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 +181,25 @@
     "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": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0.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 sha256:5ab8e24149cabc67f07ee12e83978ff5dfd8ab7bfccd222980055e822956c3be
-size 438189348
+oid sha256:b51e668e6fa103378a542a0c03deaa7e8738ad113688050a881504f26e22613c
+size 598670492

runs/Dec28_17-12-34_models-dev-9.aws.finchcomputing.com/events.out.tfevents.1735405968.models-dev-9.aws.finchcomputing.com.10104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8be59ce1e5654c51b316064a86189b8c36d851eb2b21e2784d006bcd8bd911
+size 11970

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99465a92b72c2ce2f999c5293e489bf924c29e162ced1d1431f65aacff2d4268
+oid sha256:b07d7ae488f8dc72c7abca8951efefe67e6943b1760c842dc43f19f87530be93
 size 5432