Training in progress, epoch 1

config.json

@@ -8,19 +8,19 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
+  "num_attention_heads": 6,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0",
+  "transformers_version": "4.45.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

logs/events.out.tfevents.1724866818.spartan-gpgpu092.hpc.unimelb.edu.au.196310.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a0d43f1b6aa61e47763051d2b311bf5b7b7c1cb225ccb22f07271a94f2295f
-size 10154
+oid sha256:4de4398e0f83dd3555405db9f2c2737afbc8895aed72812473906b31a39e0157
+size 11088

logs/events.out.tfevents.1724867250.spartan-gpgpu092.hpc.unimelb.edu.au.196310.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f57d144f580762d80f14b7ba129fe094bbb7b20915a3a8976c9046e5d2699a
+size 457

logs/events.out.tfevents.1727718604.spartan-gpgpu147.hpc.unimelb.edu.au.238764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4ef3dc93484b96d7bcde368bf4ed629d102026686a6d6c2b471175f4a365f6
+size 5992

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1ff919d38d2b397474b93c889702e897d8bfb4f695f36c4d4fb2477e6c3011
-size 165480304
+oid sha256:667952c2cea6f17c3e1f868e91e13fc13e4fe8f7c714bfa8d0270674aaed33cc
+size 90867952

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "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]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -41,7 +41,7 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc0266cab8c87a628e1825ed0b2649c8d8b494ac42418da0f957b4a5e496968
-size 4984
+oid sha256:abe656137c8ef51e5fc3af837a54e3979a296d63ae3078387f1ac346b857c719
+size 5240