Training in progress, step 500

config.json

@@ -1,21 +1,20 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased-whole-word-masking",
   "architectures": [
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "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",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:731f901d6ab043e8910d0019f56e993258b2fc16d15ca899c9cf7bd469f0bc75
-size 438131062
+oid sha256:c55b95e22afc7fc8a9d2e5c53069bd8fbcbdaa57b6ed00b3676df2b8bf28fea6
+size 1340837750

runs/Nov25_13-09-31_1f807fdc3ef8/1700917878.080055/events.out.tfevents.1700917878.1f807fdc3ef8.1491.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2a69c93f3c9ba2baf0ec98570e98b65721d0b7158b9d9c3f2bc32179021e73
+size 5829

runs/Nov25_13-09-31_1f807fdc3ef8/events.out.tfevents.1700917878.1f807fdc3ef8.1491.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a1512ad39e673c1bf6404a9436ee48bd36b6d04a0aa894e1c79822499537ae
+size 4112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c68ee3e3f1bce362baebb56b6e91a5a743df617d04235a934138f841cd11743c
+oid sha256:2885d192506ed92298b5a74ebc1d9fa12a43bdd1a88f8601542f995a4d2273fc
 size 4024