Hugging Face's logo

huggingartists
/
platina

Text Generation
Transformers
PyTorch
JAX
English
gpt2
huggingartists
lyrics
lm-head
causal-lm
text-generation-inference
Inference Endpoints
Model card Files Community
1
platina
File size: 2,604 Bytes 
24a82fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.7263113260269165,
  "best_model_checkpoint": "output/platina/checkpoint-86",
  "epoch": 1.0,
  "global_step": 86,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 0.00013605888543050137,
      "loss": 2.653,
      "step": 5
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001326735050590528,
      "loss": 2.339,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00012715648590796197,
      "loss": 2.2005,
      "step": 15
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011969137173622343,
      "loss": 2.1397,
      "step": 20
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00011052651678711246,
      "loss": 2.05,
      "step": 25
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.99668233786982e-05,
      "loss": 1.9257,
      "step": 30
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.83635982164553e-05,
      "loss": 1.9766,
      "step": 35
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.61028648947222e-05,
      "loss": 1.9569,
      "step": 40
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.359252141426174e-05,
      "loss": 1.9599,
      "step": 45
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.1248769967930697e-05,
      "loss": 1.8944,
      "step": 50
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.9482270457119095e-05,
      "loss": 1.8734,
      "step": 55
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.8684478392724447e-05,
      "loss": 1.8827,
      "step": 60
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.9214621700201495e-05,
      "loss": 1.8779,
      "step": 65
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.1387749692754382e-05,
      "loss": 1.776,
      "step": 70
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.464251807155671e-06,
      "loss": 1.8927,
      "step": 75
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6411947996634035e-06,
      "loss": 1.8982,
      "step": 80
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.576660180157781e-08,
      "loss": 1.8376,
      "step": 85
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.7263113260269165,
      "eval_runtime": 6.7602,
      "eval_samples_per_second": 21.153,
      "eval_steps_per_second": 2.663,
      "step": 86
    }
  ],
  "max_steps": 86,
  "num_train_epochs": 1,
  "total_flos": 88969936896000.0,
  "trial_name": null,
  "trial_params": null
}