Training in progress, epoch 1

config.json

@@ -1,11 +1,14 @@
 {
+  "add_cross_attention": false,
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
   "classifier_dropout": null,
   "directionality": "bidi",
   "dtype": "float32",
+  "eos_token_id": null,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -17,6 +20,7 @@
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": false,
   "label2id": {
     "High": 2,
     "Low": 0,
@@ -33,10 +37,10 @@
   "pooler_num_fc_layers": 3,
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "transformers_version": "4.57.3",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
   "type_vocab_size": 2,
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 21128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3a3afb006e317c428eb5eca7da7263ad56dcca690af003aa7e035767c6d606
-size 409103316
+oid sha256:b21e2cea42758995029d01f7fa854b84815cdbd675e487a8df732d6de9ea69e2
+size 409103292

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935094af26dd248b670387d3f5308da8484a88fd4487ac051fe26bf02029c55f
-size 5841
+oid sha256:8c8729a52b86b3d5a80dcc124919836fe2d108cbf50326c0e6c512ce210cd309
+size 5265