initial commit

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 +1,29 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "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": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.13.0",
+    "pytorch": "1.7.0+cu110"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,6 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.8603829184143664,0.8634439808588751,0.8520373126043029,0.8582637518032019,0.8519665769908871,0.8582077748963437,0.8305067668652699,0.8297689706234703
+1,-1,0.8738941526987756,0.8732814736395488,0.8572646949316028,0.8637278623258947,0.8572464105288398,0.863677852383028,0.8453502241053964,0.8435598021802103
+2,-1,0.8696573041220188,0.8715316450173949,0.8582154646347402,0.8656908761326176,0.8576657264057793,0.8649860002025886,0.8390346407149374,0.8374201573846959
+3,-1,0.8750163944562664,0.8760740592164935,0.8614311434759245,0.8692434586491514,0.8606418133936148,0.8685416716892201,0.8461674597377774,0.8451364687459089
+4,-1,0.8751659863714976,0.8759995162362965,0.8613002432395667,0.8694394249762125,0.860629998153408,0.8687313337414789,0.8472061320718693,0.8454604049119452

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:e0143341f5e4653b7ece14cf0685f5fbf5b68a3926beed43754a498947c3bd77
+size 442558967

sentence_bert_config.json

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

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,-1,0.8477045280392909,0.8559956140722809,0.8370636752767797,0.8440079435411166,0.8370234533153658,0.8438439443425015,0.8241822253054464,0.8233260855548581

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5b1f4865d09eaa42f5c27660916c3c9e9fc2126ea562c99da0f9834db70602
+size 442739392

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "[CLS]", "eos_token": "[SEP]", "model_max_length": 512, "special_tokens_map_file": "/home/jhgan/.cache/huggingface/transformers/9d0c87e44b00acfbfbae931b2e4068eb6311a0c3e71e23e5400bdf57cab4bfbf.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23", "name_or_path": "klue/roberta-base", "tokenizer_class": "BertTokenizer"}