Training in progress, epoch 1

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-large",
   "architectures": [
     "ModernBertForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 50281,
+  "bos_token_id": null,
   "classifier_activation": "gelu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
@@ -13,8 +12,9 @@
   "cls_token_id": 50281,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
+  "dtype": "float32",
   "embedding_dropout": 0.0,
-  "eos_token_id": 50282,
+  "eos_token_id": null,
   "global_attn_every_n_layers": 3,
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
@@ -37,12 +37,10 @@
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "reference_compile": false,
   "repad_logits_with_grad": false,
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.2",
+  "transformers_version": "4.56.1",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80798a75dc096ece87a879e5e3f00d12e6a4ddf013a17c66d42f3c42318a343a
+oid sha256:b2b30a7fa70972f00d7f8bb14ac7f4e00f3c0c2de92b3646b79ce959f7cdd842
 size 1583351632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d46990df9231e5857d1b6c532ec0fcc569054d16156e0efc119569fb6ea622ea
-size 5368
+oid sha256:cc7bf406f0ed89f45ccf0b86da1f441705bfb32e55f6bcdea77a552b1bcc93eb
+size 5432