Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
hmbench-hipe2020-de-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5 / training.log
stefan-it's picture
stefan-it
Upload ./training.log with huggingface_hub
eedda65
raw history blame contribute delete
No virus
36.9 kB
2023-10-23 23:00:28,649 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,650 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(64001, 768)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(1): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(2): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(3): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(4): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(5): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(6): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(7): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(8): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(9): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(10): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(11): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=21, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
- NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Train: 3575 sentences
2023-10-23 23:00:28,651 (train_with_dev=False, train_with_test=False)
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Training Params:
2023-10-23 23:00:28,651 - learning_rate: "3e-05"
2023-10-23 23:00:28,651 - mini_batch_size: "8"
2023-10-23 23:00:28,651 - max_epochs: "10"
2023-10-23 23:00:28,651 - shuffle: "True"
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Plugins:
2023-10-23 23:00:28,651 - TensorboardLogger
2023-10-23 23:00:28,651 - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 23:00:28,651 - metric: "('micro avg', 'f1-score')"
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Computation:
2023-10-23 23:00:28,651 - compute on device: cuda:0
2023-10-23 23:00:28,651 - embedding storage: none
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:28,651 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 23:00:32,746 epoch 1 - iter 44/447 - loss 2.52602023 - time (sec): 4.09 - samples/sec: 2195.25 - lr: 0.000003 - momentum: 0.000000
2023-10-23 23:00:36,618 epoch 1 - iter 88/447 - loss 1.70182761 - time (sec): 7.97 - samples/sec: 2171.87 - lr: 0.000006 - momentum: 0.000000
2023-10-23 23:00:40,574 epoch 1 - iter 132/447 - loss 1.31473468 - time (sec): 11.92 - samples/sec: 2185.11 - lr: 0.000009 - momentum: 0.000000
2023-10-23 23:00:44,249 epoch 1 - iter 176/447 - loss 1.09744513 - time (sec): 15.60 - samples/sec: 2207.06 - lr: 0.000012 - momentum: 0.000000
2023-10-23 23:00:48,800 epoch 1 - iter 220/447 - loss 0.92998358 - time (sec): 20.15 - samples/sec: 2172.71 - lr: 0.000015 - momentum: 0.000000
2023-10-23 23:00:52,526 epoch 1 - iter 264/447 - loss 0.83386539 - time (sec): 23.87 - samples/sec: 2166.96 - lr: 0.000018 - momentum: 0.000000
2023-10-23 23:00:56,473 epoch 1 - iter 308/447 - loss 0.75611333 - time (sec): 27.82 - samples/sec: 2152.51 - lr: 0.000021 - momentum: 0.000000
2023-10-23 23:01:00,214 epoch 1 - iter 352/447 - loss 0.69739560 - time (sec): 31.56 - samples/sec: 2134.46 - lr: 0.000024 - momentum: 0.000000
2023-10-23 23:01:04,333 epoch 1 - iter 396/447 - loss 0.64562676 - time (sec): 35.68 - samples/sec: 2144.31 - lr: 0.000027 - momentum: 0.000000
2023-10-23 23:01:08,462 epoch 1 - iter 440/447 - loss 0.59937392 - time (sec): 39.81 - samples/sec: 2143.25 - lr: 0.000029 - momentum: 0.000000
2023-10-23 23:01:09,047 ----------------------------------------------------------------------------------------------------
2023-10-23 23:01:09,048 EPOCH 1 done: loss 0.5937 - lr: 0.000029
2023-10-23 23:01:13,861 DEV : loss 0.19523081183433533 - f1-score (micro avg) 0.602
2023-10-23 23:01:13,882 saving best model
2023-10-23 23:01:14,355 ----------------------------------------------------------------------------------------------------
2023-10-23 23:01:18,559 epoch 2 - iter 44/447 - loss 0.17169884 - time (sec): 4.20 - samples/sec: 2020.76 - lr: 0.000030 - momentum: 0.000000
2023-10-23 23:01:22,581 epoch 2 - iter 88/447 - loss 0.17647433 - time (sec): 8.22 - samples/sec: 2101.90 - lr: 0.000029 - momentum: 0.000000
2023-10-23 23:01:26,617 epoch 2 - iter 132/447 - loss 0.16565784 - time (sec): 12.26 - samples/sec: 2086.54 - lr: 0.000029 - momentum: 0.000000
2023-10-23 23:01:30,763 epoch 2 - iter 176/447 - loss 0.16430118 - time (sec): 16.41 - samples/sec: 2107.26 - lr: 0.000029 - momentum: 0.000000
2023-10-23 23:01:34,549 epoch 2 - iter 220/447 - loss 0.15912237 - time (sec): 20.19 - samples/sec: 2116.34 - lr: 0.000028 - momentum: 0.000000
2023-10-23 23:01:38,548 epoch 2 - iter 264/447 - loss 0.15555409 - time (sec): 24.19 - samples/sec: 2112.73 - lr: 0.000028 - momentum: 0.000000
2023-10-23 23:01:42,387 epoch 2 - iter 308/447 - loss 0.15167650 - time (sec): 28.03 - samples/sec: 2126.29 - lr: 0.000028 - momentum: 0.000000
2023-10-23 23:01:46,396 epoch 2 - iter 352/447 - loss 0.14567258 - time (sec): 32.04 - samples/sec: 2135.14 - lr: 0.000027 - momentum: 0.000000
2023-10-23 23:01:50,342 epoch 2 - iter 396/447 - loss 0.14264947 - time (sec): 35.99 - samples/sec: 2127.62 - lr: 0.000027 - momentum: 0.000000
2023-10-23 23:01:54,245 epoch 2 - iter 440/447 - loss 0.13821798 - time (sec): 39.89 - samples/sec: 2136.97 - lr: 0.000027 - momentum: 0.000000
2023-10-23 23:01:54,864 ----------------------------------------------------------------------------------------------------
2023-10-23 23:01:54,864 EPOCH 2 done: loss 0.1395 - lr: 0.000027
2023-10-23 23:02:01,346 DEV : loss 0.12295468896627426 - f1-score (micro avg) 0.7103
2023-10-23 23:02:01,366 saving best model
2023-10-23 23:02:01,953 ----------------------------------------------------------------------------------------------------
2023-10-23 23:02:06,309 epoch 3 - iter 44/447 - loss 0.09549111 - time (sec): 4.35 - samples/sec: 2195.36 - lr: 0.000026 - momentum: 0.000000
2023-10-23 23:02:10,254 epoch 3 - iter 88/447 - loss 0.07868123 - time (sec): 8.30 - samples/sec: 2242.07 - lr: 0.000026 - momentum: 0.000000
2023-10-23 23:02:14,277 epoch 3 - iter 132/447 - loss 0.08318832 - time (sec): 12.32 - samples/sec: 2209.09 - lr: 0.000026 - momentum: 0.000000
2023-10-23 23:02:17,984 epoch 3 - iter 176/447 - loss 0.07733080 - time (sec): 16.03 - samples/sec: 2198.38 - lr: 0.000025 - momentum: 0.000000
2023-10-23 23:02:22,352 epoch 3 - iter 220/447 - loss 0.07500939 - time (sec): 20.40 - samples/sec: 2181.80 - lr: 0.000025 - momentum: 0.000000
2023-10-23 23:02:26,654 epoch 3 - iter 264/447 - loss 0.07437472 - time (sec): 24.70 - samples/sec: 2171.11 - lr: 0.000025 - momentum: 0.000000
2023-10-23 23:02:30,577 epoch 3 - iter 308/447 - loss 0.07459318 - time (sec): 28.62 - samples/sec: 2157.01 - lr: 0.000024 - momentum: 0.000000
2023-10-23 23:02:34,258 epoch 3 - iter 352/447 - loss 0.07470733 - time (sec): 32.30 - samples/sec: 2137.56 - lr: 0.000024 - momentum: 0.000000
2023-10-23 23:02:38,173 epoch 3 - iter 396/447 - loss 0.07388045 - time (sec): 36.22 - samples/sec: 2148.46 - lr: 0.000024 - momentum: 0.000000
2023-10-23 23:02:41,938 epoch 3 - iter 440/447 - loss 0.07304330 - time (sec): 39.98 - samples/sec: 2136.97 - lr: 0.000023 - momentum: 0.000000
2023-10-23 23:02:42,478 ----------------------------------------------------------------------------------------------------
2023-10-23 23:02:42,479 EPOCH 3 done: loss 0.0728 - lr: 0.000023
2023-10-23 23:02:48,963 DEV : loss 0.15343354642391205 - f1-score (micro avg) 0.7489
2023-10-23 23:02:48,983 saving best model
2023-10-23 23:02:49,570 ----------------------------------------------------------------------------------------------------
2023-10-23 23:02:53,380 epoch 4 - iter 44/447 - loss 0.03471509 - time (sec): 3.81 - samples/sec: 2180.41 - lr: 0.000023 - momentum: 0.000000
2023-10-23 23:02:57,700 epoch 4 - iter 88/447 - loss 0.04095950 - time (sec): 8.13 - samples/sec: 2166.29 - lr: 0.000023 - momentum: 0.000000
2023-10-23 23:03:01,896 epoch 4 - iter 132/447 - loss 0.04313707 - time (sec): 12.33 - samples/sec: 2145.87 - lr: 0.000022 - momentum: 0.000000
2023-10-23 23:03:05,622 epoch 4 - iter 176/447 - loss 0.04217202 - time (sec): 16.05 - samples/sec: 2123.73 - lr: 0.000022 - momentum: 0.000000
2023-10-23 23:03:10,203 epoch 4 - iter 220/447 - loss 0.04425905 - time (sec): 20.63 - samples/sec: 2113.31 - lr: 0.000022 - momentum: 0.000000
2023-10-23 23:03:14,002 epoch 4 - iter 264/447 - loss 0.04327538 - time (sec): 24.43 - samples/sec: 2107.43 - lr: 0.000021 - momentum: 0.000000
2023-10-23 23:03:18,050 epoch 4 - iter 308/447 - loss 0.04558314 - time (sec): 28.48 - samples/sec: 2129.10 - lr: 0.000021 - momentum: 0.000000
2023-10-23 23:03:22,001 epoch 4 - iter 352/447 - loss 0.04373608 - time (sec): 32.43 - samples/sec: 2127.73 - lr: 0.000021 - momentum: 0.000000
2023-10-23 23:03:25,841 epoch 4 - iter 396/447 - loss 0.04253316 - time (sec): 36.27 - samples/sec: 2127.56 - lr: 0.000020 - momentum: 0.000000
2023-10-23 23:03:29,679 epoch 4 - iter 440/447 - loss 0.04399254 - time (sec): 40.11 - samples/sec: 2125.07 - lr: 0.000020 - momentum: 0.000000
2023-10-23 23:03:30,294 ----------------------------------------------------------------------------------------------------
2023-10-23 23:03:30,294 EPOCH 4 done: loss 0.0437 - lr: 0.000020
2023-10-23 23:03:36,776 DEV : loss 0.16440840065479279 - f1-score (micro avg) 0.7465
2023-10-23 23:03:36,796 ----------------------------------------------------------------------------------------------------
2023-10-23 23:03:40,718 epoch 5 - iter 44/447 - loss 0.03153993 - time (sec): 3.92 - samples/sec: 2183.07 - lr: 0.000020 - momentum: 0.000000
2023-10-23 23:03:45,031 epoch 5 - iter 88/447 - loss 0.03158561 - time (sec): 8.23 - samples/sec: 2117.98 - lr: 0.000019 - momentum: 0.000000
2023-10-23 23:03:48,851 epoch 5 - iter 132/447 - loss 0.03154475 - time (sec): 12.05 - samples/sec: 2134.16 - lr: 0.000019 - momentum: 0.000000
2023-10-23 23:03:52,601 epoch 5 - iter 176/447 - loss 0.02896412 - time (sec): 15.80 - samples/sec: 2134.56 - lr: 0.000019 - momentum: 0.000000
2023-10-23 23:03:56,655 epoch 5 - iter 220/447 - loss 0.02964248 - time (sec): 19.86 - samples/sec: 2123.94 - lr: 0.000018 - momentum: 0.000000
2023-10-23 23:04:00,713 epoch 5 - iter 264/447 - loss 0.02934625 - time (sec): 23.92 - samples/sec: 2115.14 - lr: 0.000018 - momentum: 0.000000
2023-10-23 23:04:04,358 epoch 5 - iter 308/447 - loss 0.02819574 - time (sec): 27.56 - samples/sec: 2124.76 - lr: 0.000018 - momentum: 0.000000
2023-10-23 23:04:08,764 epoch 5 - iter 352/447 - loss 0.03063596 - time (sec): 31.97 - samples/sec: 2126.05 - lr: 0.000017 - momentum: 0.000000
2023-10-23 23:04:12,599 epoch 5 - iter 396/447 - loss 0.02978320 - time (sec): 35.80 - samples/sec: 2137.51 - lr: 0.000017 - momentum: 0.000000
2023-10-23 23:04:16,554 epoch 5 - iter 440/447 - loss 0.02930160 - time (sec): 39.76 - samples/sec: 2141.01 - lr: 0.000017 - momentum: 0.000000
2023-10-23 23:04:17,157 ----------------------------------------------------------------------------------------------------
2023-10-23 23:04:17,157 EPOCH 5 done: loss 0.0292 - lr: 0.000017
2023-10-23 23:04:23,636 DEV : loss 0.18590261042118073 - f1-score (micro avg) 0.771
2023-10-23 23:04:23,656 saving best model
2023-10-23 23:04:24,245 ----------------------------------------------------------------------------------------------------
2023-10-23 23:04:28,359 epoch 6 - iter 44/447 - loss 0.02168377 - time (sec): 4.11 - samples/sec: 2005.67 - lr: 0.000016 - momentum: 0.000000
2023-10-23 23:04:32,535 epoch 6 - iter 88/447 - loss 0.02664472 - time (sec): 8.29 - samples/sec: 2046.54 - lr: 0.000016 - momentum: 0.000000
2023-10-23 23:04:37,101 epoch 6 - iter 132/447 - loss 0.02379201 - time (sec): 12.85 - samples/sec: 2069.01 - lr: 0.000016 - momentum: 0.000000
2023-10-23 23:04:40,881 epoch 6 - iter 176/447 - loss 0.02219099 - time (sec): 16.64 - samples/sec: 2088.60 - lr: 0.000015 - momentum: 0.000000
2023-10-23 23:04:44,787 epoch 6 - iter 220/447 - loss 0.02183849 - time (sec): 20.54 - samples/sec: 2102.02 - lr: 0.000015 - momentum: 0.000000
2023-10-23 23:04:48,657 epoch 6 - iter 264/447 - loss 0.02049396 - time (sec): 24.41 - samples/sec: 2109.29 - lr: 0.000015 - momentum: 0.000000
2023-10-23 23:04:52,413 epoch 6 - iter 308/447 - loss 0.02101667 - time (sec): 28.17 - samples/sec: 2106.25 - lr: 0.000014 - momentum: 0.000000
2023-10-23 23:04:56,108 epoch 6 - iter 352/447 - loss 0.01998352 - time (sec): 31.86 - samples/sec: 2107.46 - lr: 0.000014 - momentum: 0.000000
2023-10-23 23:05:00,274 epoch 6 - iter 396/447 - loss 0.02022647 - time (sec): 36.03 - samples/sec: 2113.02 - lr: 0.000014 - momentum: 0.000000
2023-10-23 23:05:04,211 epoch 6 - iter 440/447 - loss 0.02038921 - time (sec): 39.96 - samples/sec: 2131.51 - lr: 0.000013 - momentum: 0.000000
2023-10-23 23:05:04,873 ----------------------------------------------------------------------------------------------------
2023-10-23 23:05:04,874 EPOCH 6 done: loss 0.0206 - lr: 0.000013
2023-10-23 23:05:11,385 DEV : loss 0.2045108526945114 - f1-score (micro avg) 0.7576
2023-10-23 23:05:11,406 ----------------------------------------------------------------------------------------------------
2023-10-23 23:05:15,710 epoch 7 - iter 44/447 - loss 0.02004284 - time (sec): 4.30 - samples/sec: 2123.05 - lr: 0.000013 - momentum: 0.000000
2023-10-23 23:05:19,740 epoch 7 - iter 88/447 - loss 0.01541434 - time (sec): 8.33 - samples/sec: 2121.61 - lr: 0.000013 - momentum: 0.000000
2023-10-23 23:05:23,460 epoch 7 - iter 132/447 - loss 0.01587152 - time (sec): 12.05 - samples/sec: 2141.90 - lr: 0.000012 - momentum: 0.000000
2023-10-23 23:05:27,657 epoch 7 - iter 176/447 - loss 0.01550813 - time (sec): 16.25 - samples/sec: 2171.27 - lr: 0.000012 - momentum: 0.000000
2023-10-23 23:05:31,665 epoch 7 - iter 220/447 - loss 0.01526874 - time (sec): 20.26 - samples/sec: 2146.13 - lr: 0.000012 - momentum: 0.000000
2023-10-23 23:05:35,806 epoch 7 - iter 264/447 - loss 0.01545565 - time (sec): 24.40 - samples/sec: 2129.96 - lr: 0.000011 - momentum: 0.000000
2023-10-23 23:05:39,700 epoch 7 - iter 308/447 - loss 0.01438074 - time (sec): 28.29 - samples/sec: 2135.49 - lr: 0.000011 - momentum: 0.000000
2023-10-23 23:05:43,906 epoch 7 - iter 352/447 - loss 0.01391057 - time (sec): 32.50 - samples/sec: 2137.46 - lr: 0.000011 - momentum: 0.000000
2023-10-23 23:05:47,968 epoch 7 - iter 396/447 - loss 0.01352129 - time (sec): 36.56 - samples/sec: 2134.04 - lr: 0.000010 - momentum: 0.000000
2023-10-23 23:05:51,529 epoch 7 - iter 440/447 - loss 0.01375727 - time (sec): 40.12 - samples/sec: 2126.85 - lr: 0.000010 - momentum: 0.000000
2023-10-23 23:05:52,094 ----------------------------------------------------------------------------------------------------
2023-10-23 23:05:52,095 EPOCH 7 done: loss 0.0138 - lr: 0.000010
2023-10-23 23:05:58,309 DEV : loss 0.22162960469722748 - f1-score (micro avg) 0.7836
2023-10-23 23:05:58,329 saving best model
2023-10-23 23:05:59,227 ----------------------------------------------------------------------------------------------------
2023-10-23 23:06:03,130 epoch 8 - iter 44/447 - loss 0.00338610 - time (sec): 3.90 - samples/sec: 2177.22 - lr: 0.000010 - momentum: 0.000000
2023-10-23 23:06:07,503 epoch 8 - iter 88/447 - loss 0.00649872 - time (sec): 8.28 - samples/sec: 2124.18 - lr: 0.000009 - momentum: 0.000000
2023-10-23 23:06:11,262 epoch 8 - iter 132/447 - loss 0.00844255 - time (sec): 12.03 - samples/sec: 2139.75 - lr: 0.000009 - momentum: 0.000000
2023-10-23 23:06:15,220 epoch 8 - iter 176/447 - loss 0.00810306 - time (sec): 15.99 - samples/sec: 2115.00 - lr: 0.000009 - momentum: 0.000000
2023-10-23 23:06:19,137 epoch 8 - iter 220/447 - loss 0.00775609 - time (sec): 19.91 - samples/sec: 2119.19 - lr: 0.000008 - momentum: 0.000000
2023-10-23 23:06:22,765 epoch 8 - iter 264/447 - loss 0.00753910 - time (sec): 23.54 - samples/sec: 2132.64 - lr: 0.000008 - momentum: 0.000000
2023-10-23 23:06:26,708 epoch 8 - iter 308/447 - loss 0.00742374 - time (sec): 27.48 - samples/sec: 2137.96 - lr: 0.000008 - momentum: 0.000000
2023-10-23 23:06:31,358 epoch 8 - iter 352/447 - loss 0.00757262 - time (sec): 32.13 - samples/sec: 2125.85 - lr: 0.000007 - momentum: 0.000000
2023-10-23 23:06:35,232 epoch 8 - iter 396/447 - loss 0.00893999 - time (sec): 36.00 - samples/sec: 2144.09 - lr: 0.000007 - momentum: 0.000000
2023-10-23 23:06:39,044 epoch 8 - iter 440/447 - loss 0.00911259 - time (sec): 39.82 - samples/sec: 2143.63 - lr: 0.000007 - momentum: 0.000000
2023-10-23 23:06:39,653 ----------------------------------------------------------------------------------------------------
2023-10-23 23:06:39,653 EPOCH 8 done: loss 0.0094 - lr: 0.000007
2023-10-23 23:06:45,867 DEV : loss 0.2305288016796112 - f1-score (micro avg) 0.7771
2023-10-23 23:06:45,887 ----------------------------------------------------------------------------------------------------
2023-10-23 23:06:49,797 epoch 9 - iter 44/447 - loss 0.00749318 - time (sec): 3.91 - samples/sec: 2132.77 - lr: 0.000006 - momentum: 0.000000
2023-10-23 23:06:54,055 epoch 9 - iter 88/447 - loss 0.00578018 - time (sec): 8.17 - samples/sec: 2106.92 - lr: 0.000006 - momentum: 0.000000
2023-10-23 23:06:58,041 epoch 9 - iter 132/447 - loss 0.00513309 - time (sec): 12.15 - samples/sec: 2160.03 - lr: 0.000006 - momentum: 0.000000
2023-10-23 23:07:02,056 epoch 9 - iter 176/447 - loss 0.00514188 - time (sec): 16.17 - samples/sec: 2121.05 - lr: 0.000005 - momentum: 0.000000
2023-10-23 23:07:05,872 epoch 9 - iter 220/447 - loss 0.00441923 - time (sec): 19.98 - samples/sec: 2141.34 - lr: 0.000005 - momentum: 0.000000
2023-10-23 23:07:09,433 epoch 9 - iter 264/447 - loss 0.00540403 - time (sec): 23.54 - samples/sec: 2134.74 - lr: 0.000005 - momentum: 0.000000
2023-10-23 23:07:13,624 epoch 9 - iter 308/447 - loss 0.00549172 - time (sec): 27.74 - samples/sec: 2130.38 - lr: 0.000004 - momentum: 0.000000
2023-10-23 23:07:17,938 epoch 9 - iter 352/447 - loss 0.00557974 - time (sec): 32.05 - samples/sec: 2144.11 - lr: 0.000004 - momentum: 0.000000
2023-10-23 23:07:21,891 epoch 9 - iter 396/447 - loss 0.00615603 - time (sec): 36.00 - samples/sec: 2130.07 - lr: 0.000004 - momentum: 0.000000
2023-10-23 23:07:25,987 epoch 9 - iter 440/447 - loss 0.00622433 - time (sec): 40.10 - samples/sec: 2123.91 - lr: 0.000003 - momentum: 0.000000
2023-10-23 23:07:26,557 ----------------------------------------------------------------------------------------------------
2023-10-23 23:07:26,557 EPOCH 9 done: loss 0.0061 - lr: 0.000003
2023-10-23 23:07:32,804 DEV : loss 0.24391140043735504 - f1-score (micro avg) 0.7819
2023-10-23 23:07:32,824 ----------------------------------------------------------------------------------------------------
2023-10-23 23:07:36,558 epoch 10 - iter 44/447 - loss 0.00893320 - time (sec): 3.73 - samples/sec: 2136.89 - lr: 0.000003 - momentum: 0.000000
2023-10-23 23:07:40,288 epoch 10 - iter 88/447 - loss 0.00533915 - time (sec): 7.46 - samples/sec: 2130.68 - lr: 0.000003 - momentum: 0.000000
2023-10-23 23:07:44,363 epoch 10 - iter 132/447 - loss 0.00466202 - time (sec): 11.54 - samples/sec: 2152.54 - lr: 0.000002 - momentum: 0.000000
2023-10-23 23:07:48,688 epoch 10 - iter 176/447 - loss 0.00398884 - time (sec): 15.86 - samples/sec: 2135.03 - lr: 0.000002 - momentum: 0.000000
2023-10-23 23:07:52,909 epoch 10 - iter 220/447 - loss 0.00318742 - time (sec): 20.08 - samples/sec: 2136.60 - lr: 0.000002 - momentum: 0.000000
2023-10-23 23:07:57,023 epoch 10 - iter 264/447 - loss 0.00288008 - time (sec): 24.20 - samples/sec: 2115.28 - lr: 0.000001 - momentum: 0.000000
2023-10-23 23:08:00,749 epoch 10 - iter 308/447 - loss 0.00336446 - time (sec): 27.92 - samples/sec: 2121.73 - lr: 0.000001 - momentum: 0.000000
2023-10-23 23:08:04,576 epoch 10 - iter 352/447 - loss 0.00326997 - time (sec): 31.75 - samples/sec: 2122.19 - lr: 0.000001 - momentum: 0.000000
2023-10-23 23:08:08,617 epoch 10 - iter 396/447 - loss 0.00380379 - time (sec): 35.79 - samples/sec: 2130.28 - lr: 0.000000 - momentum: 0.000000
2023-10-23 23:08:12,964 epoch 10 - iter 440/447 - loss 0.00399744 - time (sec): 40.14 - samples/sec: 2118.14 - lr: 0.000000 - momentum: 0.000000
2023-10-23 23:08:13,600 ----------------------------------------------------------------------------------------------------
2023-10-23 23:08:13,601 EPOCH 10 done: loss 0.0039 - lr: 0.000000
2023-10-23 23:08:19,844 DEV : loss 0.24326062202453613 - f1-score (micro avg) 0.7825
2023-10-23 23:08:20,336 ----------------------------------------------------------------------------------------------------
2023-10-23 23:08:20,337 Loading model from best epoch ...
2023-10-23 23:08:22,007 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
2023-10-23 23:08:26,848
Results:
- F-score (micro) 0.7342
- F-score (macro) 0.6411
- Accuracy 0.5989
By class:
precision recall f1-score support
loc 0.7823 0.8624 0.8204 596
pers 0.6778 0.7327 0.7042 333
org 0.5625 0.4773 0.5164 132
prod 0.5510 0.4091 0.4696 66
time 0.7174 0.6735 0.6947 49
micro avg 0.7198 0.7491 0.7342 1176
macro avg 0.6582 0.6310 0.6411 1176
weighted avg 0.7124 0.7491 0.7285 1176
2023-10-23 23:08:26,848 ----------------------------------------------------------------------------------------------------