Added Model

0_Transformer/config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "indobenchmark/indobert-base-p1",
+  "_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:ad4564a3774dbe82eeefe962f42daaf170f877615af0986aad2b3cab59aa890b
+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 sha256:4d21d3f20cfb49517328d2a0d9dd2192604f39521ac5695bd327e94b98f047f6
+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 +1,21 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.720948010920777,0.7318347872028519,0.7521264301309405,0.7379601749636464,0.7515344581032484,0.7373706131991906,0.6249902611251258,0.5888321338604097
+1,-1,0.7494584852913209,0.7646410348252027,0.7844000621213362,0.7732799361034216,0.7840380894151099,0.7731018484823053,0.6005862285785628,0.5735568251570807
+2,-1,0.7630490563175665,0.7782263077296959,0.7956413251252823,0.7874269928516233,0.7950814737459496,0.7868736501371603,0.5954446290373088,0.5712464805519586
+3,-1,0.7724226850899856,0.788195861328848,0.8038544538147719,0.7964790437776093,0.8030687977157446,0.7957734555146984,0.6051000455003802,0.5798886330048546
+4,-1,0.7734833520666474,0.7884292562013986,0.8051303140916412,0.7972042046159638,0.8042873074979789,0.7964505523258834,0.6164511495574725,0.5887004681166509
+5,-1,0.7798480082967596,0.7931786547628746,0.8097474589708866,0.8020643411351454,0.808622726506574,0.8008546314289889,0.6053765776673794,0.5819081222174566
+6,-1,0.7820808574669538,0.7938381247495598,0.8098837917401253,0.801175524027307,0.8091300428685745,0.8004698093112456,0.6073181005913465,0.5825225663671806
+7,-1,0.784512802445834,0.7960490224497195,0.811740451796979,0.8038961008294317,0.8109057516213092,0.8028675244232547,0.6090420752496344,0.5842722491995513
+8,-1,0.7841913574952999,0.7950928355209703,0.810531869949439,0.8029019875471413,0.8096061803462264,0.8018016423310613,0.6003359865946626,0.5788884937302443
+9,-1,0.7854179322739016,0.7959824014979426,0.8107917995491101,0.80291754608718,0.8099549442408015,0.8020398820197678,0.5832341159919637,0.5616069787169705
+10,-1,0.7870223731784464,0.797042884583984,0.8103306921152701,0.8024880639548911,0.8096465935625113,0.8015946573984308,0.5903871445145286,0.5692880088191473
+11,-1,0.7880653169231259,0.7971274615623877,0.8103035592258525,0.8025793356800125,0.8095856288918871,0.8014464103049795,0.5730872604445766,0.5532918372200876
+12,-1,0.7893964035391344,0.7994389827242512,0.8108904112412689,0.8035741435162839,0.8101043729755059,0.802566499200977,0.5702460490119903,0.5499339909281133
+13,-1,0.7916905172471835,0.8012437111611985,0.8118679434652487,0.804785096161694,0.8111121158706343,0.8037354948741517,0.5627458578490886,0.5422816577639485
+14,-1,0.7937394690799646,0.8021106452997423,0.8113622980096243,0.803717127223244,0.810593483102004,0.8027651058392473,0.5686256530839918,0.5478862871568512
+15,-1,0.7920850636537244,0.8019166533271469,0.8108750201443482,0.803722180315861,0.8100470623152011,0.8027594853416418,0.5550908241605852,0.5352419484297911
+16,-1,0.7922715293375887,0.8011840659033443,0.8093208654281385,0.8019829488031568,0.8084330581778969,0.801021175612965,0.5453469514783572,0.5267251026149404
+17,-1,0.7926030085998763,0.8016325648959185,0.8097730356071076,0.8026289074556568,0.8088918475157226,0.8015106774753351,0.5446859697110119,0.5253315224106989
+18,-1,0.7926176562203803,0.8018111185752793,0.8095735192458865,0.8023958752525909,0.8086711592192422,0.8012326647815596,0.5427731844840156,0.5235262931623265
+19,-1,0.79253207984499,0.8017778536856336,0.8091158438750315,0.8019567116367086,0.8082313687629724,0.8008126746828168,0.5440289521546717,0.5246452395466552

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"
+  }
+]