SodaXII commited on
Commit
41ce099
·
verified ·
1 Parent(s): 0f63728

Model save

Browse files
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/swin-base-patch4-window7-224
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: swin-base-patch4-window7-224_rice-leaf-disease-augmented-v2_fft
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # swin-base-patch4-window7-224_rice-leaf-disease-augmented-v2_fft
16
+
17
+ This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 64
38
+ - eval_batch_size: 64
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: cosine_with_restarts
42
+ - lr_scheduler_warmup_ratio: 0.1
43
+ - num_epochs: 15
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.48.3
49
+ - Pytorch 2.5.1+cu124
50
+ - Datasets 3.3.2
51
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-base-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 18,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 128,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "Bacterial Leaf Blight",
21
+ "1": "Brown Spot",
22
+ "2": "Healthy Rice Leaf",
23
+ "3": "Leaf Blast",
24
+ "4": "Leaf scald",
25
+ "5": "Narrow Brown Leaf Spot",
26
+ "6": "Rice Hispa",
27
+ "7": "Sheath Blight"
28
+ },
29
+ "image_size": 224,
30
+ "initializer_range": 0.02,
31
+ "label2id": {
32
+ "Bacterial Leaf Blight": 0,
33
+ "Brown Spot": 1,
34
+ "Healthy Rice Leaf": 2,
35
+ "Leaf Blast": 3,
36
+ "Leaf scald": 4,
37
+ "Narrow Brown Leaf Spot": 5,
38
+ "Rice Hispa": 6,
39
+ "Sheath Blight": 7
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "mlp_ratio": 4.0,
43
+ "model_type": "swin",
44
+ "num_channels": 3,
45
+ "num_heads": [
46
+ 4,
47
+ 8,
48
+ 16,
49
+ 32
50
+ ],
51
+ "num_layers": 4,
52
+ "out_features": [
53
+ "stage4"
54
+ ],
55
+ "out_indices": [
56
+ 4
57
+ ],
58
+ "patch_size": 4,
59
+ "path_norm": true,
60
+ "qkv_bias": true,
61
+ "stage_names": [
62
+ "stem",
63
+ "stage1",
64
+ "stage2",
65
+ "stage3",
66
+ "stage4"
67
+ ],
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.48.3",
70
+ "use_absolute_embeddings": false,
71
+ "window_size": 7
72
+ }
logs/events.out.tfevents.1740258697.17453a9827e7.637.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24b79cdc77f51291a9f069e3cdacdd0f357e35d9d43d5044e83466bd9f0c442
3
+ size 6044
logs/events.out.tfevents.1740258936.17453a9827e7.2740.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92975e3f871210646f04533749c338e6bfb0c5e324688b874a83e5b78d21d03d
3
+ size 6044
logs/events.out.tfevents.1740259144.17453a9827e7.3812.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5f3de86b90ccb26a30b8104b78e36b6592e42715871145b7e1c2877a84bb32
3
+ size 8703
logs/events.out.tfevents.1740261704.17453a9827e7.3812.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c585b36c569a4a3650732f89071165c2275ef1200a4560d168620bbfbd4a14a
3
+ size 20116
logs/events.out.tfevents.1740263799.17453a9827e7.3812.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bac0f0e28db541ba4941501b1f69a2a92a758192798c8d203bb5d9308a400b3
3
+ size 8722
logs/events.out.tfevents.1740281118.c59d799b8436.377.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f00bd5822379c857cc8b37027afe61b1b96dc308f913672f4b5d5c23b1dfa51
3
+ size 88
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8159ec2fc2e32290c999f338c3c4b05b8a5af21a1fe3b3d7ec6309b238fdaa4b
3
+ size 347523416
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
trainer_state.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3934735655784607,
3
+ "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/swin-base-patch4-window7-224_rice-leaf-disease-augmented-v2_fft/checkpoint-375",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 7.30280876159668,
14
+ "learning_rate": 6.577540106951872e-06,
15
+ "loss": 1.6649,
16
+ "step": 125
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7351190476190477,
21
+ "eval_loss": 0.8050427436828613,
22
+ "eval_runtime": 14.2308,
23
+ "eval_samples_per_second": 23.611,
24
+ "eval_steps_per_second": 0.422,
25
+ "step": 125
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 6.75390100479126,
30
+ "learning_rate": 9.871664184437119e-06,
31
+ "loss": 0.431,
32
+ "step": 250
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8511904761904762,
37
+ "eval_loss": 0.45273008942604065,
38
+ "eval_runtime": 13.8146,
39
+ "eval_samples_per_second": 24.322,
40
+ "eval_steps_per_second": 0.434,
41
+ "step": 250
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 8.129321098327637,
46
+ "learning_rate": 8.848767222994402e-06,
47
+ "loss": 0.1233,
48
+ "step": 375
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8928571428571429,
53
+ "eval_loss": 0.3934735655784607,
54
+ "eval_runtime": 14.0064,
55
+ "eval_samples_per_second": 23.989,
56
+ "eval_steps_per_second": 0.428,
57
+ "step": 375
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 1.9338823556900024,
62
+ "learning_rate": 7.007580044706666e-06,
63
+ "loss": 0.0326,
64
+ "step": 500
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.9077380952380952,
69
+ "eval_loss": 0.4275733530521393,
70
+ "eval_runtime": 13.7209,
71
+ "eval_samples_per_second": 24.488,
72
+ "eval_steps_per_second": 0.437,
73
+ "step": 500
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 0.1951848417520523,
78
+ "learning_rate": 4.739559281809819e-06,
79
+ "loss": 0.01,
80
+ "step": 625
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.9166666666666666,
85
+ "eval_loss": 0.45519202947616577,
86
+ "eval_runtime": 13.6317,
87
+ "eval_samples_per_second": 24.648,
88
+ "eval_steps_per_second": 0.44,
89
+ "step": 625
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 0.07782671600580215,
94
+ "learning_rate": 2.5674558357271096e-06,
95
+ "loss": 0.0049,
96
+ "step": 750
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.9077380952380952,
101
+ "eval_loss": 0.4804078936576843,
102
+ "eval_runtime": 12.6134,
103
+ "eval_samples_per_second": 26.638,
104
+ "eval_steps_per_second": 0.476,
105
+ "step": 750
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 0.7393015623092651,
110
+ "learning_rate": 9.974770025621516e-06,
111
+ "loss": 0.0024,
112
+ "step": 875
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.9166666666666666,
117
+ "eval_loss": 0.4863254427909851,
118
+ "eval_runtime": 12.7829,
119
+ "eval_samples_per_second": 26.285,
120
+ "eval_steps_per_second": 0.469,
121
+ "step": 875
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 0.14619985222816467,
126
+ "learning_rate": 6.511415799458836e-06,
127
+ "loss": 0.005,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.9166666666666666,
133
+ "eval_loss": 0.5142239332199097,
134
+ "eval_runtime": 12.7007,
135
+ "eval_samples_per_second": 26.455,
136
+ "eval_steps_per_second": 0.472,
137
+ "step": 1000
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 0.16888085007667542,
142
+ "learning_rate": 1.2234689624958324e-06,
143
+ "loss": 0.0026,
144
+ "step": 1125
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_accuracy": 0.9166666666666666,
149
+ "eval_loss": 0.5233145952224731,
150
+ "eval_runtime": 12.5815,
151
+ "eval_samples_per_second": 26.706,
152
+ "eval_steps_per_second": 0.477,
153
+ "step": 1125
154
+ }
155
+ ],
156
+ "logging_steps": 500,
157
+ "max_steps": 1875,
158
+ "num_input_tokens_seen": 0,
159
+ "num_train_epochs": 15,
160
+ "save_steps": 500,
161
+ "stateful_callbacks": {
162
+ "TrainerControl": {
163
+ "args": {
164
+ "should_epoch_stop": false,
165
+ "should_evaluate": false,
166
+ "should_log": false,
167
+ "should_save": true,
168
+ "should_training_stop": false
169
+ },
170
+ "attributes": {}
171
+ }
172
+ },
173
+ "total_flos": 5.761627233139556e+18,
174
+ "train_batch_size": 64,
175
+ "trial_name": null,
176
+ "trial_params": null
177
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:979002238134198a950d2de7953ccf5fdc0ff327300aafa84afa81c05f472946
3
+ size 5496