File size: 3,177 Bytes
81c5c9c
df2302d
 
b8aaf94
df2302d
81c5c9c
 
 
 
 
df2302d
 
 
81c5c9c
 
 
df2302d
 
 
81c5c9c
 
 
df2302d
 
 
81c5c9c
 
 
df2302d
 
 
81c5c9c
 
 
df2302d
 
 
81c5c9c
 
3c045f1
df2302d
 
 
3c045f1
 
 
df2302d
 
 
3c045f1
 
 
df2302d
 
 
3c045f1
 
 
df2302d
 
 
3c045f1
 
 
df2302d
 
 
3c045f1
 
 
df2302d
 
 
 
 
 
3c045f1
 
81c5c9c
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
 
df2302d
 
 
b8aaf94
 
0184747
 
df2302d
 
 
0184747
 
 
df2302d
 
 
 
 
 
0184747
b8aaf94
 
df2302d
 
 
 
 
 
81c5c9c
 
df2302d
b8aaf94
df2302d
81c5c9c
 
 
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
{
  "best_metric": 2.153944969177246,
  "best_model_checkpoint": "./vit-base/checkpoint-200",
  "epoch": 20.0,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.00019,
      "loss": 0.0007,
      "step": 10
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018,
      "loss": 0.1073,
      "step": 20
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00017,
      "loss": 0.205,
      "step": 30
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00016,
      "loss": 0.0034,
      "step": 40
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0011,
      "step": 50
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00014,
      "loss": 0.001,
      "step": 60
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.0003,
      "step": 70
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.625,
      "eval_loss": 2.155715227127075,
      "eval_runtime": 0.2927,
      "eval_samples_per_second": 54.664,
      "eval_steps_per_second": 6.833,
      "step": 100
    },
    {
      "epoch": 11.0,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 12.0,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 13.0,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 14.0,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 15.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 16.0,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 17.0,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 18.0,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 19.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.625,
      "eval_loss": 2.153944969177246,
      "eval_runtime": 0.2762,
      "eval_samples_per_second": 57.924,
      "eval_steps_per_second": 7.241,
      "step": 200
    },
    {
      "epoch": 20.0,
      "step": 200,
      "total_flos": 6.19947029495808e+16,
      "train_loss": 0.015958890169858932,
      "train_runtime": 31.8203,
      "train_samples_per_second": 25.141,
      "train_steps_per_second": 6.285
    }
  ],
  "max_steps": 200,
  "num_train_epochs": 20,
  "total_flos": 6.19947029495808e+16,
  "trial_name": null,
  "trial_params": null
}