carschno

2y ago

3mo 23d 19h 41m 45s

Jul 05 '24 08:26

n-194-171-4-145

LEARNING_RATE=0.001

Failed

Jan 01 '70 00:00

-

288

CrossEntropyLoss

21.30508

["Linear(in_features=128, out_features=4, bias=True)","Linear(in_features=512, out_features=4, bias=True)","Linear(in_features=512, out_features=6, bias=True)"]

["PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): BertModel(\n (embeddings): BertEmbeddings(\n (word_embeddings): Embedding(30500, 768, padding_idx=0)\n (position_embeddings): Embedding(512, 768)\n (token_type_embeddings): Embedding(2, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): BertEncoder(\n (layer): ModuleList(\n (0-11): 12 x BertLayer(\n (attention): BertAttention(\n (self): BertSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): BertSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): BertIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): BertOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): BertPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): RobertaModel(\n (embeddings): RobertaEmbeddings(\n (word_embeddings): Embedding(42774, 768, padding_idx=1)\n (position_embeddings): Embedding(514, 768, padding_idx=1)\n (token_type_embeddings): Embedding(1, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): RobertaEncoder(\n (layer): ModuleList(\n (0-11): 12 x RobertaLayer(\n (attention): RobertaAttention(\n (self): RobertaSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): RobertaSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): RobertaIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): RobertaOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): RobertaPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): RobertaModel(\n (embeddings): RobertaEmbeddings(\n (word_embeddings): Embedding(42774, 768, padding_idx=1)\n (position_embeddings): Embedding(514, 768, padding_idx=1)\n (token_type_embeddings): Embedding(1, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): RobertaEncoder(\n (layer): ModuleList(\n (0-11): 12 x RobertaLayer(\n (attention): RobertaAttention(\n (self): RobertaSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): RobertaSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): RobertaIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): RobertaOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): RobertaPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=512, out_features=256, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): RobertaModel(\n (embeddings): RobertaEmbeddings(\n (word_embeddings): Embedding(42774, 768, padding_idx=1)\n (position_embeddings): Embedding(514, 768, padding_idx=1)\n (token_type_embeddings): Embedding(1, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): RobertaEncoder(\n (layer): ModuleList(\n (0-11): 12 x RobertaLayer(\n (attention): RobertaAttention(\n (self): RobertaSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): RobertaSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): RobertaIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): RobertaOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): RobertaPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 512, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=1024, out_features=256, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=512, out_features=256, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 512, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=1024, out_features=256, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(9, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=512, out_features=256, bias=True)\n)"]

["LSTM(256, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)","LSTM(64, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)"]

Softmax(dim=1)

Adam

-

/home/carstens/workspace/document_segmentation/document_segmentation

/home/carstens/workspace/document_segmentation/document_segmentation/data

["HTR/obp-v2-pagexml-leon-metadata-trimmed-2023-11/","HTR/obp-v2-pagexml-leon-metadata-trimmed-2024-03/"]

https://hucdrive.huc.knaw.nl/

[",100",",200"]

["/home/carstens/workspace/document_segmentation/document_segmentation/data/Overzicht van Generale Missiven in 1.04.02 v.3.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Overzicht van Generale Missiven in 1.04.02 v.3.csv"]

/home/carstens/workspace/document_segmentation/document_segmentation/data/inventories

/home/carstens/workspace/document_segmentation/document_segmentation/data/1.04.02_inventory2uuid.json

["NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers","emanjavacas/GysBERT-v2"]

1

108.93617

1.75

20

219.23404

true

0.1

235.57447

2

true

0.1

219.23404

2

438.46809

16

["/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 1120.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 1267.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 1539.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 1547.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 1557.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 3142.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 8023.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 8121.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 8276.csv","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Analysis Renate 8284.csv"]

["/home/carstens/workspace/document_segmentation/document_segmentation/data/Appendix F - Spreadsheet concerning the TANAP document categorisation, Renate Smit, January 2024.xlsx","/home/carstens/workspace/document_segmentation/document_segmentation/data/annotations/Spreadsheet concerning the TANAP document categorisation (student assistant), Renate Smit.xlsx"]

********

/home/carstens/workspace/document_segmentation/document_segmentation/data/thumbnails

2y ago

4mo 1d 2h 37m 59s

Jul 11 '24 13:36

Carstens-MacBook-Pro.local

-

Crashed

Jan 01 '70 00:00

Linear(in_features=512, out_features=4, bias=True)

PageEmbedding( (_region_model): RegionEmbeddingSentenceTransformer( (_transformer_model): SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) (_region_type): Embedding(9, 16) (_linear): Linear(in_features=784, out_features=512, bias=True) ) (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True) (_linear): Linear(in_features=512, out_features=256, bias=True) )

LSTM(256, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)

Softmax(dim=1)

75.27246

CrossEntropyLoss

15.2012

["Linear(in_features=128, out_features=4, bias=True)","Linear(in_features=256, out_features=4, bias=True)","Linear(in_features=512, out_features=4, bias=True)","Linear(in_features=512, out_features=5, bias=True)","Linear(in_features=512, out_features=6, bias=True)"]

["PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): BertModel(\n (embeddings): BertEmbeddings(\n (word_embeddings): Embedding(30500, 768, padding_idx=0)\n (position_embeddings): Embedding(512, 768)\n (token_type_embeddings): Embedding(2, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): BertEncoder(\n (layer): ModuleList(\n (0-11): 12 x BertLayer(\n (attention): BertAttention(\n (self): BertSdpaSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): BertSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): BertIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): BertOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): BertPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbedding(\n (_transformer_model): BertModel(\n (embeddings): BertEmbeddings(\n (word_embeddings): Embedding(30522, 768, padding_idx=0)\n (position_embeddings): Embedding(512, 768)\n (token_type_embeddings): Embedding(2, 768)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (encoder): BertEncoder(\n (layer): ModuleList(\n (0-11): 12 x BertLayer(\n (attention): BertAttention(\n (self): BertSdpaSelfAttention(\n (query): Linear(in_features=768, out_features=768, bias=True)\n (key): Linear(in_features=768, out_features=768, bias=True)\n (value): Linear(in_features=768, out_features=768, bias=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n (output): BertSelfOutput(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n (intermediate): BertIntermediate(\n (dense): Linear(in_features=768, out_features=3072, bias=True)\n (intermediate_act_fn): GELUActivation()\n )\n (output): BertOutput(\n (dense): Linear(in_features=3072, out_features=768, bias=True)\n (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n (dropout): Dropout(p=0.1, inplace=False)\n )\n )\n )\n )\n (pooler): BertPooler(\n (dense): Linear(in_features=768, out_features=768, bias=True)\n (activation): Tanh()\n )\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 128, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=256, out_features=128, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=128, bias=True)\n )\n (_rnn): LSTM(128, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=128, out_features=64, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(10, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=512, out_features=256, bias=True)\n)","PageEmbedding(\n (_region_model): RegionEmbeddingSentenceTransformer(\n (_transformer_model): SentenceTransformer(\n (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel \n (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})\n )\n (_region_type): Embedding(9, 16)\n (_linear): Linear(in_features=784, out_features=512, bias=True)\n )\n (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)\n (_linear): Linear(in_features=512, out_features=256, bias=True)\n)"]

["LSTM(128, 128, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)","LSTM(256, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)","LSTM(64, 64, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)"]

Softmax(dim=1)

Adam

-

/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation

/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data

["HTR/obp-v2-pagexml-leon-metadata-trimmed-2023-11/","HTR/obp-v2-pagexml-leon-metadata-trimmed-2024-03/"]

https://hucdrive.huc.knaw.nl/

[",100",",200"]

["/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/Overzicht van Generale Missiven in 1.04.02 v.3.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Overzicht van Generale Missiven in 1.04.02 v.3.csv"]

/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/inventories

/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/1.04.02_inventory2uuid.json

["NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers","emanjavacas/GysBERT","emanjavacas/GysBERT-v2"]

1

149.85366

1.26667

21.95122

219.05691

true

0.1

219.05691

2

true

0.1

219.05691

2

437.07317

16

["/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 1120.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 1547.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 1557.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 2448.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 2775.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 3142.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 7923.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 8237.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 8276.csv","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Analysis Renate 8834.csv"]

["/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/Appendix F - Spreadsheet concerning the TANAP document categorisation, Renate Smit, January 2024.xlsx","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/Spreadsheet concerning the TANAP document categorisation (student assistant), Renate Smit.xlsx","/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/annotations/Spreadsheet concerning the TANAP document categorisation (student assistant), Renate Smit.xlsx"]

********

/Users/carstenschnober/LAHTeR/workspace/document-segmentation/document_segmentation/data/thumbnails

1y ago

6d 3h 13m 49s

Apr 08 '24 13:24

globalise-Stealth-GS66-12UHS

-

Failed

Jan 01 '70 00:00

-

CrossEntropyLoss

3

["Linear(in_features=512, out_features=5, bias=True)","Linear(in_features=512, out_features=6, bias=True)"]

PageEmbedding( (_region_model): RegionEmbeddingSentenceTransformer( (_transformer_model): SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) (_region_type): Embedding(10, 16) (_linear): Linear(in_features=784, out_features=512, bias=True) ) (_rnn): LSTM(512, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True) (_linear): Linear(in_features=512, out_features=256, bias=True) )

LSTM(256, 256, num_layers=2, batch_first=True, dropout=0.1, bidirectional=True)

Softmax(dim=1)

Adam

-

Carschno's workspace