Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/12_384",
+  "_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/6_768",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -7,12 +7,12 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
@@ -20,7 +20,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "regression",

logs/events.out.tfevents.1724690907.spartan-gpgpu095.hpc.unimelb.edu.au.75681.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbfc631f0cad5806925e07ab94c1699f8d5d976fac69f9d01ac73cce6b9792a
+size 5607

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7e3adbe3bd6c5080c5ff3b536f28ad7e704e809b92b2ddf7c95a262496af39
-size 133464836
+oid sha256:9855da089994c741fdeb7785a8611ea032c1849eb4a4e67d366b7f9467ac361f
+size 267835308