Training in progress, epoch 1

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 sha256:5c7d329f570ae54b0a9b3c6e24f714d9dfa13de9ad7a55b2cf868da6f63bc534
-size 598439784
+oid sha256:d2145701f83cb0723aef8daed88da068a1a70c99b056573e8a906cb5038b4466
+size 1583351632

runs/Feb20_23-27-25_jagupard35.stanford.edu/events.out.tfevents.1740122847.jagupard35.stanford.edu.2378267.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e96bdb29ee28935dce10cc7f9780d4fb95acad0ceb71c8641559731eb601ae
+size 8725

runs/Feb21_01-13-50_jagupard35.stanford.edu/events.out.tfevents.1740129233.jagupard35.stanford.edu.2378267.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e101f09529749c0665ef2b8b0711b4b2c46504cd3ba904f05bda31eda583c41c
+size 7594

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be767829f5faed65a9b88b3226a69d37725ffb0decf1d78abe3e8896eb7a09a
+oid sha256:14efb8c68c95e401c37d0c31daed8e9a2ef5387b9082d2cead0749c76eb41d3d
 size 5432