Upload 8 files
Browse files- config.json +60 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +259 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bit-50",
|
3 |
+
"architectures": [
|
4 |
+
"BitForImageClassification"
|
5 |
+
],
|
6 |
+
"conv_layer": "std_conv",
|
7 |
+
"depths": [
|
8 |
+
3,
|
9 |
+
4,
|
10 |
+
6,
|
11 |
+
3
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.0,
|
14 |
+
"embedding_dynamic_padding": false,
|
15 |
+
"embedding_size": 64,
|
16 |
+
"global_padding": null,
|
17 |
+
"hidden_act": "relu",
|
18 |
+
"hidden_sizes": [
|
19 |
+
256,
|
20 |
+
512,
|
21 |
+
1024,
|
22 |
+
2048
|
23 |
+
],
|
24 |
+
"id2label": {
|
25 |
+
"0": "a_noDR",
|
26 |
+
"1": "b_mildDR",
|
27 |
+
"2": "c_moderateDR",
|
28 |
+
"3": "d_severeDR",
|
29 |
+
"4": "e_proDR"
|
30 |
+
},
|
31 |
+
"label2id": {
|
32 |
+
"a_noDR": 0,
|
33 |
+
"b_mildDR": 1,
|
34 |
+
"c_moderateDR": 2,
|
35 |
+
"d_severeDR": 3,
|
36 |
+
"e_proDR": 4
|
37 |
+
},
|
38 |
+
"layer_type": "preactivation",
|
39 |
+
"model_type": "bit",
|
40 |
+
"num_channels": 3,
|
41 |
+
"num_groups": 32,
|
42 |
+
"out_features": [
|
43 |
+
"stage4"
|
44 |
+
],
|
45 |
+
"out_indices": [
|
46 |
+
4
|
47 |
+
],
|
48 |
+
"output_stride": 32,
|
49 |
+
"problem_type": "single_label_classification",
|
50 |
+
"stage_names": [
|
51 |
+
"stem",
|
52 |
+
"stage1",
|
53 |
+
"stage2",
|
54 |
+
"stage3",
|
55 |
+
"stage4"
|
56 |
+
],
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.31.0",
|
59 |
+
"width_factor": 1
|
60 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfaa04e0287febdd52ab31d966ac470302c9ee058754b2b0525db98becf8e48
|
3 |
+
size 188175045
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 448,
|
4 |
+
"width": 448
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"image_processor_type": "BitImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.5,
|
19 |
+
0.5,
|
20 |
+
0.5
|
21 |
+
],
|
22 |
+
"resample": 2,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 448
|
26 |
+
}
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d9f02a984224e4d4ef1e10a85186efaca979d7daae7dc8dc72aedb8e48d03c
|
3 |
+
size 94094001
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7833b3e0f8d87f66e34fef179b6a3a4da203b99279006279834806298225e358
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aba249e3524da66e87146578505b69c91f821996a2468f2fa2830a27d61ed65
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6310679611650486,
|
3 |
+
"best_model_checkpoint": "bit-50-IDRiD\\checkpoint-37",
|
4 |
+
"epoch": 24.666666666666668,
|
5 |
+
"global_step": 37,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.67,
|
12 |
+
"eval_accuracy": 0.1650485436893204,
|
13 |
+
"eval_loss": 2.3867640495300293,
|
14 |
+
"eval_runtime": 9.4798,
|
15 |
+
"eval_samples_per_second": 10.865,
|
16 |
+
"eval_steps_per_second": 0.211,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.5242718446601942,
|
22 |
+
"eval_loss": 1.456685185432434,
|
23 |
+
"eval_runtime": 8.8435,
|
24 |
+
"eval_samples_per_second": 11.647,
|
25 |
+
"eval_steps_per_second": 0.226,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.67,
|
30 |
+
"eval_accuracy": 0.3106796116504854,
|
31 |
+
"eval_loss": 1.688151240348816,
|
32 |
+
"eval_runtime": 9.0288,
|
33 |
+
"eval_samples_per_second": 11.408,
|
34 |
+
"eval_steps_per_second": 0.222,
|
35 |
+
"step": 4
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.42718446601941745,
|
40 |
+
"eval_loss": 1.3363385200500488,
|
41 |
+
"eval_runtime": 8.6671,
|
42 |
+
"eval_samples_per_second": 11.884,
|
43 |
+
"eval_steps_per_second": 0.231,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.67,
|
48 |
+
"eval_accuracy": 0.44660194174757284,
|
49 |
+
"eval_loss": 1.308953881263733,
|
50 |
+
"eval_runtime": 8.7719,
|
51 |
+
"eval_samples_per_second": 11.742,
|
52 |
+
"eval_steps_per_second": 0.228,
|
53 |
+
"step": 7
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 6.0,
|
57 |
+
"eval_accuracy": 0.5339805825242718,
|
58 |
+
"eval_loss": 1.2151198387145996,
|
59 |
+
"eval_runtime": 8.9493,
|
60 |
+
"eval_samples_per_second": 11.509,
|
61 |
+
"eval_steps_per_second": 0.223,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 6.67,
|
66 |
+
"learning_rate": 4.4444444444444447e-05,
|
67 |
+
"loss": 1.5527,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 6.67,
|
72 |
+
"eval_accuracy": 0.49514563106796117,
|
73 |
+
"eval_loss": 1.2200932502746582,
|
74 |
+
"eval_runtime": 9.0152,
|
75 |
+
"eval_samples_per_second": 11.425,
|
76 |
+
"eval_steps_per_second": 0.222,
|
77 |
+
"step": 10
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 8.0,
|
81 |
+
"eval_accuracy": 0.5533980582524272,
|
82 |
+
"eval_loss": 1.131609320640564,
|
83 |
+
"eval_runtime": 9.0143,
|
84 |
+
"eval_samples_per_second": 11.426,
|
85 |
+
"eval_steps_per_second": 0.222,
|
86 |
+
"step": 12
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 8.67,
|
90 |
+
"eval_accuracy": 0.5728155339805825,
|
91 |
+
"eval_loss": 1.1541801691055298,
|
92 |
+
"eval_runtime": 8.744,
|
93 |
+
"eval_samples_per_second": 11.779,
|
94 |
+
"eval_steps_per_second": 0.229,
|
95 |
+
"step": 13
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 10.0,
|
99 |
+
"eval_accuracy": 0.47572815533980584,
|
100 |
+
"eval_loss": 1.2354609966278076,
|
101 |
+
"eval_runtime": 8.8063,
|
102 |
+
"eval_samples_per_second": 11.696,
|
103 |
+
"eval_steps_per_second": 0.227,
|
104 |
+
"step": 15
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 10.67,
|
108 |
+
"eval_accuracy": 0.5728155339805825,
|
109 |
+
"eval_loss": 1.0986073017120361,
|
110 |
+
"eval_runtime": 8.837,
|
111 |
+
"eval_samples_per_second": 11.656,
|
112 |
+
"eval_steps_per_second": 0.226,
|
113 |
+
"step": 16
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 12.0,
|
117 |
+
"eval_accuracy": 0.5728155339805825,
|
118 |
+
"eval_loss": 1.1264944076538086,
|
119 |
+
"eval_runtime": 8.8171,
|
120 |
+
"eval_samples_per_second": 11.682,
|
121 |
+
"eval_steps_per_second": 0.227,
|
122 |
+
"step": 18
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 12.67,
|
126 |
+
"eval_accuracy": 0.5242718446601942,
|
127 |
+
"eval_loss": 1.1883245706558228,
|
128 |
+
"eval_runtime": 8.8398,
|
129 |
+
"eval_samples_per_second": 11.652,
|
130 |
+
"eval_steps_per_second": 0.226,
|
131 |
+
"step": 19
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 13.33,
|
135 |
+
"learning_rate": 3.3333333333333335e-05,
|
136 |
+
"loss": 0.8728,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 14.0,
|
141 |
+
"eval_accuracy": 0.5922330097087378,
|
142 |
+
"eval_loss": 1.0414934158325195,
|
143 |
+
"eval_runtime": 8.8456,
|
144 |
+
"eval_samples_per_second": 11.644,
|
145 |
+
"eval_steps_per_second": 0.226,
|
146 |
+
"step": 21
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 14.67,
|
150 |
+
"eval_accuracy": 0.6213592233009708,
|
151 |
+
"eval_loss": 1.0244377851486206,
|
152 |
+
"eval_runtime": 8.8085,
|
153 |
+
"eval_samples_per_second": 11.693,
|
154 |
+
"eval_steps_per_second": 0.227,
|
155 |
+
"step": 22
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 16.0,
|
159 |
+
"eval_accuracy": 0.5728155339805825,
|
160 |
+
"eval_loss": 1.0664492845535278,
|
161 |
+
"eval_runtime": 9.0371,
|
162 |
+
"eval_samples_per_second": 11.397,
|
163 |
+
"eval_steps_per_second": 0.221,
|
164 |
+
"step": 24
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 16.67,
|
168 |
+
"eval_accuracy": 0.6019417475728155,
|
169 |
+
"eval_loss": 1.1014405488967896,
|
170 |
+
"eval_runtime": 8.9067,
|
171 |
+
"eval_samples_per_second": 11.564,
|
172 |
+
"eval_steps_per_second": 0.225,
|
173 |
+
"step": 25
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 18.0,
|
177 |
+
"eval_accuracy": 0.5533980582524272,
|
178 |
+
"eval_loss": 1.1310096979141235,
|
179 |
+
"eval_runtime": 9.404,
|
180 |
+
"eval_samples_per_second": 10.953,
|
181 |
+
"eval_steps_per_second": 0.213,
|
182 |
+
"step": 27
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 18.67,
|
186 |
+
"eval_accuracy": 0.6019417475728155,
|
187 |
+
"eval_loss": 1.1294002532958984,
|
188 |
+
"eval_runtime": 8.9554,
|
189 |
+
"eval_samples_per_second": 11.501,
|
190 |
+
"eval_steps_per_second": 0.223,
|
191 |
+
"step": 28
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 20.0,
|
195 |
+
"learning_rate": 2.2222222222222223e-05,
|
196 |
+
"loss": 0.6827,
|
197 |
+
"step": 30
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 20.0,
|
201 |
+
"eval_accuracy": 0.5922330097087378,
|
202 |
+
"eval_loss": 1.1656121015548706,
|
203 |
+
"eval_runtime": 8.789,
|
204 |
+
"eval_samples_per_second": 11.719,
|
205 |
+
"eval_steps_per_second": 0.228,
|
206 |
+
"step": 30
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 20.67,
|
210 |
+
"eval_accuracy": 0.6116504854368932,
|
211 |
+
"eval_loss": 1.1699755191802979,
|
212 |
+
"eval_runtime": 9.0412,
|
213 |
+
"eval_samples_per_second": 11.392,
|
214 |
+
"eval_steps_per_second": 0.221,
|
215 |
+
"step": 31
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 22.0,
|
219 |
+
"eval_accuracy": 0.6116504854368932,
|
220 |
+
"eval_loss": 1.1977097988128662,
|
221 |
+
"eval_runtime": 8.8963,
|
222 |
+
"eval_samples_per_second": 11.578,
|
223 |
+
"eval_steps_per_second": 0.225,
|
224 |
+
"step": 33
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 22.67,
|
228 |
+
"eval_accuracy": 0.5825242718446602,
|
229 |
+
"eval_loss": 1.1683080196380615,
|
230 |
+
"eval_runtime": 9.0689,
|
231 |
+
"eval_samples_per_second": 11.358,
|
232 |
+
"eval_steps_per_second": 0.221,
|
233 |
+
"step": 34
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 24.0,
|
237 |
+
"eval_accuracy": 0.6116504854368932,
|
238 |
+
"eval_loss": 1.1035082340240479,
|
239 |
+
"eval_runtime": 8.6561,
|
240 |
+
"eval_samples_per_second": 11.899,
|
241 |
+
"eval_steps_per_second": 0.231,
|
242 |
+
"step": 36
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 24.67,
|
246 |
+
"eval_accuracy": 0.6310679611650486,
|
247 |
+
"eval_loss": 1.1037455797195435,
|
248 |
+
"eval_runtime": 8.9451,
|
249 |
+
"eval_samples_per_second": 11.515,
|
250 |
+
"eval_steps_per_second": 0.224,
|
251 |
+
"step": 37
|
252 |
+
}
|
253 |
+
],
|
254 |
+
"max_steps": 50,
|
255 |
+
"num_train_epochs": 50,
|
256 |
+
"total_flos": 6.985992208656384e+17,
|
257 |
+
"trial_name": null,
|
258 |
+
"trial_params": null
|
259 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4faa316678ab2b32c8e28cd2199bcc28a8a35bb5cba5dd305375a984b9e512f
|
3 |
+
size 4027
|