-
Notifications
You must be signed in to change notification settings - Fork 0
/
nlp-eval_mt_regression_fullbert.out
176 lines (160 loc) · 17.9 KB
/
nlp-eval_mt_regression_fullbert.out
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
174
175
176
comet_ml is installed but `COMET_API_KEY` is not set.
Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 2.90ba/s]
100%|██████████| 1/1 [00:00<00:00, 2.90ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 2.89ba/s]
100%|██████████| 1/1 [00:00<00:00, 2.89ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 8.21ba/s]
100%|██████████| 1/1 [00:00<00:00, 8.20ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 8.05ba/s]
100%|██████████| 1/1 [00:00<00:00, 8.03ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 6.67ba/s]
100%|██████████| 1/1 [00:00<00:00, 6.66ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 5.83ba/s]
100%|██████████| 1/1 [00:00<00:00, 5.82ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 6.46ba/s]
100%|██████████| 1/1 [00:00<00:00, 6.45ba/s]
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 5.10ba/s]
100%|██████████| 1/1 [00:00<00:00, 5.09ba/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 357
Batch size = 16
0%| | 0/23 [00:00<?, ?it/s]
13%|█▎ | 3/23 [00:00<00:00, 23.71it/s]
26%|██▌ | 6/23 [00:00<00:00, 19.98it/s]
39%|███▉ | 9/23 [00:00<00:00, 19.30it/s]
48%|████▊ | 11/23 [00:00<00:00, 19.04it/s]
57%|█████▋ | 13/23 [00:00<00:00, 18.90it/s]
65%|██████▌ | 15/23 [00:00<00:00, 18.81it/s]
74%|███████▍ | 17/23 [00:00<00:00, 18.69it/s]
83%|████████▎ | 19/23 [00:00<00:00, 18.63it/s]
91%|█████████▏| 21/23 [00:01<00:00, 18.63it/s]
100%|██████████| 23/23 [00:01<00:00, 19.35it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 360
Batch size = 16
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
{'eval_kappa': 0.7897213777018867, 'eval_loss': 0.7508907318115234, 'eval_runtime': 2.4406, 'eval_samples_per_second': 146.273, 'eval_steps_per_second': 9.424}
----------------------------------------------------------
0%| | 0/23 [00:00<?, ?it/s]
13%|█▎ | 3/23 [00:00<00:00, 27.59it/s]
26%|██▌ | 6/23 [00:00<00:00, 21.39it/s]
39%|███▉ | 9/23 [00:00<00:00, 19.57it/s]
52%|█████▏ | 12/23 [00:00<00:00, 19.14it/s]
61%|██████ | 14/23 [00:00<00:00, 18.78it/s]
70%|██████▉ | 16/23 [00:00<00:00, 18.24it/s]
78%|███████▊ | 18/23 [00:00<00:00, 17.96it/s]
87%|████████▋ | 20/23 [00:01<00:00, 17.71it/s]
96%|█████████▌| 22/23 [00:01<00:00, 17.59it/s]
100%|██████████| 23/23 [00:02<00:00, 8.22it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 345
Batch size = 16
[0, 1, 2, 3, 4, 5, 6]
{'eval_kappa': 0.6259655779915978, 'eval_loss': 0.3028137981891632, 'eval_runtime': 1.265, 'eval_samples_per_second': 284.576, 'eval_steps_per_second': 18.181}
----------------------------------------------------------
0%| | 0/22 [00:00<?, ?it/s]
18%|█▊ | 4/22 [00:00<00:00, 33.32it/s]
36%|███▋ | 8/22 [00:00<00:00, 29.63it/s]
50%|█████ | 11/22 [00:00<00:00, 28.82it/s]
64%|██████▎ | 14/22 [00:00<00:00, 27.59it/s]
77%|███████▋ | 17/22 [00:00<00:00, 27.68it/s]
91%|█████████ | 20/22 [00:00<00:00, 27.59it/s]
100%|██████████| 22/22 [00:00<00:00, 28.58it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 354
Batch size = 16
[0, 1, 2, 3]
{'eval_kappa': 0.5823670327990009, 'eval_loss': 0.49551454186439514, 'eval_runtime': 0.8138, 'eval_samples_per_second': 423.957, 'eval_steps_per_second': 27.035}
----------------------------------------------------------
0%| | 0/23 [00:00<?, ?it/s]
13%|█▎ | 3/23 [00:00<00:00, 28.37it/s]
26%|██▌ | 6/23 [00:00<00:00, 22.56it/s]
39%|███▉ | 9/23 [00:00<00:00, 21.12it/s]
52%|█████▏ | 12/23 [00:00<00:00, 20.56it/s]
65%|██████▌ | 15/23 [00:00<00:00, 20.23it/s]
78%|███████▊ | 18/23 [00:00<00:00, 20.07it/s]
91%|█████████▏| 21/23 [00:01<00:00, 19.91it/s]
100%|██████████| 23/23 [00:01<00:00, 21.24it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 361
Batch size = 16
[0, 1, 2, 3]
{'eval_kappa': 0.7983729341294628, 'eval_loss': 0.2773961126804352, 'eval_runtime': 1.1318, 'eval_samples_per_second': 312.788, 'eval_steps_per_second': 20.322}
----------------------------------------------------------
0%| | 0/23 [00:00<?, ?it/s]
13%|█▎ | 3/23 [00:00<00:00, 27.92it/s]
26%|██▌ | 6/23 [00:00<00:00, 21.58it/s]
39%|███▉ | 9/23 [00:00<00:00, 20.09it/s]
52%|█████▏ | 12/23 [00:00<00:00, 19.45it/s]
61%|██████ | 14/23 [00:00<00:00, 19.24it/s]
70%|██████▉ | 16/23 [00:00<00:00, 19.05it/s]
78%|███████▊ | 18/23 [00:00<00:00, 18.85it/s]
87%|████████▋ | 20/23 [00:01<00:00, 18.80it/s]
96%|█████████▌| 22/23 [00:01<00:00, 18.73it/s]
100%|██████████| 23/23 [00:01<00:00, 19.76it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 360
Batch size = 16
[0, 1, 2, 3, 4]
{'eval_kappa': 0.8149100257069408, 'eval_loss': 0.2750377357006073, 'eval_runtime': 1.2158, 'eval_samples_per_second': 296.924, 'eval_steps_per_second': 18.918}
----------------------------------------------------------
0%| | 0/23 [00:00<?, ?it/s]
13%|█▎ | 3/23 [00:00<00:00, 27.86it/s]
26%|██▌ | 6/23 [00:00<00:00, 21.54it/s]
39%|███▉ | 9/23 [00:00<00:00, 20.11it/s]
52%|█████▏ | 12/23 [00:00<00:00, 19.49it/s]
61%|██████ | 14/23 [00:00<00:00, 19.22it/s]
70%|██████▉ | 16/23 [00:00<00:00, 19.04it/s]
78%|███████▊ | 18/23 [00:00<00:00, 18.91it/s]
87%|████████▋ | 20/23 [00:01<00:00, 18.81it/s]
96%|█████████▌| 22/23 [00:01<00:00, 18.71it/s]
100%|██████████| 23/23 [00:01<00:00, 19.82it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 314
Batch size = 16
[0, 1, 2, 3, 4]
{'eval_kappa': 0.8485632992010058, 'eval_loss': 0.2394930124282837, 'eval_runtime': 1.2125, 'eval_samples_per_second': 296.912, 'eval_steps_per_second': 18.969}
----------------------------------------------------------
0%| | 0/20 [00:00<?, ?it/s]
15%|█▌ | 3/20 [00:00<00:00, 27.74it/s]
30%|███ | 6/20 [00:00<00:00, 21.52it/s]
45%|████▌ | 9/20 [00:00<00:00, 20.07it/s]
60%|██████ | 12/20 [00:00<00:00, 19.44it/s]
70%|███████ | 14/20 [00:00<00:00, 19.17it/s]
80%|████████ | 16/20 [00:00<00:00, 19.01it/s]
90%|█████████ | 18/20 [00:00<00:00, 18.89it/s]
100%|██████████| 20/20 [00:01<00:00, 19.84it/s]
The following columns in the evaluation set don't have a corresponding argument in `EssayScorerModel.forward` and have been ignored: rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2. If rater1_trait6, rater2_trait4, rater2_trait3, rater2_trait6, rater2_domain1, rater1_trait3, rater1_trait2, Unnamed: 0, rater2_trait2, rater2_trait1, rater1_trait4, essay_set, rater3_domain1, rater3_trait2, essay, essay_id, rater1_domain1, rater2_trait5, token_type_ids, rater3_trait3, rater3_trait6, domain2_score, rater3_trait1, rater3_trait4, rater1_domain2, __index_level_0__, rater3_trait5, rater1_trait1, rater1_trait5, rater2_domain2 are not expected by `EssayScorerModel.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 145
Batch size = 16
[0, 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]
{'eval_kappa': 0.8370258956033648, 'eval_loss': 6.148499488830566, 'eval_runtime': 1.0602, 'eval_samples_per_second': 296.165, 'eval_steps_per_second': 18.864}
----------------------------------------------------------
0%| | 0/10 [00:00<?, ?it/s]
30%|███ | 3/10 [00:00<00:00, 27.91it/s]
60%|██████ | 6/10 [00:00<00:00, 21.49it/s]
90%|█████████ | 9/10 [00:00<00:00, 20.00it/s]
100%|██████████| 10/10 [00:00<00:00, 22.55it/s]
[0, 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]
{'eval_kappa': 0.7441182548058234, 'eval_loss': 15.611396789550781, 'eval_runtime': 0.4965, 'eval_samples_per_second': 292.034, 'eval_steps_per_second': 20.14}
----------------------------------------------------------
Average eval_Kappa: 0.7551305497423852