End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +160 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.99,
|
3 |
+
"eval_accuracy": 0.9725925925925926,
|
4 |
+
"eval_loss": 0.0814141258597374,
|
5 |
+
"eval_runtime": 9.118,
|
6 |
+
"eval_samples_per_second": 296.117,
|
7 |
+
"eval_steps_per_second": 3.181,
|
8 |
+
"total_flos": 1.8097216036863345e+18,
|
9 |
+
"train_loss": 0.4343337993773203,
|
10 |
+
"train_runtime": 458.7403,
|
11 |
+
"train_samples_per_second": 158.913,
|
12 |
+
"train_steps_per_second": 0.412
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.99,
|
3 |
+
"eval_accuracy": 0.9725925925925926,
|
4 |
+
"eval_loss": 0.0814141258597374,
|
5 |
+
"eval_runtime": 9.118,
|
6 |
+
"eval_samples_per_second": 296.117,
|
7 |
+
"eval_steps_per_second": 3.181
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.99,
|
3 |
+
"total_flos": 1.8097216036863345e+18,
|
4 |
+
"train_loss": 0.4343337993773203,
|
5 |
+
"train_runtime": 458.7403,
|
6 |
+
"train_samples_per_second": 158.913,
|
7 |
+
"train_steps_per_second": 0.412
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9725925925925926,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-189",
|
4 |
+
"epoch": 2.9921259842519685,
|
5 |
+
"global_step": 189,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.16,
|
12 |
+
"learning_rate": 2.6315789473684212e-05,
|
13 |
+
"loss": 2.2277,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.31,
|
18 |
+
"learning_rate": 4.970588235294118e-05,
|
19 |
+
"loss": 1.5195,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.47,
|
24 |
+
"learning_rate": 4.6764705882352944e-05,
|
25 |
+
"loss": 0.6495,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.63,
|
30 |
+
"learning_rate": 4.382352941176471e-05,
|
31 |
+
"loss": 0.4173,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.79,
|
36 |
+
"learning_rate": 4.0882352941176474e-05,
|
37 |
+
"loss": 0.3414,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.94,
|
42 |
+
"learning_rate": 3.794117647058824e-05,
|
43 |
+
"loss": 0.3216,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.99,
|
48 |
+
"eval_accuracy": 0.9588888888888889,
|
49 |
+
"eval_loss": 0.13485009968280792,
|
50 |
+
"eval_runtime": 9.5869,
|
51 |
+
"eval_samples_per_second": 281.633,
|
52 |
+
"eval_steps_per_second": 3.025,
|
53 |
+
"step": 63
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.11,
|
57 |
+
"learning_rate": 3.5e-05,
|
58 |
+
"loss": 0.2779,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.27,
|
63 |
+
"learning_rate": 3.205882352941177e-05,
|
64 |
+
"loss": 0.2846,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.43,
|
69 |
+
"learning_rate": 2.9117647058823534e-05,
|
70 |
+
"loss": 0.2249,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.58,
|
75 |
+
"learning_rate": 2.6176470588235295e-05,
|
76 |
+
"loss": 0.2143,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.74,
|
81 |
+
"learning_rate": 2.323529411764706e-05,
|
82 |
+
"loss": 0.2253,
|
83 |
+
"step": 110
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.9,
|
87 |
+
"learning_rate": 2.0294117647058825e-05,
|
88 |
+
"loss": 0.2,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.99,
|
93 |
+
"eval_accuracy": 0.9703703703703703,
|
94 |
+
"eval_loss": 0.08727709203958511,
|
95 |
+
"eval_runtime": 8.8869,
|
96 |
+
"eval_samples_per_second": 303.818,
|
97 |
+
"eval_steps_per_second": 3.263,
|
98 |
+
"step": 126
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.06,
|
102 |
+
"learning_rate": 1.735294117647059e-05,
|
103 |
+
"loss": 0.2033,
|
104 |
+
"step": 130
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.22,
|
108 |
+
"learning_rate": 1.4411764705882352e-05,
|
109 |
+
"loss": 0.2002,
|
110 |
+
"step": 140
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.38,
|
114 |
+
"learning_rate": 1.1470588235294118e-05,
|
115 |
+
"loss": 0.1857,
|
116 |
+
"step": 150
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.54,
|
120 |
+
"learning_rate": 8.529411764705883e-06,
|
121 |
+
"loss": 0.1961,
|
122 |
+
"step": 160
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.69,
|
126 |
+
"learning_rate": 5.588235294117647e-06,
|
127 |
+
"loss": 0.1961,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.85,
|
132 |
+
"learning_rate": 2.647058823529412e-06,
|
133 |
+
"loss": 0.1664,
|
134 |
+
"step": 180
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.99,
|
138 |
+
"eval_accuracy": 0.9725925925925926,
|
139 |
+
"eval_loss": 0.0814141258597374,
|
140 |
+
"eval_runtime": 8.4958,
|
141 |
+
"eval_samples_per_second": 317.806,
|
142 |
+
"eval_steps_per_second": 3.413,
|
143 |
+
"step": 189
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.99,
|
147 |
+
"step": 189,
|
148 |
+
"total_flos": 1.8097216036863345e+18,
|
149 |
+
"train_loss": 0.4343337993773203,
|
150 |
+
"train_runtime": 458.7403,
|
151 |
+
"train_samples_per_second": 158.913,
|
152 |
+
"train_steps_per_second": 0.412
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"max_steps": 189,
|
156 |
+
"num_train_epochs": 3,
|
157 |
+
"total_flos": 1.8097216036863345e+18,
|
158 |
+
"trial_name": null,
|
159 |
+
"trial_params": null
|
160 |
+
}
|