Add SBERT+CWL λ=0.1 split=train_40 test ρ=0.8321

sbert_cwl_split_40_lambda_0_1/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
+}

sbert_cwl_split_40_lambda_0_1/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859f04a3c9369d4f6a7b3992ae31666d449e6ed46a76f47c627d9ed6fa66bd54
+size 438009407

sbert_cwl_split_40_lambda_0_1/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]"
+}

sbert_cwl_split_40_lambda_0_1/training_meta.json

@@ -0,0 +1,23 @@
+{
+  "model_type": "sbert_cwl_l2",
+  "base_model": "bert-base-uncased",
+  "train_split": "train_40",
+  "lambda_consistency": 0.1,
+  "augmentations": [
+    "back_translation",
+    "aeda"
+  ],
+  "cwl_selection": "argmax_l2_distance",
+  "augmented_dataset": "SurAyush/stsb_augmented_splits",
+  "original_dataset": "SurAyush/stsb_splits",
+  "pooling": "mean",
+  "val_spearman": 0.8668,
+  "test_spearman": 0.8321,
+  "baseline_bert": 0.4729,
+  "sbert_no_reg": 0.8192,
+  "delta_vs_bert": 0.3592,
+  "delta_vs_sbert": 0.0129,
+  "lr": 2e-05,
+  "batch_size": 16,
+  "early_stop_patience": 2
+}