Hugging Face's logo

Frikallo
/
Dodo82J-vgdunkey

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Dodo82J-vgdunkey
File size: 2,725 Bytes 
1cf1840
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0001298236559139785,
      "loss": 5.2886,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00012244731182795699,
      "loss": 4.8484,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00011507096774193549,
      "loss": 4.592,
      "step": 15
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00010769462365591397,
      "loss": 4.3362,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00010031827956989248,
      "loss": 4.3381,
      "step": 25
    },
    {
      "epoch": 0.32,
      "learning_rate": 9.294193548387097e-05,
      "loss": 4.229,
      "step": 30
    },
    {
      "epoch": 0.38,
      "learning_rate": 8.556559139784946e-05,
      "loss": 4.2006,
      "step": 35
    },
    {
      "epoch": 0.43,
      "learning_rate": 7.818924731182796e-05,
      "loss": 3.8651,
      "step": 40
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.081290322580646e-05,
      "loss": 4.0792,
      "step": 45
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.343655913978495e-05,
      "loss": 3.8664,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.606021505376345e-05,
      "loss": 3.7922,
      "step": 55
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.868387096774194e-05,
      "loss": 3.727,
      "step": 60
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.130752688172043e-05,
      "loss": 3.565,
      "step": 65
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.3931182795698924e-05,
      "loss": 3.7849,
      "step": 70
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.655483870967742e-05,
      "loss": 3.7644,
      "step": 75
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.9178494623655912e-05,
      "loss": 3.6057,
      "step": 80
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1802150537634409e-05,
      "loss": 3.648,
      "step": 85
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.4258064516129036e-06,
      "loss": 3.6404,
      "step": 90
    },
    {
      "epoch": 1.0,
      "step": 93,
      "total_flos": 48600317952000.0,
      "train_loss": 4.058929084449686,
      "train_runtime": 28.0555,
      "train_samples_per_second": 3.315,
      "train_steps_per_second": 3.315
    }
  ],
  "max_steps": 93,
  "num_train_epochs": 1,
  "total_flos": 48600317952000.0,
  "trial_name": null,
  "trial_params": null
}