Hugging Face's logo

Gantenbein
/
ADDI-CH-RoBERTa

Question Answering
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
1
ADDI-CH-RoBERTa
File size: 3,156 Bytes 
efe56ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 11250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.7777777777777784e-05,
      "loss": 0.4603,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.555555555555556e-05,
      "loss": 0.1251,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.12,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.111111111111111e-05,
      "loss": 0.0403,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0238,
      "step": 2500
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.0249,
      "step": 3000
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.444444444444445e-05,
      "loss": 0.0115,
      "step": 3500
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.222222222222223e-05,
      "loss": 0.0129,
      "step": 4000
    },
    {
      "epoch": 0.4,
      "learning_rate": 3e-05,
      "loss": 0.0098,
      "step": 4500
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0117,
      "step": 5000
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5555555555555554e-05,
      "loss": 0.0105,
      "step": 5500
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.0045,
      "step": 6000
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.111111111111111e-05,
      "loss": 0.0117,
      "step": 6500
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.888888888888889e-05,
      "loss": 0.0026,
      "step": 7000
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0088,
      "step": 7500
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.4444444444444444e-05,
      "loss": 0.0043,
      "step": 8000
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2222222222222222e-05,
      "loss": 0.002,
      "step": 8500
    },
    {
      "epoch": 0.8,
      "learning_rate": 1e-05,
      "loss": 0.0057,
      "step": 9000
    },
    {
      "epoch": 0.84,
      "learning_rate": 7.777777777777777e-06,
      "loss": 0.0043,
      "step": 9500
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0031,
      "step": 10000
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0062,
      "step": 10500
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1111111111111112e-06,
      "loss": 0.0042,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "step": 11250,
      "total_flos": 2.572437201408e+16,
      "train_runtime": 4547.1523,
      "train_samples_per_second": 2.474
    }
  ],
  "max_steps": 11250,
  "num_train_epochs": 1,
  "total_flos": 2.572437201408e+16,
  "trial_name": null,
  "trial_params": null
}