Hugging Face's logo

golaxy
/
gowizardlm

Text Generation
Transformers
PyTorch
TensorBoard
llama
text-generation-inference
Model card Files
xet
Metrics Community
2
gowizardlm
File size: 2,069 Bytes 
385f2d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 4469,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1e-05,
      "loss": 0.751,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 600
    },
    {
      "epoch": 0.2,
      "learning_rate": 3e-05,
      "loss": 0.6439,
      "step": 900
    },
    {
      "epoch": 0.27,
      "learning_rate": 4e-05,
      "loss": 0.6392,
      "step": 1200
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.6385,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "learning_rate": 6e-05,
      "loss": 0.6356,
      "step": 1800
    },
    {
      "epoch": 0.47,
      "learning_rate": 7e-05,
      "loss": 0.6297,
      "step": 2100
    },
    {
      "epoch": 0.54,
      "learning_rate": 8e-05,
      "loss": 0.6312,
      "step": 2400
    },
    {
      "epoch": 0.6,
      "learning_rate": 9e-05,
      "loss": 0.627,
      "step": 2700
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 0.6236,
      "step": 3000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 0.6269,
      "step": 3300
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 0.6273,
      "step": 3600
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 0.6158,
      "step": 3900
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 0.6154,
      "step": 4200
    },
    {
      "epoch": 1.0,
      "step": 4469,
      "total_flos": 2.955925823162417e+18,
      "train_loss": 0.6393276273497375,
      "train_runtime": 42382.3022,
      "train_samples_per_second": 3.374,
      "train_steps_per_second": 0.105
    }
  ],
  "max_steps": 4469,
  "num_train_epochs": 1,
  "total_flos": 2.955925823162417e+18,
  "trial_name": null,
  "trial_params": null
}