Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,227 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+license: cc-by-sa-4.0
+language:
+- en
+widget:
+- source_sentence: "The formula: Not everyone who voted Leave is racist. But everyone who's racist voted Leave. Not everyone who voted Leave is thick. But everyone who's thick voted Leave. The thick racists therefore called the shots, whatever the thoughts of the minority of others. #thick #Brexit"
+  sentences:
+    - "Men shouldn’t be making laws about women’s bodies #abortion #Texas"
+    - "Opinion: As the draconian (and then some) abortion law takes effecting #Texas, this is not an idle question for millions of Americans. A slippery slope towards more like-minded Republican state-legislatures to try to follow suit. #abortion #F24 HTTPURL"
+    - "’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU citizenship after #Brexit HTTPURL via @USER"
+    - "@USER Blah blah blah blah blah blah"
+  example_title: "Reason"
+
+- source_sentence: "This is NOT good for children."
+  sentences:
+    - "Men shouldn’t be making laws about women’s bodies #abortion #Texas"
+    - "Opinion: As the draconian (and then some) abortion law takes effecting #Texas, this is not an idle question for millions of Americans. A slippery slope towards more like-minded Republican state-legislatures to try to follow suit. #abortion #F24 HTTPURL"
+    - "’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU citizenship after #Brexit HTTPURL via @USER"
+    - "@USER Blah blah blah blah blah blah"
+  example_title: "Statement"
+
+- source_sentence: "Elon Musk ready with 'Plan B' if Twitter rejects his offer  Read @USER Story | HTTPURL #ElonMusk #ElonMuskTwitter #TwitterTakeover HTTPURL"
+  sentences:
+    - "Men shouldn’t be making laws about women’s bodies #abortion #Texas"
+    - "Opinion: As the draconian (and then some) abortion law takes effecting #Texas, this is not an idle question for millions of Americans. A slippery slope towards more like-minded Republican state-legislatures to try to follow suit. #abortion #F24 HTTPURL"
+    - "’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU citizenship after #Brexit HTTPURL via @USER"
+    - "@USER Blah blah blah blah blah blah"
+  example_title: "Notification"
+
+- source_sentence: "@USER 👅is the Key 😂"
+  sentences:
+    - "Men shouldn’t be making laws about women’s bodies #abortion #Texas"
+    - "Opinion: As the draconian (and then some) abortion law takes effecting #Texas, this is not an idle question for millions of Americans. A slippery slope towards more like-minded Republican state-legislatures to try to follow suit. #abortion #F24 HTTPURL"
+    - "’Bitter truth’: EU chief pours cold water on idea of Brits keeping EU citizenship after #Brexit HTTPURL via @USER"
+    - "@USER Blah blah blah blah blah blah"
+  example_title: "None"
+---
+
+# WRAPresentations
+
+Introducing WRAPresentations, a cutting-edge [sentence-transformers](https://www.SBERT.net) model that leverages the power of a 768-dimensional dense
+vector space to map tweets according to the four classes Reason, Statement, Notification and None. This powerful model is tailored for
+argument mining on Twitter, derived from the [BERTweet-base](https://huggingface.co/vinai/bertweet-base) architecture initially pre-trained on
+Twitter data. Through fine-tuning with the [TACO](https://doi.org/10.5281/zenodo.8030026) dataset, WRAPresentations is effectively in Weaving
+Relevant Argument Properties (WRAP) into the embedding space.
+
+## Class Semantics
+
+The model, to some degree, captures the semantics of the critical components of an argument, as defined by the [Cambridge Dictionary](https://dictionary.cambridge.org).
+It encodes *inference* as *a guess that one makes or an opinion formed based on available information*, and it also leverages the definition of
+*information* as *facts or details about a person, company, product, etc.*.
+
+Consequently, it has also learned the semantics of:
+
+* *Statement*, which refers to unique cases where only the *inference* is presented as *something that someone says or writes officially, or an
+action done to express an opinion* (see ex. 1).
+* *Reason*, which represents a full argument where the *inference* is based on direct *information* mentioned in the tweet, such as a
+source-reference or quotation, and thus reveals the author’s motivation *to try to understand and to make judgments based on practical facts* (see ex. 2).
+* *Notification*, which refers to a tweet that limits itself to providing *information*, such as media channels promoting their latest articles (see ex. 3).
+* *None*, a tweet that provides neither *inference* nor *information* (see ex. 4).
+
+In its entirety, WRAPresentations encodes the following hierarchy for tweets:
+![Beautiful Sunset](https://www.researchgate.net/profile/Marc-Feger/publication/371595900/figure/fig1/AS:11431281168142295@1686846469455/Hierarchy-of-arguments-with-constituting-elements_W640.jpg)
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model to generate tweet representations like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+tweets = ["This is an example #tweet", "Each tweet is converted"]
+
+model = SentenceTransformer("TomatenMarc/WRAPresentations")
+embeddings = model.encode(tweets)
+print(embeddings)
+```
+
+<a href="https://github.com/VinAIResearch/BERTweet/blob/master/TweetNormalizer.py">
+    <blockquote style="border-left: 5px solid grey; background-color: #f0f5ff; padding: 10px;">
+        Notice: The tweets need to undergo preprocessing following the specifications for BERTweet-base.
+    </blockquote>
+</a>
+
+## Usage (HuggingFace Transformers)
+
+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.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+# Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Tweets we want embeddings for
+tweets = ["This is an example #tweet", "Each tweet is converted"]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained("TomatenMarc/WRAPresentations")
+model = AutoModel.from_pretrained("TomatenMarc/WRAPresentations")
+
+# Tokenize sentences
+encoded_input = tokenizer(tweets, padding=True, truncation=True, return_tensors="pt")
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input["attention_mask"])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+Furthermore, the WRAPresentations model is a highly suitable embedding component for `AutoModelForSequenceClassification`, enabling fine-tuning of
+tweet classification tasks specifically for the four classes: Reason, Statement, Notification, and None. The categorization of Reason and Statement as
+argument classes and Notification and None as non-argument classes is implicitly learned during the fine-tuning process. This setup facilitates
+efficient identification and analysis of argumentative content and non-argumentative content in tweets.
+
+## Training
+
+The WRAPresentations model underwent fine-tuning with 1,219 golden tweets from the TACO dataset, covering six topics.
+Five topics were chosen for optimization, representing 925 tweets (75.88%) covering #brexit (33.3%), #got (17%), #lotrrop (18.8%), #squidgame (17.1%),
+and #twittertakeover (13.8%). The model used a stratified 60/40 split for training/testing on optimization data.
+Additionally, 294 golden tweets (24.12%) related to the topic of abortion were chosen as the holdout-set for final evaluation.
+
+During fine-tuning, we formed tweet pairs by matching each tweet with all remaining tweets in the same data split (training, testing, holdout) with
+similar or dissimilar class labels. This process created 307,470 pairs for training and 136,530 pairs for testing. An additional 86,142 pairs were
+used for final evaluation with the holdout data.
+
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 5065 with parameters:
+
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters:
+
+  ```
+  {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
+  ```
+
+Parameters of the fit()-Method:
+
+```
+{
+    "epochs": 5,
+    "evaluation_steps": 1000,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 4e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 2533,
+    "weight_decay": 0.01
+}
+```
+
+## Evaluation Results
+
+Following the [standard protocol](https://aclanthology.org/D17-1218.pdf) for cross-topic evaluation for argument mining, we evaluated the
+WRAPresentation model using the
+`BinaryClassificationEvaluator` showing:
+
+| Accuracy | Precision | Recall | F1     | Support |
+|----------|-----------|--------|--------|---------|
+| 71.56%   | 65.70%    | 83.20% | 73.42% | 86,142  |
+
+An evaluation was conducted on previously unseen data from the holdout topic abortion, resulting in the model achieving a sophisticated macro
+F1-score of 71.56%. The recall, which stands at 87.54%, indicates the model's ability to capture subtle tweet patterns and class-specific features for
+Reason, Statement, Notification, and None. Despite having a lower precision of 65.70%, the model's primary focus is on prioritizing recall to capture
+relevant instances. Fine-tuning precision can be addressed in a subsequent classification phase, when using this model
+for `AutoModelForSequenceClassification`.
+
+## Full Model Architecture
+
+```
+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})
+)
+```
+
+# Environmental Impact
+
+- **Hardware Type:** A100 PCIe 40GB
+- **Hours used:** 2h
+- **Cloud Provider:** [Google Cloud Platform](https://colab.research.google.com)
+- **Compute Region:** [asia-southeast1](https://cloud.google.com/compute/docs/gpus/gpu-regions-zones?hl=en) (Singapore)
+- **Carbon Emitted:** 0.21kg CO2
+
+## Licensing
+
+[WRAPresentations](https://huggingface.co/TomatenMarc/WRAPresentations) © 2023 by [Marc Feger](marc.feger@uni-duesseldorf.de) is licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/?ref=chooser-v1)
+## Contact
+
+Please contact [marc.feger@uni-duesseldorf.de](marc.feger@uni-duesseldorf.de).

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

binary_classification_evaluation_fine-tune-heldout_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_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
+-1,-1,0.7155713218820015,0.5635744333267212,0.7342164228285225,0.6569760584974643,0.8320388349514564,0.4611433148384094,0.7701340554755384,0.7225914861837192,166.821533203125,0.7399493229612176,0.651601716835792,0.8560119492158327,203.3678741455078,0.774587176530623,0.7169716206123973,8.298559188842773,0.7285230528783538,0.6809284207109235,0.7832710978342047,9.337143898010254,0.7708316235108152,0.7108849887976102,57.948116302490234,0.7276492693110648,0.6582263181749509,0.8134428678117999,41.91051483154297,0.7366228479917187

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./models/WRAPresentations/",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.31.0",
+    "pytorch": "2.0.1+cu118"
+  }
+}

eval/binary_classification_evaluation_fine-tune-test_results.csv

@@ -0,0 +1,31 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_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
+0,1000,0.7678939453016209,0.5616649389266968,0.7749335063250081,0.725400179746897,0.8317272879184537,0.4328032433986664,0.8487791808297954,0.7691472177351975,175.79025268554688,0.7765562172341834,0.7149149524389673,0.849830111959004,196.30166625976562,0.8516339941615735,0.7659165599064224,8.315374374389648,0.7702681429396022,0.7280888844799365,0.8176349356653484,9.056646347045898,0.8479770494283996,0.7686737592602908,41.60350799560547,0.7689403869344098,0.7262912890605655,0.8169108227037264,32.74320602416992,0.817298703547951
+0,2000,0.7677825433075252,0.5190510153770447,0.7758532721071993,0.7490407549517785,0.8046566033532,0.5155777335166931,0.8368960901274767,0.7638973987634379,170.4642333984375,0.770553674954282,0.721071922712819,0.8273269091516738,193.61415100097656,0.8367475169414185,0.7642594552442489,7.980064392089844,0.7707439294186635,0.7390104273154774,0.8053250153177742,8.939167976379395,0.8344096422873637,0.7718347908427561,42.945762634277344,0.7775990048809508,0.7556431480751544,0.8008689355539464,42.44209671020508,0.8302310576373584
+0,3000,0.7739375034813123,0.5127902030944824,0.7809338469536009,0.7488815604468645,0.8158525037598173,0.49300330877304077,0.8449476727696611,0.7766668523366568,200.49417114257812,0.7910268186346171,0.738614674687734,0.8514454408733916,201.90072631835938,0.8522992953865132,0.7769035815741102,9.25938606262207,0.7833858384824435,0.7612665878333991,0.8068289422380661,9.25938606262207,0.8462070606506461,0.7681306745390742,47.408573150634766,0.765128667662561,0.7744493894784891,0.7560296329304295,47.133384704589844,0.8077331359909563
+0,4000,0.7674901130730241,0.6995731592178345,0.767450599287334,0.7175846276866413,0.8247646632874729,0.4543057382106781,0.8436346872666978,0.7675875898178577,171.60763549804688,0.7672268583405124,0.7126239101875075,0.8308917729627361,204.24862670898438,0.8449665781190565,0.7665988971202584,7.342679977416992,0.7594777948805655,0.7777453441531905,0.7420486826714198,8.261296272277832,0.8416007984609263,0.7677268423104774,52.90253829956055,0.7744300725479566,0.7217516843118383,0.8354035537236116,37.78709030151367,0.794628873897718
+0,5000,0.7745919901966245,0.6659778356552124,0.7749942891951571,0.7118810034505269,0.8503871219294825,0.45358020067214966,0.8488832109960202,0.7747312426892441,170.88339233398438,0.7777511898114914,0.7440227897039373,0.8146827828218125,199.32559204101562,0.8511201654908707,0.7748983456803876,7.782614707946777,0.7700333358780569,0.7088643178410795,0.8427560853339274,9.623931884765625,0.8480727902398433,0.7755528323956998,58.938602447509766,0.7752517606792602,0.7350657779774832,0.8200857795354537,40.16120529174805,0.7930881406399948
+0,-1,0.7797304071742884,0.67124342918396,0.7751530612244898,0.7150656563279522,0.8462652481479418,0.45725303888320923,0.8486250473756219,0.776569375591823,163.75259399414062,0.7768396302036017,0.7465208237046167,0.8097253940845541,198.85543823242188,0.8510887216883583,0.7787138639781652,7.571657657623291,0.7697543500511771,0.7119325980972215,0.8377986965966691,9.60276985168457,0.8479597311663336,0.7776694702835181,55.622920989990234,0.7724684702882175,0.7064773120886734,0.8520581518409179,38.716949462890625,0.7918274296961403
+1,1000,0.7749261961789116,0.566508412361145,0.7798376850675448,0.7295042204327157,0.8376315936055255,0.4021725654602051,0.8511605513699232,0.7762630201080599,171.59909057617188,0.7799883653286795,0.7278342058915777,0.8401938394697265,213.2512969970703,0.8509098800953989,0.7749401214281736,8.299052238464355,0.7766009754023202,0.7426610751048418,0.813791566869047,9.897568702697754,0.849563100342725,0.7748565699326018,53.404930114746094,0.7776896913280311,0.7189125295508274,0.846933660112516,33.58881378173828,0.8062415345332914
+1,2000,0.7784075084944021,0.6520156264305115,0.7775647551929763,0.7401887979861548,0.8189160585974489,0.4154204726219177,0.8512251193283239,0.7775441430401604,162.30169677734375,0.7795258085187075,0.7347945070387811,0.8300562580070183,212.55264282226562,0.8508408487911324,0.7779619005180193,7.799623012542725,0.7731482731617746,0.7503144654088051,0.7974154737369799,9.854764938354492,0.8498399451414931,0.7787556397259511,54.70463562011719,0.7773618032067335,0.7245163153335259,0.8385228095582911,34.559288024902344,0.8053294570747453
+1,3000,0.7781568540076867,0.6612838506698608,0.775138972607327,0.7467031407262122,0.8058263242912048,0.4267839193344116,0.8503063748678845,0.7782682560017824,162.04498291015625,0.7756105992315158,0.7420561223191798,0.812343340945803,211.3235321044922,0.8499273517817276,0.7778922742717095,7.748963832855225,0.7710258717046972,0.7550726185390859,0.7876677992536066,9.824663162231445,0.8491794467884947,0.778449284242188,56.12619400024414,0.7765954623855644,0.7415872694100952,0.8150726898011474,36.294673919677734,0.8037081919007742
+1,4000,0.7214393137637164,0.5044573545455933,0.6962221636964856,0.7334155363748459,0.6626190608811898,0.45556509494781494,0.7796048578772816,0.7197265081044951,180.50286865234375,0.6977414421832725,0.7390816771540714,0.6607809279786108,199.2108917236328,0.7812933138616089,0.7160502422993371,8.91546630859375,0.6965976246485742,0.718189884649512,0.6762658051579123,9.800008773803711,0.7813535500643046,0.721216509775525,42.53407669067383,0.6979591222872268,0.7586725519045283,0.6462429677491227,41.97949981689453,0.7227403664766267
+1,5000,0.7312287639948755,0.6148228049278259,0.7150222843659879,0.7494504152418173,0.6836183367682281,0.45740455389022827,0.7955877922714433,0.7304768005347295,198.79611206054688,0.7168404934562157,0.7446578631452581,0.6910265693755918,201.54525756835938,0.7955900503582694,0.73104773575447,8.091403007507324,0.7107716434815439,0.7425364077669903,0.6816131008745057,9.69920539855957,0.7944885709600145,0.7335542806216231,44.558616638183594,0.713370354549338,0.7298100454492483,0.6976549880242856,39.405242919921875,0.726060786237057
+1,-1,0.7382888653706902,0.522275984287262,0.7203785844620153,0.7707202488651874,0.6762101041608645,0.48286569118499756,0.790454845458989,0.7378989583913552,190.44403076171875,0.7190101103351747,0.7725338367516719,0.6724224363616109,195.2378692626953,0.7945392109799041,0.7367431627026124,9.284839630126953,0.7173958488875616,0.7733067216070049,0.6690246755416922,9.304485321044922,0.7916372746891804,0.7394028853116471,44.70606994628906,0.7188546877581985,0.7803398454062164,0.6663510276833955,43.997772216796875,0.7269551575769607
+2,1000,0.7374254999164485,0.49638476967811584,0.7150868144060933,0.7745225412498375,0.6641229878014816,0.4762795865535736,0.7895789121471601,0.739082604578622,193.4174346923828,0.7187663965487088,0.753928942701645,0.6867375926029076,201.81869506835938,0.7920154306606293,0.7373001726730909,9.189388275146484,0.7162266969235631,0.7394424673784105,0.6944243301955105,9.865802764892578,0.7926948853939454,0.7390965298278839,45.12528991699219,0.7149767272063521,0.7877061268266524,0.6545424163092519,45.09357452392578,0.7248229185549959
+2,2000,0.7397510165431961,0.49059003591537476,0.7174882469426934,0.7846067378583,0.6609480309697544,0.49059003591537476,0.7893193607026283,0.7402662507658887,187.76220703125,0.7204597431536973,0.7606017458057327,0.6843424497298501,201.83572387695312,0.7917386019095046,0.7384141926140478,9.029869079589844,0.7164570995127929,0.7522053418279834,0.6839525427505152,9.867085456848145,0.793468666491425,0.7383027906199521,44.93938446044922,0.7148524373384624,0.7762548136544613,0.6624519578900462,42.35888671875,0.7258325223417688
+2,3000,0.7339163371024341,0.5524381399154663,0.7096153846153846,0.7704051673517323,0.6577173731409792,0.4623206853866577,0.7955165384790114,0.7348911045507714,195.80374145507812,0.7160265716422507,0.7561557283117044,0.6799420709630702,200.68942260742188,0.7945675954196826,0.7338467108561243,8.778763771057129,0.7130119479284314,0.7643535334225451,0.6681334595889267,9.822650909423828,0.7944429400411687,0.7333732523812176,44.763912200927734,0.7049359695489359,0.7890978092116612,0.6369966022391801,44.763912200927734,0.7288963131428454
+2,4000,0.7330390463989306,0.5843002796173096,0.7106344203277415,0.7663756162000194,0.6624519578900462,0.45505326986312866,0.7942846131264139,0.7349468055478193,196.8582763671875,0.71410343906709,0.7640970281940563,0.6702500974767448,200.70700073242188,0.793536220750753,0.7333175513841698,8.655280113220215,0.7148661532819949,0.7551520034708233,0.6786609480309698,9.962120056152344,0.7943300826887122,0.7332897008856458,52.494140625,0.7017251489059654,0.7867820069204152,0.6332646354369743,44.95760726928711,0.7309583504671321
+2,5000,0.7313262407397092,0.5530322790145874,0.7062788438183144,0.7762797837549222,0.6478582966635102,0.4647907316684723,0.7913764795949331,0.7316186709742104,195.1563720703125,0.7083424599523956,0.74455871066769,0.6754859911992425,201.52902221679688,0.7906407744746664,0.7307413802707069,9.934350967407227,0.7103064894913642,0.7616345786051256,0.66545981173063,9.974112510681152,0.7927391316736574,0.7327326909151674,52.273109436035156,0.702691850318914,0.7886982145952505,0.6335988414192614,45.618186950683594,0.7295537869972409
+2,-1,0.7312426892441375,0.5550357103347778,0.7061465398212633,0.7756408119729342,0.6480811006517017,0.46514391899108887,0.7913475580426201,0.7318693254609258,195.03797912597656,0.7077027565739934,0.7531031015303397,0.6674650476243524,200.6476593017578,0.7906456213707942,0.7309920347574221,9.92496109008789,0.7107233776480921,0.763473532704302,0.6647913997660558,9.963253021240234,0.7925669002708331,0.7326909151673815,52.270423889160156,0.7026601411125348,0.7883596050580287,0.6337659444104049,45.76286315917969,0.7294773211363561
+3,1000,0.7606528156854008,0.5222647190093994,0.7531634240709377,0.7448054246888701,0.7617111346293098,0.45683982968330383,0.8206757503089424,0.7610148721662118,183.16404724121094,0.7484159945569745,0.7620587131599458,0.7352531610315824,199.61854553222656,0.8093893305455506,0.7592742160084666,9.634052276611328,0.7524050488157011,0.7728994743179348,0.7329694201526207,9.713886260986328,0.8228600831850887,0.7607502924302345,47.358665466308594,0.7518852833638027,0.7716798592788039,0.7330808221467164,44.067352294921875,0.7666417639308817
+3,2000,0.733582131120147,0.48442283272743225,0.7355212850581201,0.6818917118660196,0.7983066896897455,0.44973790645599365,0.8050704151130821,0.7298083885701554,201.81997680664062,0.7293821485251464,0.7168289141074597,0.7423828886537069,207.67794799804688,0.7973270462595166,0.7338467108561243,9.741870880126953,0.7349640213947642,0.6812183465297097,0.7979167827104106,10.044559478759766,0.8076746774003403,0.7311591377485657,46.107749938964844,0.735662325546212,0.672056757192546,0.8125661449339944,40.949432373046875,0.7612766515277805
+3,3000,0.7564891661560742,0.48917582631111145,0.7576617553680882,0.708479751835785,0.8141814738483819,0.433296799659729,0.8155651684987558,0.7578538405837465,193.57858276367188,0.7464613425188873,0.7770278413884537,0.7182086559349412,205.32235717773438,0.8003775028938475,0.7567119701442656,9.687872886657715,0.7545677701850991,0.7205960617349654,0.791901075029243,10.162216186523438,0.8194534741932576,0.7561549601737871,43.90623474121094,0.7536313854538912,0.699818563789152,0.8164095137302958,39.590248107910156,0.7722236131029006
+3,4000,0.7385255946081435,0.49491021037101746,0.7461200275438319,0.7112345367331482,0.7846042444159751,0.42813336849212646,0.81639852613666,0.7406283072466997,205.55908203125,0.7280786166273001,0.7640146878824969,0.695371247145324,206.00106811523438,0.8012519667482616,0.7399459700328636,9.668192863464355,0.7449076209667629,0.6602255121363402,0.8545089957110232,10.443655014038086,0.8169782426067075,0.7380382108839748,43.70752716064453,0.7412867436077281,0.683714037027453,0.8094468890993148,38.88163375854492,0.7719869405881279
+3,5000,0.7368963404444939,0.4928392469882965,0.7346872680655826,0.7126364564517396,0.7581462708182476,0.45811888575553894,0.8043990044525555,0.7428424218793517,191.797607421875,0.7264938326316567,0.7735380162949448,0.6848437587032807,193.6221466064453,0.7963762082998681,0.7367292374533504,9.465219497680664,0.738096524887856,0.7167900068230725,0.7607085166824487,9.99488639831543,0.8096146238710167,0.73686848994597,47.051029205322266,0.7248700356433412,0.733456878118318,0.716481925026458,43.94330978393555,0.7609198118503129
+3,-1,0.7370355929371136,0.49309322237968445,0.7345518311189047,0.7122341677783881,0.7583133738093912,0.4582207500934601,0.8044314208625994,0.7428424218793517,191.74285888671875,0.7265364036773183,0.7740614764424288,0.6845095527209937,193.55892944335938,0.796406941812556,0.7366178354592547,9.466680526733398,0.7386227100292954,0.7167448319228653,0.7618782376204534,9.996031761169434,0.8097048652084639,0.736910265693756,48.42571258544922,0.7253521126760564,0.7337436598848807,0.7171503369910321,43.963096618652344,0.761129156358665
+4,1000,0.7396396145491004,0.4853218197822571,0.7335013431554459,0.7294007490636704,0.7376483039046399,0.4670202136039734,0.8048413129762076,0.7425917673926363,192.4800567626953,0.7270748459400233,0.7703431296163555,0.688408622514343,194.97476196289062,0.7964549767767972,0.7383445663677379,9.929280281066895,0.7396969404497635,0.7324759018049752,0.747061772405726,9.958412170410156,0.8107329426732655,0.737634378655378,54.005027770996094,0.7272314910626958,0.740509800525389,0.7144209881356877,44.62757110595703,0.7618423960334315
+4,2000,0.7411296162201303,0.4963013529777527,0.7339127573821732,0.7226781857451404,0.7455021444883864,0.46599581837654114,0.8046479840463622,0.7431070016153289,191.53518676757812,0.7273531493276716,0.7727927815026004,0.686960396591099,194.13693237304688,0.7963775697420389,0.7391800813234557,9.577247619628906,0.7395142578634486,0.7292518480409412,0.7500696262463098,9.973331451416016,0.8109155085919635,0.7393750348131232,54.30863571166992,0.7277907058740569,0.737221063458956,0.7185985629142762,44.826446533203125,0.7611387981164628
+4,3000,0.7421183089177297,0.5031415820121765,0.732177798748248,0.7296766520067491,0.734696151061104,0.47203877568244934,0.8043563389232249,0.7445830780370969,192.44961547851562,0.7284195563978798,0.7776302478502782,0.6850665626914721,192.44961547851562,0.7962850912010971,0.7404751295048181,9.603111267089844,0.740485187010569,0.7282029188432333,0.7531888820809892,9.98196792602539,0.8114153743268732,0.7393750348131232,55.02947235107422,0.7268186075554168,0.7409722222222223,0.713195566200635,45.50734329223633,0.7597365088009872
+4,4000,0.7426613936389461,0.5002992153167725,0.7332384699087636,0.7345706618962433,0.7319111012087116,0.47579818964004517,0.8036745730162046,0.7440121428173564,192.37493896484375,0.7282555718020294,0.7752586396654193,0.6866261906088119,193.13973999023438,0.7962240589563083,0.7407118587422715,9.621297836303711,0.7425506067348249,0.7281488421898006,0.7575335598507213,9.983221054077148,0.8113257016732922,0.7400991477747452,52.59965515136719,0.7278388859255841,0.7544305310660172,0.7030579847379268,46.75685119628906,0.7601106825613864
+4,5000,0.7427449451345179,0.5027592182159424,0.7334051545537417,0.7274769837790442,0.739430735810171,0.47258734703063965,0.8035390497206156,0.7440399933158803,192.66281127929688,0.7285880911251864,0.7753024351924588,0.6871832005792904,192.68093872070312,0.7964492468636172,0.7402662507658887,9.634147644042969,0.7427504124118938,0.7275058088294207,0.7586475797916783,9.984941482543945,0.8113731356681799,0.7408511112348911,53.53934097290039,0.728091314448982,0.7554876770580661,0.702612376761544,47.05971145629883,0.7598655772877093
+4,-1,0.7427449451345179,0.5027490258216858,0.7334116833736606,0.7282462450918477,0.7386509218515012,0.472969651222229,0.8035469606946056,0.7440539185651424,192.65733337402344,0.7286203638081739,0.7753755263654076,0.6871832005792904,192.67977905273438,0.7964520586007977,0.7402384002673648,9.634243965148926,0.7427612825793428,0.7277829747427502,0.758369074806439,9.984170913696289,0.8113810178372788,0.7408511112348911,53.53996658325195,0.7281280212406748,0.7555023207066927,0.7026680777585919,47.05809020996094,0.7598733766921927

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecd82469cb960c9ac4d7a041589441ffbde220cd2b4d5d13db88be8b9e5b462
+size 539666601

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "normalization": false,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}