Training in progress, epoch 1

config.json

@@ -14,8 +14,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1725868841.spartan-gpgpu091.hpc.unimelb.edu.au.134335.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c11463cc044a2df066977f9d345d9e376acced74199052611ae4435bef0fdc7
-size 9275
+oid sha256:a23792fd12519f8b8436bf6f46152cc54d110add458f728c098cc8c745258359
+size 10721

logs/events.out.tfevents.1725870150.spartan-gpgpu091.hpc.unimelb.edu.au.134335.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f45842d73075a968c2521f05a0b2e142b37450a323978fe5695b0b8c181abc
+size 5475

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fd5395dc2077e8634ba633ac664a17db49c46f1cae078ca110c4cad2204bc0
-size 199099944
+oid sha256:368c63f1b09f924f27bc1072169c99a2948e7525e416ba3052a9aea39f05849b
+size 266339248