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"
   ],
@@ -7,14 +7,14 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "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": "single_label_classification",

logs/events.out.tfevents.1727811070.spartan-gpgpu147.hpc.unimelb.edu.au.24329.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987cde6acd8c5f615610952b9c477904ebf22330bf0b33a3047cc2f581995d23
-size 10642
+oid sha256:fceef92c78c183e30f1d5d431c5485bf78ae51773badaa7b0ec86ff0157d41bb
+size 11596

logs/events.out.tfevents.1727811398.spartan-gpgpu147.hpc.unimelb.edu.au.24329.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a87e1214249e6a028090b51403cc291bb0409791fe75d454eab94cc522bf3f3
+size 477

logs/events.out.tfevents.1727811870.spartan-gpgpu147.hpc.unimelb.edu.au.38542.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c1d867f7b233d49537130ba1c98d5bae80bc04fc4027fcc8538264ac1a9427
+size 5910

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd8b5891421ec62837556c5115e00202da30f6ddde66b5dc94352bf30cecf6a
-size 133466376
+oid sha256:3fbccb1a1b836dec65b00fbd19d6a62b05ab53783e1419880592e3de6e858bbe
+size 267838384