Hugging Face's logo

Roner1
/
LLaMA-Colosal-NeuroIPS

PEFT
Model card Files Community
LLaMA-Colosal-NeuroIPS
File size: 1,934 Bytes 
d5b8c05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09992006394884093,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9246,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9273,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8793,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8658,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7721,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8723,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.7366,
      "step": 175
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8426,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.7238,
      "step": 225
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.8572,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.7551,
      "step": 275
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.793,
      "step": 300
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.7013,
      "step": 325
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.8157,
      "step": 350
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5965,
      "step": 375
    }
  ],
  "max_steps": 3753,
  "num_train_epochs": 1,
  "total_flos": 6702415080751104.0,
  "trial_name": null,
  "trial_params": null
}