Upload 7 files
Browse files- all_results.json +12 -0
- config.json +1 -1
- eval_results.json +8 -0
- preprocessor_config.json +29 -0
- train_results.json +7 -0
- trainer_state.json +205 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_accuracy": 0.7469458987783595,
|
4 |
+
"eval_loss": 0.5715910792350769,
|
5 |
+
"eval_runtime": 9.5739,
|
6 |
+
"eval_samples_per_second": 59.85,
|
7 |
+
"eval_steps_per_second": 1.88,
|
8 |
+
"train_loss": 0.5655017614364624,
|
9 |
+
"train_runtime": 483.5766,
|
10 |
+
"train_samples_per_second": 31.962,
|
11 |
+
"train_steps_per_second": 0.248
|
12 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "salt/beit-bestimage
|
3 |
"architectures": [
|
4 |
"BeitForImageClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "salt/beit-bestimage",
|
3 |
"architectures": [
|
4 |
"BeitForImageClassification"
|
5 |
],
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_accuracy": 0.7469458987783595,
|
4 |
+
"eval_loss": 0.5715910792350769,
|
5 |
+
"eval_runtime": 9.5739,
|
6 |
+
"eval_samples_per_second": 59.85,
|
7 |
+
"eval_steps_per_second": 1.88
|
8 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": false,
|
7 |
+
"do_normalize": true,
|
8 |
+
"do_reduce_labels": false,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "BeitFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"image_processor_type": "BeitFeatureExtractor",
|
18 |
+
"image_std": [
|
19 |
+
0.5,
|
20 |
+
0.5,
|
21 |
+
0.5
|
22 |
+
],
|
23 |
+
"resample": 2,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"height": 384,
|
27 |
+
"width": 384
|
28 |
+
}
|
29 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"train_loss": 0.5655017614364624,
|
4 |
+
"train_runtime": 483.5766,
|
5 |
+
"train_samples_per_second": 31.962,
|
6 |
+
"train_steps_per_second": 0.248
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.981366459627329,
|
5 |
+
"global_step": 120,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.25,
|
12 |
+
"learning_rate": 4.166666666666667e-05,
|
13 |
+
"loss": 0.6218,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.25,
|
18 |
+
"eval_accuracy": 0.7417102966841187,
|
19 |
+
"eval_loss": 0.573567271232605,
|
20 |
+
"eval_runtime": 9.2285,
|
21 |
+
"eval_samples_per_second": 62.09,
|
22 |
+
"eval_steps_per_second": 1.95,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5,
|
27 |
+
"learning_rate": 4.9326121764495596e-05,
|
28 |
+
"loss": 0.6103,
|
29 |
+
"step": 20
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.5,
|
33 |
+
"eval_accuracy": 0.7399650959860384,
|
34 |
+
"eval_loss": 0.5730276703834534,
|
35 |
+
"eval_runtime": 9.2303,
|
36 |
+
"eval_samples_per_second": 62.078,
|
37 |
+
"eval_steps_per_second": 1.95,
|
38 |
+
"step": 20
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.75,
|
42 |
+
"learning_rate": 4.665063509461097e-05,
|
43 |
+
"loss": 0.6105,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.75,
|
48 |
+
"eval_accuracy": 0.7277486910994765,
|
49 |
+
"eval_loss": 0.5863298177719116,
|
50 |
+
"eval_runtime": 9.2823,
|
51 |
+
"eval_samples_per_second": 61.73,
|
52 |
+
"eval_steps_per_second": 1.939,
|
53 |
+
"step": 30
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.99,
|
57 |
+
"learning_rate": 4.215604094671835e-05,
|
58 |
+
"loss": 0.6261,
|
59 |
+
"step": 40
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.99,
|
63 |
+
"eval_accuracy": 0.7068062827225131,
|
64 |
+
"eval_loss": 0.5964760184288025,
|
65 |
+
"eval_runtime": 9.2516,
|
66 |
+
"eval_samples_per_second": 61.935,
|
67 |
+
"eval_steps_per_second": 1.946,
|
68 |
+
"step": 40
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.24,
|
72 |
+
"learning_rate": 3.621997950501156e-05,
|
73 |
+
"loss": 0.5684,
|
74 |
+
"step": 50
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.24,
|
78 |
+
"eval_accuracy": 0.7521815008726004,
|
79 |
+
"eval_loss": 0.567564845085144,
|
80 |
+
"eval_runtime": 10.2074,
|
81 |
+
"eval_samples_per_second": 56.136,
|
82 |
+
"eval_steps_per_second": 1.763,
|
83 |
+
"step": 50
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.49,
|
87 |
+
"learning_rate": 2.9341204441673266e-05,
|
88 |
+
"loss": 0.5878,
|
89 |
+
"step": 60
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.49,
|
93 |
+
"eval_accuracy": 0.6561954624781849,
|
94 |
+
"eval_loss": 0.6583427786827087,
|
95 |
+
"eval_runtime": 9.2811,
|
96 |
+
"eval_samples_per_second": 61.739,
|
97 |
+
"eval_steps_per_second": 1.939,
|
98 |
+
"step": 60
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.74,
|
102 |
+
"learning_rate": 2.2097677146869242e-05,
|
103 |
+
"loss": 0.5274,
|
104 |
+
"step": 70
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.74,
|
108 |
+
"eval_accuracy": 0.7521815008726004,
|
109 |
+
"eval_loss": 0.5735621452331543,
|
110 |
+
"eval_runtime": 9.3011,
|
111 |
+
"eval_samples_per_second": 61.605,
|
112 |
+
"eval_steps_per_second": 1.935,
|
113 |
+
"step": 70
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.99,
|
117 |
+
"learning_rate": 1.509800584902108e-05,
|
118 |
+
"loss": 0.581,
|
119 |
+
"step": 80
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.99,
|
123 |
+
"eval_accuracy": 0.7399650959860384,
|
124 |
+
"eval_loss": 0.5575574636459351,
|
125 |
+
"eval_runtime": 9.3052,
|
126 |
+
"eval_samples_per_second": 61.579,
|
127 |
+
"eval_steps_per_second": 1.934,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.24,
|
132 |
+
"learning_rate": 8.930309757836517e-06,
|
133 |
+
"loss": 0.527,
|
134 |
+
"step": 90
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.24,
|
138 |
+
"eval_accuracy": 0.7539267015706806,
|
139 |
+
"eval_loss": 0.5575008988380432,
|
140 |
+
"eval_runtime": 9.355,
|
141 |
+
"eval_samples_per_second": 61.251,
|
142 |
+
"eval_steps_per_second": 1.924,
|
143 |
+
"step": 90
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.48,
|
147 |
+
"learning_rate": 4.112804714676594e-06,
|
148 |
+
"loss": 0.5228,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.48,
|
153 |
+
"eval_accuracy": 0.7521815008726004,
|
154 |
+
"eval_loss": 0.5663809776306152,
|
155 |
+
"eval_runtime": 9.3904,
|
156 |
+
"eval_samples_per_second": 61.02,
|
157 |
+
"eval_steps_per_second": 1.917,
|
158 |
+
"step": 100
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.73,
|
162 |
+
"learning_rate": 1.0502621921127776e-06,
|
163 |
+
"loss": 0.4978,
|
164 |
+
"step": 110
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.73,
|
168 |
+
"eval_accuracy": 0.7539267015706806,
|
169 |
+
"eval_loss": 0.5707576274871826,
|
170 |
+
"eval_runtime": 9.7621,
|
171 |
+
"eval_samples_per_second": 58.697,
|
172 |
+
"eval_steps_per_second": 1.844,
|
173 |
+
"step": 110
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 2.98,
|
177 |
+
"learning_rate": 0.0,
|
178 |
+
"loss": 0.5051,
|
179 |
+
"step": 120
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 2.98,
|
183 |
+
"eval_accuracy": 0.7469458987783595,
|
184 |
+
"eval_loss": 0.5715910792350769,
|
185 |
+
"eval_runtime": 9.7356,
|
186 |
+
"eval_samples_per_second": 58.856,
|
187 |
+
"eval_steps_per_second": 1.849,
|
188 |
+
"step": 120
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.98,
|
192 |
+
"step": 120,
|
193 |
+
"total_flos": 3.5051816769866957e+18,
|
194 |
+
"train_loss": 0.5655017614364624,
|
195 |
+
"train_runtime": 483.5766,
|
196 |
+
"train_samples_per_second": 31.962,
|
197 |
+
"train_steps_per_second": 0.248
|
198 |
+
}
|
199 |
+
],
|
200 |
+
"max_steps": 120,
|
201 |
+
"num_train_epochs": 3,
|
202 |
+
"total_flos": 3.5051816769866957e+18,
|
203 |
+
"trial_name": null,
|
204 |
+
"trial_params": null
|
205 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddbd65d6efb9ac54776f3ee37c9de0a5b0dcc7b09a83b0afa0d79094d6aaa9b2
|
3 |
+
size 3899
|