Training in progress, epoch 0

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "medicalai/ClinicalBERT",
-  "activation": "gelu",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-Drug",
@@ -30,6 +31,7 @@
     "18": "I-ADE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-ADE": 17,
     "B-Dosage": 11,
@@ -51,17 +53,16 @@
     "I-Strength": 8,
     "O": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
-  "vocab_size": 119547
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3825338e73eb31dd3139b5b81de4b68faca22334de0eff081908eb58b441c9
-size 539007116
+oid sha256:2e65309d7468724f6a000cf5b8e4fcb18b57ea8f491ed110737a41fdadb7d3fb
+size 435648380

tokenizer_config.json

@@ -43,16 +43,13 @@
   },
   "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,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a3e587e4c5c2407bb753e89b20cf304de63395efd55d31a667ba4ea973f45f
+oid sha256:2691cf58a6cf91103a0142e11346406658b5b3396f59b3499bd7f6410ff7edf8
 size 5176