Hugging Face's logo

Federic
/
CDAgpt-llama-13b-v2

Safetensors
Model card Files Community
CDAgpt-llama-13b-v2
File size: 2,992 Bytes 
889a66f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4461,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.428,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2611,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0726,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8897,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7397,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.699,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7029,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.63,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7011,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5865,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6309,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5263,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5052,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5682,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5076,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5277,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4567,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4831,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4565,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4851,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4713,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4407,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.486,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4523,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4273383195279360.0,
  "trial_name": null,
  "trial_params": null
}