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": 6,
-  "num_hidden_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1727808252.spartan-gpgpu147.hpc.unimelb.edu.au.271384.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d702a44dc56980382cd57fdd49245d63190e87706e13c62ee9f959585711b770
-size 7917
+oid sha256:f732f05b0ea6bc8a02c5d0ebae393e697b24c2405428f3a3d21c5cb05d6dd573
+size 8128

logs/events.out.tfevents.1727808475.spartan-gpgpu147.hpc.unimelb.edu.au.276240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9dd605fb3f51b3a5d0f85ff3fd41f0b05e3da4484c4076e1599c4311671b3e
+size 5993

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8efe24fb58262d3903ec89cf3f0e1e34417a1ceb17943f20dd7f00c91347f48e
-size 90867952
+oid sha256:769803460252eace10648005d03e95fbcc41f9e1aa191ed825bc876178a2db39
+size 133466376