Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-large",
+  "_name_or_path": "answerdotai/ModernBERT-base",
   "architectures": [
     "ModernBertForSequenceClassification"
   ],
@@ -19,14 +19,14 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "No",
     "1": "Yes"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2624,
+  "intermediate_size": 1152,
   "label2id": {
     "No": 0,
     "Yes": 1
@@ -40,8 +40,8 @@
   "model_type": "modernbert",
   "norm_bias": false,
   "norm_eps": 1e-05,
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed47f6752353911d5613798a741c3764e4d9c25edccaff3e7dfd0b7bd108b48
-size 1583351640
+oid sha256:be93ea1de837dfe5efd0fd70f96bf2322c758514249076bd16fa507c6150b96a
+size 598439784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b831e60763892fffd580e62b753aa3f08a510120c909f548f1143865c21e7a4d
+oid sha256:3cd34d27515aa662b25d9ef1617fb6e46dc2a63e3eb3d64a0dbeb6ad5f48054f
 size 5304