recbole里运行得到的结果(recommendation1) PS C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master> python test_recbole.py --dataset=ml-100k --model=DeepFM
17 Dec 10:17 INFO ['test_recbole.py', '--dataset=ml-100k', '--model=DeepFM']
17 Dec 10:17 INFO
General Hyper Parameters:
gpu_id = 0
use_gpu = True
seed = 2020
state = INFO
reproducibility = True
data_path = C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\config\../dataset_example/ml-100k
checkpoint_dir = saved
show_progress = True
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': {'RS': [0.8, 0.1, 0.1]}, 'order': 'RO', 'group_by': None, 'mode': {'valid': 'labeled', 'test': 'labeled'}}
repeatable = False
metrics = ['AUC', 'LogLoss']
topk = [10]
valid_metric = AUC
valid_metric_bigger = True
eval_batch_size = 4096
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 = {'rating': 4}
NEG_PREFIX = neg_
load_col = {'inter': ['user_id', 'item_id', 'rating', 'timestamp'], 'user': ['user_id', 'age', 'gender', 'occupation'], 'item': ['item_id', 'release_year', 'class']}
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 = None
item_inter_num_interval = None
alias_of_user_id = None
alias_of_item_id = None
alias_of_entity_id = None
alias_of_relation_id = None
preload_weight = None
normalize_field = None
normalize_all = True
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
kg_reverse_r = False
entity_kg_num_interval = None
relation_kg_num_interval = None
benchmark_filename = None
Other Hyper Parameters:
worker = 0
wandb_project = recbole
shuffle = True
require_pow = False
enable_amp = False
enable_scaler = False
transform = None
embedding_size = 32
mlp_hidden_size = [128, 128, 128]
dropout_prob = 0.1
batch_size = 512-2048
numerical_features = []
discretization = None
MODEL_TYPE = ModelType.CONTEXT
MODEL_INPUT_TYPE = InputType.POINTWISE
eval_type = EvaluatorType.VALUE
single_spec = True
local_rank = 0
device = cuda
valid_neg_sample_args = {'distribution': 'none', 'sample_num': 'none'}
test_neg_sample_args = {'distribution': 'none', 'sample_num': 'none'}
C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\data\dataset\dataset.py:501: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.
For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.
df[field].fillna(value="", inplace=True)
C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\data\dataset\dataset.py:1217: FutureWarning: using <built-in function len> in Series.agg cannot aggregate and has been deprecated. Use Series.transform to keep behavior unchanged.
split_point = np.cumsum(feat[field].agg(len))[:-1]
C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\data\dataset\dataset.py:648: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.
For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.
feat[field].fillna(value=0, inplace=True)
C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\data\dataset\dataset.py:650: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.
For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.
feat[field].fillna(value=feat[field].mean(), inplace=True)
17 Dec 10:17 INFO ml-100k
The number of users: 944
Average actions of users: 106.04453870625663
The number of items: 1683
Average actions of items: 59.45303210463734
The number of inters: 100000
The sparsity of the dataset: 93.70575143257098%
Remain Fields: ['user_id', 'item_id', 'timestamp', 'age', 'gender', 'occupation', 'release_year', 'class', 'label']
17 Dec 10:17 INFO [Training]: train_batch_size = [2048] train_neg_sample_args: [{'distribution': 'none', 'sample_num': 'none', 'alpha': 'none', 'dynamic': False, 'candidate_num': 0}]
17 Dec 10:17 INFO [Evaluation]: eval_batch_size = [4096] eval_args: [{'split': {'RS': [0.8, 0.1, 0.1]}, 'order': 'RO', 'group_by': None, 'mode': {'valid': 'labeled', 'test': 'labeled'}}]
17 Dec 10:17 INFO DeepFM(
(token_embedding_table): FMEmbedding(
(embedding): Embedding(2788, 32)
)
(token_seq_embedding_table): ModuleList(
(0): Embedding(20, 32)
)
(first_order_linear): FMFirstOrderLinear(
(token_embedding_table): FMEmbedding(
(embedding): Embedding(2788, 1)
)
(token_seq_embedding_table): ModuleList(
(0): Embedding(20, 1)
)
)
(fm): BaseFactorizationMachine()
(mlp_layers): MLPLayers(
(mlp_layers): Sequential(
(0): Dropout(p=0.1, inplace=False)
(1): Linear(in_features=224, out_features=128, bias=True)
(2): ReLU()
(3): Dropout(p=0.1, inplace=False)
(4): Linear(in_features=128, out_features=128, bias=True)
(5): ReLU()
(6): Dropout(p=0.1, inplace=False)
(7): Linear(in_features=128, out_features=128, bias=True)
(8): ReLU()
)
)
(deep_predict_layer): Linear(in_features=128, out_features=1, bias=True)
(sigmoid): Sigmoid()
(loss): BCEWithLogitsLoss()
)
Trainable parameters: 154618
17 Dec 10:17 INFO FLOPs: 61964.0
Train 0: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 0: 100%|██████████████████████████| 40/40 [00:01<00:00, 21.81it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 0 training [time: 1.84s, train loss: 26.3781]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 40.77it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 0 evaluating [time: 0.09s, valid_score: 0.737700]
17 Dec 10:17 INFO valid result:
auc : 0.7377 logloss : 0.5977
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 1: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 1: 100%|██████████████████████████| 40/40 [00:01<00:00, 31.97it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 1 training [time: 1.25s, train loss: 22.8683]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 35.89it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 1 evaluating [time: 0.09s, valid_score: 0.771900]
17 Dec 10:17 INFO valid result:
auc : 0.7719 logloss : 0.5691
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 2: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 2: 100%|██████████████████████████| 40/40 [00:01<00:00, 32.42it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 2 training [time: 1.23s, train loss: 21.9918]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 34.00it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 2 evaluating [time: 0.10s, valid_score: 0.775600]
17 Dec 10:17 INFO valid result:
auc : 0.7756 logloss : 0.5639
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 3: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 3: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.51it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 3 training [time: 1.31s, train loss: 21.7724]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 39.55it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 3 evaluating [time: 0.08s, valid_score: 0.777200]
17 Dec 10:17 INFO valid result:
auc : 0.7772 logloss : 0.5626
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 4: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 4: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.77it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 4 training [time: 1.30s, train loss: 21.5593]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 40.46it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 4 evaluating [time: 0.08s, valid_score: 0.778700]
17 Dec 10:17 INFO valid result:
auc : 0.7787 logloss : 0.5621
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 5: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 5: 100%|██████████████████████████| 40/40 [00:01<00:00, 29.79it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 5 training [time: 1.34s, train loss: 21.3957]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 39.69it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:17 INFO epoch 5 evaluating [time: 0.08s, valid_score: 0.780200]
17 Dec 10:17 INFO valid result:
auc : 0.7802 logloss : 0.5597
17 Dec 10:17 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 6: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 6: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.85it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 6 training [time: 1.30s, train loss: 20.9730]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 40.77it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 6 evaluating [time: 0.08s, valid_score: 0.781200]
17 Dec 10:18 INFO valid result:
auc : 0.7812 logloss : 0.5603
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 7: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 7: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.89it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 7 training [time: 1.30s, train loss: 20.7414]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 41.91it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 7 evaluating [time: 0.08s, valid_score: 0.783900]
17 Dec 10:18 INFO valid result:
auc : 0.7839 logloss : 0.5607
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 8: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 8: 100%|██████████████████████████| 40/40 [00:01<00:00, 31.58it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 8 training [time: 1.27s, train loss: 20.4771]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 36.69it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 8 evaluating [time: 0.09s, valid_score: 0.785200]
17 Dec 10:18 INFO valid result:
auc : 0.7852 logloss : 0.5588
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 9: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 9: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.17it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 9 training [time: 1.33s, train loss: 20.2486]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 37.23it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 9 evaluating [time: 0.09s, valid_score: 0.787100]
17 Dec 10:18 INFO valid result:
auc : 0.7871 logloss : 0.5611
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 10: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 10: 100%|██████████████████████████| 40/40 [00:01<00:00, 31.66it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 10 training [time: 1.27s, train loss: 19.9889]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 36.32it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 10 evaluating [time: 0.09s, valid_score: 0.788000]
17 Dec 10:18 INFO valid result:
auc : 0.788 logloss : 0.5588
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 11: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 11: 100%|██████████████████████████| 40/40 [00:01<00:00, 24.90it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 11 training [time: 1.61s, train loss: 19.7072]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 27.64it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 11 evaluating [time: 0.12s, valid_score: 0.789100]
17 Dec 10:18 INFO valid result:
auc : 0.7891 logloss : 0.5617
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 12: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 12: 100%|██████████████████████████| 40/40 [00:01<00:00, 26.04it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 12 training [time: 1.54s, train loss: 19.4520]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 33.89it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 12 evaluating [time: 0.10s, valid_score: 0.790000]
17 Dec 10:18 INFO valid result:
auc : 0.79 logloss : 0.5581
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 13: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 13: 100%|██████████████████████████| 40/40 [00:01<00:00, 29.97it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 13 training [time: 1.34s, train loss: 19.2969]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 36.50it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 13 evaluating [time: 0.09s, valid_score: 0.791400]
17 Dec 10:18 INFO valid result:
auc : 0.7914 logloss : 0.5581
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 14: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 14: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.51it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 14 training [time: 1.31s, train loss: 19.0033]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 35.45it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 14 evaluating [time: 0.09s, valid_score: 0.791500]
17 Dec 10:18 INFO valid result:
auc : 0.7915 logloss : 0.561
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 15: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 15: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.45it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 15 training [time: 1.32s, train loss: 18.7053]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 35.12it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 15 evaluating [time: 0.09s, valid_score: 0.793200]
17 Dec 10:18 INFO valid result:
auc : 0.7932 logloss : 0.5667
17 Dec 10:18 INFO Saving current: saved\DeepFM-Dec-17-2025_10-17-44.pth
Train 16: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 16: 100%|██████████████████████████| 40/40 [00:01<00:00, 31.18it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 16 training [time: 1.28s, train loss: 18.4229]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 34.65it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 16 evaluating [time: 0.10s, valid_score: 0.791300]
17 Dec 10:18 INFO valid result:
auc : 0.7913 logloss : 0.5645
Train 17: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 17: 100%|██████████████████████████| 40/40 [00:01<00:00, 29.71it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 17 training [time: 1.35s, train loss: 18.1685]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 35.82it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 17 evaluating [time: 0.09s, valid_score: 0.791200]
17 Dec 10:18 INFO valid result:
auc : 0.7912 logloss : 0.5736
Train 18: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 18: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.61it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 18 training [time: 1.31s, train loss: 17.8669]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 38.32it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 18 evaluating [time: 0.09s, valid_score: 0.788900]
17 Dec 10:18 INFO valid result:
auc : 0.7889 logloss : 0.5763
Train 19: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 19: 100%|██████████████████████████| 40/40 [00:01<00:00, 29.01it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 19 training [time: 1.38s, train loss: 17.6062]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 37.43it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 19 evaluating [time: 0.09s, valid_score: 0.789100]
17 Dec 10:18 INFO valid result:
auc : 0.7891 logloss : 0.5865
Train 20: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 20: 100%|██████████████████████████| 40/40 [00:01<00:00, 29.06it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 20 training [time: 1.38s, train loss: 17.3334]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 32.66it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 20 evaluating [time: 0.10s, valid_score: 0.786900]
17 Dec 10:18 INFO valid result:
auc : 0.7869 logloss : 0.5885
Train 21: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 21: 100%|██████████████████████████| 40/40 [00:01<00:00, 27.89it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 21 training [time: 1.44s, train loss: 17.0732]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 32.78it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 21 evaluating [time: 0.10s, valid_score: 0.785500]
17 Dec 10:18 INFO valid result:
auc : 0.7855 logloss : 0.5946
Train 22: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 22: 100%|██████████████████████████| 40/40 [00:01<00:00, 27.73it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 22 training [time: 1.44s, train loss: 16.7729]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 24.63it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 22 evaluating [time: 0.14s, valid_score: 0.784300]
17 Dec 10:18 INFO valid result:
auc : 0.7843 logloss : 0.6011
Train 23: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 23: 100%|██████████████████████████| 40/40 [00:01<00:00, 23.59it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 23 training [time: 1.70s, train loss: 16.5185]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 33.71it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 23 evaluating [time: 0.10s, valid_score: 0.783100]
17 Dec 10:18 INFO valid result:
auc : 0.7831 logloss : 0.6128
Train 24: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 24: 100%|██████████████████████████| 40/40 [00:01<00:00, 28.51it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 24 training [time: 1.40s, train loss: 16.0847]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 37.70it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 24 evaluating [time: 0.09s, valid_score: 0.783400]
17 Dec 10:18 INFO valid result:
auc : 0.7834 logloss : 0.6102
Train 25: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 25: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.56it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 25 training [time: 1.31s, train loss: 15.8857]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 33.61it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 25 evaluating [time: 0.10s, valid_score: 0.780200]
17 Dec 10:18 INFO valid result:
auc : 0.7802 logloss : 0.6161
Train 26: 0%| | 0/40 [00:00<?, ?it/s]C:\Users\李超洋\Desktop\项目\RecBole-master\RecBole-master\recbole\trainer\trainer.py:235: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
scaler = amp.GradScaler(enabled=self.enable_scaler)
Train 26: 100%|██████████████████████████| 40/40 [00:01<00:00, 30.24it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 26 training [time: 1.33s, train loss: 15.6743]
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 32.43it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO epoch 26 evaluating [time: 0.10s, valid_score: 0.780700]
17 Dec 10:18 INFO valid result:
auc : 0.7807 logloss : 0.6301
17 Dec 10:18 INFO Finished training, best eval result in epoch 15
17 Dec 10:18 INFO Loading model structure and parameters from saved\DeepFM-Dec-17-2025_10-17-44.pth
Evaluate : 100%|████████████████████████████| 3/3 [00:00<00:00, 35.29it/s, GPU RAM: 0.05 G/6.00 G]
17 Dec 10:18 INFO The running environment of this training is as follows:
+-------------+----------------+
| Environment | Usage |
+=============+================+
| CPU | 9.00 % |
+-------------+----------------+
| GPU | 0.05 G/6.00 G |
+-------------+----------------+
| Memory | 1.25 G/15.40 G |
+-------------+----------------+
17 Dec 10:18 INFO best valid : OrderedDict([('auc', 0.7932), ('logloss', 0.5667)])
17 Dec 10:18 INFO test result: OrderedDict([('auc', 0.784), ('logloss', 0.577)])
最新发布
作者在Python中使用pandas处理json数据时遇到FutureWarning，因为pandas.io.json模块已弃用。他们寻求帮助，指出应将`frompandas.io.jsonimportjson_normalize`替换为`frompandasimportjson_normalize`。
扫一扫
7362
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
