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": "sst-2",
   "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_hidden_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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.1724851568.spartan-gpgpu092.hpc.unimelb.edu.au.199860.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9359702a996c844d6c46dd032a5f124c1147b57cb8ddec1e4d553877efa8d365
-size 9676
+oid sha256:59202bd1e2613b5c4045bec454073c823d9d54c998b90cd31c3870980abe2abf
+size 10564

logs/events.out.tfevents.1724858283.spartan-gpgpu092.hpc.unimelb.edu.au.199860.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3874a420149c000f319fae4bad3c10771152f3d14f8e998d11785418021117c6
+size 411

logs/events.out.tfevents.1727725862.spartan-gpgpu147.hpc.unimelb.edu.au.116319.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fd0b228c22a7a43270a2cb446db9ce8c4f74ee47bd1f2ff3eb8554f6a099f1
+size 5883

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82502dc56b28ee4f27771bcb019a138d21af8077d5bec2401c4606a45f42e6c8
-size 165480304
+oid sha256:774647636b32119027595bedb091b007018818ba37d511dfe7b458c9e69fb769
+size 133466376

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:ba0abb8edd82c8779b2624d5a123b8ca8ce20afd1ccf9de599e3b613e2b7bf17
-size 4984
+oid sha256:46eeb5538a0185c2eff2f2b2a73333f17eccb4c40fe9c55defa4d1c6b0ead6f4
+size 5304