Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForMaskedLM"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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 sha256:4b4dd3ba38fccdb1a54fff739d0cfc8e07eb66d54cae5efab459e2bfc913e37a
-size 473110392
+oid sha256:1c1abf2585bd49ca9da5e2f5ed8997fe3f5d10c48f43bdbe29f9e44ecf64186b
+size 1387435848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd916a46950fa37216f50dc88d6057bf4bcd00ede35b2e4e9c7dcdb1062abc7
+oid sha256:a07065a1f35e8d3b45ad70b4b636ea9149875b03fe0a33983f24945fcaf60098
 size 4664