Commit
•
d956365
1
Parent(s):
8df375f
End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Dec11_08-56-27_24d728a6ec27/events.out.tfevents.1670749247.24d728a6ec27.73.5 +3 -0
- train_results.json +6 -6
- trainer_state.json +146 -35
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"total_flos":
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.97,
|
3 |
+
"eval_accuracy": 0.9506172839506173,
|
4 |
+
"eval_loss": 0.5076120495796204,
|
5 |
+
"eval_runtime": 0.658,
|
6 |
+
"eval_samples_per_second": 123.091,
|
7 |
+
"eval_steps_per_second": 31.913,
|
8 |
+
"total_flos": 9.475214412238848e+16,
|
9 |
+
"train_loss": 0.5672112387159597,
|
10 |
+
"train_runtime": 101.9242,
|
11 |
+
"train_samples_per_second": 37.086,
|
12 |
+
"train_steps_per_second": 2.257
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.97,
|
3 |
+
"eval_accuracy": 0.9506172839506173,
|
4 |
+
"eval_loss": 0.5076120495796204,
|
5 |
+
"eval_runtime": 0.658,
|
6 |
+
"eval_samples_per_second": 123.091,
|
7 |
+
"eval_steps_per_second": 31.913
|
8 |
}
|
runs/Dec11_08-56-27_24d728a6ec27/events.out.tfevents.1670749247.24d728a6ec27.73.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1497ee6aebc3489fd5b3325f5c7c23003af1e716107041c432e35f1d1b9b4fd1
|
3 |
+
size 363
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.97,
|
3 |
+
"total_flos": 9.475214412238848e+16,
|
4 |
+
"train_loss": 0.5672112387159597,
|
5 |
+
"train_runtime": 101.9242,
|
6 |
+
"train_samples_per_second": 37.086,
|
7 |
+
"train_steps_per_second": 2.257
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,70 +1,181 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat-att-auto/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": 0.84,
|
12 |
-
"learning_rate":
|
13 |
-
"loss":
|
14 |
"step": 20
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.97,
|
18 |
-
"eval_accuracy": 0.
|
19 |
-
"eval_loss":
|
20 |
-
"eval_runtime": 0.
|
21 |
-
"eval_samples_per_second":
|
22 |
-
"eval_steps_per_second":
|
23 |
"step": 23
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.72,
|
27 |
-
"learning_rate":
|
28 |
-
"loss": 1.
|
29 |
"step": 40
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.97,
|
33 |
-
"eval_accuracy": 0.
|
34 |
-
"eval_loss": 1.
|
35 |
-
"eval_runtime": 0.
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_steps_per_second": 35.
|
38 |
"step": 46
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.59,
|
42 |
-
"learning_rate":
|
43 |
-
"loss":
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.97,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_runtime": 0.
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second":
|
53 |
"step": 69
|
54 |
},
|
55 |
{
|
56 |
-
"epoch":
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
|
61 |
-
|
62 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
-
"max_steps":
|
66 |
-
"num_train_epochs":
|
67 |
-
"total_flos":
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9506172839506173,
|
3 |
+
"best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat-att-auto/checkpoint-184",
|
4 |
+
"epoch": 9.968421052631578,
|
5 |
+
"global_step": 230,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.84,
|
12 |
+
"learning_rate": 4.347826086956522e-05,
|
13 |
+
"loss": 1.5583,
|
14 |
"step": 20
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.97,
|
18 |
+
"eval_accuracy": 0.7160493827160493,
|
19 |
+
"eval_loss": 1.6008388996124268,
|
20 |
+
"eval_runtime": 0.5509,
|
21 |
+
"eval_samples_per_second": 147.042,
|
22 |
+
"eval_steps_per_second": 38.122,
|
23 |
"step": 23
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.72,
|
27 |
+
"learning_rate": 4.589371980676328e-05,
|
28 |
+
"loss": 1.2953,
|
29 |
"step": 40
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.97,
|
33 |
+
"eval_accuracy": 0.7530864197530864,
|
34 |
+
"eval_loss": 1.2957005500793457,
|
35 |
+
"eval_runtime": 0.5979,
|
36 |
+
"eval_samples_per_second": 135.485,
|
37 |
+
"eval_steps_per_second": 35.126,
|
38 |
"step": 46
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.59,
|
42 |
+
"learning_rate": 4.106280193236715e-05,
|
43 |
+
"loss": 0.9488,
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.97,
|
48 |
+
"eval_accuracy": 0.8148148148148148,
|
49 |
+
"eval_loss": 1.072020411491394,
|
50 |
+
"eval_runtime": 0.594,
|
51 |
+
"eval_samples_per_second": 136.355,
|
52 |
+
"eval_steps_per_second": 35.351,
|
53 |
"step": 69
|
54 |
},
|
55 |
{
|
56 |
+
"epoch": 3.46,
|
57 |
+
"learning_rate": 3.6231884057971014e-05,
|
58 |
+
"loss": 0.7036,
|
59 |
+
"step": 80
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 3.97,
|
63 |
+
"eval_accuracy": 0.8641975308641975,
|
64 |
+
"eval_loss": 0.8964575529098511,
|
65 |
+
"eval_runtime": 0.579,
|
66 |
+
"eval_samples_per_second": 139.885,
|
67 |
+
"eval_steps_per_second": 36.267,
|
68 |
+
"step": 92
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 4.34,
|
72 |
+
"learning_rate": 3.140096618357488e-05,
|
73 |
+
"loss": 0.5446,
|
74 |
+
"step": 100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 4.97,
|
78 |
+
"eval_accuracy": 0.9382716049382716,
|
79 |
+
"eval_loss": 0.7573724985122681,
|
80 |
+
"eval_runtime": 0.5915,
|
81 |
+
"eval_samples_per_second": 136.936,
|
82 |
+
"eval_steps_per_second": 35.502,
|
83 |
+
"step": 115
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 5.21,
|
87 |
+
"learning_rate": 2.6570048309178748e-05,
|
88 |
+
"loss": 0.4113,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.97,
|
93 |
+
"eval_accuracy": 0.9382716049382716,
|
94 |
+
"eval_loss": 0.6521688103675842,
|
95 |
+
"eval_runtime": 0.6064,
|
96 |
+
"eval_samples_per_second": 133.581,
|
97 |
+
"eval_steps_per_second": 34.632,
|
98 |
+
"step": 138
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.08,
|
102 |
+
"learning_rate": 2.173913043478261e-05,
|
103 |
+
"loss": 0.3143,
|
104 |
+
"step": 140
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.93,
|
108 |
+
"learning_rate": 1.6908212560386476e-05,
|
109 |
+
"loss": 0.2259,
|
110 |
+
"step": 160
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.97,
|
114 |
+
"eval_accuracy": 0.9382716049382716,
|
115 |
+
"eval_loss": 0.572002649307251,
|
116 |
+
"eval_runtime": 0.5945,
|
117 |
+
"eval_samples_per_second": 136.243,
|
118 |
+
"eval_steps_per_second": 35.322,
|
119 |
+
"step": 161
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 7.8,
|
123 |
+
"learning_rate": 1.2077294685990338e-05,
|
124 |
+
"loss": 0.1863,
|
125 |
+
"step": 180
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 7.97,
|
129 |
+
"eval_accuracy": 0.9506172839506173,
|
130 |
+
"eval_loss": 0.5076120495796204,
|
131 |
+
"eval_runtime": 0.6943,
|
132 |
+
"eval_samples_per_second": 116.67,
|
133 |
+
"eval_steps_per_second": 30.248,
|
134 |
+
"step": 184
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 8.67,
|
138 |
+
"learning_rate": 7.246376811594203e-06,
|
139 |
+
"loss": 0.1443,
|
140 |
+
"step": 200
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 8.97,
|
144 |
+
"eval_accuracy": 0.9382716049382716,
|
145 |
+
"eval_loss": 0.4794546961784363,
|
146 |
+
"eval_runtime": 0.5986,
|
147 |
+
"eval_samples_per_second": 135.327,
|
148 |
+
"eval_steps_per_second": 35.085,
|
149 |
+
"step": 207
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 9.55,
|
153 |
+
"learning_rate": 2.4154589371980677e-06,
|
154 |
+
"loss": 0.1289,
|
155 |
+
"step": 220
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 9.97,
|
159 |
+
"eval_accuracy": 0.9382716049382716,
|
160 |
+
"eval_loss": 0.4685024619102478,
|
161 |
+
"eval_runtime": 0.6007,
|
162 |
+
"eval_samples_per_second": 134.835,
|
163 |
+
"eval_steps_per_second": 34.957,
|
164 |
+
"step": 230
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 9.97,
|
168 |
+
"step": 230,
|
169 |
+
"total_flos": 9.475214412238848e+16,
|
170 |
+
"train_loss": 0.5672112387159597,
|
171 |
+
"train_runtime": 101.9242,
|
172 |
+
"train_samples_per_second": 37.086,
|
173 |
+
"train_steps_per_second": 2.257
|
174 |
}
|
175 |
],
|
176 |
+
"max_steps": 230,
|
177 |
+
"num_train_epochs": 10,
|
178 |
+
"total_flos": 9.475214412238848e+16,
|
179 |
"trial_name": null,
|
180 |
"trial_params": null
|
181 |
}
|