Training in progress, epoch 1

config.json

@@ -1,15 +1,11 @@
 {
-  "activation": "gelu",
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dim": 768,
-  "dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dim": 3072,
   "hidden_dropout_prob": 0.1,
   "hidden_size": 512,
   "initializer_range": 0.02,
@@ -17,19 +13,13 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "num_attention_heads": 4,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0",
+  "transformers_version": "4.39.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

logs/events.out.tfevents.1715757548.spartan-gpgpu093.hpc.unimelb.edu.au

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d86812ef45468de74120c3e15acbd7f3e5c7eab4cca8e6d70a08c9a45801902
+size 5064

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39f32b3dc7675f03c19051526bdad2f94960e59606b8b5c9aafe0f2716c9b52
+size 199099944

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

@@ -1,4 +1,46 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fdf41783bab7b8a5f1d4fe468d800a5d7400ca4d9d7357248e84035b8aa6b2
-size 4091
+oid sha256:d55612314a7be6f9a922d1731809e4ce24f8e9d9d1c251219b2d4c9ec6c92b03
+size 4984