Commit
•
94638eb
1
Parent(s):
aa207cb
End of training
Browse files- all_results.json +10 -10
- eval_results.json +5 -5
- runs/May27_20-27-48_0922109e5cf6/events.out.tfevents.1685219354.0922109e5cf6.8213.11 +3 -0
- train_results.json +6 -6
- trainer_state.json +70 -127
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 0.7647058823529411,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples_per_second": 81.
|
7 |
-
"eval_steps_per_second": 23.
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
"eval_accuracy": 0.7647058823529411,
|
4 |
+
"eval_loss": 0.6600015163421631,
|
5 |
+
"eval_runtime": 0.2093,
|
6 |
+
"eval_samples_per_second": 81.21,
|
7 |
+
"eval_steps_per_second": 23.885,
|
8 |
+
"total_flos": 1.608168860024832e+16,
|
9 |
+
"train_loss": 0.36969062089920046,
|
10 |
+
"train_runtime": 46.5,
|
11 |
+
"train_samples_per_second": 13.763,
|
12 |
+
"train_steps_per_second": 0.86
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 0.7647058823529411,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples_per_second": 81.
|
7 |
-
"eval_steps_per_second": 23.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
"eval_accuracy": 0.7647058823529411,
|
4 |
+
"eval_loss": 0.6600015163421631,
|
5 |
+
"eval_runtime": 0.2093,
|
6 |
+
"eval_samples_per_second": 81.21,
|
7 |
+
"eval_steps_per_second": 23.885
|
8 |
}
|
runs/May27_20-27-48_0922109e5cf6/events.out.tfevents.1685219354.0922109e5cf6.8213.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:155880a25fda563ab545e7166d6aae8a78cbc15ac5646252293d7fd0f050a813
|
3 |
+
size 405
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 1.608168860024832e+16,
|
4 |
+
"train_loss": 0.36969062089920046,
|
5 |
+
"train_runtime": 46.5,
|
6 |
+
"train_samples_per_second": 13.763,
|
7 |
+
"train_steps_per_second": 0.86
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,196 +1,139 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7647058823529411,
|
3 |
-
"best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
-
"eval_accuracy": 0.
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime": 0.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second":
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
-
"eval_accuracy": 0.
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_runtime": 0.
|
24 |
-
"eval_samples_per_second":
|
25 |
-
"eval_steps_per_second":
|
26 |
"step": 8
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.5,
|
30 |
-
"learning_rate": 4.
|
31 |
-
"loss": 0.
|
32 |
"step": 10
|
33 |
},
|
34 |
{
|
35 |
"epoch": 3.0,
|
36 |
-
"eval_accuracy": 0.
|
37 |
-
"eval_loss": 0.
|
38 |
-
"eval_runtime": 0.
|
39 |
-
"eval_samples_per_second":
|
40 |
-
"eval_steps_per_second":
|
41 |
"step": 12
|
42 |
},
|
43 |
{
|
44 |
"epoch": 4.0,
|
45 |
-
"eval_accuracy": 0.
|
46 |
-
"eval_loss": 0.
|
47 |
-
"eval_runtime": 0.
|
48 |
-
"eval_samples_per_second":
|
49 |
-
"eval_steps_per_second":
|
50 |
"step": 16
|
51 |
},
|
52 |
{
|
53 |
"epoch": 5.0,
|
54 |
-
"learning_rate":
|
55 |
-
"loss": 0.
|
56 |
"step": 20
|
57 |
},
|
58 |
{
|
59 |
"epoch": 5.0,
|
60 |
-
"eval_accuracy": 0.
|
61 |
-
"eval_loss": 0.
|
62 |
-
"eval_runtime": 0.
|
63 |
-
"eval_samples_per_second":
|
64 |
-
"eval_steps_per_second":
|
65 |
"step": 20
|
66 |
},
|
67 |
{
|
68 |
"epoch": 6.0,
|
69 |
-
"eval_accuracy": 0.
|
70 |
-
"eval_loss": 0.
|
71 |
-
"eval_runtime": 0.
|
72 |
-
"eval_samples_per_second":
|
73 |
-
"eval_steps_per_second":
|
74 |
"step": 24
|
75 |
},
|
76 |
{
|
77 |
"epoch": 7.0,
|
78 |
-
"eval_accuracy": 0.
|
79 |
-
"eval_loss": 0.
|
80 |
-
"eval_runtime": 0.
|
81 |
-
"eval_samples_per_second":
|
82 |
-
"eval_steps_per_second":
|
83 |
"step": 28
|
84 |
},
|
85 |
{
|
86 |
"epoch": 7.5,
|
87 |
-
"learning_rate":
|
88 |
-
"loss": 0.
|
89 |
"step": 30
|
90 |
},
|
91 |
{
|
92 |
"epoch": 8.0,
|
93 |
-
"eval_accuracy": 0.
|
94 |
-
"eval_loss": 0.
|
95 |
-
"eval_runtime": 0.
|
96 |
-
"eval_samples_per_second":
|
97 |
-
"eval_steps_per_second":
|
98 |
"step": 32
|
99 |
},
|
100 |
{
|
101 |
"epoch": 9.0,
|
102 |
-
"eval_accuracy": 0.
|
103 |
-
"eval_loss": 0.
|
104 |
-
"eval_runtime": 0.
|
105 |
-
"eval_samples_per_second":
|
106 |
-
"eval_steps_per_second":
|
107 |
"step": 36
|
108 |
},
|
109 |
{
|
110 |
"epoch": 10.0,
|
111 |
-
"learning_rate":
|
112 |
-
"loss": 0.
|
113 |
"step": 40
|
114 |
},
|
115 |
{
|
116 |
"epoch": 10.0,
|
117 |
"eval_accuracy": 0.7647058823529411,
|
118 |
-
"eval_loss": 0.
|
119 |
-
"eval_runtime": 0.
|
120 |
-
"eval_samples_per_second":
|
121 |
-
"eval_steps_per_second": 27.
|
122 |
"step": 40
|
123 |
},
|
124 |
{
|
125 |
-
"epoch":
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
},
|
133 |
-
{
|
134 |
-
"epoch": 12.0,
|
135 |
-
"eval_accuracy": 0.7647058823529411,
|
136 |
-
"eval_loss": 0.6389846205711365,
|
137 |
-
"eval_runtime": 0.155,
|
138 |
-
"eval_samples_per_second": 109.699,
|
139 |
-
"eval_steps_per_second": 32.264,
|
140 |
-
"step": 48
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 12.5,
|
144 |
-
"learning_rate": 9.259259259259259e-06,
|
145 |
-
"loss": 0.5086,
|
146 |
-
"step": 50
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 13.0,
|
150 |
-
"eval_accuracy": 0.7647058823529411,
|
151 |
-
"eval_loss": 0.6434133052825928,
|
152 |
-
"eval_runtime": 0.1482,
|
153 |
-
"eval_samples_per_second": 114.73,
|
154 |
-
"eval_steps_per_second": 33.744,
|
155 |
-
"step": 52
|
156 |
-
},
|
157 |
-
{
|
158 |
-
"epoch": 14.0,
|
159 |
-
"eval_accuracy": 0.7647058823529411,
|
160 |
-
"eval_loss": 0.6424618363380432,
|
161 |
-
"eval_runtime": 0.1541,
|
162 |
-
"eval_samples_per_second": 110.305,
|
163 |
-
"eval_steps_per_second": 32.443,
|
164 |
-
"step": 56
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 15.0,
|
168 |
-
"learning_rate": 0.0,
|
169 |
-
"loss": 0.448,
|
170 |
-
"step": 60
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 15.0,
|
174 |
-
"eval_accuracy": 0.7647058823529411,
|
175 |
-
"eval_loss": 0.645173192024231,
|
176 |
-
"eval_runtime": 0.1497,
|
177 |
-
"eval_samples_per_second": 113.564,
|
178 |
-
"eval_steps_per_second": 33.401,
|
179 |
-
"step": 60
|
180 |
-
},
|
181 |
-
{
|
182 |
-
"epoch": 15.0,
|
183 |
-
"step": 60,
|
184 |
-
"total_flos": 2.412253290037248e+16,
|
185 |
-
"train_loss": 0.5445812543233236,
|
186 |
-
"train_runtime": 64.3122,
|
187 |
-
"train_samples_per_second": 14.927,
|
188 |
-
"train_steps_per_second": 0.933
|
189 |
}
|
190 |
],
|
191 |
-
"max_steps":
|
192 |
-
"num_train_epochs":
|
193 |
-
"total_flos":
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.7647058823529411,
|
3 |
+
"best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-4",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 40,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.7647058823529411,
|
13 |
+
"eval_loss": 0.6600015163421631,
|
14 |
+
"eval_runtime": 0.1838,
|
15 |
+
"eval_samples_per_second": 92.505,
|
16 |
+
"eval_steps_per_second": 27.207,
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.5882352941176471,
|
22 |
+
"eval_loss": 0.7135058045387268,
|
23 |
+
"eval_runtime": 0.2157,
|
24 |
+
"eval_samples_per_second": 78.8,
|
25 |
+
"eval_steps_per_second": 23.177,
|
26 |
"step": 8
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.5,
|
30 |
+
"learning_rate": 4.166666666666667e-05,
|
31 |
+
"loss": 0.4055,
|
32 |
"step": 10
|
33 |
},
|
34 |
{
|
35 |
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.6470588235294118,
|
37 |
+
"eval_loss": 0.6851004958152771,
|
38 |
+
"eval_runtime": 0.1807,
|
39 |
+
"eval_samples_per_second": 94.088,
|
40 |
+
"eval_steps_per_second": 27.673,
|
41 |
"step": 12
|
42 |
},
|
43 |
{
|
44 |
"epoch": 4.0,
|
45 |
+
"eval_accuracy": 0.6470588235294118,
|
46 |
+
"eval_loss": 0.6512044668197632,
|
47 |
+
"eval_runtime": 0.1486,
|
48 |
+
"eval_samples_per_second": 114.416,
|
49 |
+
"eval_steps_per_second": 33.652,
|
50 |
"step": 16
|
51 |
},
|
52 |
{
|
53 |
"epoch": 5.0,
|
54 |
+
"learning_rate": 2.777777777777778e-05,
|
55 |
+
"loss": 0.3895,
|
56 |
"step": 20
|
57 |
},
|
58 |
{
|
59 |
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.6470588235294118,
|
61 |
+
"eval_loss": 0.7130866646766663,
|
62 |
+
"eval_runtime": 0.1511,
|
63 |
+
"eval_samples_per_second": 112.526,
|
64 |
+
"eval_steps_per_second": 33.096,
|
65 |
"step": 20
|
66 |
},
|
67 |
{
|
68 |
"epoch": 6.0,
|
69 |
+
"eval_accuracy": 0.6470588235294118,
|
70 |
+
"eval_loss": 0.7157571315765381,
|
71 |
+
"eval_runtime": 0.1508,
|
72 |
+
"eval_samples_per_second": 112.708,
|
73 |
+
"eval_steps_per_second": 33.149,
|
74 |
"step": 24
|
75 |
},
|
76 |
{
|
77 |
"epoch": 7.0,
|
78 |
+
"eval_accuracy": 0.7647058823529411,
|
79 |
+
"eval_loss": 0.6532735228538513,
|
80 |
+
"eval_runtime": 0.1506,
|
81 |
+
"eval_samples_per_second": 112.877,
|
82 |
+
"eval_steps_per_second": 33.199,
|
83 |
"step": 28
|
84 |
},
|
85 |
{
|
86 |
"epoch": 7.5,
|
87 |
+
"learning_rate": 1.388888888888889e-05,
|
88 |
+
"loss": 0.363,
|
89 |
"step": 30
|
90 |
},
|
91 |
{
|
92 |
"epoch": 8.0,
|
93 |
+
"eval_accuracy": 0.7058823529411765,
|
94 |
+
"eval_loss": 0.6210929155349731,
|
95 |
+
"eval_runtime": 0.1672,
|
96 |
+
"eval_samples_per_second": 101.678,
|
97 |
+
"eval_steps_per_second": 29.905,
|
98 |
"step": 32
|
99 |
},
|
100 |
{
|
101 |
"epoch": 9.0,
|
102 |
+
"eval_accuracy": 0.7647058823529411,
|
103 |
+
"eval_loss": 0.6221739649772644,
|
104 |
+
"eval_runtime": 0.1853,
|
105 |
+
"eval_samples_per_second": 91.73,
|
106 |
+
"eval_steps_per_second": 26.979,
|
107 |
"step": 36
|
108 |
},
|
109 |
{
|
110 |
"epoch": 10.0,
|
111 |
+
"learning_rate": 0.0,
|
112 |
+
"loss": 0.3207,
|
113 |
"step": 40
|
114 |
},
|
115 |
{
|
116 |
"epoch": 10.0,
|
117 |
"eval_accuracy": 0.7647058823529411,
|
118 |
+
"eval_loss": 0.6255453824996948,
|
119 |
+
"eval_runtime": 0.1847,
|
120 |
+
"eval_samples_per_second": 92.059,
|
121 |
+
"eval_steps_per_second": 27.076,
|
122 |
"step": 40
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 10.0,
|
126 |
+
"step": 40,
|
127 |
+
"total_flos": 1.608168860024832e+16,
|
128 |
+
"train_loss": 0.36969062089920046,
|
129 |
+
"train_runtime": 46.5,
|
130 |
+
"train_samples_per_second": 13.763,
|
131 |
+
"train_steps_per_second": 0.86
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
}
|
133 |
],
|
134 |
+
"max_steps": 40,
|
135 |
+
"num_train_epochs": 10,
|
136 |
+
"total_flos": 1.608168860024832e+16,
|
137 |
"trial_name": null,
|
138 |
"trial_params": null
|
139 |
}
|