Hugging Face's logo

huggingartists
/
aaron-watson

Text Generation
Transformers
PyTorch
JAX
English
gpt2
huggingartists
lyrics
lm-head
causal-lm
text-generation-inference
Inference Endpoints
Model card Files Community
aaron-watson
File size: 2,703 Bytes 
2baf059
6df531f
 
 
 
2baf059
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6df531f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2baf059
 
6df531f
 
 
2baf059
 
 
 
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
 
{
  "best_metric": 2.9697048664093018,
  "best_model_checkpoint": "output/aaron-watson/checkpoint-75",
  "epoch": 3.0,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.0001240985658141214,
      "loss": 3.6755,
      "step": 5
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.97985658141214e-05,
      "loss": 3.521,
      "step": 10
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.740143418587861e-05,
      "loss": 3.4758,
      "step": 15
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3101434185878613e-05,
      "loss": 3.2857,
      "step": 20
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 3.2955,
      "step": 25
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.0358455181121826,
      "eval_runtime": 1.5968,
      "eval_samples_per_second": 21.293,
      "eval_steps_per_second": 3.131,
      "step": 25
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3101434185878598e-05,
      "loss": 3.1772,
      "step": 30
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.74014341858786e-05,
      "loss": 3.1081,
      "step": 35
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.979856581412138e-05,
      "loss": 3.3239,
      "step": 40
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001240985658141214,
      "loss": 3.0381,
      "step": 45
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001372,
      "loss": 3.0911,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.996838331222534,
      "eval_runtime": 1.5805,
      "eval_samples_per_second": 21.512,
      "eval_steps_per_second": 3.163,
      "step": 50
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012409856581412136,
      "loss": 3.0342,
      "step": 55
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.979856581412141e-05,
      "loss": 2.8495,
      "step": 60
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.7401434185878625e-05,
      "loss": 2.895,
      "step": 65
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.310143418587862e-05,
      "loss": 2.8209,
      "step": 70
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 2.7285,
      "step": 75
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.9697048664093018,
      "eval_runtime": 1.7446,
      "eval_samples_per_second": 21.208,
      "eval_steps_per_second": 2.866,
      "step": 75
    }
  ],
  "max_steps": 125,
  "num_train_epochs": 5,
  "total_flos": 76689211392000.0,
  "trial_name": null,
  "trial_params": null
}