Training in progress, epoch 2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-base",
+  "_name_or_path": "answerdotai/ModernBERT-large",
   "architectures": [
     "ModernBertForSequenceClassification"
   ],
@@ -19,7 +19,7 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "Cybercrime",
     "1": "Drugs",
@@ -33,7 +33,7 @@
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
+  "intermediate_size": 2624,
   "label2id": {
     "Cybercrime": 0,
     "Drugs": 1,
@@ -54,8 +54,8 @@
   "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",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e2f0fc8ff67073748e47a2c481930d0e6e909987bb1b294b5f1e223c411542
-size 598461316
+oid sha256:9d8f17b1cad46fa95c08e2c7e65f5255438a65e86ace86fcf58e08b918ad3093
+size 1583380340

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98919011773fa79aad9d0a2f5e350ebc3d1ef31f63a789dbf08d97f95264b8c
+oid sha256:064661a9a471e66faca7c0a5236df67c5db4552a1283dd08400a3e20ff809acb
 size 5368