Training in progress, epoch 1

config.json

@@ -1,20 +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,
-  "finetuning_task": "glue:rte",
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "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.1727810586.spartan-gpgpu147.hpc.unimelb.edu.au.14514.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bfca1f3c76cbfc7e87255ef11987840cd814c978a63a128913432cf954ba10
-size 10684
+oid sha256:31716f775a1a1aceb4ab9ea8432781cfb6ce62c9c7be228a12165fb5933d4399
+size 11638

logs/events.out.tfevents.1727810986.spartan-gpgpu147.hpc.unimelb.edu.au.14514.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d161c224492eeeb1dd9d0e2c5134b66926b398cf1076fe72cec1ef27098c5d5
+size 477

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dd95de5c6af7208fb406d325754a5a3af650a3101eb9341c00cc2b7e6033aa
+size 5864

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1b81497291173a588d21f64d1c461267bc1de10946e2187c37a735e79b6e84
-size 266339248
+oid sha256:294c7564b439e9ce732ffc5b4ec9ae43af0f4ae7fe7c417e57f29a4749cb084b
+size 133466376