Hugging Face's logo

Azaz666
/
flan-t5-strategyqa

t5
Model card Files Community
flan-t5-strategyqa
File size: 2,636 Bytes 
12513c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 10767,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.703,
      "step": 500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.5833,
      "step": 1000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.5444,
      "step": 1500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.5199,
      "step": 2000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.4972,
      "step": 2500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 1.4789,
      "step": 3000
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 1.448,
      "step": 3500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 1.3726,
      "step": 4000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 1.3587,
      "step": 4500
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 1.3301,
      "step": 5000
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 1.3619,
      "step": 5500
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 1.3321,
      "step": 6000
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 1.3311,
      "step": 6500
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 1.328,
      "step": 7000
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 1.2657,
      "step": 7500
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 1.2526,
      "step": 8000
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001,
      "loss": 1.2357,
      "step": 8500
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 1.234,
      "step": 9000
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001,
      "loss": 1.2335,
      "step": 9500
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001,
      "loss": 1.2372,
      "step": 10000
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 1.2362,
      "step": 10500
    }
  ],
  "logging_steps": 500,
  "max_steps": 10767,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 6298513440768.0,
  "trial_name": null,
  "trial_params": null
}