002	1.0
0.0009	30.0	30	0.0002	1.0
0.0009	31.0	31	0.0002	1.0
0.0009	32.0	32	0.0002	1.0
0.0009	33.0	33	0.0002	1.0
0.0009	34.0	34	0.0002	1.0
0.0009	35.0	35	0.0002	1.0
0.0009	36.0	36	0.0002	1.0
0.0009	37.0	37	0.0002	1.0
0.0009	38.0	38	0.0002	1.0
0.0009	39.0	39	0.0002	1.0
0.0003	40.0	40	0.0002	1.0
0.0003	41.0	41	0.0002	1.0
0.0003	42.0	42	0.0002	1.0
0.0003	43.0	43	0.0002	1.0
0.0003	44.0	44	0.0002	1.0
0.0003	45.0	45	0.0002	1.0
0.0003	46.0	46	0.0002	1.0
0.0003	47.0	47	0.0002	1.0
0.0003	48.0	48	0.0002	1.0
0.0003	49.0	49	0.0002	1.0
0.0002	50.0	50	0.0002	1.0

Framework versions

Transformers 4.35.2

Pytorch 2.1.0+cu121

Datasets 2.17.1

Tokenizers 0.15.2

raoulmago/image_classification

image_classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

image_classification

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions