Training in progress, epoch 1

config.json

@@ -1,19 +1,19 @@
 {
-  "_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": 384,
+  "hidden_size": 512,
   "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_attention_heads": 16,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",

logs/events.out.tfevents.1724058634.spartan-gpgpu095.hpc.unimelb.edu.au.131842.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602604369751157a0ccef5ec55f9523486388ec20eb62dc380403337874efdfc
-size 9647
+oid sha256:b005cb0266cb78782043d8f090d596afb87d746bd5f623239b18ae73c671053c
+size 10535

logs/events.out.tfevents.1724071527.spartan-gpgpu095.hpc.unimelb.edu.au.195463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227ee0ec69f64af72965344a0baabc970c816149dae5175ac3191b85f41412b3
+size 5393

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2440c0f5aa3e826a33846ffce8204a83a7f354ae4b51321131180ef19ff1cb
-size 133466376
+oid sha256:b469066452d545ba23506790b99f29848512ea0b14abe3cabce95cdca458b26e
+size 266339248

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d5cc6afa18d4a37013886dde9d358141451b793992f3cd2b2a381673d398c4
+oid sha256:f5e1e5fda334b1abdb0dffbbbcf22ec838ea11956ef938ca650d25dfd57dce76
 size 4984