Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+test.csv filter=lfs diff=lfs merge=lfs -text
+train.csv 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

@@ -1,3 +1,88 @@
----
-license: apache-2.0
----
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# {MODEL_NAME}
+
+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.
+
+<!--- Describe your model here -->
+
+## 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 like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 296 with parameters:
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 100,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 296,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "../../models/SentSecBert_10k/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "2.0.1"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,31 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,100,0.7767165296976706,0.7825528385894479,0.7722803478792969,0.7825528385894479,0.7717405275291487,0.7821055391719218,0.7767165256168398,0.7825528385518995
+0,200,0.7921398127977428,0.7938857413991663,0.7935166762405468,0.7938857414372585,0.7934722509182599,0.793777105237588,0.7921398152683232,0.7938859613103474
+0,-1,0.817672720878249,0.80569101338735,0.8160408596971968,0.80569101338735,0.8155512402445846,0.8056721010644293,0.8176727236015884,0.8056910133486914
+1,100,0.8269388173519301,0.8136174919615351,0.8289767040437148,0.8136174920005742,0.8284016396078292,0.8134415631337184,0.8269388156358446,0.8136174920005742
+1,200,0.8377112278237773,0.818250580804218,0.8378772576670477,0.8182505808434793,0.8374931789796534,0.8181604171806868,0.8377112275722225,0.8182505807649567
+1,-1,0.8485055754141746,0.8217568445977179,0.843786555759838,0.8217568446371475,0.8435382862056614,0.8218294153269257,0.8485055765498164,0.821756844676577
+2,100,0.8472687737940862,0.8188843647890193,0.8376910156119721,0.8188843647890193,0.8373942723912529,0.8187928816983753,0.8472687787620491,0.8188843647890193
+2,200,0.8524454263912835,0.8206568489484323,0.8446270730670355,0.8206568489484323,0.8444596551928384,0.8205754818114043,0.8524454247600131,0.8206568489484323
+2,-1,0.850857561334697,0.821881314365676,0.8473673163624467,0.821881314365676,0.8469431465737933,0.8216636022963416,0.8508575610214818,0.8218813143262406
+3,100,0.8514365916254149,0.8193373818221799,0.8426546565015118,0.8193373817828664,0.8421336441953314,0.8189019576835108,0.8514365901452959,0.8193373818221799
+3,200,0.8555724237155002,0.8219318939373397,0.8461787158808152,0.8219318938979017,0.845831874861548,0.8217198995981426,0.8555724240717741,0.8219318940162155
+3,-1,0.8591605522948231,0.8225450063498418,0.8440867186397281,0.8225450063498418,0.8436843245471843,0.8222375704791325,0.8591605515675516,0.8225450062709072
+4,100,0.8569069635045521,0.8209563678983851,0.8447241832873182,0.8209563680165585,0.8442307824782811,0.8204989526809926,0.8569069632147116,0.8209563679377762
+4,200,0.8539244648046733,0.8179051003386211,0.8418073744832226,0.8179053202498022,0.8415078520475464,0.8177109188048953,0.8539244665916373,0.8179048803489505
+4,-1,0.8535630545471954,0.8181617366870307,0.8406542588134209,0.8181617366870307,0.8402956857354933,0.8177672160280359,0.8535630538972292,0.8181617366477737
+5,100,0.8531654928661945,0.8171730160165512,0.838365383973362,0.8171730160165512,0.8378914933685018,0.8164354338757781,0.8531654889049933,0.8171730160557609
+5,200,0.8516811164690643,0.8157532693918633,0.8361600962301626,0.8157530494806823,0.8357657162535961,0.8151581898530214,0.8516811162184573,0.8157532693918633
+5,-1,0.850645402630859,0.8166056451691674,0.8409800925597333,0.8166056451299851,0.8407424275971783,0.8164662214411386,0.8506454013649966,0.8166056450908027
+6,100,0.8479752173613797,0.8131064184546054,0.8341299563935005,0.8131064183765765,0.8338750932416426,0.8128126170385797,0.8479752212393277,0.813106418415591
+6,200,0.849920837286756,0.8143106520435462,0.835990622204247,0.8143106520435462,0.8356380452332411,0.81383740318172,0.8499208385019955,0.8143106520435462
+6,-1,0.8508729394328989,0.8151533516505847,0.8362178227317338,0.8151533516505847,0.8358512290585075,0.8146070923157308,0.8508729377113814,0.8151533516505847
+7,100,0.8490710228232873,0.813288944695942,0.8347706750903306,0.813288944695942,0.8345251988420637,0.8130197734102195,0.8490710215185728,0.8132889446569189
+7,200,0.8481477396217937,0.8132075775979375,0.8353909391871244,0.8132075776369568,0.835121440953439,0.8128517613068262,0.8481477375817182,0.8132075775589181
+7,-1,0.8460978103907613,0.8113581245254808,0.8324593098591324,0.8113581245644114,0.8322705017907741,0.8112103442117508,0.8460978109627689,0.8113581244865503
+8,100,0.8453171173065693,0.8108914729601809,0.8317433167318551,0.8108914730379974,0.8315887130825804,0.8105761203653259,0.8453171179415402,0.8108914730379974
+8,200,0.8469921731033707,0.81207195629741,0.8340925992596693,0.8120719562194805,0.8338235612540428,0.8117504460336957,0.8469921712547479,0.8120719562584452
+8,-1,0.8460002218987764,0.8112138627906491,0.8315596485028064,0.8112138627517254,0.8312735381658762,0.8107357758439371,0.8460002221463571,0.8112140827018303
+9,100,0.8456311253832645,0.8108760792164089,0.8312416341039841,0.8108760792942239,0.8309784004582101,0.8104582480888939,0.8456311255171476,0.8108760792164089
+9,200,0.8454572597962404,0.8108114253680563,0.8318181416948303,0.810811425329152,0.8315887709240848,0.8104274604457572,0.8454572605660785,0.810811425329152
+9,-1,0.8454518591198237,0.8107089467965368,0.8316193923446009,0.8107089467576374,0.8313967752970463,0.8103724826115848,0.8454518563012295,0.8107089467187379

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295fce88c7848ceb7b918c5e03fae0aefe2585c0f2197e98c0c6eac522f8879b
+size 333842221

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 514,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcddac2e3086d6ad4880595b150e3b42f2ce4cafe7248434be06f90683ed6ed1
+size 29517597

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e34c47c63ebb63e7c36a489488747244db894fd1cf8d1cafbd3ef73af88f0be
+size 70753576