Training in progress, epoch 1

config.json

@@ -1,24 +1,13 @@
 {
-  "_name_or_path": "answerdotai/ModernBERT-base",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
-    "ModernBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "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,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "gradient_checkpointing": false,
-  "hidden_activation": "gelu",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "activate_my_card",
@@ -99,9 +88,8 @@
     "8": "cancel_transfer",
     "9": "card_about_to_expire"
   },
-  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
+  "intermediate_size": 3072,
   "label2id": {
     "Refund_not_showing_up": "51",
     "activate_my_card": "0",
@@ -181,26 +169,17 @@
     "wrong_amount_of_cash_received": "75",
     "wrong_exchange_rate_for_cash_withdrawal": "76"
   },
-  "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,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 22,
-  "pad_token_id": 50283,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "reference_compile": true,
-  "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",
-  "vocab_size": 50368
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c024e5fa7161f3c1c64ae688e370fd1e49a5580c347249fb5c977461f56141
-size 598670492
+oid sha256:97cf062af635a67bfe257c33a3158515482d19d477ba5429598dc02fb8364040
+size 438189348

runs/Feb26_19-51-07_modal/events.out.tfevents.1740599469.modal.2.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300244d0702c2670141feddabb96a2963990d2bbfa05e65a8064f8cb3f492e98
+size 11347

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b89ed0d78b2b159cc8be9ac1bc64e702999b5856c8670055ab04255b467f3f1
+oid sha256:d0b48c17154bbcd6136d02a4aadf00ecd29601f8006e609e7591fa683bc09a7c
 size 5368