Training in progress, epoch 1

config.json

@@ -2,17 +2,12 @@
   "_name_or_path": "medicalai/ClinicalBERT",
   "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
   "dim": 768,
   "dropout": 0.1,
-  "hidden_act": "gelu",
   "hidden_dim": 3072,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -56,7 +51,6 @@
     "39": "LABEL_39"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -99,16 +93,12 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
@@ -116,7 +106,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9c95ba60c638a1ba5e39eb70f149fac8f4fd18b4dbf7479434502a0c8b432c
-size 711560352
+oid sha256:56545c6bcbc5d885e4a1c70a642d7e9ab5bed87fb373c5b95d9d2a578608a6a5
+size 541434272