-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathtedrec_Food.out
271 lines (265 loc) · 12.3 KB
/
tedrec_Food.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
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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
command line args [-d Food] will not be used in RecBole
08 Feb 13:47 INFO
General Hyper Parameters:
gpu_id = 3
use_gpu = True
seed = 2020
state = INFO
reproducibility = True
data_path = dataset/Food
checkpoint_dir = saved
show_progress = False
save_dataset = False
dataset_save_path = None
save_dataloaders = False
dataloaders_save_path = None
log_wandb = False
Training Hyper Parameters:
epochs = 300
train_batch_size = 2048
learner = adam
learning_rate = 0.001
train_neg_sample_args = {'distribution': 'none', 'sample_num': 'none', 'alpha': 'none', 'dynamic': False, 'candidate_num': 0}
eval_step = 1
stopping_step = 10
clip_grad_norm = None
weight_decay = 0.0
loss_decimal_place = 4
Evaluation Hyper Parameters:
eval_args = {'split': {'LS': 'valid_and_test'}, 'order': 'TO', 'group_by': 'user', 'mode': {'valid': 'full', 'test': 'full'}}
repeatable = True
metrics = ['Recall', 'NDCG']
topk = [10, 20]
valid_metric = NDCG@10
valid_metric_bigger = True
eval_batch_size = 2048
metric_decimal_place = 4
Dataset Hyper Parameters:
field_separator =
seq_separator =
USER_ID_FIELD = user_id
ITEM_ID_FIELD = item_id
RATING_FIELD = rating
TIME_FIELD = timestamp
seq_len = None
LABEL_FIELD = label
threshold = None
NEG_PREFIX = neg_
load_col = {'inter': ['user_id', 'item_id_list', 'item_id']}
unload_col = None
unused_col = None
additional_feat_suffix = None
rm_dup_inter = None
val_interval = None
filter_inter_by_user_or_item = True
user_inter_num_interval = [0,inf)
item_inter_num_interval = [0,inf)
alias_of_user_id = None
alias_of_item_id = ['item_id_list']
alias_of_entity_id = None
alias_of_relation_id = None
preload_weight = None
normalize_field = None
normalize_all = None
ITEM_LIST_LENGTH_FIELD = item_length
LIST_SUFFIX = _list
MAX_ITEM_LIST_LENGTH = 50
POSITION_FIELD = position_id
HEAD_ENTITY_ID_FIELD = head_id
TAIL_ENTITY_ID_FIELD = tail_id
RELATION_ID_FIELD = relation_id
ENTITY_ID_FIELD = entity_id
benchmark_filename = ['train', 'valid', 'test']
Other Hyper Parameters:
worker = 0
wandb_project = recbole
shuffle = True
require_pow = False
enable_amp = False
enable_scaler = False
transform = None
numerical_features = []
discretization = None
kg_reverse_r = False
entity_kg_num_interval = [0,inf)
relation_kg_num_interval = [0,inf)
MODEL_TYPE = ModelType.SEQUENTIAL
n_layers = 2
n_heads = 2
hidden_size = 300
inner_size = 256
hidden_dropout_prob = 0.5
attn_dropout_prob = 0.5
hidden_act = gelu
layer_norm_eps = 1e-12
initializer_range = 0.02
loss_type = CE
plm_suffix = feat1CLS
plm_size = 768
adaptor_dropout_prob = 0.2
adaptor_layers = [768, 300]
temperature = 0.07
n_exps = 8
MODEL_INPUT_TYPE = InputType.POINTWISE
eval_type = EvaluatorType.RANKING
single_spec = True
local_rank = 0
device = cuda
valid_neg_sample_args = {'distribution': 'uniform', 'sample_num': 'none'}
test_neg_sample_args = {'distribution': 'uniform', 'sample_num': 'none'}
08 Feb 13:47 INFO Food
The number of users: 115350
Average actions of users: 7.906995292546966
The number of items: 39671
Average actions of items: 22.994176225891845
The number of inters: 912064
The sparsity of the dataset: 99.98006874859547%
Remain Fields: ['user_id', 'item_id_list', 'item_id', 'item_length']
08 Feb 13:48 INFO [Training]: train_batch_size = [2048] train_neg_sample_args: [{'distribution': 'none', 'sample_num': 'none', 'alpha': 'none', 'dynamic': False, 'candidate_num': 0}]
08 Feb 13:48 INFO [Evaluation]: eval_batch_size = [2048] eval_args: [{'split': {'LS': 'valid_and_test'}, 'order': 'TO', 'group_by': 'user', 'mode': {'valid': 'full', 'test': 'full'}}]
08 Feb 13:48 INFO TedRec(
(item_embedding): Embedding(39671, 300, padding_idx=0)
(position_embedding): Embedding(50, 300)
(trm_encoder): TransformerEncoder(
(layer): ModuleList(
(0-1): 2 x TransformerLayer(
(multi_head_attention): MultiHeadAttention(
(query): Linear(in_features=300, out_features=300, bias=True)
(key): Linear(in_features=300, out_features=300, bias=True)
(value): Linear(in_features=300, out_features=300, bias=True)
(softmax): Softmax(dim=-1)
(attn_dropout): Dropout(p=0.5, inplace=False)
(dense): Linear(in_features=300, out_features=300, bias=True)
(LayerNorm): LayerNorm((300,), eps=1e-12, elementwise_affine=True)
(out_dropout): Dropout(p=0.5, inplace=False)
)
(feed_forward): FeedForward(
(dense_1): Linear(in_features=300, out_features=256, bias=True)
(dense_2): Linear(in_features=256, out_features=300, bias=True)
(LayerNorm): LayerNorm((300,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
)
)
(LayerNorm): LayerNorm((300,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
(loss_fct): CrossEntropyLoss()
(plm_embedding): Embedding(39671, 768, padding_idx=0)
(item_gating): Linear(in_features=300, out_features=1, bias=True)
(fusion_gating): Linear(in_features=300, out_features=1, bias=True)
(moe_adaptor): MoEAdaptorLayer(
(experts): ModuleList(
(0-7): 8 x DTRLayer(
(dropout): Dropout(p=0.2, inplace=False)
(lin): Linear(in_features=768, out_features=300, bias=False)
)
)
)
)
Trainable parameters: 15128902
08 Feb 13:49 INFO epoch 0 training [time: 89.47s, train loss: 3142.5863]
08 Feb 13:49 INFO epoch 0 evaluating [time: 8.12s, valid_score: 0.090700]
08 Feb 13:49 INFO valid result:
recall@10 : 0.1261 recall@20 : 0.1468 ndcg@10 : 0.0907 ndcg@20 : 0.0959
08 Feb 13:49 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:51 INFO epoch 1 training [time: 88.32s, train loss: 2820.6732]
08 Feb 13:51 INFO epoch 1 evaluating [time: 7.46s, valid_score: 0.104200]
08 Feb 13:51 INFO valid result:
recall@10 : 0.1437 recall@20 : 0.1694 ndcg@10 : 0.1042 ndcg@20 : 0.1106
08 Feb 13:51 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:52 INFO epoch 2 training [time: 87.95s, train loss: 2664.1517]
08 Feb 13:52 INFO epoch 2 evaluating [time: 7.38s, valid_score: 0.108400]
08 Feb 13:52 INFO valid result:
recall@10 : 0.1501 recall@20 : 0.1788 ndcg@10 : 0.1084 ndcg@20 : 0.1157
08 Feb 13:53 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:54 INFO epoch 3 training [time: 88.21s, train loss: 2568.3808]
08 Feb 13:54 INFO epoch 3 evaluating [time: 7.31s, valid_score: 0.110500]
08 Feb 13:54 INFO valid result:
recall@10 : 0.1529 recall@20 : 0.1826 ndcg@10 : 0.1105 ndcg@20 : 0.118
08 Feb 13:54 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:56 INFO epoch 4 training [time: 88.74s, train loss: 2503.9698]
08 Feb 13:56 INFO epoch 4 evaluating [time: 7.38s, valid_score: 0.111900]
08 Feb 13:56 INFO valid result:
recall@10 : 0.1547 recall@20 : 0.1848 ndcg@10 : 0.1119 ndcg@20 : 0.1195
08 Feb 13:56 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:57 INFO epoch 5 training [time: 88.31s, train loss: 2457.1046]
08 Feb 13:57 INFO epoch 5 evaluating [time: 7.90s, valid_score: 0.112200]
08 Feb 13:57 INFO valid result:
recall@10 : 0.155 recall@20 : 0.1863 ndcg@10 : 0.1122 ndcg@20 : 0.1201
08 Feb 13:57 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 13:59 INFO epoch 6 training [time: 88.41s, train loss: 2422.2981]
08 Feb 13:59 INFO epoch 6 evaluating [time: 7.31s, valid_score: 0.113100]
08 Feb 13:59 INFO valid result:
recall@10 : 0.156 recall@20 : 0.1871 ndcg@10 : 0.1131 ndcg@20 : 0.1209
08 Feb 13:59 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 14:01 INFO epoch 7 training [time: 89.20s, train loss: 2394.6163]
08 Feb 14:01 INFO epoch 7 evaluating [time: 7.33s, valid_score: 0.113900]
08 Feb 14:01 INFO valid result:
recall@10 : 0.157 recall@20 : 0.1876 ndcg@10 : 0.1139 ndcg@20 : 0.1216
08 Feb 14:01 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 14:02 INFO epoch 8 training [time: 88.32s, train loss: 2372.2479]
08 Feb 14:02 INFO epoch 8 evaluating [time: 7.32s, valid_score: 0.114000]
08 Feb 14:02 INFO valid result:
recall@10 : 0.1572 recall@20 : 0.1873 ndcg@10 : 0.114 ndcg@20 : 0.1216
08 Feb 14:02 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 14:04 INFO epoch 9 training [time: 87.98s, train loss: 2353.2693]
08 Feb 14:04 INFO epoch 9 evaluating [time: 7.37s, valid_score: 0.113700]
08 Feb 14:04 INFO valid result:
recall@10 : 0.156 recall@20 : 0.1877 ndcg@10 : 0.1137 ndcg@20 : 0.1217
08 Feb 14:05 INFO epoch 10 training [time: 88.10s, train loss: 2336.5240]
08 Feb 14:06 INFO epoch 10 evaluating [time: 9.42s, valid_score: 0.114500]
08 Feb 14:06 INFO valid result:
recall@10 : 0.157 recall@20 : 0.1882 ndcg@10 : 0.1145 ndcg@20 : 0.1224
08 Feb 14:06 INFO Saving current: saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 14:07 INFO epoch 11 training [time: 87.73s, train loss: 2322.4793]
08 Feb 14:07 INFO epoch 11 evaluating [time: 7.18s, valid_score: 0.114400]
08 Feb 14:07 INFO valid result:
recall@10 : 0.1568 recall@20 : 0.1872 ndcg@10 : 0.1144 ndcg@20 : 0.1221
08 Feb 14:09 INFO epoch 12 training [time: 88.31s, train loss: 2308.9730]
08 Feb 14:09 INFO epoch 12 evaluating [time: 7.46s, valid_score: 0.114400]
08 Feb 14:09 INFO valid result:
recall@10 : 0.1566 recall@20 : 0.1871 ndcg@10 : 0.1144 ndcg@20 : 0.1221
08 Feb 14:10 INFO epoch 13 training [time: 88.33s, train loss: 2296.9651]
08 Feb 14:11 INFO epoch 13 evaluating [time: 8.47s, valid_score: 0.114200]
08 Feb 14:11 INFO valid result:
recall@10 : 0.1562 recall@20 : 0.1869 ndcg@10 : 0.1142 ndcg@20 : 0.1219
08 Feb 14:12 INFO epoch 14 training [time: 88.67s, train loss: 2285.5447]
08 Feb 14:12 INFO epoch 14 evaluating [time: 7.29s, valid_score: 0.114400]
08 Feb 14:12 INFO valid result:
recall@10 : 0.1564 recall@20 : 0.186 ndcg@10 : 0.1144 ndcg@20 : 0.1218
08 Feb 14:14 INFO epoch 15 training [time: 87.44s, train loss: 2274.9365]
08 Feb 14:14 INFO epoch 15 evaluating [time: 7.04s, valid_score: 0.114300]
08 Feb 14:14 INFO valid result:
recall@10 : 0.156 recall@20 : 0.1859 ndcg@10 : 0.1143 ndcg@20 : 0.1218
08 Feb 14:15 INFO epoch 16 training [time: 87.77s, train loss: 2264.3382]
08 Feb 14:15 INFO epoch 16 evaluating [time: 7.05s, valid_score: 0.114200]
08 Feb 14:15 INFO valid result:
recall@10 : 0.1563 recall@20 : 0.1861 ndcg@10 : 0.1142 ndcg@20 : 0.1217
08 Feb 14:17 INFO epoch 17 training [time: 87.54s, train loss: 2253.8656]
08 Feb 14:17 INFO epoch 17 evaluating [time: 7.30s, valid_score: 0.113700]
08 Feb 14:17 INFO valid result:
recall@10 : 0.155 recall@20 : 0.1853 ndcg@10 : 0.1137 ndcg@20 : 0.1213
08 Feb 14:18 INFO epoch 18 training [time: 87.98s, train loss: 2244.8590]
08 Feb 14:18 INFO epoch 18 evaluating [time: 7.16s, valid_score: 0.113700]
08 Feb 14:18 INFO valid result:
recall@10 : 0.1549 recall@20 : 0.1847 ndcg@10 : 0.1137 ndcg@20 : 0.1212
08 Feb 14:20 INFO epoch 19 training [time: 87.55s, train loss: 2235.8442]
08 Feb 14:20 INFO epoch 19 evaluating [time: 7.07s, valid_score: 0.113800]
08 Feb 14:20 INFO valid result:
recall@10 : 0.1547 recall@20 : 0.1838 ndcg@10 : 0.1138 ndcg@20 : 0.1211
08 Feb 14:21 INFO epoch 20 training [time: 87.36s, train loss: 2226.7574]
08 Feb 14:22 INFO epoch 20 evaluating [time: 7.48s, valid_score: 0.113500]
08 Feb 14:22 INFO valid result:
recall@10 : 0.1546 recall@20 : 0.1839 ndcg@10 : 0.1135 ndcg@20 : 0.1209
08 Feb 14:23 INFO epoch 21 training [time: 87.87s, train loss: 2219.5084]
08 Feb 14:23 INFO epoch 21 evaluating [time: 6.89s, valid_score: 0.113300]
08 Feb 14:23 INFO valid result:
recall@10 : 0.1536 recall@20 : 0.1828 ndcg@10 : 0.1133 ndcg@20 : 0.1207
08 Feb 14:23 INFO Finished training, best eval result in epoch 10
08 Feb 14:23 INFO Loading model structure and parameters from saved/TedRec-Feb-08-2024_13-48-04.pth
08 Feb 14:23 INFO best valid : OrderedDict([('recall@10', 0.157), ('recall@20', 0.1882), ('ndcg@10', 0.1145), ('ndcg@20', 0.1224)])
08 Feb 14:23 INFO test result: OrderedDict([('recall@10', 0.1327), ('recall@20', 0.1604), ('ndcg@10', 0.1012), ('ndcg@20', 0.1082)])
08 Feb 14:23 INFO 0.1327 0.1604 0.1012 0.1082
Namespace(d='Food')
['props/TedRec.yaml', 'props/overall.yaml']