Hugging Face's logo

sabersaleh
/
Llama2-7B-IPO

PyTorch
llama
Model card Files Community
1
Llama2-7B-IPO
File size: 2,484 Bytes 
9add6e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9956483899042646,
  "global_step": 143,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 9.63768115942029e-06,
      "loss": 249945.65,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.91304347826087e-06,
      "loss": 249865.2,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.188405797101449e-06,
      "loss": 249854.025,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.4637681159420295e-06,
      "loss": 249333.625,
      "step": 40
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.739130434782609e-06,
      "loss": 249087.425,
      "step": 50
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.014492753623189e-06,
      "loss": 248773.0,
      "step": 60
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.289855072463769e-06,
      "loss": 250035.3,
      "step": 70
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.565217391304348e-06,
      "loss": 248390.65,
      "step": 80
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.840579710144928e-06,
      "loss": 249652.4,
      "step": 90
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.1159420289855073e-06,
      "loss": 248661.85,
      "step": 100
    },
    {
      "epoch": 0.7,
      "eval_loss": 248310.953125,
      "eval_runtime": 23.5447,
      "eval_samples_per_second": 21.236,
      "eval_steps_per_second": 1.359,
      "step": 100
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.391304347826087e-06,
      "loss": 247836.9,
      "step": 110
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 250259.4,
      "step": 120
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.420289855072465e-07,
      "loss": 247886.225,
      "step": 130
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.173913043478261e-07,
      "loss": 246939.925,
      "step": 140
    },
    {
      "epoch": 1.0,
      "step": 143,
      "total_flos": 0.0,
      "train_loss": 249038.73645104896,
      "train_runtime": 2191.4571,
      "train_samples_per_second": 4.194,
      "train_steps_per_second": 0.065
    }
  ],
  "max_steps": 143,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}