File size: 5,652 Bytes
4412eff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.24191519618034363,
  "best_model_checkpoint": "/workspace/training_output/perspectives-vit-large-patch16-224-in21k-v3/checkpoint-9210",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 15350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 1.93485342019544e-05,
      "loss": 0.9017,
      "step": 500
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.8697068403908796e-05,
      "loss": 0.5698,
      "step": 1000
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8045602605863193e-05,
      "loss": 0.4974,
      "step": 1500
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.7394136807817594e-05,
      "loss": 0.4646,
      "step": 2000
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6742671009771988e-05,
      "loss": 0.4538,
      "step": 2500
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6091205211726385e-05,
      "loss": 0.4353,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8811721273650208,
      "eval_loss": 0.33953866362571716,
      "eval_runtime": 349.0715,
      "eval_samples_per_second": 12.416,
      "eval_steps_per_second": 1.553,
      "step": 3070
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.5439739413680782e-05,
      "loss": 0.3613,
      "step": 3500
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.478827361563518e-05,
      "loss": 0.3571,
      "step": 4000
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.4136807817589578e-05,
      "loss": 0.3861,
      "step": 4500
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.3485342019543975e-05,
      "loss": 0.3657,
      "step": 5000
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.2833876221498372e-05,
      "loss": 0.3615,
      "step": 5500
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2182410423452771e-05,
      "loss": 0.3415,
      "step": 6000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9192431933548685,
      "eval_loss": 0.25435712933540344,
      "eval_runtime": 357.646,
      "eval_samples_per_second": 12.118,
      "eval_steps_per_second": 1.515,
      "step": 6140
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1530944625407168e-05,
      "loss": 0.3178,
      "step": 6500
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.0879478827361565e-05,
      "loss": 0.2954,
      "step": 7000
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.0228013029315963e-05,
      "loss": 0.3127,
      "step": 7500
    },
    {
      "epoch": 2.61,
      "learning_rate": 9.576547231270358e-06,
      "loss": 0.3116,
      "step": 8000
    },
    {
      "epoch": 2.77,
      "learning_rate": 8.925081433224755e-06,
      "loss": 0.2747,
      "step": 8500
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.273615635179154e-06,
      "loss": 0.2689,
      "step": 9000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.92455006922012,
      "eval_loss": 0.24191519618034363,
      "eval_runtime": 319.492,
      "eval_samples_per_second": 13.565,
      "eval_steps_per_second": 1.696,
      "step": 9210
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.622149837133551e-06,
      "loss": 0.2727,
      "step": 9500
    },
    {
      "epoch": 3.26,
      "learning_rate": 6.9706840390879485e-06,
      "loss": 0.2362,
      "step": 10000
    },
    {
      "epoch": 3.42,
      "learning_rate": 6.319218241042345e-06,
      "loss": 0.2617,
      "step": 10500
    },
    {
      "epoch": 3.58,
      "learning_rate": 5.667752442996744e-06,
      "loss": 0.2437,
      "step": 11000
    },
    {
      "epoch": 3.75,
      "learning_rate": 5.016286644951141e-06,
      "loss": 0.2494,
      "step": 11500
    },
    {
      "epoch": 3.91,
      "learning_rate": 4.364820846905538e-06,
      "loss": 0.2525,
      "step": 12000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9192431933548685,
      "eval_loss": 0.29525890946388245,
      "eval_runtime": 322.9797,
      "eval_samples_per_second": 13.419,
      "eval_steps_per_second": 1.678,
      "step": 12280
    },
    {
      "epoch": 4.07,
      "learning_rate": 3.7133550488599353e-06,
      "loss": 0.2265,
      "step": 12500
    },
    {
      "epoch": 4.23,
      "learning_rate": 3.061889250814333e-06,
      "loss": 0.204,
      "step": 13000
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.4104234527687296e-06,
      "loss": 0.2261,
      "step": 13500
    },
    {
      "epoch": 4.56,
      "learning_rate": 1.7589576547231272e-06,
      "loss": 0.2152,
      "step": 14000
    },
    {
      "epoch": 4.72,
      "learning_rate": 1.1074918566775244e-06,
      "loss": 0.1766,
      "step": 14500
    },
    {
      "epoch": 4.89,
      "learning_rate": 4.5602605863192187e-07,
      "loss": 0.1977,
      "step": 15000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9356252884171666,
      "eval_loss": 0.24443966150283813,
      "eval_runtime": 321.057,
      "eval_samples_per_second": 13.499,
      "eval_steps_per_second": 1.688,
      "step": 15350
    },
    {
      "epoch": 5.0,
      "step": 15350,
      "total_flos": 3.363363283622308e+19,
      "train_loss": 0.3319820684874097,
      "train_runtime": 13677.2564,
      "train_samples_per_second": 8.977,
      "train_steps_per_second": 1.122
    }
  ],
  "logging_steps": 500,
  "max_steps": 15350,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 3.363363283622308e+19,
  "trial_name": null,
  "trial_params": null
}