Push model

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
+}

added_tokens.json

@@ -0,0 +1 @@
+{"<mask>": 64000}

config.json

@@ -1,24 +1,29 @@
 {
+  "_name_or_path": "sentence_phobert_nli\\",
   "architectures": [
-    "BertModel"
+    "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-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.12.5",
-  "type_vocab_size": 2,
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 64001
 }

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.11.3",
+    "pytorch": "1.10.2+cpu"
+  }
+}

eval/similarity_evaluation_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,-1,0.8078286933987654,0.8068675782136558,0.7826592675151728,0.7868028226819643,0.7807693868686497,0.7844094389688113,0.750560538312266,0.7567512236263219
+1,-1,0.8141910092889064,0.8132247090159028,0.7927358135349715,0.7967180091229377,0.7912690373690494,0.7950951810589162,0.7629149612065824,0.7688506534784273
+2,-1,0.8213888261354507,0.8200802249399388,0.8014694226634118,0.8063164716361716,0.8002064148053362,0.8046039741807846,0.7731418158158698,0.7791783534950835
+3,-1,0.8230233654608273,0.821893616196692,0.8035552172896905,0.8082517954348161,0.8024512539715857,0.806933904809289,0.7800862039068843,0.7844405198389021

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8ae6acf1e3eef45dab826964740341eb3484bd3d09845b3bca2caa0dacbe09
-size 438007537
+oid sha256:f442320a1ae3cd68748245e47ca504703bb182f661af0e9acfd3e438aafeb104
+size 540069681

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

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": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 256, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "sentence_phobert_nli\\", "tokenizer_class": "PhobertTokenizer"}