Hugging Face's logo

s3nh
/
pythia-410m-103k-steps-self-instruct-polish

Text Generation
Transformers
PyTorch
Safetensors
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Community
1
pythia-410m-103k-steps-self-instruct-polish
File size: 2,818 Bytes 
0f0c3f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 21.278782894736842,
  "global_step": 103500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.03,
      "learning_rate": 9.588973502853666e-06,
      "loss": 0.6499,
      "step": 5000
    },
    {
      "epoch": 2.06,
      "learning_rate": 9.177782529317917e-06,
      "loss": 0.5129,
      "step": 10000
    },
    {
      "epoch": 3.08,
      "learning_rate": 8.766591555782168e-06,
      "loss": 0.4726,
      "step": 15000
    },
    {
      "epoch": 4.11,
      "learning_rate": 8.355400582246419e-06,
      "loss": 0.4026,
      "step": 20000
    },
    {
      "epoch": 5.14,
      "learning_rate": 7.94420960871067e-06,
      "loss": 0.3312,
      "step": 25000
    },
    {
      "epoch": 6.17,
      "learning_rate": 7.533018635174921e-06,
      "loss": 0.2952,
      "step": 30000
    },
    {
      "epoch": 7.2,
      "learning_rate": 7.121827661639172e-06,
      "loss": 0.229,
      "step": 35000
    },
    {
      "epoch": 8.22,
      "learning_rate": 6.710636688103423e-06,
      "loss": 0.1724,
      "step": 40000
    },
    {
      "epoch": 9.25,
      "learning_rate": 6.2994457145676745e-06,
      "loss": 0.1658,
      "step": 45000
    },
    {
      "epoch": 10.28,
      "learning_rate": 5.888254741031926e-06,
      "loss": 0.1506,
      "step": 50000
    },
    {
      "epoch": 11.31,
      "learning_rate": 5.477063767496177e-06,
      "loss": 0.1034,
      "step": 55000
    },
    {
      "epoch": 12.34,
      "learning_rate": 5.065872793960427e-06,
      "loss": 0.0735,
      "step": 60000
    },
    {
      "epoch": 13.36,
      "learning_rate": 4.654681820424679e-06,
      "loss": 0.0548,
      "step": 65000
    },
    {
      "epoch": 14.39,
      "learning_rate": 4.24349084688893e-06,
      "loss": 0.0437,
      "step": 70000
    },
    {
      "epoch": 15.42,
      "learning_rate": 3.83229987335318e-06,
      "loss": 0.0721,
      "step": 75000
    },
    {
      "epoch": 16.45,
      "learning_rate": 3.421108899817431e-06,
      "loss": 0.0555,
      "step": 80000
    },
    {
      "epoch": 17.48,
      "learning_rate": 3.0099179262816823e-06,
      "loss": 0.041,
      "step": 85000
    },
    {
      "epoch": 18.5,
      "learning_rate": 2.5987269527459334e-06,
      "loss": 0.034,
      "step": 90000
    },
    {
      "epoch": 19.53,
      "learning_rate": 2.187535979210185e-06,
      "loss": 0.0392,
      "step": 95000
    },
    {
      "epoch": 20.56,
      "learning_rate": 1.7763450056744355e-06,
      "loss": 0.035,
      "step": 100000
    }
  ],
  "max_steps": 121600,
  "num_train_epochs": 25,
  "total_flos": 8.999206543215821e+17,
  "trial_name": null,
  "trial_params": null
}