Training in progress, epoch 1

config.json

@@ -1,13 +1,24 @@
 {
   "architectures": [
-    "BertForSequenceClassification"
+    "ModernBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "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,
+  "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
     "0": "activate_my_card",
@@ -88,8 +99,9 @@
     "8": "cancel_transfer",
     "9": "card_about_to_expire"
   },
+  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1152,
   "label2id": {
     "Refund_not_showing_up": "51",
     "activate_my_card": "0",
@@ -169,16 +181,24 @@
     "wrong_amount_of_cash_received": "75",
     "wrong_exchange_rate_for_cash_withdrawal": "76"
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
   "transformers_version": "4.57.0.dev0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6938422e845b0b01a44b11754c9474eb057f6631551844ede72c16543e19802
-size 438189348
+oid sha256:e2e7d25ee7fef88a283818bbfea693dce730676935d058bf15c6f6dcb22f2637
+size 598670492

runs/Sep17_21-41-43_6624b0b7ce54/events.out.tfevents.1758145304.6624b0b7ce54.866.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c38922f0ed4046f89dfd9a952a1fb848ed88b37b352f2ba7c98b2a6ce98c020
+size 12456

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe09c855c93c00838a4a83990e7fa0944ef094ebbff66cf2ef4ea81363c21ae
+oid sha256:d78f6d656d01063dc7d2ad337f9d167e7fa9d902af40fce9428563c12a4bba63
 size 5841