Training in progress, epoch 0

config.json

@@ -1,67 +1,67 @@
-{
-  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
-  "architectures": [
-    "BertForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "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,
-  "intermediate_size": 3072,
-  "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
-  },
-  "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",
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
-}
+{
+  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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,
+  "intermediate_size": 3072,
+  "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
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5352aa29aa1af8b1c6f3b7ae7f8f545717f8738104c2671d6403cb82e6550ea2
+oid sha256:158f0abb30e4f3de6a7d06e8fcb2d7f5453f3de3797aaa738c1d6fe621327d9b
 size 430960500

runs/Aug23_14-19-07_ee1898c059d7/events.out.tfevents.1724422748.ee1898c059d7.1664.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ddb92aa6701f58e149f6182f5ec5629fc0fd04171be4b9b9e9475ab3570c21c
+size 6167

special_tokens_map.json

@@ -1,7 +1,7 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,58 +1,58 @@
-{
-  "add_prefix_space": true,
-  "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,
-  "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": "BertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "add_prefix_space": true,
+  "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,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc375330080ba71d1fbc6db912d18cbd6c5c161f174ce7e6f17b6377fad65e17
+oid sha256:f714d1608b9edb48b0911f1a3b3b8abfefd9e24dfd9f24164d8f3ced3a8421c1
 size 5240