File size: 2,539 Bytes
63a2b4a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 8472,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 4.7049102927289904e-05,
      "loss": 2.2823,
      "step": 500
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.409820585457979e-05,
      "loss": 1.8016,
      "step": 1000
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.114730878186969e-05,
      "loss": 1.6528,
      "step": 1500
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.819641170915959e-05,
      "loss": 1.5503,
      "step": 2000
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.524551463644948e-05,
      "loss": 1.4888,
      "step": 2500
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.229461756373938e-05,
      "loss": 1.3657,
      "step": 3000
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.9343720491029275e-05,
      "loss": 1.2204,
      "step": 3500
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.639282341831917e-05,
      "loss": 1.2022,
      "step": 4000
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.3441926345609068e-05,
      "loss": 1.1694,
      "step": 4500
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.0491029272898962e-05,
      "loss": 1.17,
      "step": 5000
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.7540132200188857e-05,
      "loss": 1.136,
      "step": 5500
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.4589235127478753e-05,
      "loss": 1.008,
      "step": 6000
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.1638338054768651e-05,
      "loss": 0.9451,
      "step": 6500
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.687440982058546e-06,
      "loss": 0.9494,
      "step": 7000
    },
    {
      "epoch": 2.66,
      "learning_rate": 5.736543909348442e-06,
      "loss": 0.928,
      "step": 7500
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.785646836638338e-06,
      "loss": 0.9309,
      "step": 8000
    },
    {
      "epoch": 3.0,
      "step": 8472,
      "total_flos": 1.6919257779388416e+16,
      "train_loss": 1.278769531826347,
      "train_runtime": 2749.7174,
      "train_samples_per_second": 30.809,
      "train_steps_per_second": 3.081
    }
  ],
  "max_steps": 8472,
  "num_train_epochs": 3,
  "total_flos": 1.6919257779388416e+16,
  "trial_name": null,
  "trial_params": null
}