persain-flair-ner / training.log
hamedkhaledi's picture
add Model
62cd4ef
raw
history blame
15.4 kB
2022-03-27 02:06:28,163 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,170 Model: "SequenceTagger(
(embeddings): StackedEmbeddings(
(list_embedding_0): WordEmbeddings('fa')
(list_embedding_1): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(5105, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=5105, bias=True)
)
)
(list_embedding_2): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(5105, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=5105, bias=True)
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(embedding2nn): Linear(in_features=4396, out_features=4396, bias=True)
(rnn): LSTM(4396, 256, batch_first=True, bidirectional=True)
(linear): Linear(in_features=512, out_features=17, bias=True)
(beta): 1.0
(weights): None
(weight_tensor) None
)"
2022-03-27 02:06:28,173 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,178 Corpus: "Corpus: 23060 train + 4070 dev + 4150 test sentences"
2022-03-27 02:06:28,184 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,189 Parameters:
2022-03-27 02:06:28,194 - learning_rate: "0.1"
2022-03-27 02:06:28,198 - mini_batch_size: "4"
2022-03-27 02:06:28,203 - patience: "3"
2022-03-27 02:06:28,207 - anneal_factor: "0.5"
2022-03-27 02:06:28,212 - max_epochs: "2"
2022-03-27 02:06:28,217 - shuffle: "True"
2022-03-27 02:06:28,219 - train_with_dev: "False"
2022-03-27 02:06:28,225 - batch_growth_annealing: "False"
2022-03-27 02:06:28,227 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,231 Model training base path: "/content/gdrive/MyDrive/project/data/ner/model2"
2022-03-27 02:06:28,238 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,242 Device: cuda:0
2022-03-27 02:06:28,244 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,247 Embeddings storage mode: none
2022-03-27 02:06:30,459 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:30,469 Testing using last state of model ...
2022-03-27 02:12:42,501 0.8475 0.7185 0.7777 0.647
2022-03-27 02:12:42,506
Results:
- F-score (micro) 0.7777
- F-score (macro) 0.7833
- Accuracy 0.647
By class:
precision recall f1-score support
LOC 0.8821 0.7877 0.8322 4083
ORG 0.8088 0.6105 0.6958 3166
PER 0.8381 0.7443 0.7884 2741
DAT 0.8298 0.6487 0.7282 1150
MON 0.9377 0.8852 0.9107 357
TIM 0.5741 0.5602 0.5671 166
PCT 0.9737 0.9487 0.9610 156
micro avg 0.8475 0.7185 0.7777 11819
macro avg 0.8349 0.7408 0.7833 11819
weighted avg 0.8457 0.7185 0.7757 11819
samples avg 0.6470 0.6470 0.6470 11819
2022-03-27 02:12:42,508 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,163 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,170 Model: "SequenceTagger(
(embeddings): StackedEmbeddings(
(list_embedding_0): WordEmbeddings('fa')
(list_embedding_1): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(5105, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=5105, bias=True)
)
)
(list_embedding_2): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(5105, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=5105, bias=True)
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(embedding2nn): Linear(in_features=4396, out_features=4396, bias=True)
(rnn): LSTM(4396, 256, batch_first=True, bidirectional=True)
(linear): Linear(in_features=512, out_features=17, bias=True)
(beta): 1.0
(weights): None
(weight_tensor) None
)"
2022-03-27 02:06:28,173 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,178 Corpus: "Corpus: 23060 train + 4070 dev + 4150 test sentences"
2022-03-27 02:06:28,184 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,189 Parameters:
2022-03-27 02:06:28,194 - learning_rate: "0.1"
2022-03-27 02:06:28,198 - mini_batch_size: "4"
2022-03-27 02:06:28,203 - patience: "3"
2022-03-27 02:06:28,207 - anneal_factor: "0.5"
2022-03-27 02:06:28,212 - max_epochs: "2"
2022-03-27 02:06:28,217 - shuffle: "True"
2022-03-27 02:06:28,219 - train_with_dev: "False"
2022-03-27 02:06:28,225 - batch_growth_annealing: "False"
2022-03-27 02:06:28,227 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,231 Model training base path: "/content/gdrive/MyDrive/project/data/ner/model2"
2022-03-27 02:06:28,238 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,242 Device: cuda:0
2022-03-27 02:06:28,244 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:28,247 Embeddings storage mode: none
2022-03-27 02:06:30,459 ----------------------------------------------------------------------------------------------------
2022-03-27 02:06:30,469 Testing using last state of model ...
2022-03-27 02:12:42,501 0.8475 0.7185 0.7777 0.647
2022-03-27 02:12:42,506
Results:
- F-score (micro) 0.7777
- F-score (macro) 0.7833
- Accuracy 0.647
By class:
precision recall f1-score support
LOC 0.8821 0.7877 0.8322 4083
ORG 0.8088 0.6105 0.6958 3166
PER 0.8381 0.7443 0.7884 2741
DAT 0.8298 0.6487 0.7282 1150
MON 0.9377 0.8852 0.9107 357
TIM 0.5741 0.5602 0.5671 166
PCT 0.9737 0.9487 0.9610 156
micro avg 0.8475 0.7185 0.7777 11819
macro avg 0.8349 0.7408 0.7833 11819
weighted avg 0.8457 0.7185 0.7757 11819
samples avg 0.6470 0.6470 0.6470 11819
2022-03-27 02:12:42,508 ----------------------------------------------------------------------------------------------------