added model

0_Transformer/added_tokens.json

@@ -0,0 +1 @@
+{"IDchainreactionID": 250012, "IDgooseeggID": 250030, "IDprivateeyeID": 250047, "IDeconomicaidID": 250024, "IDphonebookID": 250045, "IDfishstoryID": 250027, "IDweddinganniversaryID": 250060, "IDthinktankID": 250057, "IDtopdogID": 250058, "IDdreamticketID": 250020, "IDmailserviceID": 250039, "IDbadhatID": 250004, "IDentrancehallID": 250026, "IDsittingduckID": 250053, "IDskintoneID": 250054, "IDcomputerprogramID": 250014, "IDancienthistoryID": 250002, "IDsacredcowID": 250050, "IDbusybeeID": 250009, "IDinsurancecompanyID": 250034, "IDdisabilityinsuranceID": 250019, "IDhighlifeID": 250032, "IDhealthcheckID": 250031, "IDbadappleID": 250003, "IDnarrowescapeID": 250042, "IDloansharkID": 250037, "IDswansongID": 250056, "IDsexbombID": 250051, "IDpublicserviceID": 250048, "IDconartistID": 250015, "IDsugardaddyID": 250055, "IDpillowslipID": 250046, "IDhomerunID": 250033, "IDcookingstoveID": 250016, "IDlifevestID": 250036, "IDflowerchildID": 250028, "IDlabourunionID": 250035, "IDricepaperID": 250049, "IDbananarepublicID": 250005, "IDfoodmarketID": 250029, "IDbirthrateID": 250007, "IDmentaldisorderID": 250040, "IDcriticalreviewID": 250018, "IDweddingdayID": 250061, "IDeagerbeaverID": 250023, "IDbowtieID": 250008, "IDtravelguideID": 250059, "IDbigfishID": 250006, "IDcallcentreID": 250010, "IDpeaceconferenceID": 250044, "IDsilverliningID": 250052, "IDcottoncandyID": 250017, "IDpandacarID": 250043, "IDduststormID": 250022, "IDclosedbookID": 250013, "IDelbowroomID": 250025, "IDdrylandID": 250021, "IDmailinglistID": 250038, "IDcellularphoneID": 250011, "IDmiddleschoolID": 250041}

0_Transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "../LanguageModeling/models-no-git/models/v3-dev-test-all/xlm-roberta-base/",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "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": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250062
+}

0_Transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3d29a43a0918aa480be627d73423d7115fcb917785b3b29299aa6f9b6fe708
+size 1112445495

0_Transformer/sentence_bert_config.json

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

0_Transformer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

0_Transformer/special_tokens_map.json

@@ -0,0 +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": true}}

0_Transformer/tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "truncation": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "../LanguageModeling/models-no-git/models/v3-dev-test-all/xlm-roberta-base/"}

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
+}

config.json

@@ -0,0 +1,3 @@
+{
+  "__version__": "1.1.0"
+}

modules.json

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

similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.7590523963776727,0.7598221062118787,0.7459687654214501,0.7486735931800926,0.7530161313406729,0.7554306707969608,0.7186822547685223,0.723145663394404
+1,-1,0.8100863594816122,0.8119396831040417,0.8005924617633648,0.8065635601768402,0.8109547064045524,0.8137044174179893,0.7443976040118677,0.7550698093379621
+2,-1,0.8347015939764308,0.8355774912316921,0.824214054099338,0.827866783063475,0.8314851851730087,0.8340910400279403,0.7823562282360816,0.7902288069111701
+3,-1,0.8387172176695159,0.8389083369467144,0.8275321678302563,0.8313678886824722,0.833959290696516,0.8365965951378336,0.7877268098387735,0.7943423257641882

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.8022711717561148,0.7922299461533238,0.7872947249810125,0.7773999642086977,0.79632645624612,0.785578434609383,0.742660067375635,0.7325416240615885