Training in progress, step 2634

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -8,7 +8,7 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -21,7 +21,7 @@
     "8": "I-MISC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "B-LOC": 5,
     "B-MISC": 7,
@@ -36,8 +36,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93adbba002de4da818263e110638eae20bfcc998bc12c7f3874dcaddcd71594d
-size 435617620
+oid sha256:4f1aa56528ed4b4845a575d24806836ace270e86df537b76bb0e8677ae5724af
+size 1336452868