Training in progress, epoch 1

config.json

@@ -1,13 +1,24 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "answerdotai/ModernBERT-base",
   "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,
+  "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",
@@ -169,17 +181,26 @@
     "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",
+  "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": "4.49.0",
-  "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:a50971eb875a02aec8a2935185ea0ad5668aebe0cdd61e8f53ff49677c6d4457
-size 438189348
+oid sha256:f2f5ce69a068cb1b94e4540877714d899cc06cdc8e34a58d7a81158b50fc31c8
+size 598670492

runs/Mar21_16-39-28_DESKTOP-AV7HM21/events.out.tfevents.1742546369.DESKTOP-AV7HM21.8340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1021262d9120702f132eedfc6f32bd0eefe3c264863f1d9cbb31936cc881bd
+size 11560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c632528778b4240464e08f66b417e6ce558769b0e6748765ede3e38f945eb43
+oid sha256:04c6291063fd3be993e77f2bf658df778aecca6be44902a4ef1fc5b1c23d2fc0
 size 5368