Hugging Face's logo

wangrongsheng
/
Aurora-Plus

Text Generation
Safetensors
Chinese
English
Model card Files Community
Aurora-Plus
File size: 2,906 Bytes 
dc1d3d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10301976691777735,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.9996726480206315e-05,
      "loss": 0.7422,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9986906778099784e-05,
      "loss": 0.6673,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9970543465279565e-05,
      "loss": 0.6749,
      "step": 300
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994764082699591e-05,
      "loss": 0.6481,
      "step": 400
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.991820486102801e-05,
      "loss": 0.6505,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9882243276113245e-05,
      "loss": 0.6708,
      "step": 600
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.983976548992841e-05,
      "loss": 0.6596,
      "step": 700
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9790782626623436e-05,
      "loss": 0.6657,
      "step": 800
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.97353075139081e-05,
      "loss": 0.659,
      "step": 900
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9673354679692785e-05,
      "loss": 0.6519,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.960494034828381e-05,
      "loss": 0.638,
      "step": 1100
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9530082436134614e-05,
      "loss": 0.629,
      "step": 1200
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.944880054715378e-05,
      "loss": 0.6464,
      "step": 1300
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9361115967571094e-05,
      "loss": 0.642,
      "step": 1400
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.926705166036311e-05,
      "loss": 0.6431,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.916663225923953e-05,
      "loss": 0.6465,
      "step": 1600
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.905988406219217e-05,
      "loss": 0.6439,
      "step": 1700
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8946835024607885e-05,
      "loss": 0.652,
      "step": 1800
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8827514751947656e-05,
      "loss": 0.6376,
      "step": 1900
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8701954491993426e-05,
      "loss": 0.6357,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 19413,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "total_flos": 4.5346633176597135e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}