Add SBERT model trained on train_10 (test ρ=0.7442)

split_10/config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

split_10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaf60d1847ea0f5667cdcd008da58ca693bf0330554bfe38c18f411f2d0e42b
+size 438009407

split_10/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

split_10/training_meta.json

@@ -0,0 +1,13 @@
+{
+  "base_model": "bert-base-uncased",
+  "train_split": "train_10",
+  "dataset": "SurAyush/stsb_splits",
+  "pooling": "mean",
+  "val_spearman": 0.8074,
+  "test_spearman": 0.7442,
+  "baseline_bert": 0.4729,
+  "delta": 0.2713,
+  "epochs": 6,
+  "lr": 2e-05,
+  "batch_size": 16
+}