Training in progress, step 500

config.json

@@ -18,7 +18,7 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -174,7 +174,7 @@
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
+  "intermediate_size": 2624,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -337,8 +337,8 @@
   "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:c957eba4f99a10527e0109a9fa2d7597a42803103ae7b4cd631d0f23966ad41a
-size 598898116
+oid sha256:18e59832b1c70607be80679e27ef64d0883c170e2ba5a4e9fc913ad233593833
+size 1583962548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba46382351804384bfb837c33b2895492a910cd05c94f202772010033e16d2f7
+oid sha256:ae58804986a9c1f0b4fca19d217be86e8661630333ba2d9fad702fd66bba2f7b
 size 5713