Hugging Face's logo

huggingartists
/
viktor-tsoi

Text Generation
Transformers
PyTorch
JAX
English
gpt2
huggingartists
lyrics
lm-head
causal-lm
Inference Endpoints
text-generation-inference
Model card Files Community
1
viktor-tsoi
File size: 2,686 Bytes 
17aae1f
4008979
 
 
 
17aae1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4008979
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17aae1f
 
4008979
 
 
17aae1f
 
 
 
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
 
{
  "best_metric": 1.6593416929244995,
  "best_model_checkpoint": "output/viktor-tsoi/checkpoint-82",
  "epoch": 2.0,
  "global_step": 82,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 0.0001322266681456037,
      "loss": 2.2855,
      "step": 5
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011802778132101399,
      "loss": 2.0776,
      "step": 10
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.666210850995393e-05,
      "loss": 1.9417,
      "step": 15
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.122756753113643e-05,
      "loss": 1.7633,
      "step": 20
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.541204214117672e-05,
      "loss": 1.9391,
      "step": 25
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.2958656968642224e-05,
      "loss": 1.7733,
      "step": 30
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.123042792471594e-06,
      "loss": 1.864,
      "step": 35
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.0128603879540573e-07,
      "loss": 1.8436,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.742375135421753,
      "eval_runtime": 2.5783,
      "eval_samples_per_second": 20.944,
      "eval_steps_per_second": 2.715,
      "step": 41
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.197007505031765e-06,
      "loss": 1.858,
      "step": 45
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.5675842264214697e-05,
      "loss": 1.8206,
      "step": 50
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.58284204500588e-05,
      "loss": 1.7518,
      "step": 55
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.0732717017669706e-05,
      "loss": 1.744,
      "step": 60
    },
    {
      "epoch": 1.59,
      "learning_rate": 8.677773105069102e-05,
      "loss": 1.7542,
      "step": 65
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00011018706319231134,
      "loss": 1.7612,
      "step": 70
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00012756647503932202,
      "loss": 1.7551,
      "step": 75
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001363960370713319,
      "loss": 1.7343,
      "step": 80
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.6593416929244995,
      "eval_runtime": 2.6581,
      "eval_samples_per_second": 21.444,
      "eval_steps_per_second": 3.01,
      "step": 82
    }
  ],
  "max_steps": 82,
  "num_train_epochs": 2,
  "total_flos": 84397326336000.0,
  "trial_name": null,
  "trial_params": null
}