File size: 3,414 Bytes
1bdfc49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 12500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 4.8e-05,
      "loss": 12.8478,
      "step": 500
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.600000000000001e-05,
      "loss": 5.1514,
      "step": 1000
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 4.1916,
      "step": 1500
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.2e-05,
      "loss": 3.7203,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "learning_rate": 4e-05,
      "loss": 3.499,
      "step": 2500
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.8e-05,
      "loss": 3.2552,
      "step": 3000
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.6e-05,
      "loss": 3.1375,
      "step": 3500
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 3.0225,
      "step": 4000
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.9281,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "learning_rate": 3e-05,
      "loss": 2.8417,
      "step": 5000
    },
    {
      "epoch": 2.2,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.7951,
      "step": 5500
    },
    {
      "epoch": 2.4,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.69,
      "step": 6000
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.4e-05,
      "loss": 2.6722,
      "step": 6500
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.6165,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-05,
      "loss": 2.6169,
      "step": 7500
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.8e-05,
      "loss": 2.5503,
      "step": 8000
    },
    {
      "epoch": 3.4,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.5508,
      "step": 8500
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.4659,
      "step": 9000
    },
    {
      "epoch": 3.8,
      "learning_rate": 1.2e-05,
      "loss": 2.5075,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "learning_rate": 1e-05,
      "loss": 2.4532,
      "step": 10000
    },
    {
      "epoch": 4.2,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.4201,
      "step": 10500
    },
    {
      "epoch": 4.4,
      "learning_rate": 6e-06,
      "loss": 2.3937,
      "step": 11000
    },
    {
      "epoch": 4.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4281,
      "step": 11500
    },
    {
      "epoch": 4.8,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4592,
      "step": 12000
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 2.4106,
      "step": 12500
    },
    {
      "epoch": 5.0,
      "step": 12500,
      "total_flos": 2522355797975040.0,
      "train_loss": 3.305007841796875,
      "train_runtime": 2877.6666,
      "train_samples_per_second": 17.375,
      "train_steps_per_second": 4.344
    }
  ],
  "max_steps": 12500,
  "num_train_epochs": 5,
  "total_flos": 2522355797975040.0,
  "trial_name": null,
  "trial_params": null
}