Hugging Face's logo

dima806
/
sea_animals_image_detection

Image Classification
Transformers
PyTorch
vit
Inference Endpoints
Model card Files Community
dima806 commited on
Commit
cb713ad
•
1 Parent(s): a119cb1

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-6840/config.json +74 -0
  2. checkpoint-6840/optimizer.pt +3 -0
  3. checkpoint-6840/preprocessor_config.json +22 -0
  4. checkpoint-6840/pytorch_model.bin +3 -0
  5. checkpoint-6840/rng_state.pth +3 -0
  6. checkpoint-6840/scheduler.pt +3 -0
  7. checkpoint-6840/trainer_state.json +277 -0
  8. checkpoint-6840/training_args.bin +3 -0
  9. config.json +74 -0
  10. preprocessor_config.json +22 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-6840/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "Squid",
13
+ "1": "Eel",
14
+ "2": "Seal",
15
+ "3": "Octopus",
16
+ "4": "Otter",
17
+ "5": "Whale",
18
+ "6": "Sharks",
19
+ "7": "Jelly Fish",
20
+ "8": "Turtle_Tortoise",
21
+ "9": "Penguin",
22
+ "10": "Shrimp",
23
+ "11": "Sea Urchins",
24
+ "12": "Fish",
25
+ "13": "Nudibranchs",
26
+ "14": "Corals",
27
+ "15": "Puffers",
28
+ "16": "Clams",
29
+ "17": "Sea Rays",
30
+ "18": "Dolphin",
31
+ "19": "Seahorse",
32
+ "20": "Starfish",
33
+ "21": "Lobster",
34
+ "22": "Crabs"
35
+ },
36
+ "image_size": 224,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "Clams": 16,
41
+ "Corals": 14,
42
+ "Crabs": 22,
43
+ "Dolphin": 18,
44
+ "Eel": 1,
45
+ "Fish": 12,
46
+ "Jelly Fish": 7,
47
+ "Lobster": 21,
48
+ "Nudibranchs": 13,
49
+ "Octopus": 3,
50
+ "Otter": 4,
51
+ "Penguin": 9,
52
+ "Puffers": 15,
53
+ "Sea Rays": 17,
54
+ "Sea Urchins": 11,
55
+ "Seahorse": 19,
56
+ "Seal": 2,
57
+ "Sharks": 6,
58
+ "Shrimp": 10,
59
+ "Squid": 0,
60
+ "Starfish": 20,
61
+ "Turtle_Tortoise": 8,
62
+ "Whale": 5
63
+ },
64
+ "layer_norm_eps": 1e-12,
65
+ "model_type": "vit",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "problem_type": "single_label_classification",
71
+ "qkv_bias": true,
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.32.1"
74
+ }
checkpoint-6840/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e91eb5fdf63352f8c2fa0c5ea9147dd01e98e09052e1a51d7609b3993ec145
3
+ size 686697605
checkpoint-6840/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
checkpoint-6840/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa4d2806b5e71b251941eab55df5269a40e5b56aea8ab014d79154ec51cd8d4
3
+ size 343333293
checkpoint-6840/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6725a5eae0f422cbf0507c36b31f45fc5bb2d9aff601d121e947ad6e6bacbea
3
+ size 14575
checkpoint-6840/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87bff0d7bcb5321252f7116c82215f25597c2f863981984aae637fa80c95d8b
3
+ size 627
checkpoint-6840/trainer_state.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44989213347435,
3
+ "best_model_checkpoint": "sea_animals_image_detection/checkpoint-6840",
4
+ "epoch": 20.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6840,
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
+ "eval_accuracy": 0.7951719092904169,
14
+ "eval_loss": 2.152780294418335,
15
+ "eval_runtime": 27.056,
16
+ "eval_samples_per_second": 101.05,
17
+ "eval_steps_per_second": 12.64,
18
+ "step": 342
19
+ },
20
+ {
21
+ "epoch": 1.46,
22
+ "learning_rate": 9.470588235294119e-06,
23
+ "loss": 2.4104,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.8555230431602048,
29
+ "eval_loss": 1.5588719844818115,
30
+ "eval_runtime": 26.6265,
31
+ "eval_samples_per_second": 102.68,
32
+ "eval_steps_per_second": 12.844,
33
+ "step": 684
34
+ },
35
+ {
36
+ "epoch": 2.92,
37
+ "learning_rate": 8.88235294117647e-06,
38
+ "loss": 1.4121,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_accuracy": 0.8822238478419897,
44
+ "eval_loss": 1.2037461996078491,
45
+ "eval_runtime": 26.9677,
46
+ "eval_samples_per_second": 101.381,
47
+ "eval_steps_per_second": 12.682,
48
+ "step": 1026
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_accuracy": 0.8935625457205559,
53
+ "eval_loss": 0.9822039008140564,
54
+ "eval_runtime": 26.4016,
55
+ "eval_samples_per_second": 103.555,
56
+ "eval_steps_per_second": 12.954,
57
+ "step": 1368
58
+ },
59
+ {
60
+ "epoch": 4.39,
61
+ "learning_rate": 8.294117647058825e-06,
62
+ "loss": 0.9335,
63
+ "step": 1500
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "eval_accuracy": 0.9041697147037308,
68
+ "eval_loss": 0.8228352665901184,
69
+ "eval_runtime": 27.2507,
70
+ "eval_samples_per_second": 100.328,
71
+ "eval_steps_per_second": 12.55,
72
+ "step": 1710
73
+ },
74
+ {
75
+ "epoch": 5.85,
76
+ "learning_rate": 7.705882352941178e-06,
77
+ "loss": 0.6607,
78
+ "step": 2000
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "eval_accuracy": 0.9012435991221653,
83
+ "eval_loss": 0.7257607579231262,
84
+ "eval_runtime": 26.6826,
85
+ "eval_samples_per_second": 102.464,
86
+ "eval_steps_per_second": 12.817,
87
+ "step": 2052
88
+ },
89
+ {
90
+ "epoch": 7.0,
91
+ "eval_accuracy": 0.9030724213606437,
92
+ "eval_loss": 0.6461441516876221,
93
+ "eval_runtime": 26.5418,
94
+ "eval_samples_per_second": 103.007,
95
+ "eval_steps_per_second": 12.885,
96
+ "step": 2394
97
+ },
98
+ {
99
+ "epoch": 7.31,
100
+ "learning_rate": 7.11764705882353e-06,
101
+ "loss": 0.485,
102
+ "step": 2500
103
+ },
104
+ {
105
+ "epoch": 8.0,
106
+ "eval_accuracy": 0.9034381858083395,
107
+ "eval_loss": 0.5806209444999695,
108
+ "eval_runtime": 28.3386,
109
+ "eval_samples_per_second": 96.476,
110
+ "eval_steps_per_second": 12.068,
111
+ "step": 2736
112
+ },
113
+ {
114
+ "epoch": 8.77,
115
+ "learning_rate": 6.529411764705883e-06,
116
+ "loss": 0.3676,
117
+ "step": 3000
118
+ },
119
+ {
120
+ "epoch": 9.0,
121
+ "eval_accuracy": 0.8994147768836869,
122
+ "eval_loss": 0.5495482087135315,
123
+ "eval_runtime": 28.0784,
124
+ "eval_samples_per_second": 97.37,
125
+ "eval_steps_per_second": 12.18,
126
+ "step": 3078
127
+ },
128
+ {
129
+ "epoch": 10.0,
130
+ "eval_accuracy": 0.9019751280175567,
131
+ "eval_loss": 0.5101125240325928,
132
+ "eval_runtime": 26.8282,
133
+ "eval_samples_per_second": 101.908,
134
+ "eval_steps_per_second": 12.748,
135
+ "step": 3420
136
+ },
137
+ {
138
+ "epoch": 10.23,
139
+ "learning_rate": 5.941176470588236e-06,
140
+ "loss": 0.2796,
141
+ "step": 3500
142
+ },
143
+ {
144
+ "epoch": 11.0,
145
+ "eval_accuracy": 0.8997805413313826,
146
+ "eval_loss": 0.4954698383808136,
147
+ "eval_runtime": 29.3485,
148
+ "eval_samples_per_second": 93.156,
149
+ "eval_steps_per_second": 11.653,
150
+ "step": 3762
151
+ },
152
+ {
153
+ "epoch": 11.7,
154
+ "learning_rate": 5.352941176470589e-06,
155
+ "loss": 0.2236,
156
+ "step": 4000
157
+ },
158
+ {
159
+ "epoch": 12.0,
160
+ "eval_accuracy": 0.9012435991221653,
161
+ "eval_loss": 0.4771639108657837,
162
+ "eval_runtime": 26.8132,
163
+ "eval_samples_per_second": 101.965,
164
+ "eval_steps_per_second": 12.755,
165
+ "step": 4104
166
+ },
167
+ {
168
+ "epoch": 13.0,
169
+ "eval_accuracy": 0.8979517190929042,
170
+ "eval_loss": 0.47096940875053406,
171
+ "eval_runtime": 27.6019,
172
+ "eval_samples_per_second": 99.051,
173
+ "eval_steps_per_second": 12.39,
174
+ "step": 4446
175
+ },
176
+ {
177
+ "epoch": 13.16,
178
+ "learning_rate": 4.764705882352941e-06,
179
+ "loss": 0.1847,
180
+ "step": 4500
181
+ },
182
+ {
183
+ "epoch": 14.0,
184
+ "eval_accuracy": 0.8986832479882956,
185
+ "eval_loss": 0.46488723158836365,
186
+ "eval_runtime": 28.4412,
187
+ "eval_samples_per_second": 96.128,
188
+ "eval_steps_per_second": 12.025,
189
+ "step": 4788
190
+ },
191
+ {
192
+ "epoch": 14.62,
193
+ "learning_rate": 4.176470588235295e-06,
194
+ "loss": 0.1505,
195
+ "step": 5000
196
+ },
197
+ {
198
+ "epoch": 15.0,
199
+ "eval_accuracy": 0.9008778346744697,
200
+ "eval_loss": 0.455506831407547,
201
+ "eval_runtime": 27.2614,
202
+ "eval_samples_per_second": 100.288,
203
+ "eval_steps_per_second": 12.545,
204
+ "step": 5130
205
+ },
206
+ {
207
+ "epoch": 16.0,
208
+ "eval_accuracy": 0.8990490124359912,
209
+ "eval_loss": 0.4557651877403259,
210
+ "eval_runtime": 26.9577,
211
+ "eval_samples_per_second": 101.418,
212
+ "eval_steps_per_second": 12.687,
213
+ "step": 5472
214
+ },
215
+ {
216
+ "epoch": 16.08,
217
+ "learning_rate": 3.5882352941176475e-06,
218
+ "loss": 0.129,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 17.0,
223
+ "eval_accuracy": 0.9023408924652524,
224
+ "eval_loss": 0.45066457986831665,
225
+ "eval_runtime": 27.4851,
226
+ "eval_samples_per_second": 99.472,
227
+ "eval_steps_per_second": 12.443,
228
+ "step": 5814
229
+ },
230
+ {
231
+ "epoch": 17.54,
232
+ "learning_rate": 3e-06,
233
+ "loss": 0.1116,
234
+ "step": 6000
235
+ },
236
+ {
237
+ "epoch": 18.0,
238
+ "eval_accuracy": 0.8983174835405998,
239
+ "eval_loss": 0.4530565142631531,
240
+ "eval_runtime": 27.2399,
241
+ "eval_samples_per_second": 100.368,
242
+ "eval_steps_per_second": 12.555,
243
+ "step": 6156
244
+ },
245
+ {
246
+ "epoch": 19.0,
247
+ "eval_accuracy": 0.8986832479882956,
248
+ "eval_loss": 0.45476871728897095,
249
+ "eval_runtime": 27.1006,
250
+ "eval_samples_per_second": 100.883,
251
+ "eval_steps_per_second": 12.62,
252
+ "step": 6498
253
+ },
254
+ {
255
+ "epoch": 19.01,
256
+ "learning_rate": 2.411764705882353e-06,
257
+ "loss": 0.0964,
258
+ "step": 6500
259
+ },
260
+ {
261
+ "epoch": 20.0,
262
+ "eval_accuracy": 0.8997805413313826,
263
+ "eval_loss": 0.44989213347435,
264
+ "eval_runtime": 27.224,
265
+ "eval_samples_per_second": 100.426,
266
+ "eval_steps_per_second": 12.562,
267
+ "step": 6840
268
+ }
269
+ ],
270
+ "logging_steps": 500,
271
+ "max_steps": 8550,
272
+ "num_train_epochs": 25,
273
+ "save_steps": 500,
274
+ "total_flos": 1.6946037530587791e+19,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }
checkpoint-6840/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c66b736dab6c6a050d63c8cc850fb2118ef53cd6851afbdcf7cad252fc6d303
3
+ size 4027
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "Squid",
13
+ "1": "Eel",
14
+ "2": "Seal",
15
+ "3": "Octopus",
16
+ "4": "Otter",
17
+ "5": "Whale",
18
+ "6": "Sharks",
19
+ "7": "Jelly Fish",
20
+ "8": "Turtle_Tortoise",
21
+ "9": "Penguin",
22
+ "10": "Shrimp",
23
+ "11": "Sea Urchins",
24
+ "12": "Fish",
25
+ "13": "Nudibranchs",
26
+ "14": "Corals",
27
+ "15": "Puffers",
28
+ "16": "Clams",
29
+ "17": "Sea Rays",
30
+ "18": "Dolphin",
31
+ "19": "Seahorse",
32
+ "20": "Starfish",
33
+ "21": "Lobster",
34
+ "22": "Crabs"
35
+ },
36
+ "image_size": 224,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "Clams": 16,
41
+ "Corals": 14,
42
+ "Crabs": 22,
43
+ "Dolphin": 18,
44
+ "Eel": 1,
45
+ "Fish": 12,
46
+ "Jelly Fish": 7,
47
+ "Lobster": 21,
48
+ "Nudibranchs": 13,
49
+ "Octopus": 3,
50
+ "Otter": 4,
51
+ "Penguin": 9,
52
+ "Puffers": 15,
53
+ "Sea Rays": 17,
54
+ "Sea Urchins": 11,
55
+ "Seahorse": 19,
56
+ "Seal": 2,
57
+ "Sharks": 6,
58
+ "Shrimp": 10,
59
+ "Squid": 0,
60
+ "Starfish": 20,
61
+ "Turtle_Tortoise": 8,
62
+ "Whale": 5
63
+ },
64
+ "layer_norm_eps": 1e-12,
65
+ "model_type": "vit",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "problem_type": "single_label_classification",
71
+ "qkv_bias": true,
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.32.1"
74
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa4d2806b5e71b251941eab55df5269a40e5b56aea8ab014d79154ec51cd8d4
3
+ size 343333293
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c66b736dab6c6a050d63c8cc850fb2118ef53cd6851afbdcf7cad252fc6d303
3
+ size 4027