first iteration

CECorrelationEvaluator_sts-dev_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,Pearson_Correlation,Spearman_Correlation
+0,-1,0.8916829700066211,0.8914940752912296
+1,-1,0.8989842513223796,0.8948733160544396
+2,-1,0.8982956000494986,0.8935477732304848
+3,-1,0.899478384521511,0.8946152731719645

README.md

@@ -0,0 +1,3 @@
+## Custom notes
+
+This model has been initaialized from the TSDAE checkpoint and fine-tuned as a CE with binary label and continious score on STS.

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "models/tsdae",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c8a5c3da2f93d50a870ec454123abf47b6aa8c4205ea94c81f0526c7a12ce3
+size 438002037

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "models/tsdae",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}