ighina commited on
Commit
baf3a3a
1 Parent(s): 272a499

Upload 13 files

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md CHANGED
@@ -1,3 +1,136 @@
1
  ---
2
- license: cc-by-nc-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
  ---
9
+
10
+ # {MODEL_NAME}
11
+
12
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
13
+
14
+ <!--- Describe your model here -->
15
+
16
+ ## Usage (Sentence-Transformers)
17
+
18
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
19
+
20
+ ```
21
+ pip install -U sentence-transformers
22
+ ```
23
+
24
+ Then you can use the model like this:
25
+
26
+ ```python
27
+ from sentence_transformers import SentenceTransformer
28
+ sentences = ["This is an example sentence", "Each sentence is converted"]
29
+
30
+ model = SentenceTransformer('{MODEL_NAME}')
31
+ embeddings = model.encode(sentences)
32
+ print(embeddings)
33
+ ```
34
+
35
+
36
+
37
+ ## Usage (HuggingFace Transformers)
38
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
39
+
40
+ ```python
41
+ from transformers import AutoTokenizer, AutoModel
42
+ import torch
43
+
44
+
45
+ #Mean Pooling - Take attention mask into account for correct averaging
46
+ def mean_pooling(model_output, attention_mask):
47
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
48
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
49
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
50
+
51
+
52
+ # Sentences we want sentence embeddings for
53
+ sentences = ['This is an example sentence', 'Each sentence is converted']
54
+
55
+ # Load model from HuggingFace Hub
56
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
57
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
58
+
59
+ # Tokenize sentences
60
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
61
+
62
+ # Compute token embeddings
63
+ with torch.no_grad():
64
+ model_output = model(**encoded_input)
65
+
66
+ # Perform pooling. In this case, mean pooling.
67
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
68
+
69
+ print("Sentence embeddings:")
70
+ print(sentence_embeddings)
71
+ ```
72
+
73
+
74
+
75
+ ## Evaluation Results
76
+
77
+ <!--- Describe how your model was evaluated -->
78
+
79
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
80
+
81
+
82
+ ## Training
83
+ The model was trained with the parameters:
84
+
85
+ **DataLoader**:
86
+
87
+ `torch.utils.data.dataloader.DataLoader` of length 6033 with parameters:
88
+ ```
89
+ {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
90
+ ```
91
+
92
+ **Loss**:
93
+
94
+ `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
95
+
96
+ **DataLoader**:
97
+
98
+ `torch.utils.data.dataloader.DataLoader` of length 5765 with parameters:
99
+ ```
100
+ {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
101
+ ```
102
+
103
+ **Loss**:
104
+
105
+ `sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss`
106
+
107
+ Parameters of the fit()-Method:
108
+ ```
109
+ {
110
+ "epochs": 10,
111
+ "evaluation_steps": 0,
112
+ "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
113
+ "max_grad_norm": 1,
114
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
115
+ "optimizer_params": {
116
+ "lr": 2e-05
117
+ },
118
+ "scheduler": "WarmupLinear",
119
+ "steps_per_epoch": null,
120
+ "warmup_steps": 10000,
121
+ "weight_decay": 0.01
122
+ }
123
+ ```
124
+
125
+
126
+ ## Full Model Architecture
127
+ ```
128
+ SentenceTransformer(
129
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: RobertaModel
130
+ (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})
131
+ )
132
+ ```
133
+
134
+ ## Citing & Authors
135
+
136
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.18.0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.0",
4
+ "transformers": "4.18.0",
5
+ "pytorch": "1.11.0"
6
+ }
7
+ }
eval/binary_classification_evaluation_Valid_Topic_Boundaries_results.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhatten_accuracy,manhatten_accuracy_threshold,manhatten_f1,manhatten_precision,manhatten_recall,manhatten_f1_threshold,manhatten_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
2
+ 0,-1,0.8724363792548051,-0.4885462522506714,0.9315210505097046,0.8746721466619798,0.9962733684437464,-0.5198167562484741,0.9482870767152217,0.8815634059916246,475.5308837890625,0.9356532392147713,0.888633404438042,0.9879269457020543,475.8710632324219,0.9523934225130386,0.8756845270052614,25.743106842041016,0.9327036256630097,0.8829582347438508,0.9883889248205981,25.743106842041016,0.9486990778147659,0.874261784602169,-103.4189453125,0.9323140949683534,0.8782021615441157,0.9935322923403862,-103.4189453125,0.945713013926162
3
+ 1,-1,0.8715773649736926,-0.8653514385223389,0.9313826735513483,0.8716007623956404,0.9999692013920971,-0.8653514385223389,0.9406942729659287,0.8791742725222806,520.5626220703125,0.9345224262142692,0.8843013826658237,0.990791216237026,539.4521484375,0.9498210302666706,0.8720874047031032,39.98064422607422,0.9315481748574221,0.8729470680092618,0.9985832640364656,39.98064422607422,0.9400555719254167,0.871657897562547,-295.98388671875,0.9314247192300521,0.8716510067114094,1.0,-435.1869812011719,0.936878204714809
4
+ 2,-1,0.871657897562547,-0.8735333681106567,0.9314109461301198,0.8717907401439468,0.9997844097446795,-0.8735333681106567,0.9321755298271551,0.876758294856652,599.8697509765625,0.9335456321922269,0.8806805767970286,0.9931627090455512,599.8697509765625,0.9445760392019119,0.8716847417588317,47.64161682128906,0.9314282435301544,0.8717742152044899,0.9998460069604854,47.64161682128906,0.9333497223616692,0.871657897562547,-541.7020263671875,0.9314247192300521,0.8716510067114094,1.0,-547.5809936523438,0.9255973081265415
5
+ 3,-1,0.8716847417588317,-0.8504114151000977,0.9314361122267485,0.8716943646468172,0.9999692013920971,-0.898491382598877,0.9321154275057468,0.8745570707613014,606.3648681640625,0.9324413753416775,0.8748953861936772,0.9980904863100187,645.5669555664062,0.944834245947181,0.8716847417588317,48.6949462890625,0.9314262760737957,0.8717941832048769,0.9998152083525824,48.6949462890625,0.9358121899237093,0.8716847417588317,-567.5224609375,0.9314361122267485,0.8716943646468172,0.9999692013920971,-567.5224609375,0.9199484899635636
6
+ 4,-1,0.8716310533662622,-0.8704615235328674,0.9313877410468319,0.8718671931662503,0.999630416705165,-0.8704615235328674,0.9302681043990398,0.8764361645012348,624.4132690429688,0.9333140334370702,0.880462093074066,0.9929163201823278,641.5534057617188,0.9402572160452738,0.8716847417588317,49.69243621826172,0.9314380791187354,0.8716744073666407,1.0,49.69243621826172,0.9328739446647275,0.871657897562547,-561.347412109375,0.9314247192300521,0.8716510067114094,1.0,-588.161376953125,0.9184166581589492
7
+ 5,-1,0.8716847417588317,-0.8523590564727783,0.9314148818660432,0.8717508055853921,0.9998460069604854,-0.8868223428726196,0.9307782643507979,0.8750939546869967,646.148681640625,0.9327749295978048,0.8781542310202306,0.9946410422248915,655.21923828125,0.9390805040751276,0.8716310533662622,48.66355895996094,0.9314074244075965,0.8716675168469944,0.9999384027841941,48.66355895996094,0.9337836096373169,0.8716310533662622,-555.56787109375,0.9314113597246128,0.8716276073125554,1.0,-572.7196044921875,0.9173812233431777
8
+ 6,-1,0.8717115859551166,-0.8353337049484253,0.9314341452219067,0.871714324070345,0.9999384027841941,-0.8730157613754272,0.9318065746498914,0.8736712122839042,687.2959594726562,0.9321706543672529,0.8760803012652055,0.9959345837568142,687.2959594726562,0.9384547883542511,0.871657897562547,47.198280334472656,0.9314207846231083,0.8716909198303173,0.9999384027841941,47.198280334472656,0.9345394143691392,0.8716310533662622,-509.2225646972656,0.9314113597246128,0.8716276073125554,1.0,-539.64306640625,0.9210116283711751
9
+ 7,-1,0.8718458069365403,-0.8367456793785095,0.931487591450294,0.8718079535995275,0.9999384027841941,-0.8653423190116882,0.9253199547135915,0.8732148609470632,719.7484130859375,0.9320765019470347,0.8736396939984915,0.9988912501154947,733.858154296875,0.9313230885505059,0.8716847417588317,46.59550094604492,0.9314361122267485,0.8716943646468172,0.9999692013920971,46.59550094604492,0.9284372566707704,0.8717384301514013,-482.0269775390625,0.9314451331496786,0.87192091761356,0.9996920139209707,-482.0269775390625,0.9130355782493194
10
+ 8,-1,0.871657897562547,-0.8646595478057861,0.9314207846231083,0.8716909198303173,0.9999384027841941,-0.866702675819397,0.9293619748440078,0.8727048212176527,755.4833374023438,0.9318776037925586,0.8732667402600899,0.9989220487233977,755.4833374023438,0.9329840867700735,0.8716042091699775,45.98941421508789,0.931392096392455,0.8716640713096708,0.9999076041762912,46.117164611816406,0.9316092546065409,0.8716310533662622,-500.8504638671875,0.9314113597246128,0.8716276073125554,1.0,-500.8504638671875,0.9175780640419731
11
+ 9,-1,0.8716847417588317,-0.8721379041671753,0.9314361122267485,0.8716943646468172,0.9999692013920971,-0.8721379041671753,0.9269127373142997,0.872677977021368,764.776123046875,0.9318720464241083,0.8731628532974428,0.9990452431550094,766.3433837890625,0.9299146316450253,0.8716847417588317,45.79191970825195,0.9314321781042001,0.8717342856375695,0.9999076041762912,45.79191970825195,0.929184382505271,0.8716310533662622,-472.2821960449219,0.9314113597246128,0.8716276073125554,1.0,-497.92877197265625,0.9154256756951731
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f360d99580445075472cdbb7b439e937b9b3a53cdff3b062979db40610e5ef3
3
+ size 498652017
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff