Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NazaGara/NER-fine-tuned-BETO",
+  "_name_or_path": "google-bert/bert-base-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -10,82 +10,39 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "B_CANCER_CONCEPT",
-    "1": "B_CHEMOTHERAPY",
-    "2": "B_DATE",
-    "3": "B_DRUG",
-    "4": "B_FAMILY",
-    "5": "B_FREQ",
-    "6": "B_IMPLICIT_DATE",
-    "7": "B_INTERVAL",
-    "8": "B_METRIC",
-    "9": "B_OCURRENCE_EVENT",
-    "10": "B_QUANTITY",
-    "11": "B_RADIOTHERAPY",
-    "12": "B_SMOKER_STATUS",
-    "13": "B_STAGE",
-    "14": "B_SURGERY",
-    "15": "B_TNM",
-    "16": "I_CANCER_CONCEPT",
-    "17": "I_DATE",
-    "18": "I_DRUG",
-    "19": "I_FAMILY",
-    "20": "I_FREQ",
-    "21": "I_IMPLICIT_DATE",
-    "22": "I_INTERVAL",
-    "23": "I_METRIC",
-    "24": "I_OCURRENCE_EVENT",
-    "25": "I_SMOKER_STATUS",
-    "26": "I_STAGE",
-    "27": "I_SURGERY",
-    "28": "I_TNM",
-    "29": "O"
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B_CANCER_CONCEPT": 0,
-    "B_CHEMOTHERAPY": 1,
-    "B_DATE": 2,
-    "B_DRUG": 3,
-    "B_FAMILY": 4,
-    "B_FREQ": 5,
-    "B_IMPLICIT_DATE": 6,
-    "B_INTERVAL": 7,
-    "B_METRIC": 8,
-    "B_OCURRENCE_EVENT": 9,
-    "B_QUANTITY": 10,
-    "B_RADIOTHERAPY": 11,
-    "B_SMOKER_STATUS": 12,
-    "B_STAGE": 13,
-    "B_SURGERY": 14,
-    "B_TNM": 15,
-    "I_CANCER_CONCEPT": 16,
-    "I_DATE": 17,
-    "I_DRUG": 18,
-    "I_FAMILY": 19,
-    "I_FREQ": 20,
-    "I_IMPLICIT_DATE": 21,
-    "I_INTERVAL": 22,
-    "I_METRIC": 23,
-    "I_OCURRENCE_EVENT": 24,
-    "I_SMOKER_STATUS": 25,
-    "I_STAGE": 26,
-    "I_SURGERY": 27,
-    "I_TNM": 28,
-    "O": 29
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 31002
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09088173a42d3b80d2e015ef1d10ed5011e4e5b74be66b29a7fa61958a51f26a
-size 437156776
+oid sha256:05b9292b948245f5edc26607bf0bb9a0dada1b678d9d0969ce4471560ad86a71
+size 430929740

runs/Nov16_00-54-18_1d16b391ae26/events.out.tfevents.1731718464.1d16b391ae26.326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eec7d158c0f80d06b98606cf04934cb27e0c46b12bfac75acef4485b8fb15a6
+size 6315

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "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
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -2,39 +2,39 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[MASK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[PAD]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[CLS]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "[SEP]",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -44,15 +44,12 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "never_split": null,
-  "num_labels": 9,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": false,
+  "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 sha256:7b4bf572f2a7ac155812882c84626cf338a191c1410ac8ff92bad2ca84b62f9d
+oid sha256:b1822f4241d2b1e0457daee5e5c2c1e40d76f7d2f9140ea1d52f776183f0bad7
 size 5304