SaffalPoosh commited on
Commit
6dd16f9
1 Parent(s): 1d7a566

End of training

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swin-tiny-patch4-window7-224
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: swin-tiny-patch4-window7-224-finetuned-eurosat
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # swin-tiny-patch4-window7-224-finetuned-eurosat
17
+
18
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.9148
21
+ - Accuracy: 0.3938
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 5
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 2.6414 | 0.9630 | 13 | 2.4260 | 0.2746 |
56
+ | 2.4558 | 2.0 | 27 | 2.1558 | 0.3368 |
57
+ | 2.1176 | 2.9630 | 40 | 2.0164 | 0.3834 |
58
+ | 2.0264 | 4.0 | 54 | 1.9314 | 0.3886 |
59
+ | 1.9409 | 4.8148 | 65 | 1.9148 | 0.3938 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.40.2
65
+ - Pytorch 2.2.1+cu121
66
+ - Datasets 2.19.1
67
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.814814814814815,
3
+ "eval_accuracy": 0.39378238341968913,
4
+ "eval_loss": 1.9148268699645996,
5
+ "eval_runtime": 4.2598,
6
+ "eval_samples_per_second": 45.307,
7
+ "eval_steps_per_second": 1.643,
8
+ "total_flos": 1.0808265111345562e+18,
9
+ "train_loss": 2.2193346903874325,
10
+ "train_runtime": 316.4726,
11
+ "train_samples_per_second": 27.301,
12
+ "train_steps_per_second": 0.205
13
+ }
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "Amoxicillin",
21
+ "1": "Ampicillin",
22
+ "2": "Aspirin",
23
+ "3": "Bleomycine",
24
+ "4": "Cefixime",
25
+ "5": "Cefotaxime",
26
+ "6": "Ceftriaxone",
27
+ "7": "Cefuroxime",
28
+ "8": "Ciprofloxacin",
29
+ "9": "Clopidogre",
30
+ "10": "Gentamycine",
31
+ "11": "Levofloxacin",
32
+ "12": "Losartan",
33
+ "13": "Neomycin",
34
+ "14": "Valsartan"
35
+ },
36
+ "image_size": 224,
37
+ "initializer_range": 0.02,
38
+ "label2id": {
39
+ "Amoxicillin": 0,
40
+ "Ampicillin": 1,
41
+ "Aspirin": 2,
42
+ "Bleomycine": 3,
43
+ "Cefixime": 4,
44
+ "Cefotaxime": 5,
45
+ "Ceftriaxone": 6,
46
+ "Cefuroxime": 7,
47
+ "Ciprofloxacin": 8,
48
+ "Clopidogre": 9,
49
+ "Gentamycine": 10,
50
+ "Levofloxacin": 11,
51
+ "Losartan": 12,
52
+ "Neomycin": 13,
53
+ "Valsartan": 14
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "mlp_ratio": 4.0,
57
+ "model_type": "swin",
58
+ "num_channels": 3,
59
+ "num_heads": [
60
+ 3,
61
+ 6,
62
+ 12,
63
+ 24
64
+ ],
65
+ "num_layers": 4,
66
+ "out_features": [
67
+ "stage4"
68
+ ],
69
+ "out_indices": [
70
+ 4
71
+ ],
72
+ "patch_size": 4,
73
+ "path_norm": true,
74
+ "problem_type": "single_label_classification",
75
+ "qkv_bias": true,
76
+ "stage_names": [
77
+ "stem",
78
+ "stage1",
79
+ "stage2",
80
+ "stage3",
81
+ "stage4"
82
+ ],
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.40.2",
85
+ "use_absolute_embeddings": false,
86
+ "window_size": 7
87
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.814814814814815,
3
+ "eval_accuracy": 0.39378238341968913,
4
+ "eval_loss": 1.9148268699645996,
5
+ "eval_runtime": 4.2598,
6
+ "eval_samples_per_second": 45.307,
7
+ "eval_steps_per_second": 1.643
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41416dd74ed6d5ead67d64c9bfdf2fc0c2f4b36b3f4acd6b8a457eb728ffc72
3
+ size 110382828
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.485,
21
+ 0.456,
22
+ 0.406
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.229,
27
+ 0.224,
28
+ 0.225
29
+ ],
30
+ "resample": 3,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
runs/May18_22-58-23_aad0bb7717de/events.out.tfevents.1716073130.aad0bb7717de.2141.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e9a62aa015331b8b1e21a8d6968df0ef0fd435fae3c0da130b777266566b11
3
+ size 10368
runs/May18_22-58-23_aad0bb7717de/events.out.tfevents.1716073286.aad0bb7717de.2141.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f9f53239a1aa5686b6b0eea294f7fffca47a9d49d40c0f6b50acb4783c7561
3
+ size 411
runs/May18_23-02-06_aad0bb7717de/events.out.tfevents.1716073333.aad0bb7717de.2141.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ef005a7267119445fc45f04257d7d4434692f40d7909006fcdbab0ea89574d
3
+ size 5779
runs/May18_23-02-29_aad0bb7717de/events.out.tfevents.1716073354.aad0bb7717de.2141.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0676c4b1cb42e5b3395901ab27dd8aa8b73a4e14f6e688f0899ab7ad8064f369
3
+ size 8955
runs/May18_23-02-29_aad0bb7717de/events.out.tfevents.1716073572.aad0bb7717de.2141.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0801e458300b1340df94d10ab9a4d3b56c3318db42309ad65e4c6233bbe1cd06
3
+ size 405
runs/May18_23-07-12_aad0bb7717de/events.out.tfevents.1716073636.aad0bb7717de.2141.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af206ebefbef2d257c9a7c2d1a7e0f639ecda0a76529af0db6c8ae6d94d5ada2
3
+ size 8906
runs/May18_23-07-12_aad0bb7717de/events.out.tfevents.1716073957.aad0bb7717de.2141.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c51dfcbe08e35be1b8a8f051387f13eb9ef1e1603a03c1db354a83dec1ab45
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.814814814814815,
3
+ "total_flos": 1.0808265111345562e+18,
4
+ "train_loss": 2.2193346903874325,
5
+ "train_runtime": 316.4726,
6
+ "train_samples_per_second": 27.301,
7
+ "train_steps_per_second": 0.205
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.39378238341968913,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-65",
4
+ "epoch": 4.814814814814815,
5
+ "eval_steps": 500,
6
+ "global_step": 65,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7407407407407407,
13
+ "grad_norm": 2.7531347274780273,
14
+ "learning_rate": 4.741379310344828e-05,
15
+ "loss": 2.6414,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.9629629629629629,
20
+ "eval_accuracy": 0.27461139896373055,
21
+ "eval_loss": 2.4260499477386475,
22
+ "eval_runtime": 4.2205,
23
+ "eval_samples_per_second": 45.729,
24
+ "eval_steps_per_second": 1.659,
25
+ "step": 13
26
+ },
27
+ {
28
+ "epoch": 1.4814814814814814,
29
+ "grad_norm": 6.018283843994141,
30
+ "learning_rate": 3.8793103448275865e-05,
31
+ "loss": 2.4558,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.33678756476683935,
37
+ "eval_loss": 2.15580415725708,
38
+ "eval_runtime": 4.3823,
39
+ "eval_samples_per_second": 44.04,
40
+ "eval_steps_per_second": 1.597,
41
+ "step": 27
42
+ },
43
+ {
44
+ "epoch": 2.2222222222222223,
45
+ "grad_norm": 8.673904418945312,
46
+ "learning_rate": 3.017241379310345e-05,
47
+ "loss": 2.2726,
48
+ "step": 30
49
+ },
50
+ {
51
+ "epoch": 2.962962962962963,
52
+ "grad_norm": 10.522686004638672,
53
+ "learning_rate": 2.1551724137931033e-05,
54
+ "loss": 2.1176,
55
+ "step": 40
56
+ },
57
+ {
58
+ "epoch": 2.962962962962963,
59
+ "eval_accuracy": 0.38341968911917096,
60
+ "eval_loss": 2.01640248298645,
61
+ "eval_runtime": 4.245,
62
+ "eval_samples_per_second": 45.465,
63
+ "eval_steps_per_second": 1.649,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 3.7037037037037037,
68
+ "grad_norm": 12.191962242126465,
69
+ "learning_rate": 1.2931034482758622e-05,
70
+ "loss": 2.0264,
71
+ "step": 50
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.38860103626943004,
76
+ "eval_loss": 1.9313786029815674,
77
+ "eval_runtime": 4.1882,
78
+ "eval_samples_per_second": 46.082,
79
+ "eval_steps_per_second": 1.671,
80
+ "step": 54
81
+ },
82
+ {
83
+ "epoch": 4.444444444444445,
84
+ "grad_norm": 8.964757919311523,
85
+ "learning_rate": 4.310344827586207e-06,
86
+ "loss": 1.9409,
87
+ "step": 60
88
+ },
89
+ {
90
+ "epoch": 4.814814814814815,
91
+ "eval_accuracy": 0.39378238341968913,
92
+ "eval_loss": 1.9148268699645996,
93
+ "eval_runtime": 4.182,
94
+ "eval_samples_per_second": 46.15,
95
+ "eval_steps_per_second": 1.674,
96
+ "step": 65
97
+ },
98
+ {
99
+ "epoch": 4.814814814814815,
100
+ "step": 65,
101
+ "total_flos": 1.0808265111345562e+18,
102
+ "train_loss": 2.2193346903874325,
103
+ "train_runtime": 316.4726,
104
+ "train_samples_per_second": 27.301,
105
+ "train_steps_per_second": 0.205
106
+ }
107
+ ],
108
+ "logging_steps": 10,
109
+ "max_steps": 65,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 5,
112
+ "save_steps": 500,
113
+ "total_flos": 1.0808265111345562e+18,
114
+ "train_batch_size": 32,
115
+ "trial_name": null,
116
+ "trial_params": null
117
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb31e9d4d50d02e8532dbcc44d1d18bda3bffd7a9fe9bde163fc47c402866e6
3
+ size 5048