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": 16,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1725870642.spartan-gpgpu091.hpc.unimelb.edu.au.134335.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31f324ebf651ab7e8fc6454b6899c1e37d54a10c0146069ea93e0f18e13832b
-size 9823
+oid sha256:9e85c30baef1bd6517a9dc4c14f61a9885503c8721abc5528930f166ab7c15bf
+size 10723

logs/events.out.tfevents.1725871099.spartan-gpgpu091.hpc.unimelb.edu.au.134335.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c33cd4276770173aaccc49e2c2d9e4521b1968f2b208b4eee292443fbbc4cf
+size 423

logs/events.out.tfevents.1725871189.spartan-gpgpu091.hpc.unimelb.edu.au.134335.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94559d2565f20953e0862a4c0a2b87de95519e71366f6951970346de3b73245a
+size 5473

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645f890336b562b68a85dc98f7fb8e5248e7b0af1e6bdbe1553884db0e3a4b45
-size 266339248
+oid sha256:166ed542bcf5f9a92919d39b88879f96026e76807fe3c68e83d56b6f4a74e479
+size 165480304