Upload 8 files
Browse files- config.json +52 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +241 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_first_stage": false,
|
13 |
+
"embedding_size": 64,
|
14 |
+
"hidden_act": "relu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
256,
|
17 |
+
512,
|
18 |
+
1024,
|
19 |
+
2048
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "skinny",
|
23 |
+
"1": "ordinary",
|
24 |
+
"2": "overweight",
|
25 |
+
"3": "hulk"
|
26 |
+
},
|
27 |
+
"label2id": {
|
28 |
+
"hulk": 3,
|
29 |
+
"ordinary": 1,
|
30 |
+
"overweight": 2,
|
31 |
+
"skinny": 0
|
32 |
+
},
|
33 |
+
"layer_type": "bottleneck",
|
34 |
+
"model_type": "resnet",
|
35 |
+
"num_channels": 3,
|
36 |
+
"out_features": [
|
37 |
+
"stage4"
|
38 |
+
],
|
39 |
+
"out_indices": [
|
40 |
+
4
|
41 |
+
],
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"stage_names": [
|
44 |
+
"stem",
|
45 |
+
"stage1",
|
46 |
+
"stage2",
|
47 |
+
"stage3",
|
48 |
+
"stage4"
|
49 |
+
],
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.32.1"
|
52 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3546e497a314a5a0854beb747efe074fcdf7eb96e7c8ce9fc2b0ba889ea93de0
|
3 |
+
size 188260794
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
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": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe719a2cc79442f68d8213ddc917aacf9c0576f46a0a6be189c01bec9dc3508
|
3 |
+
size 94387338
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2aae0eb17ec4030c16f8de59faef22f5c2e1b783205ff8e279aa5a27de09d38a
|
3 |
+
size 13990
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9dc46ed75caf7c13b1c82b2d3080503780b4b6a06d1d538d876480afa99ffe9
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 22.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2354,
|
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": 0.5887850467289719,
|
14 |
+
"eval_loss": 1.2691198587417603,
|
15 |
+
"eval_runtime": 4.8417,
|
16 |
+
"eval_samples_per_second": 44.199,
|
17 |
+
"eval_steps_per_second": 5.577,
|
18 |
+
"step": 107
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6214953271028038,
|
23 |
+
"eval_loss": 1.0963133573532104,
|
24 |
+
"eval_runtime": 5.0021,
|
25 |
+
"eval_samples_per_second": 42.782,
|
26 |
+
"eval_steps_per_second": 5.398,
|
27 |
+
"step": 214
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.6308411214953271,
|
32 |
+
"eval_loss": 0.860569179058075,
|
33 |
+
"eval_runtime": 4.6891,
|
34 |
+
"eval_samples_per_second": 45.638,
|
35 |
+
"eval_steps_per_second": 5.758,
|
36 |
+
"step": 321
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.7990654205607477,
|
41 |
+
"eval_loss": 0.672334611415863,
|
42 |
+
"eval_runtime": 4.717,
|
43 |
+
"eval_samples_per_second": 45.368,
|
44 |
+
"eval_steps_per_second": 5.724,
|
45 |
+
"step": 428
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.67,
|
49 |
+
"learning_rate": 4.0654205607476636e-05,
|
50 |
+
"loss": 1.1331,
|
51 |
+
"step": 500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.0,
|
55 |
+
"eval_accuracy": 0.8457943925233645,
|
56 |
+
"eval_loss": 0.48274144530296326,
|
57 |
+
"eval_runtime": 4.6309,
|
58 |
+
"eval_samples_per_second": 46.212,
|
59 |
+
"eval_steps_per_second": 5.83,
|
60 |
+
"step": 535
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 6.0,
|
64 |
+
"eval_accuracy": 0.8551401869158879,
|
65 |
+
"eval_loss": 0.35962656140327454,
|
66 |
+
"eval_runtime": 4.7112,
|
67 |
+
"eval_samples_per_second": 45.424,
|
68 |
+
"eval_steps_per_second": 5.731,
|
69 |
+
"step": 642
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 7.0,
|
73 |
+
"eval_accuracy": 0.8925233644859814,
|
74 |
+
"eval_loss": 0.26292115449905396,
|
75 |
+
"eval_runtime": 5.4422,
|
76 |
+
"eval_samples_per_second": 39.322,
|
77 |
+
"eval_steps_per_second": 4.961,
|
78 |
+
"step": 749
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 8.0,
|
82 |
+
"eval_accuracy": 0.9158878504672897,
|
83 |
+
"eval_loss": 0.22579917311668396,
|
84 |
+
"eval_runtime": 4.8554,
|
85 |
+
"eval_samples_per_second": 44.074,
|
86 |
+
"eval_steps_per_second": 5.561,
|
87 |
+
"step": 856
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 9.0,
|
91 |
+
"eval_accuracy": 0.9158878504672897,
|
92 |
+
"eval_loss": 0.19785191118717194,
|
93 |
+
"eval_runtime": 4.9901,
|
94 |
+
"eval_samples_per_second": 42.885,
|
95 |
+
"eval_steps_per_second": 5.411,
|
96 |
+
"step": 963
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 9.35,
|
100 |
+
"learning_rate": 3.130841121495327e-05,
|
101 |
+
"loss": 0.6031,
|
102 |
+
"step": 1000
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 10.0,
|
106 |
+
"eval_accuracy": 0.9719626168224299,
|
107 |
+
"eval_loss": 0.16760671138763428,
|
108 |
+
"eval_runtime": 4.8143,
|
109 |
+
"eval_samples_per_second": 44.451,
|
110 |
+
"eval_steps_per_second": 5.608,
|
111 |
+
"step": 1070
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 11.0,
|
115 |
+
"eval_accuracy": 1.0,
|
116 |
+
"eval_loss": 0.1423913985490799,
|
117 |
+
"eval_runtime": 4.7195,
|
118 |
+
"eval_samples_per_second": 45.343,
|
119 |
+
"eval_steps_per_second": 5.721,
|
120 |
+
"step": 1177
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 12.0,
|
124 |
+
"eval_accuracy": 0.985981308411215,
|
125 |
+
"eval_loss": 0.12256418913602829,
|
126 |
+
"eval_runtime": 5.1046,
|
127 |
+
"eval_samples_per_second": 41.923,
|
128 |
+
"eval_steps_per_second": 5.289,
|
129 |
+
"step": 1284
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 13.0,
|
133 |
+
"eval_accuracy": 0.9953271028037384,
|
134 |
+
"eval_loss": 0.11292136460542679,
|
135 |
+
"eval_runtime": 4.8426,
|
136 |
+
"eval_samples_per_second": 44.191,
|
137 |
+
"eval_steps_per_second": 5.576,
|
138 |
+
"step": 1391
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 14.0,
|
142 |
+
"eval_accuracy": 0.9906542056074766,
|
143 |
+
"eval_loss": 0.106930673122406,
|
144 |
+
"eval_runtime": 4.9097,
|
145 |
+
"eval_samples_per_second": 43.587,
|
146 |
+
"eval_steps_per_second": 5.499,
|
147 |
+
"step": 1498
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 14.02,
|
151 |
+
"learning_rate": 2.196261682242991e-05,
|
152 |
+
"loss": 0.4317,
|
153 |
+
"step": 1500
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 15.0,
|
157 |
+
"eval_accuracy": 0.9953271028037384,
|
158 |
+
"eval_loss": 0.09224073588848114,
|
159 |
+
"eval_runtime": 4.854,
|
160 |
+
"eval_samples_per_second": 44.087,
|
161 |
+
"eval_steps_per_second": 5.562,
|
162 |
+
"step": 1605
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 16.0,
|
166 |
+
"eval_accuracy": 0.9953271028037384,
|
167 |
+
"eval_loss": 0.08621260523796082,
|
168 |
+
"eval_runtime": 4.7695,
|
169 |
+
"eval_samples_per_second": 44.868,
|
170 |
+
"eval_steps_per_second": 5.661,
|
171 |
+
"step": 1712
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 17.0,
|
175 |
+
"eval_accuracy": 1.0,
|
176 |
+
"eval_loss": 0.07688089460134506,
|
177 |
+
"eval_runtime": 4.8878,
|
178 |
+
"eval_samples_per_second": 43.782,
|
179 |
+
"eval_steps_per_second": 5.524,
|
180 |
+
"step": 1819
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 18.0,
|
184 |
+
"eval_accuracy": 1.0,
|
185 |
+
"eval_loss": 0.061450209468603134,
|
186 |
+
"eval_runtime": 4.7171,
|
187 |
+
"eval_samples_per_second": 45.367,
|
188 |
+
"eval_steps_per_second": 5.724,
|
189 |
+
"step": 1926
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 18.69,
|
193 |
+
"learning_rate": 1.2616822429906542e-05,
|
194 |
+
"loss": 0.3584,
|
195 |
+
"step": 2000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 19.0,
|
199 |
+
"eval_accuracy": 1.0,
|
200 |
+
"eval_loss": 0.0667119175195694,
|
201 |
+
"eval_runtime": 4.8093,
|
202 |
+
"eval_samples_per_second": 44.498,
|
203 |
+
"eval_steps_per_second": 5.614,
|
204 |
+
"step": 2033
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 20.0,
|
208 |
+
"eval_accuracy": 0.9953271028037384,
|
209 |
+
"eval_loss": 0.05547282472252846,
|
210 |
+
"eval_runtime": 4.7518,
|
211 |
+
"eval_samples_per_second": 45.036,
|
212 |
+
"eval_steps_per_second": 5.682,
|
213 |
+
"step": 2140
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 21.0,
|
217 |
+
"eval_accuracy": 1.0,
|
218 |
+
"eval_loss": 0.054027605801820755,
|
219 |
+
"eval_runtime": 4.7251,
|
220 |
+
"eval_samples_per_second": 45.29,
|
221 |
+
"eval_steps_per_second": 5.714,
|
222 |
+
"step": 2247
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 22.0,
|
226 |
+
"eval_accuracy": 1.0,
|
227 |
+
"eval_loss": 0.04496881738305092,
|
228 |
+
"eval_runtime": 4.6636,
|
229 |
+
"eval_samples_per_second": 45.887,
|
230 |
+
"eval_steps_per_second": 5.79,
|
231 |
+
"step": 2354
|
232 |
+
}
|
233 |
+
],
|
234 |
+
"logging_steps": 500,
|
235 |
+
"max_steps": 2675,
|
236 |
+
"num_train_epochs": 25,
|
237 |
+
"save_steps": 200,
|
238 |
+
"total_flos": 3.9904029741839155e+17,
|
239 |
+
"trial_name": null,
|
240 |
+
"trial_params": null
|
241 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f4adf1f1ac0a22b0edea63f1c021c30c1d5c157a49322bc4e73ffb74a7fc9f0
|
3 |
+
size 4472
|