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.1724056376.spartan-gpgpu095.hpc.unimelb.edu.au.131842.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d630d64f028e0e714c44057d9bc951aa75e20c414cfdd5011c0e086a4ba73915
-size 9903
+oid sha256:c70a01b696341b8a47a7a826183a42b5c2668e015c16867b72a9d3216d4e9b15
+size 10803

logs/events.out.tfevents.1724060472.spartan-gpgpu095.hpc.unimelb.edu.au.281327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e78b8fb5277ed307a5f503cac26d51a6c42032d19583bd9f1bd97c088de4209
+size 5440

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c17d9e203e43624eec205fa45c48b266beef983bbdbcbaefa6943ba5bc6575f
-size 133466376
+oid sha256:ab5bdc4ed221c19d9799b6622ab3a39e8bcfc43d53e40678d9c35b2f2bbc8c11
+size 266339248