alanakbik's picture
initial commit
c0da81a
2021-02-20 12:03:00,991 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,994 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): XLMRobertaModel(
(embeddings): RobertaEmbeddings(
(word_embeddings): Embedding(250002, 1024, padding_idx=1)
(position_embeddings): Embedding(514, 1024, padding_idx=1)
(token_type_embeddings): Embedding(1, 1024)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): RobertaEncoder(
(layer): ModuleList(
(0): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(1): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(2): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(3): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(4): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(5): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(6): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(7): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(8): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(9): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(10): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(11): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(12): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(13): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(14): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(15): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(16): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(17): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(18): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(19): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(20): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(21): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(22): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(23): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): RobertaPooler(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(activation): Tanh()
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1024, out_features=76, bias=True)
(beta): 1.0
(weights): None
(weight_tensor) None
)"
2021-02-20 12:03:00,995 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,995 Corpus: "Corpus: 75187 train + 9603 dev + 9479 test sentences"
2021-02-20 12:03:00,995 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,995 Parameters:
2021-02-20 12:03:00,995 - learning_rate: "5e-06"
2021-02-20 12:03:00,995 - mini_batch_size: "4"
2021-02-20 12:03:00,995 - patience: "3"
2021-02-20 12:03:00,995 - anneal_factor: "0.5"
2021-02-20 12:03:00,995 - max_epochs: "20"
2021-02-20 12:03:00,995 - shuffle: "True"
2021-02-20 12:03:00,995 - train_with_dev: "True"
2021-02-20 12:03:00,996 - batch_growth_annealing: "False"
2021-02-20 12:03:00,996 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,996 Model training base path: "resources/contextdrop/d-flert-ontonotes-ft+dev-xlm-roberta-large-context+drop-64-True-42"
2021-02-20 12:03:00,996 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,996 Device: cuda:0
2021-02-20 12:03:00,996 ----------------------------------------------------------------------------------------------------
2021-02-20 12:03:00,996 Embeddings storage mode: none
2021-02-20 12:03:01,005 ----------------------------------------------------------------------------------------------------
2021-02-20 12:17:26,941 epoch 1 - iter 2119/21198 - loss 0.46498391 - samples/sec: 9.79 - lr: 0.000005
2021-02-20 12:32:25,501 epoch 1 - iter 4238/21198 - loss 0.43484389 - samples/sec: 9.43 - lr: 0.000005
2021-02-20 12:47:30,355 epoch 1 - iter 6357/21198 - loss 0.42857357 - samples/sec: 9.37 - lr: 0.000005
2021-02-20 13:02:33,037 epoch 1 - iter 8476/21198 - loss 0.40114081 - samples/sec: 9.39 - lr: 0.000005
2021-02-20 13:17:06,534 epoch 1 - iter 10595/21198 - loss 0.36551536 - samples/sec: 9.70 - lr: 0.000005
2021-02-20 13:31:52,079 epoch 1 - iter 12714/21198 - loss 0.34481658 - samples/sec: 9.57 - lr: 0.000005
2021-02-20 13:47:10,517 epoch 1 - iter 14833/21198 - loss 0.33967654 - samples/sec: 9.23 - lr: 0.000005
2021-02-20 14:02:14,283 epoch 1 - iter 16952/21198 - loss 0.33393062 - samples/sec: 9.38 - lr: 0.000005
2021-02-20 14:16:49,633 epoch 1 - iter 19071/21198 - loss 0.32924976 - samples/sec: 9.68 - lr: 0.000005
2021-02-20 14:31:45,192 epoch 1 - iter 21190/21198 - loss 0.32628298 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 14:31:48,270 ----------------------------------------------------------------------------------------------------
2021-02-20 14:31:48,271 EPOCH 1 done: loss 0.3263 - lr 0.0000050
2021-02-20 14:37:34,463 TEST : loss 0.12760598957538605 - score 0.8669
2021-02-20 14:37:34,546 BAD EPOCHS (no improvement): 4
2021-02-20 14:37:34,556 ----------------------------------------------------------------------------------------------------
2021-02-20 14:52:29,571 epoch 2 - iter 2119/21198 - loss 0.29859233 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 15:07:24,765 epoch 2 - iter 4238/21198 - loss 0.29870475 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 15:22:22,170 epoch 2 - iter 6357/21198 - loss 0.29288750 - samples/sec: 9.45 - lr: 0.000005
2021-02-20 15:37:18,156 epoch 2 - iter 8476/21198 - loss 0.29279330 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 15:52:13,883 epoch 2 - iter 10595/21198 - loss 0.28788203 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 16:07:12,097 epoch 2 - iter 12714/21198 - loss 0.28927318 - samples/sec: 9.44 - lr: 0.000005
2021-02-20 16:22:07,642 epoch 2 - iter 14833/21198 - loss 0.28514545 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 16:37:06,266 epoch 2 - iter 16952/21198 - loss 0.28311760 - samples/sec: 9.43 - lr: 0.000005
2021-02-20 16:52:00,498 epoch 2 - iter 19071/21198 - loss 0.28229767 - samples/sec: 9.48 - lr: 0.000005
2021-02-20 17:06:54,963 epoch 2 - iter 21190/21198 - loss 0.28044944 - samples/sec: 9.48 - lr: 0.000005
2021-02-20 17:06:58,266 ----------------------------------------------------------------------------------------------------
2021-02-20 17:06:58,266 EPOCH 2 done: loss 0.2804 - lr 0.0000049
2021-02-20 17:12:47,188 TEST : loss 0.08660610020160675 - score 0.8953
2021-02-20 17:12:47,273 BAD EPOCHS (no improvement): 4
2021-02-20 17:12:47,275 ----------------------------------------------------------------------------------------------------
2021-02-20 17:27:41,889 epoch 3 - iter 2119/21198 - loss 0.26828308 - samples/sec: 9.48 - lr: 0.000005
2021-02-20 17:42:34,288 epoch 3 - iter 4238/21198 - loss 0.26184351 - samples/sec: 9.50 - lr: 0.000005
2021-02-20 17:57:29,878 epoch 3 - iter 6357/21198 - loss 0.25940653 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 18:12:25,470 epoch 3 - iter 8476/21198 - loss 0.25828841 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 18:27:24,608 epoch 3 - iter 10595/21198 - loss 0.25551183 - samples/sec: 9.43 - lr: 0.000005
2021-02-20 18:42:18,429 epoch 3 - iter 12714/21198 - loss 0.25481692 - samples/sec: 9.48 - lr: 0.000005
2021-02-20 18:57:16,717 epoch 3 - iter 14833/21198 - loss 0.25506844 - samples/sec: 9.44 - lr: 0.000005
2021-02-20 19:12:13,807 epoch 3 - iter 16952/21198 - loss 0.25407433 - samples/sec: 9.45 - lr: 0.000005
2021-02-20 19:27:12,592 epoch 3 - iter 19071/21198 - loss 0.25575351 - samples/sec: 9.43 - lr: 0.000005
2021-02-20 19:42:07,912 epoch 3 - iter 21190/21198 - loss 0.25645391 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 19:42:10,991 ----------------------------------------------------------------------------------------------------
2021-02-20 19:42:10,991 EPOCH 3 done: loss 0.2565 - lr 0.0000047
2021-02-20 19:48:05,928 TEST : loss 0.08892939984798431 - score 0.9015
2021-02-20 19:48:06,017 BAD EPOCHS (no improvement): 4
2021-02-20 19:48:06,022 ----------------------------------------------------------------------------------------------------
2021-02-20 20:03:04,520 epoch 4 - iter 2119/21198 - loss 0.24164433 - samples/sec: 9.43 - lr: 0.000005
2021-02-20 20:17:56,429 epoch 4 - iter 4238/21198 - loss 0.24019658 - samples/sec: 9.50 - lr: 0.000005
2021-02-20 20:32:52,945 epoch 4 - iter 6357/21198 - loss 0.24219914 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 20:47:50,199 epoch 4 - iter 8476/21198 - loss 0.23953211 - samples/sec: 9.45 - lr: 0.000005
2021-02-20 21:02:44,855 epoch 4 - iter 10595/21198 - loss 0.23751325 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 21:17:41,522 epoch 4 - iter 12714/21198 - loss 0.23782852 - samples/sec: 9.45 - lr: 0.000005
2021-02-20 21:32:38,226 epoch 4 - iter 14833/21198 - loss 0.24096846 - samples/sec: 9.45 - lr: 0.000005
2021-02-20 21:47:40,951 epoch 4 - iter 16952/21198 - loss 0.23932344 - samples/sec: 9.39 - lr: 0.000005
2021-02-20 22:02:36,247 epoch 4 - iter 19071/21198 - loss 0.24064527 - samples/sec: 9.47 - lr: 0.000005
2021-02-20 22:17:29,253 epoch 4 - iter 21190/21198 - loss 0.24016898 - samples/sec: 9.49 - lr: 0.000005
2021-02-20 22:17:32,358 ----------------------------------------------------------------------------------------------------
2021-02-20 22:17:32,358 EPOCH 4 done: loss 0.2402 - lr 0.0000045
2021-02-20 22:23:24,429 TEST : loss 0.09627319127321243 - score 0.9076
2021-02-20 22:23:24,520 BAD EPOCHS (no improvement): 4
2021-02-20 22:23:24,535 ----------------------------------------------------------------------------------------------------
2021-02-20 22:38:20,470 epoch 5 - iter 2119/21198 - loss 0.22083609 - samples/sec: 9.46 - lr: 0.000004
2021-02-20 22:53:16,946 epoch 5 - iter 4238/21198 - loss 0.22353303 - samples/sec: 9.46 - lr: 0.000004
2021-02-20 23:08:09,262 epoch 5 - iter 6357/21198 - loss 0.22526515 - samples/sec: 9.50 - lr: 0.000004
2021-02-20 23:23:05,354 epoch 5 - iter 8476/21198 - loss 0.22450491 - samples/sec: 9.46 - lr: 0.000004
2021-02-20 23:38:01,961 epoch 5 - iter 10595/21198 - loss 0.22317870 - samples/sec: 9.45 - lr: 0.000004
2021-02-20 23:53:00,849 epoch 5 - iter 12714/21198 - loss 0.22493520 - samples/sec: 9.43 - lr: 0.000004
2021-02-21 00:07:59,228 epoch 5 - iter 14833/21198 - loss 0.22554395 - samples/sec: 9.44 - lr: 0.000004
2021-02-21 00:22:55,492 epoch 5 - iter 16952/21198 - loss 0.22640472 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 00:37:51,438 epoch 5 - iter 19071/21198 - loss 0.22662263 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 00:52:55,596 epoch 5 - iter 21190/21198 - loss 0.22627673 - samples/sec: 9.38 - lr: 0.000004
2021-02-21 00:52:58,870 ----------------------------------------------------------------------------------------------------
2021-02-21 00:52:58,870 EPOCH 5 done: loss 0.2263 - lr 0.0000043
2021-02-21 00:58:49,962 TEST : loss 0.09906419366598129 - score 0.9046
2021-02-21 00:58:50,051 BAD EPOCHS (no improvement): 4
2021-02-21 00:58:50,053 ----------------------------------------------------------------------------------------------------
2021-02-21 01:13:45,979 epoch 6 - iter 2119/21198 - loss 0.21128728 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 01:28:42,436 epoch 6 - iter 4238/21198 - loss 0.21192698 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 01:43:40,811 epoch 6 - iter 6357/21198 - loss 0.21388017 - samples/sec: 9.44 - lr: 0.000004
2021-02-21 01:58:32,902 epoch 6 - iter 8476/21198 - loss 0.21433303 - samples/sec: 9.50 - lr: 0.000004
2021-02-21 02:13:28,053 epoch 6 - iter 10595/21198 - loss 0.21527260 - samples/sec: 9.47 - lr: 0.000004
2021-02-21 02:28:23,770 epoch 6 - iter 12714/21198 - loss 0.21578637 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 02:43:23,477 epoch 6 - iter 14833/21198 - loss 0.21742266 - samples/sec: 9.42 - lr: 0.000004
2021-02-21 02:58:20,917 epoch 6 - iter 16952/21198 - loss 0.21671573 - samples/sec: 9.45 - lr: 0.000004
2021-02-21 03:13:22,283 epoch 6 - iter 19071/21198 - loss 0.21638606 - samples/sec: 9.40 - lr: 0.000004
2021-02-21 03:28:18,668 epoch 6 - iter 21190/21198 - loss 0.21601016 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 03:28:21,833 ----------------------------------------------------------------------------------------------------
2021-02-21 03:28:21,833 EPOCH 6 done: loss 0.2160 - lr 0.0000040
2021-02-21 03:34:15,000 TEST : loss 0.10325756669044495 - score 0.9076
2021-02-21 03:34:15,094 BAD EPOCHS (no improvement): 4
2021-02-21 03:34:15,120 ----------------------------------------------------------------------------------------------------
2021-02-21 03:49:07,155 epoch 7 - iter 2119/21198 - loss 0.21960439 - samples/sec: 9.50 - lr: 0.000004
2021-02-21 04:04:03,005 epoch 7 - iter 4238/21198 - loss 0.22004925 - samples/sec: 9.46 - lr: 0.000004
2021-02-21 04:18:56,753 epoch 7 - iter 6357/21198 - loss 0.21543406 - samples/sec: 9.48 - lr: 0.000004
2021-02-21 04:33:52,219 epoch 7 - iter 8476/21198 - loss 0.21504576 - samples/sec: 9.47 - lr: 0.000004
2021-02-21 04:48:46,766 epoch 7 - iter 10595/21198 - loss 0.21323903 - samples/sec: 9.48 - lr: 0.000004
2021-02-21 05:03:47,214 epoch 7 - iter 12714/21198 - loss 0.21486108 - samples/sec: 9.41 - lr: 0.000004
2021-02-21 05:18:42,062 epoch 7 - iter 14833/21198 - loss 0.21180056 - samples/sec: 9.47 - lr: 0.000004
2021-02-21 05:33:36,547 epoch 7 - iter 16952/21198 - loss 0.21059053 - samples/sec: 9.48 - lr: 0.000004
2021-02-21 05:48:34,692 epoch 7 - iter 19071/21198 - loss 0.21256070 - samples/sec: 9.44 - lr: 0.000004
2021-02-21 06:03:32,420 epoch 7 - iter 21190/21198 - loss 0.21049512 - samples/sec: 9.44 - lr: 0.000004
2021-02-21 06:03:35,617 ----------------------------------------------------------------------------------------------------
2021-02-21 06:03:35,617 EPOCH 7 done: loss 0.2105 - lr 0.0000036
2021-02-21 06:09:34,438 TEST : loss 0.11405058950185776 - score 0.904
2021-02-21 06:09:34,531 BAD EPOCHS (no improvement): 4
2021-02-21 06:09:34,562 ----------------------------------------------------------------------------------------------------
2021-02-21 06:24:28,495 epoch 8 - iter 2119/21198 - loss 0.20943523 - samples/sec: 9.48 - lr: 0.000004
2021-02-21 06:39:27,118 epoch 8 - iter 4238/21198 - loss 0.20855714 - samples/sec: 9.43 - lr: 0.000004
2021-02-21 06:54:21,524 epoch 8 - iter 6357/21198 - loss 0.20901557 - samples/sec: 9.48 - lr: 0.000004
2021-02-21 07:09:19,131 epoch 8 - iter 8476/21198 - loss 0.20346961 - samples/sec: 9.44 - lr: 0.000003
2021-02-21 07:24:13,963 epoch 8 - iter 10595/21198 - loss 0.20279742 - samples/sec: 9.47 - lr: 0.000003
2021-02-21 07:39:11,643 epoch 8 - iter 12714/21198 - loss 0.20257371 - samples/sec: 9.44 - lr: 0.000003
2021-02-21 07:54:11,363 epoch 8 - iter 14833/21198 - loss 0.19941560 - samples/sec: 9.42 - lr: 0.000003
2021-02-21 08:09:12,189 epoch 8 - iter 16952/21198 - loss 0.19895001 - samples/sec: 9.41 - lr: 0.000003
2021-02-21 08:24:10,631 epoch 8 - iter 19071/21198 - loss 0.19874614 - samples/sec: 9.43 - lr: 0.000003
2021-02-21 08:39:11,135 epoch 8 - iter 21190/21198 - loss 0.19883000 - samples/sec: 9.41 - lr: 0.000003
2021-02-21 08:39:14,364 ----------------------------------------------------------------------------------------------------
2021-02-21 08:39:14,365 EPOCH 8 done: loss 0.1989 - lr 0.0000033
2021-02-21 08:45:06,010 TEST : loss 0.12001997232437134 - score 0.9062
2021-02-21 08:45:06,104 BAD EPOCHS (no improvement): 4
2021-02-21 08:45:06,108 ----------------------------------------------------------------------------------------------------
2021-02-21 09:00:02,412 epoch 9 - iter 2119/21198 - loss 0.19438574 - samples/sec: 9.46 - lr: 0.000003
2021-02-21 09:15:05,242 epoch 9 - iter 4238/21198 - loss 0.18942482 - samples/sec: 9.39 - lr: 0.000003
2021-02-21 09:30:02,818 epoch 9 - iter 6357/21198 - loss 0.19236360 - samples/sec: 9.44 - lr: 0.000003
2021-02-21 09:44:58,840 epoch 9 - iter 8476/21198 - loss 0.19256963 - samples/sec: 9.46 - lr: 0.000003
2021-02-21 09:59:56,642 epoch 9 - iter 10595/21198 - loss 0.19253633 - samples/sec: 9.44 - lr: 0.000003
2021-02-21 10:14:53,595 epoch 9 - iter 12714/21198 - loss 0.19368548 - samples/sec: 9.45 - lr: 0.000003
2021-02-21 10:29:47,614 epoch 9 - iter 14833/21198 - loss 0.19452139 - samples/sec: 9.48 - lr: 0.000003
2021-02-21 10:44:41,415 epoch 9 - iter 16952/21198 - loss 0.19339405 - samples/sec: 9.48 - lr: 0.000003
2021-02-21 10:59:36,337 epoch 9 - iter 19071/21198 - loss 0.19242064 - samples/sec: 9.47 - lr: 0.000003
2021-02-21 11:14:30,614 epoch 9 - iter 21190/21198 - loss 0.19248543 - samples/sec: 9.48 - lr: 0.000003
2021-02-21 11:14:33,791 ----------------------------------------------------------------------------------------------------
2021-02-21 11:14:33,791 EPOCH 9 done: loss 0.1925 - lr 0.0000029
2021-02-21 11:20:25,946 TEST : loss 0.12788806855678558 - score 0.9075
2021-02-21 11:20:26,040 BAD EPOCHS (no improvement): 4
2021-02-21 11:20:26,059 ----------------------------------------------------------------------------------------------------
2021-02-21 11:35:18,369 epoch 10 - iter 2119/21198 - loss 0.19003716 - samples/sec: 9.50 - lr: 0.000003
2021-02-21 11:50:08,521 epoch 10 - iter 4238/21198 - loss 0.18305573 - samples/sec: 9.52 - lr: 0.000003
2021-02-21 12:05:00,626 epoch 10 - iter 6357/21198 - loss 0.18276790 - samples/sec: 9.50 - lr: 0.000003
2021-02-21 12:19:58,182 epoch 10 - iter 8476/21198 - loss 0.18408200 - samples/sec: 9.44 - lr: 0.000003
2021-02-21 12:34:51,607 epoch 10 - iter 10595/21198 - loss 0.18396061 - samples/sec: 9.49 - lr: 0.000003
2021-02-21 12:49:50,161 epoch 10 - iter 12714/21198 - loss 0.18350312 - samples/sec: 9.43 - lr: 0.000003
2021-02-21 13:04:45,147 epoch 10 - iter 14833/21198 - loss 0.18334288 - samples/sec: 9.47 - lr: 0.000003
2021-02-21 13:19:40,466 epoch 10 - iter 16952/21198 - loss 0.18425802 - samples/sec: 9.47 - lr: 0.000003
2021-02-21 13:34:36,952 epoch 10 - iter 19071/21198 - loss 0.18414841 - samples/sec: 9.46 - lr: 0.000003
2021-02-21 13:49:30,328 epoch 10 - iter 21190/21198 - loss 0.18456898 - samples/sec: 9.49 - lr: 0.000003
2021-02-21 13:49:33,450 ----------------------------------------------------------------------------------------------------
2021-02-21 13:49:33,450 EPOCH 10 done: loss 0.1846 - lr 0.0000025
2021-02-21 13:55:29,322 TEST : loss 0.14910565316677094 - score 0.9058
2021-02-21 13:55:29,415 BAD EPOCHS (no improvement): 4
2021-02-21 13:55:29,417 ----------------------------------------------------------------------------------------------------
2021-02-21 14:10:21,804 epoch 11 - iter 2119/21198 - loss 0.17609195 - samples/sec: 9.50 - lr: 0.000002
2021-02-21 14:25:16,338 epoch 11 - iter 4238/21198 - loss 0.18154520 - samples/sec: 9.48 - lr: 0.000002
2021-02-21 14:40:12,223 epoch 11 - iter 6357/21198 - loss 0.18097113 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 14:55:03,642 epoch 11 - iter 8476/21198 - loss 0.18053539 - samples/sec: 9.51 - lr: 0.000002
2021-02-21 15:09:56,533 epoch 11 - iter 10595/21198 - loss 0.17876087 - samples/sec: 9.49 - lr: 0.000002
2021-02-21 15:24:53,173 epoch 11 - iter 12714/21198 - loss 0.17894441 - samples/sec: 9.45 - lr: 0.000002
2021-02-21 15:39:48,175 epoch 11 - iter 14833/21198 - loss 0.17978821 - samples/sec: 9.47 - lr: 0.000002
2021-02-21 15:54:40,494 epoch 11 - iter 16952/21198 - loss 0.18011143 - samples/sec: 9.50 - lr: 0.000002
2021-02-21 16:09:33,438 epoch 11 - iter 19071/21198 - loss 0.17919032 - samples/sec: 9.49 - lr: 0.000002
2021-02-21 16:24:22,957 epoch 11 - iter 21190/21198 - loss 0.17903132 - samples/sec: 9.53 - lr: 0.000002
2021-02-21 16:24:26,245 ----------------------------------------------------------------------------------------------------
2021-02-21 16:24:26,245 EPOCH 11 done: loss 0.1790 - lr 0.0000021
2021-02-21 16:30:17,246 TEST : loss 0.15147249400615692 - score 0.9062
2021-02-21 16:30:17,342 BAD EPOCHS (no improvement): 4
2021-02-21 16:30:17,350 ----------------------------------------------------------------------------------------------------
2021-02-21 16:45:13,575 epoch 12 - iter 2119/21198 - loss 0.17364982 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 17:00:11,813 epoch 12 - iter 4238/21198 - loss 0.17305974 - samples/sec: 9.44 - lr: 0.000002
2021-02-21 17:15:07,540 epoch 12 - iter 6357/21198 - loss 0.17213052 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 17:30:04,059 epoch 12 - iter 8476/21198 - loss 0.16983198 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 17:44:57,853 epoch 12 - iter 10595/21198 - loss 0.17052354 - samples/sec: 9.48 - lr: 0.000002
2021-02-21 17:59:52,951 epoch 12 - iter 12714/21198 - loss 0.16948349 - samples/sec: 9.47 - lr: 0.000002
2021-02-21 18:14:48,715 epoch 12 - iter 14833/21198 - loss 0.16890758 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 18:29:40,011 epoch 12 - iter 16952/21198 - loss 0.16929059 - samples/sec: 9.51 - lr: 0.000002
2021-02-21 18:44:42,153 epoch 12 - iter 19071/21198 - loss 0.16928360 - samples/sec: 9.40 - lr: 0.000002
2021-02-21 18:59:37,616 epoch 12 - iter 21190/21198 - loss 0.17211801 - samples/sec: 9.47 - lr: 0.000002
2021-02-21 18:59:40,898 ----------------------------------------------------------------------------------------------------
2021-02-21 18:59:40,898 EPOCH 12 done: loss 0.1721 - lr 0.0000017
2021-02-21 19:05:31,029 TEST : loss 0.147916778922081 - score 0.9085
2021-02-21 19:05:31,125 BAD EPOCHS (no improvement): 4
2021-02-21 19:05:31,142 ----------------------------------------------------------------------------------------------------
2021-02-21 19:20:24,965 epoch 13 - iter 2119/21198 - loss 0.16896267 - samples/sec: 9.48 - lr: 0.000002
2021-02-21 19:35:21,463 epoch 13 - iter 4238/21198 - loss 0.16653116 - samples/sec: 9.46 - lr: 0.000002
2021-02-21 19:50:15,194 epoch 13 - iter 6357/21198 - loss 0.16770765 - samples/sec: 9.48 - lr: 0.000002
2021-02-21 20:05:12,891 epoch 13 - iter 8476/21198 - loss 0.17108344 - samples/sec: 9.44 - lr: 0.000002
2021-02-21 20:20:06,566 epoch 13 - iter 10595/21198 - loss 0.17184402 - samples/sec: 9.49 - lr: 0.000002
2021-02-21 20:34:59,890 epoch 13 - iter 12714/21198 - loss 0.17303152 - samples/sec: 9.49 - lr: 0.000002
2021-02-21 20:49:50,908 epoch 13 - iter 14833/21198 - loss 0.17325989 - samples/sec: 9.51 - lr: 0.000001
2021-02-21 21:04:47,902 epoch 13 - iter 16952/21198 - loss 0.17294630 - samples/sec: 9.45 - lr: 0.000001
2021-02-21 21:19:41,901 epoch 13 - iter 19071/21198 - loss 0.17373625 - samples/sec: 9.48 - lr: 0.000001
2021-02-21 21:34:36,135 epoch 13 - iter 21190/21198 - loss 0.17394207 - samples/sec: 9.48 - lr: 0.000001
2021-02-21 21:34:39,310 ----------------------------------------------------------------------------------------------------
2021-02-21 21:34:39,310 EPOCH 13 done: loss 0.1739 - lr 0.0000014
2021-02-21 21:40:34,294 TEST : loss 0.16395367681980133 - score 0.9076
2021-02-21 21:40:34,393 BAD EPOCHS (no improvement): 4
2021-02-21 21:40:34,407 ----------------------------------------------------------------------------------------------------
2021-02-21 21:55:30,019 epoch 14 - iter 2119/21198 - loss 0.17210424 - samples/sec: 9.46 - lr: 0.000001
2021-02-21 22:10:22,785 epoch 14 - iter 4238/21198 - loss 0.17224407 - samples/sec: 9.49 - lr: 0.000001
2021-02-21 22:25:15,502 epoch 14 - iter 6357/21198 - loss 0.17196186 - samples/sec: 9.50 - lr: 0.000001
2021-02-21 22:40:13,225 epoch 14 - iter 8476/21198 - loss 0.17131693 - samples/sec: 9.44 - lr: 0.000001
2021-02-21 22:55:12,609 epoch 14 - iter 10595/21198 - loss 0.17336075 - samples/sec: 9.43 - lr: 0.000001
2021-02-21 23:10:03,405 epoch 14 - iter 12714/21198 - loss 0.17249936 - samples/sec: 9.52 - lr: 0.000001
2021-02-21 23:24:55,615 epoch 14 - iter 14833/21198 - loss 0.17318785 - samples/sec: 9.50 - lr: 0.000001
2021-02-21 23:39:39,560 epoch 14 - iter 16952/21198 - loss 0.17208304 - samples/sec: 9.59 - lr: 0.000001
2021-02-21 23:54:35,004 epoch 14 - iter 19071/21198 - loss 0.17228505 - samples/sec: 9.47 - lr: 0.000001
2021-02-22 00:09:25,613 epoch 14 - iter 21190/21198 - loss 0.17228047 - samples/sec: 9.52 - lr: 0.000001
2021-02-22 00:09:28,876 ----------------------------------------------------------------------------------------------------
2021-02-22 00:09:28,877 EPOCH 14 done: loss 0.1723 - lr 0.0000010
2021-02-22 00:15:21,867 TEST : loss 0.16743017733097076 - score 0.909
2021-02-22 00:15:21,963 BAD EPOCHS (no improvement): 4
2021-02-22 00:15:21,965 ----------------------------------------------------------------------------------------------------
2021-02-22 00:30:16,862 epoch 15 - iter 2119/21198 - loss 0.15790436 - samples/sec: 9.47 - lr: 0.000001
2021-02-22 00:45:09,621 epoch 15 - iter 4238/21198 - loss 0.15811998 - samples/sec: 9.49 - lr: 0.000001
2021-02-22 01:00:03,426 epoch 15 - iter 6357/21198 - loss 0.16041062 - samples/sec: 9.48 - lr: 0.000001
2021-02-22 01:14:56,991 epoch 15 - iter 8476/21198 - loss 0.16204753 - samples/sec: 9.49 - lr: 0.000001
2021-02-22 01:29:46,578 epoch 15 - iter 10595/21198 - loss 0.16310173 - samples/sec: 9.53 - lr: 0.000001
2021-02-22 01:44:39,948 epoch 15 - iter 12714/21198 - loss 0.16249272 - samples/sec: 9.49 - lr: 0.000001
2021-02-22 01:59:33,810 epoch 15 - iter 14833/21198 - loss 0.16196562 - samples/sec: 9.48 - lr: 0.000001
2021-02-22 02:14:26,647 epoch 15 - iter 16952/21198 - loss 0.16333266 - samples/sec: 9.49 - lr: 0.000001
2021-02-22 02:29:18,415 epoch 15 - iter 19071/21198 - loss 0.16459359 - samples/sec: 9.51 - lr: 0.000001
2021-02-22 02:44:12,651 epoch 15 - iter 21190/21198 - loss 0.16491666 - samples/sec: 9.48 - lr: 0.000001
2021-02-22 02:44:15,874 ----------------------------------------------------------------------------------------------------
2021-02-22 02:44:15,874 EPOCH 15 done: loss 0.1649 - lr 0.0000007
2021-02-22 02:50:08,356 TEST : loss 0.17295649647712708 - score 0.9101
2021-02-22 02:50:08,450 BAD EPOCHS (no improvement): 4
2021-02-22 02:50:08,452 ----------------------------------------------------------------------------------------------------
2021-02-22 03:05:07,383 epoch 16 - iter 2119/21198 - loss 0.16869372 - samples/sec: 9.43 - lr: 0.000001
2021-02-22 03:20:04,205 epoch 16 - iter 4238/21198 - loss 0.16204002 - samples/sec: 9.45 - lr: 0.000001
2021-02-22 03:34:56,532 epoch 16 - iter 6357/21198 - loss 0.16115018 - samples/sec: 9.50 - lr: 0.000001
2021-02-22 03:49:52,676 epoch 16 - iter 8476/21198 - loss 0.16290083 - samples/sec: 9.46 - lr: 0.000001
2021-02-22 04:04:43,904 epoch 16 - iter 10595/21198 - loss 0.16286029 - samples/sec: 9.51 - lr: 0.000001
2021-02-22 04:19:37,979 epoch 16 - iter 12714/21198 - loss 0.16258104 - samples/sec: 9.48 - lr: 0.000001
2021-02-22 04:34:27,662 epoch 16 - iter 14833/21198 - loss 0.16217931 - samples/sec: 9.53 - lr: 0.000001
2021-02-22 04:49:18,263 epoch 16 - iter 16952/21198 - loss 0.16190092 - samples/sec: 9.52 - lr: 0.000001
2021-02-22 05:04:09,607 epoch 16 - iter 19071/21198 - loss 0.16271366 - samples/sec: 9.51 - lr: 0.000001
2021-02-22 05:19:03,032 epoch 16 - iter 21190/21198 - loss 0.16309304 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 05:19:06,131 ----------------------------------------------------------------------------------------------------
2021-02-22 05:19:06,131 EPOCH 16 done: loss 0.1631 - lr 0.0000005
2021-02-22 05:24:59,209 TEST : loss 0.1732577085494995 - score 0.9099
2021-02-22 05:24:59,306 BAD EPOCHS (no improvement): 4
2021-02-22 05:24:59,318 ----------------------------------------------------------------------------------------------------
2021-02-22 05:39:50,755 epoch 17 - iter 2119/21198 - loss 0.15607883 - samples/sec: 9.51 - lr: 0.000000
2021-02-22 05:54:41,713 epoch 17 - iter 4238/21198 - loss 0.16295560 - samples/sec: 9.51 - lr: 0.000000
2021-02-22 06:09:33,595 epoch 17 - iter 6357/21198 - loss 0.16030109 - samples/sec: 9.50 - lr: 0.000000
2021-02-22 06:24:26,942 epoch 17 - iter 8476/21198 - loss 0.16028383 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 06:39:19,965 epoch 17 - iter 10595/21198 - loss 0.16179951 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 06:54:14,002 epoch 17 - iter 12714/21198 - loss 0.16064671 - samples/sec: 9.48 - lr: 0.000000
2021-02-22 07:09:02,879 epoch 17 - iter 14833/21198 - loss 0.16118933 - samples/sec: 9.54 - lr: 0.000000
2021-02-22 07:23:53,696 epoch 17 - iter 16952/21198 - loss 0.16233903 - samples/sec: 9.52 - lr: 0.000000
2021-02-22 07:38:43,895 epoch 17 - iter 19071/21198 - loss 0.16244551 - samples/sec: 9.52 - lr: 0.000000
2021-02-22 07:53:35,588 epoch 17 - iter 21190/21198 - loss 0.16243178 - samples/sec: 9.51 - lr: 0.000000
2021-02-22 07:53:38,781 ----------------------------------------------------------------------------------------------------
2021-02-22 07:53:38,781 EPOCH 17 done: loss 0.1624 - lr 0.0000003
2021-02-22 07:59:36,439 TEST : loss 0.1792287975549698 - score 0.9098
2021-02-22 07:59:36,538 BAD EPOCHS (no improvement): 4
2021-02-22 07:59:36,561 ----------------------------------------------------------------------------------------------------
2021-02-22 08:14:29,823 epoch 18 - iter 2119/21198 - loss 0.16946072 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 08:29:28,618 epoch 18 - iter 4238/21198 - loss 0.16431210 - samples/sec: 9.43 - lr: 0.000000
2021-02-22 08:44:23,757 epoch 18 - iter 6357/21198 - loss 0.16285664 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 08:59:18,330 epoch 18 - iter 8476/21198 - loss 0.16406026 - samples/sec: 9.48 - lr: 0.000000
2021-02-22 09:14:15,549 epoch 18 - iter 10595/21198 - loss 0.16218940 - samples/sec: 9.45 - lr: 0.000000
2021-02-22 09:29:11,539 epoch 18 - iter 12714/21198 - loss 0.16137864 - samples/sec: 9.46 - lr: 0.000000
2021-02-22 09:44:06,143 epoch 18 - iter 14833/21198 - loss 0.16211856 - samples/sec: 9.48 - lr: 0.000000
2021-02-22 09:59:03,167 epoch 18 - iter 16952/21198 - loss 0.16214711 - samples/sec: 9.45 - lr: 0.000000
2021-02-22 10:13:57,239 epoch 18 - iter 19071/21198 - loss 0.16058721 - samples/sec: 9.48 - lr: 0.000000
2021-02-22 10:28:52,182 epoch 18 - iter 21190/21198 - loss 0.16093573 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 10:28:55,515 ----------------------------------------------------------------------------------------------------
2021-02-22 10:28:55,515 EPOCH 18 done: loss 0.1610 - lr 0.0000001
2021-02-22 10:34:48,208 TEST : loss 0.17890706658363342 - score 0.9095
2021-02-22 10:34:48,308 BAD EPOCHS (no improvement): 4
2021-02-22 10:34:48,332 ----------------------------------------------------------------------------------------------------
2021-02-22 10:49:43,738 epoch 19 - iter 2119/21198 - loss 0.16694990 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 11:04:30,455 epoch 19 - iter 4238/21198 - loss 0.15984197 - samples/sec: 9.56 - lr: 0.000000
2021-02-22 11:19:21,091 epoch 19 - iter 6357/21198 - loss 0.15796573 - samples/sec: 9.52 - lr: 0.000000
2021-02-22 11:34:16,935 epoch 19 - iter 8476/21198 - loss 0.16031077 - samples/sec: 9.46 - lr: 0.000000
2021-02-22 11:49:14,170 epoch 19 - iter 10595/21198 - loss 0.16114764 - samples/sec: 9.45 - lr: 0.000000
2021-02-22 12:04:12,070 epoch 19 - iter 12714/21198 - loss 0.16077654 - samples/sec: 9.44 - lr: 0.000000
2021-02-22 12:19:05,634 epoch 19 - iter 14833/21198 - loss 0.16093868 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 12:34:03,912 epoch 19 - iter 16952/21198 - loss 0.16092922 - samples/sec: 9.44 - lr: 0.000000
2021-02-22 12:48:59,408 epoch 19 - iter 19071/21198 - loss 0.16176484 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 13:03:55,588 epoch 19 - iter 21190/21198 - loss 0.16136077 - samples/sec: 9.46 - lr: 0.000000
2021-02-22 13:03:58,842 ----------------------------------------------------------------------------------------------------
2021-02-22 13:03:58,842 EPOCH 19 done: loss 0.1613 - lr 0.0000000
2021-02-22 13:09:51,774 TEST : loss 0.1799449324607849 - score 0.9093
2021-02-22 13:09:51,873 BAD EPOCHS (no improvement): 4
2021-02-22 13:09:51,889 ----------------------------------------------------------------------------------------------------
2021-02-22 13:24:48,886 epoch 20 - iter 2119/21198 - loss 0.15743940 - samples/sec: 9.45 - lr: 0.000000
2021-02-22 13:39:41,650 epoch 20 - iter 4238/21198 - loss 0.15941045 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 13:54:35,155 epoch 20 - iter 6357/21198 - loss 0.16085263 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 14:09:30,408 epoch 20 - iter 8476/21198 - loss 0.16038502 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 14:24:21,244 epoch 20 - iter 10595/21198 - loss 0.15929046 - samples/sec: 9.52 - lr: 0.000000
2021-02-22 14:39:15,988 epoch 20 - iter 12714/21198 - loss 0.15817473 - samples/sec: 9.47 - lr: 0.000000
2021-02-22 14:54:08,818 epoch 20 - iter 14833/21198 - loss 0.16049560 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 15:09:01,889 epoch 20 - iter 16952/21198 - loss 0.16079237 - samples/sec: 9.49 - lr: 0.000000
2021-02-22 15:23:54,278 epoch 20 - iter 19071/21198 - loss 0.16175262 - samples/sec: 9.50 - lr: 0.000000
2021-02-22 15:38:48,341 epoch 20 - iter 21190/21198 - loss 0.16071107 - samples/sec: 9.48 - lr: 0.000000
2021-02-22 15:38:51,585 ----------------------------------------------------------------------------------------------------
2021-02-22 15:38:51,586 EPOCH 20 done: loss 0.1607 - lr 0.0000000
2021-02-22 15:44:48,115 TEST : loss 0.17999354004859924 - score 0.9093
2021-02-22 15:44:48,213 BAD EPOCHS (no improvement): 4
2021-02-22 15:45:25,862 ----------------------------------------------------------------------------------------------------
2021-02-22 15:45:25,862 Testing using best model ...
2021-02-22 15:51:35,093 0.9055 0.9132 0.9093
2021-02-22 15:51:35,093
Results:
- F1-score (micro) 0.9093
- F1-score (macro) 0.8233
By class:
CARDINAL tp: 802 - fp: 124 - fn: 133 - precision: 0.8661 - recall: 0.8578 - f1-score: 0.8619
DATE tp: 1435 - fp: 219 - fn: 167 - precision: 0.8676 - recall: 0.8958 - f1-score: 0.8814
EVENT tp: 45 - fp: 19 - fn: 18 - precision: 0.7031 - recall: 0.7143 - f1-score: 0.7087
FAC tp: 105 - fp: 26 - fn: 30 - precision: 0.8015 - recall: 0.7778 - f1-score: 0.7895
GPE tp: 2161 - fp: 62 - fn: 79 - precision: 0.9721 - recall: 0.9647 - f1-score: 0.9684
LANGUAGE tp: 14 - fp: 2 - fn: 8 - precision: 0.8750 - recall: 0.6364 - f1-score: 0.7368
LAW tp: 26 - fp: 18 - fn: 14 - precision: 0.5909 - recall: 0.6500 - f1-score: 0.6190
LOC tp: 140 - fp: 41 - fn: 39 - precision: 0.7735 - recall: 0.7821 - f1-score: 0.7778
MONEY tp: 286 - fp: 29 - fn: 28 - precision: 0.9079 - recall: 0.9108 - f1-score: 0.9094
NORP tp: 820 - fp: 45 - fn: 21 - precision: 0.9480 - recall: 0.9750 - f1-score: 0.9613
ORDINAL tp: 168 - fp: 38 - fn: 27 - precision: 0.8155 - recall: 0.8615 - f1-score: 0.8379
ORG tp: 1650 - fp: 168 - fn: 145 - precision: 0.9076 - recall: 0.9192 - f1-score: 0.9134
PERCENT tp: 310 - fp: 37 - fn: 39 - precision: 0.8934 - recall: 0.8883 - f1-score: 0.8908
PERSON tp: 1903 - fp: 81 - fn: 85 - precision: 0.9592 - recall: 0.9572 - f1-score: 0.9582
PRODUCT tp: 66 - fp: 21 - fn: 10 - precision: 0.7586 - recall: 0.8684 - f1-score: 0.8098
QUANTITY tp: 87 - fp: 22 - fn: 18 - precision: 0.7982 - recall: 0.8286 - f1-score: 0.8131
TIME tp: 144 - fp: 72 - fn: 68 - precision: 0.6667 - recall: 0.6792 - f1-score: 0.6729
WORK_OF_ART tp: 118 - fp: 49 - fn: 48 - precision: 0.7066 - recall: 0.7108 - f1-score: 0.7087
2021-02-22 15:51:35,093 ----------------------------------------------------------------------------------------------------