Hugging Face's logo

RedMist137
/
RLHF_5k_preference

PyTorch
Model card Files
xet
Community
RLHF_5k_preference
File size: 2,661 Bytes
f0afa73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988901220865705,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 8.859191006777897e-06,
      "loss": 13.3153,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 1e-05,
      "loss": 12.4846,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 12.2623,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 11.9316,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 11.6846,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 11.4766,
      "step": 60
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 11.1113,
      "step": 70
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 11.8791,
      "step": 80
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 11.0548,
      "step": 90
    },
    {
      "epoch": 0.44,
      "learning_rate": 1e-05,
      "loss": 11.2625,
      "step": 100
    },
    {
      "epoch": 0.49,
      "learning_rate": 1e-05,
      "loss": 10.8404,
      "step": 110
    },
    {
      "epoch": 0.53,
      "learning_rate": 1e-05,
      "loss": 11.0007,
      "step": 120
    },
    {
      "epoch": 0.58,
      "learning_rate": 1e-05,
      "loss": 11.1484,
      "step": 130
    },
    {
      "epoch": 0.62,
      "learning_rate": 1e-05,
      "loss": 11.1086,
      "step": 140
    },
    {
      "epoch": 0.67,
      "learning_rate": 1e-05,
      "loss": 10.8408,
      "step": 150
    },
    {
      "epoch": 0.71,
      "learning_rate": 1e-05,
      "loss": 10.9842,
      "step": 160
    },
    {
      "epoch": 0.75,
      "learning_rate": 1e-05,
      "loss": 10.6507,
      "step": 170
    },
    {
      "epoch": 0.8,
      "learning_rate": 1e-05,
      "loss": 11.2162,
      "step": 180
    },
    {
      "epoch": 0.84,
      "learning_rate": 1e-05,
      "loss": 10.999,
      "step": 190
    },
    {
      "epoch": 0.89,
      "learning_rate": 1e-05,
      "loss": 10.9756,
      "step": 200
    },
    {
      "epoch": 0.93,
      "learning_rate": 1e-05,
      "loss": 11.0555,
      "step": 210
    },
    {
      "epoch": 0.98,
      "learning_rate": 1e-05,
      "loss": 11.0574,
      "step": 220
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 2,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}