Hugging Face's logo

LawChat-tw
/
chinese-llama2-files

Model card Files Community
chinese-llama2-files
File size: 3,080 Bytes 
f35c203
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.6186352968215942,
  "best_model_checkpoint": "saves/ChineseLLaMA2-7B-Chat/lora/2023-09-07-12-02-29/checkpoint-100",
  "epoch": 0.1083717149823896,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0009999919374161553,
      "loss": 2.0025,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009999677499246417,
      "loss": 1.7737,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0009999274383055143,
      "loss": 1.7391,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0009998710038588363,
      "loss": 1.7959,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009997984484046375,
      "loss": 1.713,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009997097742828556,
      "loss": 1.6441,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009996049843532607,
      "loss": 1.704,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009994840819953633,
      "loss": 1.6532,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009993470711083048,
      "loss": 1.6791,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009991939561107325,
      "loss": 1.6465,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000999024741940656,
      "loss": 1.6511,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009988394340552898,
      "loss": 1.6727,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009986380384308746,
      "loss": 1.6653,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009984205615624873,
      "loss": 1.6339,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009981870104638294,
      "loss": 1.5562,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009979373926670028,
      "loss": 1.6291,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009976717162222645,
      "loss": 1.625,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009973899896977695,
      "loss": 1.6008,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000997092222179292,
      "loss": 1.6821,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009967784232699352,
      "loss": 1.582,
      "step": 100
    },
    {
      "epoch": 0.11,
      "eval_loss": 1.6186352968215942,
      "eval_runtime": 10.6735,
      "eval_samples_per_second": 14.054,
      "eval_steps_per_second": 1.78,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 2766,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.29660416131072e+16,
  "trial_name": null,
  "trial_params": null
}