Training in progress, epoch 1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-base",
   "architectures": [
     "ModernBertForSequenceClassification"
   ],
@@ -13,6 +12,7 @@
   "cls_token_id": 50281,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
+  "dtype": "float32",
   "embedding_dropout": 0.0,
   "eos_token_id": 50282,
   "global_attn_every_n_layers": 3,
@@ -37,11 +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": "4.48.0.dev0",
+  "transformers_version": "4.57.6",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e930518cf22d7eddb95db21d2cf17c6b03ec595add25ac0eba2cae60ef82e43
+oid sha256:17fe230aaedf3392b66e507b65e0aaa896372e052b65caf0da37be252f069d47
 size 598439784

runs/Jun16_15-55-05_MacBook-Pro-4.local/events.out.tfevents.1781643306.MacBook-Pro-4.local.90244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bdca51a6d7bbb464011af3b64d667ed4d25d39cb5b9dd7c9e9f945e74b2b7a
+size 132498

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b239f3747383c254dbfc6a73438cde1cde919aa0d11c6e5afa681f6d97a51f2e
-size 5432
+oid sha256:ba5971613585868e0656e6d8f2eea8efa876bb6ea227b63bbd9bd77f1e8f339a
+size 5496