Training in progress, epoch 1

config.json

@@ -13,8 +13,8 @@
   "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": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1724661920.spartan-gpgpu095.hpc.unimelb.edu.au.168472.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e899dcc3022deee69d765ca7623b67b24e6f5fc5eb729493390d47f0fac722
-size 9429
+oid sha256:5403b0eeaad9e377b49f7d0f72fb73569acf20e867a240eafa97ae7efeb7a6fd
+size 10317

logs/events.out.tfevents.1724684648.spartan-gpgpu095.hpc.unimelb.edu.au.17812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8564fa44256508731afa6d1b833bec72c66ce0a7261bd9762396e707609581
+size 5084

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b0e4bfcc3993a9b474874f028e5128e9ece64b48a66ae2b71b225d59946bf1
-size 266339248
+oid sha256:167e97de42571fd08a6e7eea7b9776d7c318d68945b46cf5a9c0525141787d3c
+size 199099944