Hugging Face's logo

Sigurdur
/
jonas-hallgrimsson-gpt

Text Generation
Transformers
PyTorch
TensorBoard
Icelandic
gpt2
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jonas-hallgrimsson-gpt
File size: 3,915 Bytes 
f0765a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0106375,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "eval_loss": 2.681640625,
      "eval_runtime": 8.3811,
      "eval_samples_per_second": 109.293,
      "eval_steps_per_second": 13.721,
      "step": 200
    },
    {
      "epoch": 0.04,
      "eval_loss": 2.513671875,
      "eval_runtime": 8.2785,
      "eval_samples_per_second": 110.649,
      "eval_steps_per_second": 13.891,
      "step": 400
    },
    {
      "epoch": 1.01,
      "learning_rate": 5e-05,
      "loss": 6.5037,
      "step": 500
    },
    {
      "epoch": 1.02,
      "eval_loss": 2.380859375,
      "eval_runtime": 8.3078,
      "eval_samples_per_second": 110.258,
      "eval_steps_per_second": 13.842,
      "step": 600
    },
    {
      "epoch": 1.04,
      "eval_loss": 2.34375,
      "eval_runtime": 8.3276,
      "eval_samples_per_second": 109.996,
      "eval_steps_per_second": 13.81,
      "step": 800
    },
    {
      "epoch": 2.02,
      "learning_rate": 5e-05,
      "loss": 4.8504,
      "step": 1000
    },
    {
      "epoch": 2.02,
      "eval_loss": 2.275390625,
      "eval_runtime": 8.3087,
      "eval_samples_per_second": 110.247,
      "eval_steps_per_second": 13.841,
      "step": 1000
    },
    {
      "epoch": 2.04,
      "eval_loss": 2.333984375,
      "eval_runtime": 8.287,
      "eval_samples_per_second": 110.535,
      "eval_steps_per_second": 13.877,
      "step": 1200
    },
    {
      "epoch": 3.02,
      "eval_loss": 2.20703125,
      "eval_runtime": 8.3018,
      "eval_samples_per_second": 110.337,
      "eval_steps_per_second": 13.852,
      "step": 1400
    },
    {
      "epoch": 3.03,
      "learning_rate": 5e-05,
      "loss": 4.3741,
      "step": 1500
    },
    {
      "epoch": 3.04,
      "eval_loss": 2.248046875,
      "eval_runtime": 8.2881,
      "eval_samples_per_second": 110.521,
      "eval_steps_per_second": 13.875,
      "step": 1600
    },
    {
      "epoch": 4.01,
      "eval_loss": 2.205078125,
      "eval_runtime": 8.2889,
      "eval_samples_per_second": 110.51,
      "eval_steps_per_second": 13.874,
      "step": 1800
    },
    {
      "epoch": 4.03,
      "learning_rate": 5e-05,
      "loss": 5.6907,
      "step": 2000
    },
    {
      "epoch": 4.03,
      "eval_loss": 2.25,
      "eval_runtime": 8.2748,
      "eval_samples_per_second": 110.698,
      "eval_steps_per_second": 13.898,
      "step": 2000
    },
    {
      "epoch": 5.01,
      "eval_loss": 2.1640625,
      "eval_runtime": 8.2832,
      "eval_samples_per_second": 110.586,
      "eval_steps_per_second": 13.884,
      "step": 2200
    },
    {
      "epoch": 5.03,
      "eval_loss": 2.146484375,
      "eval_runtime": 8.2965,
      "eval_samples_per_second": 110.408,
      "eval_steps_per_second": 13.861,
      "step": 2400
    },
    {
      "epoch": 6.0,
      "learning_rate": 5e-05,
      "loss": 4.6906,
      "step": 2500
    },
    {
      "epoch": 6.01,
      "eval_loss": 2.13671875,
      "eval_runtime": 8.2725,
      "eval_samples_per_second": 110.729,
      "eval_steps_per_second": 13.902,
      "step": 2600
    },
    {
      "epoch": 6.03,
      "eval_loss": 2.140625,
      "eval_runtime": 8.2842,
      "eval_samples_per_second": 110.572,
      "eval_steps_per_second": 13.882,
      "step": 2800
    },
    {
      "epoch": 7.01,
      "learning_rate": 5e-05,
      "loss": 3.4001,
      "step": 3000
    },
    {
      "epoch": 7.01,
      "eval_loss": 2.146484375,
      "eval_runtime": 8.2802,
      "eval_samples_per_second": 110.625,
      "eval_steps_per_second": 13.888,
      "step": 3000
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 17891409788928.0,
  "trial_name": null,
  "trial_params": null
}