Hugging Face's logo

Teddysum
/
bllossom-polyglot-12.8b-lima-ko-adapter-4bit

Generated from Trainer
Model card Files Community
bllossom-polyglot-12.8b-lima-ko-adapter-4bit
File size: 2,705 Bytes 
bb196a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.2745098039215685,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.0663,
      "step": 10
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 2.0741,
      "step": 20
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.9687,
      "step": 30
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.9634,
      "step": 40
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.8635,
      "step": 50
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.8845,
      "step": 60
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 1.7803,
      "step": 70
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 1.6615,
      "step": 80
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0002,
      "loss": 1.7173,
      "step": 90
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0002,
      "loss": 1.6624,
      "step": 100
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0002,
      "loss": 1.3819,
      "step": 110
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0002,
      "loss": 1.5122,
      "step": 120
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0002,
      "loss": 1.5129,
      "step": 130
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0002,
      "loss": 1.3089,
      "step": 140
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0002,
      "loss": 1.2554,
      "step": 150
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0002,
      "loss": 1.3004,
      "step": 160
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0002,
      "loss": 1.1838,
      "step": 170
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.0002,
      "loss": 1.0549,
      "step": 180
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.0002,
      "loss": 1.1998,
      "step": 190
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.0002,
      "loss": 0.9754,
      "step": 200
    },
    {
      "epoch": 6.27,
      "step": 200,
      "total_flos": 1.7550743484911616e+17,
      "train_loss": 1.5663859701156617,
      "train_runtime": 4414.9851,
      "train_samples_per_second": 1.45,
      "train_steps_per_second": 0.045
    }
  ],
  "max_steps": 200,
  "num_train_epochs": 7,
  "total_flos": 1.7550743484911616e+17,
  "trial_name": null,
  "trial_params": null
}