File size: 2,870 Bytes
262245a
 
 
20416a5
262245a
20416a5
262245a
 
 
 
7066f4b
f67b561
20416a5
 
f67b561
 
 
b1391f0
20416a5
 
b1391f0
 
 
 
20416a5
 
b1391f0
 
 
74f00ed
20416a5
 
74f00ed
 
 
 
20416a5
 
74f00ed
 
 
 
20416a5
 
74f00ed
 
 
 
20416a5
 
74f00ed
 
 
 
20416a5
 
74f00ed
 
 
 
20416a5
 
74f00ed
 
 
20416a5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
262245a
 
 
20416a5
 
262245a
20416a5
262245a
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 9400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.32,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.6879,
      "step": 500
    },
    {
      "epoch": 10.64,
      "learning_rate": 4.468085106382979e-05,
      "loss": 0.1213,
      "step": 1000
    },
    {
      "epoch": 15.96,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.0743,
      "step": 1500
    },
    {
      "epoch": 21.28,
      "learning_rate": 3.936170212765958e-05,
      "loss": 0.0487,
      "step": 2000
    },
    {
      "epoch": 26.6,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.0615,
      "step": 2500
    },
    {
      "epoch": 31.91,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 0.0804,
      "step": 3000
    },
    {
      "epoch": 37.23,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.0936,
      "step": 3500
    },
    {
      "epoch": 42.55,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 0.1289,
      "step": 4000
    },
    {
      "epoch": 47.87,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.1842,
      "step": 4500
    },
    {
      "epoch": 53.19,
      "learning_rate": 2.340425531914894e-05,
      "loss": 0.2967,
      "step": 5000
    },
    {
      "epoch": 58.51,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.394,
      "step": 5500
    },
    {
      "epoch": 63.83,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.6998,
      "step": 6000
    },
    {
      "epoch": 69.15,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.7916,
      "step": 6500
    },
    {
      "epoch": 74.47,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.7954,
      "step": 7000
    },
    {
      "epoch": 79.79,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.8401,
      "step": 7500
    },
    {
      "epoch": 85.11,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.8077,
      "step": 8000
    },
    {
      "epoch": 90.43,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.6265,
      "step": 8500
    },
    {
      "epoch": 95.74,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.511,
      "step": 9000
    },
    {
      "epoch": 100.0,
      "step": 9400,
      "total_flos": 4968855705600000.0,
      "train_loss": 0.3965238536672389,
      "train_runtime": 2138.0517,
      "train_samples_per_second": 140.315,
      "train_steps_per_second": 4.397
    }
  ],
  "logging_steps": 500,
  "max_steps": 9400,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 4968855705600000.0,
  "trial_name": null,
  "trial_params": null
}