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.1724661234.spartan-gpgpu095.hpc.unimelb.edu.au.168472.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4083c3786f2e9a28d5cf82608190684bbe39cd4a36723430f513663a86a91964
-size 9849
+oid sha256:1ee78cf79f79ee7f7ddb8121254cab30fbdca6443e5820e4eba29dae83786fc9
+size 10783

logs/events.out.tfevents.1724661802.spartan-gpgpu095.hpc.unimelb.edu.au.168472.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7941711228ee83d781c006be07eb9f6db311b51ce86518797498b70ba91dca
+size 457

logs/events.out.tfevents.1724683343.spartan-gpgpu095.hpc.unimelb.edu.au.117650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77147c3a938422fa4e03a5c793a477bb6dc54f839d58682f5203d4fb8c8402a9
+size 5127

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7384efd774d62b387b950fafccb70dfe381c68525c52f7ac41b2ac7194db98d6
-size 266339248
+oid sha256:65e326a0f54493123e36cef6c5a1a879cdbf1b58a36f3417215c966361375399
+size 199099944

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,