Training in progress, epoch 1

config.json

@@ -19,7 +19,7 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -29,7 +29,7 @@
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2624,
+  "intermediate_size": 1152,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -46,8 +46,8 @@
   "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",
   "repad_logits_with_grad": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ca347646dcc9c9a9ebadae157e9ef721b5522a1bf3e3c9d2349655ce8cae54
-size 1583363940
+oid sha256:72b06aaa781b46eea9666e986770d2b116d30b075a79bca3408a480f37a1036b
+size 598449012

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3359fa1fc4e53c0ded3f111e8b863fe1d2fb1f29ee401122c3df41ecff0414af
+oid sha256:03f9a050303d280a540f94358ebb062837b15b5fde58ac6fbb161d9fd0901003
 size 5496