Hugging Face's logo

sptrodon
/
Optimum-Graphcore-Demo

Question Answering
Transformers
PyTorch
Graphcore
bert
Inference Endpoints
Model card Files Community
1
Optimum-Graphcore-Demo
File size: 1,944 Bytes 
b4fefc8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0001927536231884058,
      "loss": 2.497,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001855072463768116,
      "loss": 1.0576,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001782608695652174,
      "loss": 1.063,
      "step": 75
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001710144927536232,
      "loss": 1.5434,
      "step": 100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000163768115942029,
      "loss": 1.1751,
      "step": 125
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.9868,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00014927536231884058,
      "loss": 1.0466,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.7962,
      "step": 200
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001347826086956522,
      "loss": 1.0158,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00012753623188405797,
      "loss": 0.8366,
      "step": 250
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00012028985507246378,
      "loss": 1.2794,
      "step": 275
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.6535,
      "step": 300
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010579710144927538,
      "loss": 0.878,
      "step": 325
    }
  ],
  "max_steps": 690,
  "num_train_epochs": 2,
  "start_time": 1678594586.128044,
  "total_flos": 1.5748493096591032e+19,
  "trial_name": null,
  "trial_params": null
}