Training in progress, epoch 3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-base",
+  "_name_or_path": "answerdotai/ModernBERT-large",
   "architectures": [
     "ModernBertForSequenceClassification"
   ],
@@ -19,14 +19,14 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "not selected",
     "1": "selected"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
+  "intermediate_size": 2624,
   "label2id": {
     "not selected": "0",
     "selected": "1"
@@ -40,8 +40,8 @@
   "model_type": "modernbert",
   "norm_bias": false,
   "norm_eps": 1e-05,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 22,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "reference_compile": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d16c26bfe0f8b2dd0eea2f67916931fd9f10d5c35c709955d2d3efd1f3c826b
-size 598439784
+oid sha256:f75dd8c68a1b09c87f8c918e9960ce24910be8567dc5a1d041020d3d29a98ab9
+size 1583351632

runs/Feb20_22-25-31_jagupard35.stanford.edu/events.out.tfevents.1740119133.jagupard35.stanford.edu.2378267.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fe55293451159d4e1613851ca306ab8af0b04c3051c850d9e1bcc645712243
+size 10469

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1280a6ecb01058a5fb010f3d1a05f4c7e1741565c7781b991e05a3c2711ca2
+oid sha256:b8b556ecc7b845c26998514d7e52b6049bee6ce36d52e2ba4ee8f0f8ce632c4b
 size 5432