Added Model

0_Transformer/config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "LazarusNLP/simcse-indobert-base",
+  "_num_labels": 5,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

0_Transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805c1b4b2b7fad9ee3a042ed6c32552bb01019d16477f88a3492f545446abe09
+size 497836589

0_Transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32,
+  "do_lower_case": false
+}

0_Transformer/special_tokens_map.json

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

0_Transformer/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]"
+}

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d221280b121b50477c1df240e37149c3f8d55bec281259bf927b40471e39df
+size 2363583

README.md

@@ -1,3 +1,89 @@
 ---
-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 6524 with parameters:
+```
+{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers_congen.losses.ConGenLoss.ConGenLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 20,
+    "evaluation_steps": 0,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "correct_bias": false,
+        "eps": 1e-06,
+        "lr": 0.0001
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 13048,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 32, '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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "1.0.0",
+    "transformers": "4.29.2",
+    "pytorch": "2.0.1+cu117"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,18 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.7549801652876834,0.7773568206020748,0.7866759041719932,0.7834028047551163,0.7852862401773307,0.7825944151995093,0.6896391094326394,0.6844280090892415
+1,-1,0.7847668828189469,0.8039669069020774,0.8121336526056565,0.808983844193213,0.8114571591692638,0.8087648351415765,0.7115387584412941,0.7016501686459619
+2,-1,0.7992853124188911,0.8166844406641893,0.824898638753694,0.8221694691738071,0.8237765461501285,0.821372625924178,0.7076383867518875,0.6963353375807293
+3,-1,0.8098387823447282,0.8269563432238602,0.834132171888215,0.8326572691437634,0.8331463214346222,0.8320829192431101,0.699207552213865,0.6882365105465501
+4,-1,0.8170999860695889,0.832943788774763,0.8391728928428005,0.8371489566326253,0.838036323687782,0.8364639650451339,0.7094635650131131,0.6986988481065094
+5,-1,0.8199692296461245,0.8351361108919974,0.842502309265778,0.8403654738885686,0.8415662371992431,0.8393730728301876,0.6877013204350539,0.6757211246853495
+6,-1,0.8216498381863574,0.8361694195849096,0.8435246055904845,0.841987890658732,0.8427364357808801,0.8413094781155371,0.6888481115614082,0.6767505115167366
+7,-1,0.8203275851403183,0.8348932482942423,0.8427799201690414,0.8409641006468491,0.8419299106218932,0.8403636927485176,0.6810481647062651,0.6698828324000539
+8,-1,0.8230823005257395,0.8368828212810016,0.8437538473757997,0.842065782172876,0.84297443008527,0.841438574292332,0.6844884191171795,0.6721888927103519
+9,-1,0.8248806896788521,0.8387562712472385,0.8442255412373584,0.8428542934065095,0.8436630032834103,0.8424743917515538,0.6674671156199542,0.6546952098192693
+10,-1,0.8258356117033007,0.8389840051357336,0.8431601980238087,0.8422182456627578,0.8426208270544481,0.8418695123198082,0.6626941850813575,0.6506253030959924
+11,-1,0.8284652475943988,0.841086496648774,0.8426511133266086,0.8422131602499052,0.841939859323034,0.8417027381803982,0.6599547048383673,0.6498603962965184
+12,-1,0.8282270475803677,0.8401680019659091,0.8407454303693322,0.8405057579382668,0.8402584983233138,0.8402383573933428,0.649248245099541,0.6397506514631653
+13,-1,0.8285424775064761,0.8406562817339212,0.8400079831187269,0.8404315700207666,0.8393971042568438,0.8398508090766418,0.6379017674627657,0.6284314657157315
+14,-1,0.8299030586659109,0.8414774720645537,0.8395022525025194,0.8401036374042852,0.838962731239484,0.8396137420397003,0.638690105535253,0.6296494493223689
+15,-1,0.8279209791074977,0.8401593392901441,0.8382420243095788,0.8393101937821174,0.8376061350028109,0.8387565279097566,0.62763507998445,0.6180745363107193
+16,-1,0.8293730946203294,0.8408973940353227,0.8371376970617006,0.8380426191861527,0.8365043857534152,0.8374649977813333,0.6292709383555336,0.6208646277535623

modules.json

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