Hugging Face's logo

JennnDexter
/
clm

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
clm
File size: 2,648 Bytes 
8d455d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.3767106549364614,
  "best_model_checkpoint": "D:/1_SyscoPY_D/NLP/Data/Transformers_Hug/checkpoint/distilgpt2\\checkpoint-145",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 3.9461,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.884615384615385e-05,
      "loss": 3.813,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.6538461538461538e-05,
      "loss": 3.6952,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.423076923076923e-05,
      "loss": 3.6721,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.1923076923076924e-05,
      "loss": 3.6339,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9615384615384617e-05,
      "loss": 3.6567,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7307692307692306e-05,
      "loss": 3.6063,
      "step": 70
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.5e-05,
      "loss": 3.6228,
      "step": 80
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.2692307692307693e-05,
      "loss": 3.5844,
      "step": 90
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.0384615384615384e-05,
      "loss": 3.6194,
      "step": 100
    },
    {
      "epoch": 0.76,
      "learning_rate": 8.076923076923077e-06,
      "loss": 3.5918,
      "step": 110
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.76923076923077e-06,
      "loss": 3.5682,
      "step": 120
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 3.5482,
      "step": 130
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.153846153846154e-06,
      "loss": 3.585,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3767106549364614,
      "eval_loss": 3.4325666427612305,
      "eval_runtime": 12.5136,
      "eval_samples_per_second": 19.179,
      "eval_steps_per_second": 2.397,
      "step": 145
    },
    {
      "epoch": 1.0,
      "step": 145,
      "total_flos": 605685867872256.0,
      "train_loss": 3.6505329921327787,
      "train_runtime": 308.0636,
      "train_samples_per_second": 7.524,
      "train_steps_per_second": 0.471
    }
  ],
  "logging_steps": 10,
  "max_steps": 145,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 605685867872256.0,
  "trial_name": null,
  "trial_params": null
}