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 sha256:3c33ca97292fdd46f09a7b19a59f96dc6ad75e535cb0c48c48beae6f9bb54b15
-size 438189348
+oid sha256:414e6c73376c7867799587ef20a8c1b27fa3ba79fd6148c55a0211a69a1611c8
+size 598670492

runs/Dec29_10-09-09_ai4d-Lambda-Vector/events.out.tfevents.1735456152.ai4d-Lambda-Vector.3573610.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6184454e26ff8798a8e3a92dbdfe54c9147a4b3400d7d981f48083c717aba11c
-size 12287
+oid sha256:1d87ec5f526dfd20d51fd3245da00d675ed16133a9d68db241a4ef989c9d9e38
+size 13448

runs/Dec29_10-18-31_ai4d-Lambda-Vector/events.out.tfevents.1735456713.ai4d-Lambda-Vector.3593434.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02aa6beafc4d33c9c76a2d565d0220816418f2d80a8c16af8775d921366280b9
+size 11953

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64f026dbb1e79c7f03137eecd75a588d71dd10f1dcb2cb5730541cbe30053fb
+oid sha256:1e908d222c31579c05702fd41933d3f271e38f933f26b982d2d8140d3212c129
 size 5368