Training in progress, epoch 1

config.json

@@ -4,22 +4,22 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "finetuning_task": "cola",
   "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.1724863799.spartan-gpgpu092.hpc.unimelb.edu.au.137964.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd8f9cbee51281f4ba3478664fc866881e2b69ff5fb0b8711fe439dbbdfc048
-size 9809
+oid sha256:f672b5c8097ef91bc5d8e34fa3a1ac97443956e78d01635e0fa3b69a4a28a153
+size 10709

logs/events.out.tfevents.1724864762.spartan-gpgpu092.hpc.unimelb.edu.au.137964.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79021d69efeb5b6962aee3e09d9d4056b82967974b3e404439523d029c2d9b94
+size 423

logs/events.out.tfevents.1727720543.spartan-gpgpu147.hpc.unimelb.edu.au.287278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c135b59eddea4baee0c7d395c4d2b315d356785ff125a52925e2d7f0ea98542
+size 5916

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b255ac98128f84db2bae759022690c1c0eac66a446360d773191e0d5f0a858
-size 165480304
+oid sha256:292dec7b5ae3c3abac4db8a3a65fb5434886745c325cf8d5d3166d9fda6c91e1
+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 sha256:925e8471589fc75da21c2475f1919b14568bc98fe8b964726a8c55b47a2c8f1b
-size 4984
+oid sha256:5dd30c4f59e6e8332f8b195b2ff5c6bb7651e72c6102926ee01f38778202687d
+size 5304