Training in progress, epoch 1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "textattack/bert-base-uncased-STS-B",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,7 +7,7 @@
   "finetuning_task": "sts-b",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "id2label": {
     "0": "LABEL_0"
   },
@@ -20,7 +19,7 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",

logs/events.out.tfevents.1724687736.spartan-gpgpu095.hpc.unimelb.edu.au.193153.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6654ffb44a513676e4b74632e9c9cea52615f4c53945bd15a5a1fda7541232c5
-size 13254
+oid sha256:f01355cc2ca521ca91fbf9e81a6e36bc36d0929af17a4bcfcabbaadfaab94411
+size 14194

logs/events.out.tfevents.1724688457.spartan-gpgpu095.hpc.unimelb.edu.au.193153.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc4c17938baaa71c2b7603e7b3c8687bf7ba53dc6c676ac96bfab0adf908aa2
+size 463

logs/events.out.tfevents.1724688721.spartan-gpgpu095.hpc.unimelb.edu.au.41215.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1784225bd8b4b8b5cfa3a7318b542a061794055a2273bbf465039f85bb1248c6
+size 5565

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6ee6fea555a869b9f1f7d96aa50455147399a8abd6a78c2f8d604d19dfb15c
-size 437955572
+oid sha256:0da9685274818cbdfe34eddb7eb49dccff1a50f36cbd1c9a0dbd1e8775a6fbb4
+size 266337196

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51d5613e590fef62b0cc6ea732f65be25b2c25c2651c43aa09f6b4c572a40c2
-size 4920
+oid sha256:a79294f81fa03ce50b8c693e6b5d02da18f4620b216075429a19b766ef6b95c0
+size 4984