Training in progress, epoch 1

config.json

@@ -1,25 +1,25 @@
 {
+  "_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/12_384",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "finetuning_task": "sts-b",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 384,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "label2id": {
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",

logs/events.out.tfevents.1724690433.spartan-gpgpu095.hpc.unimelb.edu.au.2329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c497a7dd8337b770585e200733ac2ce22bffd9659ef30413779f36985896bdd
+size 5561

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96b34a059c2350d71da9a1f8df6961cafb95f48c01126030eaa9f51c9bbf85d
-size 266337196
+oid sha256:fed9cd48789a7e2eb8757e88e72e360d5b570909b82b3494629cccbe0f4a9276
+size 133464836