File size: 4,297 Bytes
3989295
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
{
  "best_metric": 0.9991525423728813,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-83",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 249,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.4995,
      "step": 10
    },
    {
      "epoch": 0.24,
      "learning_rate": 4e-05,
      "loss": 0.1624,
      "step": 20
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.888392857142857e-05,
      "loss": 0.0535,
      "step": 30
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.665178571428572e-05,
      "loss": 0.0346,
      "step": 40
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.4419642857142854e-05,
      "loss": 0.0452,
      "step": 50
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.21875e-05,
      "loss": 0.0238,
      "step": 60
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.9955357142857144e-05,
      "loss": 0.0239,
      "step": 70
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.7723214285714286e-05,
      "loss": 0.0344,
      "step": 80
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9991525423728813,
      "eval_loss": 0.005057646427303553,
      "eval_runtime": 8.2623,
      "eval_samples_per_second": 142.817,
      "eval_steps_per_second": 4.478,
      "step": 83
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.5491071428571435e-05,
      "loss": 0.032,
      "step": 90
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.325892857142857e-05,
      "loss": 0.017,
      "step": 100
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.102678571428572e-05,
      "loss": 0.0119,
      "step": 110
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.8794642857142857e-05,
      "loss": 0.0215,
      "step": 120
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 0.0219,
      "step": 130
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.4330357142857144e-05,
      "loss": 0.0293,
      "step": 140
    },
    {
      "epoch": 1.81,
      "learning_rate": 2.2098214285714286e-05,
      "loss": 0.0202,
      "step": 150
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.9866071428571427e-05,
      "loss": 0.0112,
      "step": 160
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9983050847457627,
      "eval_loss": 0.005177544895559549,
      "eval_runtime": 8.4063,
      "eval_samples_per_second": 140.37,
      "eval_steps_per_second": 4.401,
      "step": 166
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.7633928571428573e-05,
      "loss": 0.0088,
      "step": 170
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.5401785714285715e-05,
      "loss": 0.0193,
      "step": 180
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.3169642857142858e-05,
      "loss": 0.0102,
      "step": 190
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.09375e-05,
      "loss": 0.0083,
      "step": 200
    },
    {
      "epoch": 2.53,
      "learning_rate": 8.705357142857143e-06,
      "loss": 0.0077,
      "step": 210
    },
    {
      "epoch": 2.65,
      "learning_rate": 6.473214285714287e-06,
      "loss": 0.0097,
      "step": 220
    },
    {
      "epoch": 2.77,
      "learning_rate": 4.241071428571429e-06,
      "loss": 0.0207,
      "step": 230
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.0089285714285715e-06,
      "loss": 0.0146,
      "step": 240
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9991525423728813,
      "eval_loss": 0.004469145555049181,
      "eval_runtime": 8.3109,
      "eval_samples_per_second": 141.983,
      "eval_steps_per_second": 4.452,
      "step": 249
    },
    {
      "epoch": 3.0,
      "step": 249,
      "total_flos": 7.913152653537116e+17,
      "train_loss": 0.04654426268305645,
      "train_runtime": 513.1593,
      "train_samples_per_second": 62.039,
      "train_steps_per_second": 0.485
    }
  ],
  "logging_steps": 10,
  "max_steps": 249,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 7.913152653537116e+17,
  "trial_name": null,
  "trial_params": null
}