Training in progress, epoch 1

config.json

@@ -1,20 +1,20 @@
 {
+  "_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/12_384",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "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_hidden_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1715826550.spartan-gpgpu093.hpc.unimelb.edu.au

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82797f9d0a8417229660ecad8cc6fce59db425e457e115621d122237ca67c1f1
-size 9303
+oid sha256:ad37e98854fb089a40bda20a3a5b8afcd8f1739bd78df6cc45abc701b58a6b2b
+size 10514

logs/events.out.tfevents.1715833467.spartan-gpgpu093.hpc.unimelb.edu.au

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362c509fbe7e79a7f12d9cfddf7f0d550a406fc4aec8dccb0b2c71afa0c6ecb9
+size 686

logs/events.out.tfevents.1724074917.spartan-gpgpu095.hpc.unimelb.edu.au.260921.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47be8b3af2e38dfe902b51e8d1443f39e02b6df87d084ab52d1bf34c300a705
+size 4878

logs/events.out.tfevents.1724074942.spartan-gpgpu095.hpc.unimelb.edu.au.260921.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2a52bd81eac4f3f5bc0e33e0d57693b3a751d293bb9ee176cebbcaa573a2ad
+size 5411

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be8aea2507ce13de6f3db5dc4cb09836cc23e5a82538ee18d25d4062ea5cda6
-size 165480304
+oid sha256:97ccaae4a25f7fc421ee21f43d64679d8f9043fb22908f87cedd540e47e08f1e
+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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de73987401f63f90e57b5067ebb8a3bf4e6fadeb8a8cb1da5c785dbd7ecf9ce5
+oid sha256:8508e3b4e345904352910e51d8e49cb0a6b328c2c55d50def6296d8d65607bea
 size 4984