Hugging Face's logo

Bruno
/
Caramelo_7B

Text Generation
Adapters
Portuguese
English
Model card Files Community
1
Caramelo_7B
File size: 2,244 Bytes 
00efc34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 180.0,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 10.0,
      "learning_rate": 0.0002,
      "loss": 0.4973,
      "step": 10
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0002,
      "loss": 0.1772,
      "step": 20
    },
    {
      "epoch": 30.0,
      "learning_rate": 0.0002,
      "loss": 0.0441,
      "step": 30
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.0002,
      "loss": 0.0221,
      "step": 40
    },
    {
      "epoch": 50.0,
      "learning_rate": 0.0002,
      "loss": 0.0174,
      "step": 50
    },
    {
      "epoch": 60.0,
      "learning_rate": 0.0002,
      "loss": 0.0132,
      "step": 60
    },
    {
      "epoch": 70.0,
      "learning_rate": 0.0002,
      "loss": 0.0088,
      "step": 70
    },
    {
      "epoch": 80.0,
      "learning_rate": 0.0002,
      "loss": 0.0071,
      "step": 80
    },
    {
      "epoch": 90.0,
      "learning_rate": 0.0002,
      "loss": 0.0061,
      "step": 90
    },
    {
      "epoch": 100.0,
      "learning_rate": 0.0002,
      "loss": 0.0056,
      "step": 100
    },
    {
      "epoch": 110.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 110
    },
    {
      "epoch": 120.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 120
    },
    {
      "epoch": 130.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 130
    },
    {
      "epoch": 140.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 140
    },
    {
      "epoch": 150.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 150
    },
    {
      "epoch": 160.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 160
    },
    {
      "epoch": 170.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 170
    },
    {
      "epoch": 180.0,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 180
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 500,
  "total_flos": 3.046874617479168e+16,
  "trial_name": null,
  "trial_params": null
}