Upload best checkpoint (Spearman=0.8112)

README.md

@@ -0,0 +1,39 @@
+---
+language: en
+tags:
+  - clinical-nlp
+  - text-similarity
+  - regression
+  - bert
+base_model: cross-encoder/monoelectra-large
+---
+ 
+# Clinical STS Regression Model
+ 
+Fine-tuned from `cross-encoder/monoelectra-large` on a clinical text-pair similarity dataset.
+ 
+## Training config
+```json
+{
+  "train": "./med_sts/clinicalSTS.train.txt",
+  "test": "./med_sts/clinicalSTS.test.txt",
+  "model": [
+    "cross-encoder/monoelectra-large"
+  ],
+  "epochs": 20,
+  "batch_size": 16,
+  "lr": 2e-05,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.1,
+  "max_grad_norm": 1.0,
+  "dropout": 0.1,
+  "max_len": 256,
+  "seed": 42,
+  "patience": 5,
+  "output_dir": "./sts_val/monoelectra-large",
+  "wandb_project": "clinical-sts",
+  "hf_repo": "youssefkhalil320/monoelectra-large"
+}
+```
+ 
+## Best test Spearman ρ: `0.8112`

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoModelForSequenceClassification": "modeling.WebisCrossEncoderForSequenceClassification"
+  },
+  "backbone_model_type": "electra",
+  "classifier_dropout": null,
+  "doc_length": 256,
+  "dtype": "float32",
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooling_strategy": "first",
+  "position_embedding_type": "absolute",
+  "query_length": 32,
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.linear.Identity",
+    "version": "4.0.1"
+  },
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68636c402191001c398957544898a7331b6e0e07570005a7de2cb01f7810328c
+size 1336413848

regressor.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec9de9c3b986c6dca1fe164c214467dcb2480dff3cb3033405af51b5cf183a8
+size 6069

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "doc_length": 256,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "query_length": 32,
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}