File size: 5,708 Bytes
b1b1461
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
{
  "best_metric": 0.9990069513406157,
  "best_model_checkpoint": "Brain_Tumor_Detector_swin/checkpoint-339",
  "epoch": 3.0,
  "global_step": 339,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.6023,
      "step": 10
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.368,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.2555,
      "step": 30
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.9016393442622957e-05,
      "loss": 0.1834,
      "step": 40
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.737704918032787e-05,
      "loss": 0.1955,
      "step": 50
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.5737704918032786e-05,
      "loss": 0.168,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.409836065573771e-05,
      "loss": 0.1057,
      "step": 70
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.245901639344262e-05,
      "loss": 0.1323,
      "step": 80
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.081967213114754e-05,
      "loss": 0.0936,
      "step": 90
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.9180327868852464e-05,
      "loss": 0.0855,
      "step": 100
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.754098360655738e-05,
      "loss": 0.079,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9881619937694704,
      "eval_f1": 0.9905894006934126,
      "eval_loss": 0.02834915742278099,
      "eval_precision": 0.9881422924901185,
      "eval_recall": 0.9930486593843099,
      "eval_runtime": 203.14,
      "eval_samples_per_second": 7.901,
      "eval_steps_per_second": 0.251,
      "step": 113
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.590163934426229e-05,
      "loss": 0.0843,
      "step": 120
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.4262295081967214e-05,
      "loss": 0.0651,
      "step": 130
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.2622950819672136e-05,
      "loss": 0.0893,
      "step": 140
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.098360655737705e-05,
      "loss": 0.093,
      "step": 150
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.934426229508197e-05,
      "loss": 0.0666,
      "step": 160
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.7704918032786886e-05,
      "loss": 0.0601,
      "step": 170
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.6065573770491804e-05,
      "loss": 0.0734,
      "step": 180
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.442622950819672e-05,
      "loss": 0.0523,
      "step": 190
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.278688524590164e-05,
      "loss": 0.0572,
      "step": 200
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.114754098360656e-05,
      "loss": 0.0415,
      "step": 210
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.9508196721311475e-05,
      "loss": 0.0575,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9956386292834891,
      "eval_f1": 0.9965191447041274,
      "eval_loss": 0.01207876205444336,
      "eval_precision": 0.99800796812749,
      "eval_recall": 0.9950347567030785,
      "eval_runtime": 193.9311,
      "eval_samples_per_second": 8.276,
      "eval_steps_per_second": 0.263,
      "step": 226
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.7868852459016393e-05,
      "loss": 0.0398,
      "step": 230
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.6229508196721314e-05,
      "loss": 0.0419,
      "step": 240
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.4590163934426229e-05,
      "loss": 0.0467,
      "step": 250
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.2950819672131149e-05,
      "loss": 0.0502,
      "step": 260
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.1311475409836065e-05,
      "loss": 0.0304,
      "step": 270
    },
    {
      "epoch": 2.48,
      "learning_rate": 9.672131147540984e-06,
      "loss": 0.0442,
      "step": 280
    },
    {
      "epoch": 2.57,
      "learning_rate": 8.032786885245902e-06,
      "loss": 0.0396,
      "step": 290
    },
    {
      "epoch": 2.65,
      "learning_rate": 6.393442622950819e-06,
      "loss": 0.0429,
      "step": 300
    },
    {
      "epoch": 2.74,
      "learning_rate": 4.754098360655738e-06,
      "loss": 0.0387,
      "step": 310
    },
    {
      "epoch": 2.83,
      "learning_rate": 3.114754098360656e-06,
      "loss": 0.0537,
      "step": 320
    },
    {
      "epoch": 2.92,
      "learning_rate": 1.4754098360655739e-06,
      "loss": 0.0312,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9981308411214953,
      "eval_f1": 0.9985111662531018,
      "eval_loss": 0.0054078237153589725,
      "eval_precision": 0.998015873015873,
      "eval_recall": 0.9990069513406157,
      "eval_runtime": 193.8262,
      "eval_samples_per_second": 8.281,
      "eval_steps_per_second": 0.263,
      "step": 339
    },
    {
      "epoch": 3.0,
      "step": 339,
      "total_flos": 3.3948696164738826e+18,
      "train_loss": 0.1033598997775784,
      "train_runtime": 25716.3258,
      "train_samples_per_second": 1.685,
      "train_steps_per_second": 0.013
    }
  ],
  "max_steps": 339,
  "num_train_epochs": 3,
  "total_flos": 3.3948696164738826e+18,
  "trial_name": null,
  "trial_params": null
}