-
Notifications
You must be signed in to change notification settings - Fork 0
/
log
211 lines (202 loc) · 13.6 KB
/
log
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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
PS C:\Users\MyUser\Desktop\ML> ludwig train --dataset .\Tweets.csv --config .\model_definition.yaml
2020-12-22 00:28:22.830053: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\typeguard\__init__.py:885: UserWarning: no type annotations present -- not typechecking tensorflow_addons.layers.max_unpooling_2d.MaxUnpooling2D.__init__
warn('no type annotations present -- not typechecking {}'.format(function_name(func)))
███████████████████████
█ █ █ █ ▜█ █ █ █ █ █
█ █ █ █ █ █ █ █ █ █ ███
█ █ █ █ █ █ █ █ █ ▌ █
█ █████ █ █ █ █ █ █ █ █
█ █ ▟█ █ █ █
███████████████████████
ludwig v0.3.2-dev1 - Train
2020-12-22 00:28:24.518257: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2020-12-22 00:28:24.530613: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library nvcuda.dll
2020-12-22 00:28:25.225415: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:02:00.0 name: GeForce MX150 computeCapability: 6.1
coreClock: 1.0375GHz coreCount: 3 deviceMemorySize: 2.00GiB deviceMemoryBandwidth: 37.33GiB/s
2020-12-22 00:28:25.226828: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
2020-12-22 00:28:25.248354: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll
2020-12-22 00:28:25.248774: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll
2020-12-22 00:28:25.254368: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cufft64_10.dll
2020-12-22 00:28:25.266474: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library curand64_10.dll
2020-12-22 00:28:25.277095: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusolver64_10.dll
2020-12-22 00:28:25.287228: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusparse64_11.dll
2020-12-22 00:28:25.303626: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudnn64_8.dll
2020-12-22 00:28:25.304654: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
Experiment name: experiment
Model name: run
Output directory: results\experiment_run_9
ludwig_version: '0.3.2-dev1'
command: ('C:\\Users\\MyUser\\AppData\\Roaming\\Python\\Python38\\Scripts\\ludwig train '
'--dataset .\\Tweets.csv --config .\\model_definition.yaml')
random_seed: 42
dataset: '.\\Tweets.csv'
data_format: 'csv'
config: { 'combiner': {'type': 'concat'},
'input_features': [ { 'column': 'content',
'encoder': 'parallel_cnn',
'level': 'word',
'name': 'content',
'proc_column': 'content_mZFLky',
'tied': None,
'type': 'text'}],
'output_features': [ { 'column': 'airline_sentiment',
'dependencies': [],
'loss': { 'class_similarities_temperature': 0,
'class_weights': 1,
'confidence_penalty': 0,
'labels_smoothing': 0,
'robust_lambda': 0,
'type': 'softmax_cross_entropy',
'weight': 1},
'name': 'airline_sentiment',
'proc_column': 'airline_sentiment_mZFLky',
'reduce_dependencies': 'sum',
'reduce_input': 'sum',
'top_k': 3,
'type': 'category'}],
'preprocessing': { 'audio': { 'audio_feature': {'type': 'raw'},
'audio_file_length_limit_in_s': 7.5,
'in_memory': True,
'missing_value_strategy': 'backfill',
'norm': None,
'padding_value': 0},
'bag': { 'fill_value': '<UNK>',
'lowercase': False,
'missing_value_strategy': 'fill_with_const',
'most_common': 10000,
'tokenizer': 'space'},
'binary': { 'fill_value': 0,
'missing_value_strategy': 'fill_with_const'},
'category': { 'fill_value': '<UNK>',
'lowercase': False,
'missing_value_strategy': 'fill_with_const',
'most_common': 10000},
'date': { 'datetime_format': None,
'fill_value': '',
'missing_value_strategy': 'fill_with_const'},
'force_split': False,
'h3': { 'fill_value': 576495936675512319,
'missing_value_strategy': 'fill_with_const'},
'image': { 'in_memory': True,
'missing_value_strategy': 'backfill',
'num_processes': 1,
'resize_method': 'interpolate',
'scaling': 'pixel_normalization'},
'numerical': { 'fill_value': 0,
'missing_value_strategy': 'fill_with_const',
'normalization': None},
'sequence': { 'fill_value': '<UNK>',
'lowercase': False,
'missing_value_strategy': 'fill_with_const',
'most_common': 20000,
'padding': 'right',
'padding_symbol': '<PAD>',
'sequence_length_limit': 256,
'tokenizer': 'space',
'unknown_symbol': '<UNK>',
'vocab_file': None},
'set': { 'fill_value': '<UNK>',
'lowercase': False,
'missing_value_strategy': 'fill_with_const',
'most_common': 10000,
'tokenizer': 'space'},
'split_probabilities': (0.7, 0.1, 0.2),
'stratify': None,
'text': { 'char_most_common': 70,
'char_sequence_length_limit': 1024,
'char_tokenizer': 'characters',
'char_vocab_file': None,
'fill_value': '<UNK>',
'lowercase': True,
'missing_value_strategy': 'fill_with_const',
'padding': 'right',
'padding_symbol': '<PAD>',
'pretrained_model_name_or_path': None,
'unknown_symbol': '<UNK>',
'word_most_common': 20000,
'word_sequence_length_limit': 256,
'word_tokenizer': 'space_punct',
'word_vocab_file': None},
'timeseries': { 'fill_value': '',
'missing_value_strategy': 'fill_with_const',
'padding': 'right',
'padding_value': 0,
'timeseries_length_limit': 256,
'tokenizer': 'space'},
'vector': { 'fill_value': '',
'missing_value_strategy': 'fill_with_const'}},
'training': { 'batch_size': 128,
'bucketing_field': None,
'decay': False,
'decay_rate': 0.96,
'decay_steps': 10000,
'early_stop': 5,
'epochs': 100,
'eval_batch_size': 0,
'gradient_clipping': None,
'increase_batch_size_on_plateau': 0,
'increase_batch_size_on_plateau_max': 512,
'increase_batch_size_on_plateau_patience': 5,
'increase_batch_size_on_plateau_rate': 2,
'learning_rate': 0.001,
'learning_rate_warmup_epochs': 1,
'optimizer': { 'beta_1': 0.9,
'beta_2': 0.999,
'epsilon': 1e-08,
'type': 'adam'},
'reduce_learning_rate_on_plateau': 0,
'reduce_learning_rate_on_plateau_patience': 5,
'reduce_learning_rate_on_plateau_rate': 0.5,
'regularization_lambda': 0,
'regularizer': 'l2',
'staircase': False,
'validation_field': 'combined',
'validation_metric': 'loss'}}
tf_version: '2.4.0'
Using full raw csv, no hdf5 and json file with the same name have been found
Building dataset (it may take a while)
Traceback (most recent call last):
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\pandas\core\indexes\base.py", line 2895, in get_loc
return self._engine.get_loc(casted_key)
File "pandas\_libs\index.pyx", line 70, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 101, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1675, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1683, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'content'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\Scripts\ludwig-script.py", line 11, in <module>
load_entry_point('ludwig==0.3.2.dev1', 'console_scripts', 'ludwig')()
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\cli.py", line 146, in main
CLI()
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\cli.py", line 72, in __init__
getattr(self, args.command)()
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\cli.py", line 77, in train
train.cli(sys.argv[2:])
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\train.py", line 412, in cli
train_cli(**vars(args))
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\train.py", line 179, in train_cli
model.train(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\api.py", line 398, in train
preprocessed_data = self.preprocess(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\api.py", line 1252, in preprocess
preprocessed_data = preprocess_for_training(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 1387, in preprocess_for_training
processed = data_format_processor.preprocess_for_training(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 220, in preprocess_for_training
return _preprocess_file_for_training(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 1482, in _preprocess_file_for_training
data, training_set_metadata = build_dataset(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 1011, in build_dataset
metadata = build_metadata(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 1106, in build_metadata
dataset_df = handle_missing_values(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\ludwig\data\preprocessing.py", line 1189, in handle_missing_values
dataset_df[feature[COLUMN]] = dataset_df[feature[COLUMN]].fillna(
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\pandas\core\frame.py", line 2906, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\MyUser\AppData\Roaming\Python\Python38\site-packages\pandas\core\indexes\base.py", line 2897, in get_loc
raise KeyError(key) from err
KeyError: 'content'