Hugging Face's logo

philschmid
/
f9749f03ca

Text Generation
Transformers
TensorBoard
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
f9749f03ca
File size: 2,469 Bytes 
ee5ddfb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06666666666666667,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 9.4994,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.7223,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.3713,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.2695,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.2811,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.2291,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.1263,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 7.0881,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 6.5989,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 6.0091,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.5511,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.3413,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.1775,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 5.104,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 5.0133,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 4.9843,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.9256,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.8692,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.9233,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 4.9139,
      "step": 200
    }
  ],
  "max_steps": 3000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 83751862272000.0,
  "trial_name": null,
  "trial_params": null
}