Push fold-3 checkpoint (Death F1=0.8418, Weighted F1=0.8693)

classifier_head.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90e8def213e5854be9706189083a1e2076bf4197ce55d24b10cc36ae8d390b3
-size 17509
+oid sha256:c134f568970e1214d3fafb47103ffd477e570457486b383121411d437f614078
+size 26725

config.json

@@ -1,28 +1,28 @@
-{
-  "add_cross_attention": false,
-  "architectures": [
-    "BertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": null,
-  "classifier_dropout": null,
-  "dtype": "float32",
-  "eos_token_id": null,
-  "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,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.0.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
-}
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

config_phase2.json

@@ -0,0 +1,32 @@
+{
+  "pretrained_model": "emilyalsentzer/Bio_ClinicalBERT",
+  "pooling": "cls_mean_concat",
+  "max_length": 512,
+  "num_labels": 4,
+  "label_order": [
+    "D",
+    "I",
+    "M",
+    "O"
+  ],
+  "dropout": 0.1,
+  "fold": 3,
+  "val_metrics": {
+    "f1_D": 0.8418,
+    "f1_I": 0.8749,
+    "f1_M": 0.9056,
+    "f1_O": 0.4764,
+    "f1_macro": 0.7747,
+    "f1_weighted": 0.8693
+  },
+  "cv_aggregated": {
+    "f1_D_mean": 0.8318,
+    "f1_D_std": 0.0076,
+    "f1_weighted_mean": 0.8691,
+    "f1_weighted_std": 0.001
+  },
+  "phase1_baseline": {
+    "f1_D": 0.7701,
+    "f1_weighted": 0.8484
+  }
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ed985178e7a3156983b98e52e7e43f9dcf01ba3a1d147b27e5b2511eb13e49
-size 433263424
+oid sha256:da78d3d89317123ba27e76940ad13fd49ed0afed30a9da9f68552d447d19b781
+size 433263448

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d82632aef0195ad5f1db88276a2e6a0728eee5f13a110217de4a09cf514864f
+size 433346119

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 256
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -68,7 +54,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": false
+    "lowercase": true
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -1,14 +1,15 @@
-{
-  "backend": "tokenizers",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "is_local": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}