Hugging Face's logo

encku
/
corbin-04-2025

Image Classification
Transformers
Safetensors
vit
Trained with AutoTrain
Model card Files Community
encku commited on
Commit
bae85e8
·
verified ·
1 Parent(s): e0a166f

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +42 -0
  2. autotrain-data/dataset_dict.json +1 -0
  3. autotrain-data/train/data-00000-of-00004.arrow +3 -0
  4. autotrain-data/train/data-00001-of-00004.arrow +3 -0
  5. autotrain-data/train/data-00002-of-00004.arrow +3 -0
  6. autotrain-data/train/data-00003-of-00004.arrow +3 -0
  7. autotrain-data/train/dataset_info.json +0 -0
  8. autotrain-data/train/state.json +22 -0
  9. autotrain-data/validation/data-00000-of-00001.arrow +3 -0
  10. autotrain-data/validation/dataset_info.json +0 -0
  11. autotrain-data/validation/state.json +13 -0
  12. checkpoint-1806/config.json +113 -0
  13. checkpoint-1806/model.safetensors +3 -0
  14. checkpoint-1806/optimizer.pt +3 -0
  15. checkpoint-1806/rng_state.pth +3 -0
  16. checkpoint-1806/scheduler.pt +3 -0
  17. checkpoint-1806/trainer_state.json +600 -0
  18. checkpoint-1806/training_args.bin +3 -0
  19. config.json +113 -0
  20. model.safetensors +3 -0
  21. preprocessor_config.json +23 -0
  22. training_args.bin +3 -0
  23. training_params.json +30 -0
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - transformers
6
+ - image-classification
7
+ base_model: google/vit-large-patch32-384
8
+ widget:
9
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
10
+ example_title: Tiger
11
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
12
+ example_title: Teapot
13
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
14
+ example_title: Palace
15
+ ---
16
+
17
+ # Model Trained Using AutoTrain
18
+
19
+ - Problem type: Image Classification
20
+
21
+ ## Validation Metrics
22
+ loss: 0.0022578395437449217
23
+
24
+ f1_macro: 0.9993728898422963
25
+
26
+ f1_micro: 0.9994462901439646
27
+
28
+ f1_weighted: 0.9994461479999952
29
+
30
+ precision_macro: 0.999304490903036
31
+
32
+ precision_micro: 0.9994462901439646
33
+
34
+ precision_weighted: 0.9994521433108384
35
+
36
+ recall_macro: 0.999448205969945
37
+
38
+ recall_micro: 0.9994462901439646
39
+
40
+ recall_weighted: 0.9994462901439646
41
+
42
+ accuracy: 0.9994462901439646
autotrain-data/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "validation"]}
autotrain-data/train/data-00000-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ae3e09337c2d147b847ad9e4a555be251dcdc08b2b3d4a4944f9f111385f78
3
+ size 461938232
autotrain-data/train/data-00001-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce83694e5774a896100c8e156ff3b98e7c369a280eaf81a9009e67ca6c0c2f4
3
+ size 476474976
autotrain-data/train/data-00002-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf4d2ddb7aba6e134b07ec933336e5c2e73c699c29569c7866d37df09239a94
3
+ size 524048336
autotrain-data/train/data-00003-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55f94d666e05698ed5d565424a91eac03ad8aa0794f8fe103ddcb90fa3e3a2b
3
+ size 500062896
autotrain-data/train/dataset_info.json ADDED
The diff for this file is too large to render. See raw diff
 
autotrain-data/train/state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00004.arrow"
5
+ },
6
+ {
7
+ "filename": "data-00001-of-00004.arrow"
8
+ },
9
+ {
10
+ "filename": "data-00002-of-00004.arrow"
11
+ },
12
+ {
13
+ "filename": "data-00003-of-00004.arrow"
14
+ }
15
+ ],
16
+ "_fingerprint": "0e1792c57ddca18f",
17
+ "_format_columns": null,
18
+ "_format_kwargs": {},
19
+ "_format_type": null,
20
+ "_output_all_columns": false,
21
+ "_split": "train"
22
+ }
autotrain-data/validation/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9910aec869bd16b1b431f5148d6a930382498206ad2f0aaabd8d56c449d18760
3
+ size 493799864
autotrain-data/validation/dataset_info.json ADDED
The diff for this file is too large to render. See raw diff
 
autotrain-data/validation/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "a5da6592ae29347b",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "validation"
13
+ }
checkpoint-1806/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-large-patch32-384",
3
+ "_num_labels": 42,
4
+ "architectures": [
5
+ "ViTForImageClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "encoder_stride": 16,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "018200250002",
14
+ "1": "018200250019",
15
+ "2": "018200250101",
16
+ "3": "018200261244",
17
+ "4": "01823743",
18
+ "5": "021136180596",
19
+ "6": "021136180947",
20
+ "7": "021136181364",
21
+ "8": "021136181371",
22
+ "9": "025000058011",
23
+ "10": "03435515",
24
+ "11": "049000003710",
25
+ "12": "049000007909",
26
+ "13": "049000019162",
27
+ "14": "049000040869",
28
+ "15": "049000071542",
29
+ "16": "04904403",
30
+ "17": "04904500",
31
+ "18": "04976400",
32
+ "19": "04997704",
33
+ "20": "070847012474",
34
+ "21": "070847811169",
35
+ "22": "070847898245",
36
+ "23": "071990095451",
37
+ "24": "071990300654",
38
+ "25": "080660956435",
39
+ "26": "080660957210",
40
+ "27": "083783375534",
41
+ "28": "083900005757",
42
+ "29": "083900005771",
43
+ "30": "085000027141",
44
+ "31": "085000028728",
45
+ "32": "085000029275",
46
+ "33": "085000031377",
47
+ "34": "087692832317",
48
+ "35": "786162200433",
49
+ "36": "786162338006",
50
+ "37": "796030250965",
51
+ "38": "810628031474",
52
+ "39": "816751021214",
53
+ "40": "855352008064",
54
+ "41": "857531005284"
55
+ },
56
+ "image_size": 384,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "label2id": {
60
+ "018200250002": 0,
61
+ "018200250019": 1,
62
+ "018200250101": 2,
63
+ "018200261244": 3,
64
+ "01823743": 4,
65
+ "021136180596": 5,
66
+ "021136180947": 6,
67
+ "021136181364": 7,
68
+ "021136181371": 8,
69
+ "025000058011": 9,
70
+ "03435515": 10,
71
+ "049000003710": 11,
72
+ "049000007909": 12,
73
+ "049000019162": 13,
74
+ "049000040869": 14,
75
+ "049000071542": 15,
76
+ "04904403": 16,
77
+ "04904500": 17,
78
+ "04976400": 18,
79
+ "04997704": 19,
80
+ "070847012474": 20,
81
+ "070847811169": 21,
82
+ "070847898245": 22,
83
+ "071990095451": 23,
84
+ "071990300654": 24,
85
+ "080660956435": 25,
86
+ "080660957210": 26,
87
+ "083783375534": 27,
88
+ "083900005757": 28,
89
+ "083900005771": 29,
90
+ "085000027141": 30,
91
+ "085000028728": 31,
92
+ "085000029275": 32,
93
+ "085000031377": 33,
94
+ "087692832317": 34,
95
+ "786162200433": 35,
96
+ "786162338006": 36,
97
+ "796030250965": 37,
98
+ "810628031474": 38,
99
+ "816751021214": 39,
100
+ "855352008064": 40,
101
+ "857531005284": 41
102
+ },
103
+ "layer_norm_eps": 1e-12,
104
+ "model_type": "vit",
105
+ "num_attention_heads": 16,
106
+ "num_channels": 3,
107
+ "num_hidden_layers": 24,
108
+ "patch_size": 32,
109
+ "problem_type": "single_label_classification",
110
+ "qkv_bias": true,
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.48.0"
113
+ }
checkpoint-1806/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78df14c9c954d51c6282508096f9385632eb277c1b1c049646a2b3a45a3e5a26
3
+ size 1222649496
checkpoint-1806/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fc83c2cf91494b1521c37b47528017b67837604a3592ab61f3b855d7e5b08a
3
+ size 2445534331
checkpoint-1806/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd9432b50864b1799d071a2391f13a188cc959e985675ab69fd688672db2853
3
+ size 14645
checkpoint-1806/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca46ad72d3fcf65150dd538238b045dbb9478781d25f27f8b47ce542f099834
3
+ size 1465
checkpoint-1806/trainer_state.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0022578395437449217,
3
+ "best_model_checkpoint": "project-name/checkpoint-1806",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1806,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04152823920265781,
13
+ "grad_norm": 5.379489898681641,
14
+ "learning_rate": 6.906077348066299e-06,
15
+ "loss": 3.8859,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.08305647840531562,
20
+ "grad_norm": 8.003674507141113,
21
+ "learning_rate": 1.3812154696132598e-05,
22
+ "loss": 3.4497,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.12458471760797342,
27
+ "grad_norm": 4.87650203704834,
28
+ "learning_rate": 2.0718232044198896e-05,
29
+ "loss": 2.6429,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.16611295681063123,
34
+ "grad_norm": 3.833146095275879,
35
+ "learning_rate": 2.7624309392265197e-05,
36
+ "loss": 1.5907,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.20764119601328904,
41
+ "grad_norm": 2.214146614074707,
42
+ "learning_rate": 3.4530386740331494e-05,
43
+ "loss": 0.7225,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.24916943521594684,
48
+ "grad_norm": 1.3430291414260864,
49
+ "learning_rate": 4.143646408839779e-05,
50
+ "loss": 0.3209,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.29069767441860467,
55
+ "grad_norm": 0.761883556842804,
56
+ "learning_rate": 4.834254143646409e-05,
57
+ "loss": 0.2108,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.33222591362126247,
62
+ "grad_norm": 1.163543939590454,
63
+ "learning_rate": 4.941538461538462e-05,
64
+ "loss": 0.1191,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.37375415282392027,
69
+ "grad_norm": 0.919347882270813,
70
+ "learning_rate": 4.864615384615385e-05,
71
+ "loss": 0.1199,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.4152823920265781,
76
+ "grad_norm": 1.222544550895691,
77
+ "learning_rate": 4.787692307692308e-05,
78
+ "loss": 0.0968,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.4568106312292359,
83
+ "grad_norm": 1.4635224342346191,
84
+ "learning_rate": 4.710769230769231e-05,
85
+ "loss": 0.097,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.4983388704318937,
90
+ "grad_norm": 1.3402526378631592,
91
+ "learning_rate": 4.633846153846154e-05,
92
+ "loss": 0.0689,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.5398671096345515,
97
+ "grad_norm": 0.8671730160713196,
98
+ "learning_rate": 4.556923076923077e-05,
99
+ "loss": 0.0985,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.5813953488372093,
104
+ "grad_norm": 1.5626745223999023,
105
+ "learning_rate": 4.4800000000000005e-05,
106
+ "loss": 0.1026,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.6229235880398671,
111
+ "grad_norm": 0.6234097480773926,
112
+ "learning_rate": 4.403076923076923e-05,
113
+ "loss": 0.1204,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.6644518272425249,
118
+ "grad_norm": 1.1657061576843262,
119
+ "learning_rate": 4.3261538461538464e-05,
120
+ "loss": 0.0758,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.7059800664451827,
125
+ "grad_norm": 0.9871473908424377,
126
+ "learning_rate": 4.2492307692307694e-05,
127
+ "loss": 0.1,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.7475083056478405,
132
+ "grad_norm": 0.6370132565498352,
133
+ "learning_rate": 4.1723076923076924e-05,
134
+ "loss": 0.078,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.7890365448504983,
139
+ "grad_norm": 1.5644354820251465,
140
+ "learning_rate": 4.0953846153846154e-05,
141
+ "loss": 0.0815,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.8305647840531561,
146
+ "grad_norm": 2.4982550144195557,
147
+ "learning_rate": 4.018461538461539e-05,
148
+ "loss": 0.0825,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.872093023255814,
153
+ "grad_norm": 1.3120901584625244,
154
+ "learning_rate": 3.941538461538461e-05,
155
+ "loss": 0.0659,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.9136212624584718,
160
+ "grad_norm": 1.236675500869751,
161
+ "learning_rate": 3.864615384615385e-05,
162
+ "loss": 0.0628,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.9551495016611296,
167
+ "grad_norm": 1.1188125610351562,
168
+ "learning_rate": 3.787692307692308e-05,
169
+ "loss": 0.0762,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.9966777408637874,
174
+ "grad_norm": 1.2520239353179932,
175
+ "learning_rate": 3.710769230769231e-05,
176
+ "loss": 0.0513,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "eval_accuracy": 0.9968161683277962,
182
+ "eval_f1_macro": 0.9965727646072912,
183
+ "eval_f1_micro": 0.9968161683277962,
184
+ "eval_f1_weighted": 0.9968213765950431,
185
+ "eval_loss": 0.008436347357928753,
186
+ "eval_precision_macro": 0.9963284135987243,
187
+ "eval_precision_micro": 0.9968161683277962,
188
+ "eval_precision_weighted": 0.9969410521911278,
189
+ "eval_recall_macro": 0.9969503142190713,
190
+ "eval_recall_micro": 0.9968161683277962,
191
+ "eval_recall_weighted": 0.9968161683277962,
192
+ "eval_runtime": 66.3126,
193
+ "eval_samples_per_second": 108.939,
194
+ "eval_steps_per_second": 1.146,
195
+ "step": 602
196
+ },
197
+ {
198
+ "epoch": 1.0382059800664452,
199
+ "grad_norm": 0.6366732716560364,
200
+ "learning_rate": 3.633846153846154e-05,
201
+ "loss": 0.0526,
202
+ "step": 625
203
+ },
204
+ {
205
+ "epoch": 1.079734219269103,
206
+ "grad_norm": 1.8220373392105103,
207
+ "learning_rate": 3.556923076923077e-05,
208
+ "loss": 0.0818,
209
+ "step": 650
210
+ },
211
+ {
212
+ "epoch": 1.1212624584717608,
213
+ "grad_norm": 1.0081020593643188,
214
+ "learning_rate": 3.48e-05,
215
+ "loss": 0.0778,
216
+ "step": 675
217
+ },
218
+ {
219
+ "epoch": 1.1627906976744187,
220
+ "grad_norm": 0.17098402976989746,
221
+ "learning_rate": 3.4030769230769235e-05,
222
+ "loss": 0.0875,
223
+ "step": 700
224
+ },
225
+ {
226
+ "epoch": 1.2043189368770764,
227
+ "grad_norm": 0.3888116776943207,
228
+ "learning_rate": 3.326153846153846e-05,
229
+ "loss": 0.0604,
230
+ "step": 725
231
+ },
232
+ {
233
+ "epoch": 1.2458471760797343,
234
+ "grad_norm": 0.4702301621437073,
235
+ "learning_rate": 3.2492307692307695e-05,
236
+ "loss": 0.0613,
237
+ "step": 750
238
+ },
239
+ {
240
+ "epoch": 1.287375415282392,
241
+ "grad_norm": 0.26242753863334656,
242
+ "learning_rate": 3.1723076923076925e-05,
243
+ "loss": 0.0462,
244
+ "step": 775
245
+ },
246
+ {
247
+ "epoch": 1.3289036544850499,
248
+ "grad_norm": 1.047985553741455,
249
+ "learning_rate": 3.0953846153846155e-05,
250
+ "loss": 0.0419,
251
+ "step": 800
252
+ },
253
+ {
254
+ "epoch": 1.3704318936877076,
255
+ "grad_norm": 0.8426637649536133,
256
+ "learning_rate": 3.0184615384615384e-05,
257
+ "loss": 0.058,
258
+ "step": 825
259
+ },
260
+ {
261
+ "epoch": 1.4119601328903655,
262
+ "grad_norm": 0.32604917883872986,
263
+ "learning_rate": 2.9415384615384618e-05,
264
+ "loss": 0.0622,
265
+ "step": 850
266
+ },
267
+ {
268
+ "epoch": 1.4534883720930232,
269
+ "grad_norm": 0.9149531126022339,
270
+ "learning_rate": 2.8646153846153844e-05,
271
+ "loss": 0.077,
272
+ "step": 875
273
+ },
274
+ {
275
+ "epoch": 1.495016611295681,
276
+ "grad_norm": 1.723166584968567,
277
+ "learning_rate": 2.7876923076923077e-05,
278
+ "loss": 0.0556,
279
+ "step": 900
280
+ },
281
+ {
282
+ "epoch": 1.536544850498339,
283
+ "grad_norm": 0.5741901993751526,
284
+ "learning_rate": 2.710769230769231e-05,
285
+ "loss": 0.0515,
286
+ "step": 925
287
+ },
288
+ {
289
+ "epoch": 1.5780730897009967,
290
+ "grad_norm": 1.2806332111358643,
291
+ "learning_rate": 2.633846153846154e-05,
292
+ "loss": 0.0624,
293
+ "step": 950
294
+ },
295
+ {
296
+ "epoch": 1.6196013289036544,
297
+ "grad_norm": 0.016820058226585388,
298
+ "learning_rate": 2.5569230769230773e-05,
299
+ "loss": 0.0567,
300
+ "step": 975
301
+ },
302
+ {
303
+ "epoch": 1.6611295681063123,
304
+ "grad_norm": 0.07608214765787125,
305
+ "learning_rate": 2.48e-05,
306
+ "loss": 0.0479,
307
+ "step": 1000
308
+ },
309
+ {
310
+ "epoch": 1.7026578073089702,
311
+ "grad_norm": 0.5414699912071228,
312
+ "learning_rate": 2.4030769230769233e-05,
313
+ "loss": 0.0544,
314
+ "step": 1025
315
+ },
316
+ {
317
+ "epoch": 1.744186046511628,
318
+ "grad_norm": 1.1329694986343384,
319
+ "learning_rate": 2.3261538461538463e-05,
320
+ "loss": 0.0637,
321
+ "step": 1050
322
+ },
323
+ {
324
+ "epoch": 1.7857142857142856,
325
+ "grad_norm": 0.3416385352611542,
326
+ "learning_rate": 2.2492307692307692e-05,
327
+ "loss": 0.0426,
328
+ "step": 1075
329
+ },
330
+ {
331
+ "epoch": 1.8272425249169435,
332
+ "grad_norm": 0.03737162798643112,
333
+ "learning_rate": 2.1723076923076922e-05,
334
+ "loss": 0.0555,
335
+ "step": 1100
336
+ },
337
+ {
338
+ "epoch": 1.8687707641196014,
339
+ "grad_norm": 1.7364981174468994,
340
+ "learning_rate": 2.0953846153846155e-05,
341
+ "loss": 0.0638,
342
+ "step": 1125
343
+ },
344
+ {
345
+ "epoch": 1.910299003322259,
346
+ "grad_norm": 2.366119384765625,
347
+ "learning_rate": 2.0184615384615385e-05,
348
+ "loss": 0.0412,
349
+ "step": 1150
350
+ },
351
+ {
352
+ "epoch": 1.9518272425249168,
353
+ "grad_norm": 0.04764602333307266,
354
+ "learning_rate": 1.9415384615384615e-05,
355
+ "loss": 0.047,
356
+ "step": 1175
357
+ },
358
+ {
359
+ "epoch": 1.9933554817275747,
360
+ "grad_norm": 1.8723899126052856,
361
+ "learning_rate": 1.8646153846153845e-05,
362
+ "loss": 0.0681,
363
+ "step": 1200
364
+ },
365
+ {
366
+ "epoch": 2.0,
367
+ "eval_accuracy": 0.9994462901439646,
368
+ "eval_f1_macro": 0.9993863106544856,
369
+ "eval_f1_micro": 0.9994462901439646,
370
+ "eval_f1_weighted": 0.999446389268536,
371
+ "eval_loss": 0.0026618363335728645,
372
+ "eval_precision_macro": 0.9993719331532139,
373
+ "eval_precision_micro": 0.9994462901439646,
374
+ "eval_precision_weighted": 0.9994504223070693,
375
+ "eval_recall_macro": 0.9994055488584712,
376
+ "eval_recall_micro": 0.9994462901439646,
377
+ "eval_recall_weighted": 0.9994462901439646,
378
+ "eval_runtime": 66.1379,
379
+ "eval_samples_per_second": 109.226,
380
+ "eval_steps_per_second": 1.149,
381
+ "step": 1204
382
+ },
383
+ {
384
+ "epoch": 2.0348837209302326,
385
+ "grad_norm": 1.302878975868225,
386
+ "learning_rate": 1.7876923076923078e-05,
387
+ "loss": 0.0419,
388
+ "step": 1225
389
+ },
390
+ {
391
+ "epoch": 2.0764119601328903,
392
+ "grad_norm": 0.5144720673561096,
393
+ "learning_rate": 1.7107692307692308e-05,
394
+ "loss": 0.062,
395
+ "step": 1250
396
+ },
397
+ {
398
+ "epoch": 2.117940199335548,
399
+ "grad_norm": 0.30704957246780396,
400
+ "learning_rate": 1.6338461538461538e-05,
401
+ "loss": 0.051,
402
+ "step": 1275
403
+ },
404
+ {
405
+ "epoch": 2.159468438538206,
406
+ "grad_norm": 0.014852220192551613,
407
+ "learning_rate": 1.556923076923077e-05,
408
+ "loss": 0.0598,
409
+ "step": 1300
410
+ },
411
+ {
412
+ "epoch": 2.200996677740864,
413
+ "grad_norm": 0.3403995633125305,
414
+ "learning_rate": 1.48e-05,
415
+ "loss": 0.046,
416
+ "step": 1325
417
+ },
418
+ {
419
+ "epoch": 2.2425249169435215,
420
+ "grad_norm": 0.502398669719696,
421
+ "learning_rate": 1.403076923076923e-05,
422
+ "loss": 0.0461,
423
+ "step": 1350
424
+ },
425
+ {
426
+ "epoch": 2.284053156146179,
427
+ "grad_norm": 0.31954801082611084,
428
+ "learning_rate": 1.3261538461538462e-05,
429
+ "loss": 0.0648,
430
+ "step": 1375
431
+ },
432
+ {
433
+ "epoch": 2.3255813953488373,
434
+ "grad_norm": 0.3058352470397949,
435
+ "learning_rate": 1.2492307692307693e-05,
436
+ "loss": 0.0501,
437
+ "step": 1400
438
+ },
439
+ {
440
+ "epoch": 2.367109634551495,
441
+ "grad_norm": 1.0894181728363037,
442
+ "learning_rate": 1.1723076923076925e-05,
443
+ "loss": 0.0373,
444
+ "step": 1425
445
+ },
446
+ {
447
+ "epoch": 2.4086378737541527,
448
+ "grad_norm": 0.060482293367385864,
449
+ "learning_rate": 1.0953846153846155e-05,
450
+ "loss": 0.0511,
451
+ "step": 1450
452
+ },
453
+ {
454
+ "epoch": 2.4501661129568104,
455
+ "grad_norm": 0.31768345832824707,
456
+ "learning_rate": 1.0184615384615386e-05,
457
+ "loss": 0.0478,
458
+ "step": 1475
459
+ },
460
+ {
461
+ "epoch": 2.4916943521594686,
462
+ "grad_norm": 0.1634824424982071,
463
+ "learning_rate": 9.415384615384616e-06,
464
+ "loss": 0.0504,
465
+ "step": 1500
466
+ },
467
+ {
468
+ "epoch": 2.5332225913621262,
469
+ "grad_norm": 0.30424895882606506,
470
+ "learning_rate": 8.646153846153847e-06,
471
+ "loss": 0.0533,
472
+ "step": 1525
473
+ },
474
+ {
475
+ "epoch": 2.574750830564784,
476
+ "grad_norm": 1.7913155555725098,
477
+ "learning_rate": 7.876923076923077e-06,
478
+ "loss": 0.055,
479
+ "step": 1550
480
+ },
481
+ {
482
+ "epoch": 2.616279069767442,
483
+ "grad_norm": 0.3424425423145294,
484
+ "learning_rate": 7.107692307692308e-06,
485
+ "loss": 0.0533,
486
+ "step": 1575
487
+ },
488
+ {
489
+ "epoch": 2.6578073089700998,
490
+ "grad_norm": 0.02855181321501732,
491
+ "learning_rate": 6.338461538461539e-06,
492
+ "loss": 0.066,
493
+ "step": 1600
494
+ },
495
+ {
496
+ "epoch": 2.6993355481727574,
497
+ "grad_norm": 0.3200845718383789,
498
+ "learning_rate": 5.56923076923077e-06,
499
+ "loss": 0.0542,
500
+ "step": 1625
501
+ },
502
+ {
503
+ "epoch": 2.740863787375415,
504
+ "grad_norm": 0.6209678649902344,
505
+ "learning_rate": 4.800000000000001e-06,
506
+ "loss": 0.0513,
507
+ "step": 1650
508
+ },
509
+ {
510
+ "epoch": 2.782392026578073,
511
+ "grad_norm": 0.009850960224866867,
512
+ "learning_rate": 4.030769230769231e-06,
513
+ "loss": 0.0357,
514
+ "step": 1675
515
+ },
516
+ {
517
+ "epoch": 2.823920265780731,
518
+ "grad_norm": 0.5470796823501587,
519
+ "learning_rate": 3.261538461538462e-06,
520
+ "loss": 0.0672,
521
+ "step": 1700
522
+ },
523
+ {
524
+ "epoch": 2.8654485049833887,
525
+ "grad_norm": 0.3075508177280426,
526
+ "learning_rate": 2.4923076923076926e-06,
527
+ "loss": 0.0487,
528
+ "step": 1725
529
+ },
530
+ {
531
+ "epoch": 2.9069767441860463,
532
+ "grad_norm": 1.3108922243118286,
533
+ "learning_rate": 1.7230769230769232e-06,
534
+ "loss": 0.0415,
535
+ "step": 1750
536
+ },
537
+ {
538
+ "epoch": 2.9485049833887045,
539
+ "grad_norm": 0.3696553409099579,
540
+ "learning_rate": 9.53846153846154e-07,
541
+ "loss": 0.0432,
542
+ "step": 1775
543
+ },
544
+ {
545
+ "epoch": 2.990033222591362,
546
+ "grad_norm": 0.40178290009498596,
547
+ "learning_rate": 1.846153846153846e-07,
548
+ "loss": 0.0603,
549
+ "step": 1800
550
+ },
551
+ {
552
+ "epoch": 3.0,
553
+ "eval_accuracy": 0.9994462901439646,
554
+ "eval_f1_macro": 0.9993728898422963,
555
+ "eval_f1_micro": 0.9994462901439646,
556
+ "eval_f1_weighted": 0.9994461479999952,
557
+ "eval_loss": 0.0022578395437449217,
558
+ "eval_precision_macro": 0.999304490903036,
559
+ "eval_precision_micro": 0.9994462901439646,
560
+ "eval_precision_weighted": 0.9994521433108384,
561
+ "eval_recall_macro": 0.999448205969945,
562
+ "eval_recall_micro": 0.9994462901439646,
563
+ "eval_recall_weighted": 0.9994462901439646,
564
+ "eval_runtime": 64.626,
565
+ "eval_samples_per_second": 111.782,
566
+ "eval_steps_per_second": 1.176,
567
+ "step": 1806
568
+ }
569
+ ],
570
+ "logging_steps": 25,
571
+ "max_steps": 1806,
572
+ "num_input_tokens_seen": 0,
573
+ "num_train_epochs": 3,
574
+ "save_steps": 500,
575
+ "stateful_callbacks": {
576
+ "EarlyStoppingCallback": {
577
+ "args": {
578
+ "early_stopping_patience": 5,
579
+ "early_stopping_threshold": 0.01
580
+ },
581
+ "attributes": {
582
+ "early_stopping_patience_counter": 2
583
+ }
584
+ },
585
+ "TrainerControl": {
586
+ "args": {
587
+ "should_epoch_stop": false,
588
+ "should_evaluate": false,
589
+ "should_log": false,
590
+ "should_save": true,
591
+ "should_training_stop": true
592
+ },
593
+ "attributes": {}
594
+ }
595
+ },
596
+ "total_flos": 7.032655999996527e+19,
597
+ "train_batch_size": 48,
598
+ "trial_name": null,
599
+ "trial_params": null
600
+ }
checkpoint-1806/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5c3f143f2ba661829205959c31c550c9baea9da3ea7c6d3c01754590aa7474
3
+ size 5713
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-large-patch32-384",
3
+ "_num_labels": 42,
4
+ "architectures": [
5
+ "ViTForImageClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "encoder_stride": 16,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "018200250002",
14
+ "1": "018200250019",
15
+ "2": "018200250101",
16
+ "3": "018200261244",
17
+ "4": "01823743",
18
+ "5": "021136180596",
19
+ "6": "021136180947",
20
+ "7": "021136181364",
21
+ "8": "021136181371",
22
+ "9": "025000058011",
23
+ "10": "03435515",
24
+ "11": "049000003710",
25
+ "12": "049000007909",
26
+ "13": "049000019162",
27
+ "14": "049000040869",
28
+ "15": "049000071542",
29
+ "16": "04904403",
30
+ "17": "04904500",
31
+ "18": "04976400",
32
+ "19": "04997704",
33
+ "20": "070847012474",
34
+ "21": "070847811169",
35
+ "22": "070847898245",
36
+ "23": "071990095451",
37
+ "24": "071990300654",
38
+ "25": "080660956435",
39
+ "26": "080660957210",
40
+ "27": "083783375534",
41
+ "28": "083900005757",
42
+ "29": "083900005771",
43
+ "30": "085000027141",
44
+ "31": "085000028728",
45
+ "32": "085000029275",
46
+ "33": "085000031377",
47
+ "34": "087692832317",
48
+ "35": "786162200433",
49
+ "36": "786162338006",
50
+ "37": "796030250965",
51
+ "38": "810628031474",
52
+ "39": "816751021214",
53
+ "40": "855352008064",
54
+ "41": "857531005284"
55
+ },
56
+ "image_size": 384,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "label2id": {
60
+ "018200250002": 0,
61
+ "018200250019": 1,
62
+ "018200250101": 2,
63
+ "018200261244": 3,
64
+ "01823743": 4,
65
+ "021136180596": 5,
66
+ "021136180947": 6,
67
+ "021136181364": 7,
68
+ "021136181371": 8,
69
+ "025000058011": 9,
70
+ "03435515": 10,
71
+ "049000003710": 11,
72
+ "049000007909": 12,
73
+ "049000019162": 13,
74
+ "049000040869": 14,
75
+ "049000071542": 15,
76
+ "04904403": 16,
77
+ "04904500": 17,
78
+ "04976400": 18,
79
+ "04997704": 19,
80
+ "070847012474": 20,
81
+ "070847811169": 21,
82
+ "070847898245": 22,
83
+ "071990095451": 23,
84
+ "071990300654": 24,
85
+ "080660956435": 25,
86
+ "080660957210": 26,
87
+ "083783375534": 27,
88
+ "083900005757": 28,
89
+ "083900005771": 29,
90
+ "085000027141": 30,
91
+ "085000028728": 31,
92
+ "085000029275": 32,
93
+ "085000031377": 33,
94
+ "087692832317": 34,
95
+ "786162200433": 35,
96
+ "786162338006": 36,
97
+ "796030250965": 37,
98
+ "810628031474": 38,
99
+ "816751021214": 39,
100
+ "855352008064": 40,
101
+ "857531005284": 41
102
+ },
103
+ "layer_norm_eps": 1e-12,
104
+ "model_type": "vit",
105
+ "num_attention_heads": 16,
106
+ "num_channels": 3,
107
+ "num_hidden_layers": 24,
108
+ "patch_size": 32,
109
+ "problem_type": "single_label_classification",
110
+ "qkv_bias": true,
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.48.0"
113
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78df14c9c954d51c6282508096f9385632eb277c1b1c049646a2b3a45a3e5a26
3
+ size 1222649496
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
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 384,
21
+ "width": 384
22
+ }
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5c3f143f2ba661829205959c31c550c9baea9da3ea7c6d3c01754590aa7474
3
+ size 5713
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "project-name/autotrain-data",
3
+ "model": "google/vit-large-patch32-384",
4
+ "username": null,
5
+ "lr": 0.00005,
6
+ "epochs": 3,
7
+ "batch_size": 48,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "logging_steps": -1,
18
+ "project_name": "project-name",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": null,
21
+ "save_total_limit": 1,
22
+ "token": null,
23
+ "push_to_hub": false,
24
+ "eval_strategy": "epoch",
25
+ "image_column": "autotrain_image",
26
+ "target_column": "autotrain_label",
27
+ "log": "none",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }