Training in progress, epoch 0

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "medicalai/ClinicalBERT",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-Drug",
+    "2": "I-Drug",
+    "3": "B-Reason",
+    "4": "I-Reason",
+    "5": "B-Route",
+    "6": "I-Route",
+    "7": "B-Strength",
+    "8": "I-Strength",
+    "9": "B-Form",
+    "10": "I-Form",
+    "11": "B-Dosage",
+    "12": "I-Dosage",
+    "13": "B-Frequency",
+    "14": "I-Frequency",
+    "15": "B-Duration",
+    "16": "I-Duration",
+    "17": "B-ADE",
+    "18": "I-ADE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ADE": 17,
+    "B-Dosage": 11,
+    "B-Drug": 1,
+    "B-Duration": 15,
+    "B-Form": 9,
+    "B-Frequency": 13,
+    "B-Reason": 3,
+    "B-Route": 5,
+    "B-Strength": 7,
+    "I-ADE": 18,
+    "I-Dosage": 12,
+    "I-Drug": 2,
+    "I-Duration": 16,
+    "I-Form": 10,
+    "I-Frequency": 14,
+    "I-Reason": 4,
+    "I-Route": 6,
+    "I-Strength": 8,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916bf8eb0ffc0eb96bdbe63f8932fcc61c7355372f9296d32e74293a353ede20
+size 539007116

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81d9af48d91f22459a19919f5c7900b136a76db1a2262ae9f9291c295daafbf
+size 5240