New model – mse=0.1021

config.json

@@ -1,35 +1,23 @@
 {
   "architectures": [
-    "XLMRobertaModel"
+    "MPNetModel"
   ],
   "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,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "mpnet",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "regression",
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 30527
 }

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 128,
+  "max_seq_length": 256,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -42,7 +42,7 @@
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
-size 17082999
+oid sha256:0ee64512c4fd9554e98781bbe75e2b5c6a08dfbd32a970e8da4d4c5aae059fec
+size 710932

tokenizer_config.json

@@ -27,12 +27,20 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "30526": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -44,19 +52,22 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
+  "do_lower_case": true,
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
   "max_length": 128,
-  "model_max_length": 128,
+  "model_max_length": 256,
   "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
   "sep_token": "</s>",
   "stride": 0,
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }