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,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -16,6 +19,7 @@
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": false,
   "label2id": {
     "negative": 0,
     "neutral": 1,
@@ -32,10 +36,10 @@
   "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": "5.0.0",
   "type_vocab_size": 2,
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 105879
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f84b4e866c30a1870bb5cbf7c815a7d1410b5a1002eadbd18010a0088c4fc80
-size 669458436
+oid sha256:ab587d659b1f78952339453fb6cf000ac1a1fba3c2e07ffa94ac9c5cb791180a
+size 669458412

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6619abeaf10a1ea5cd64792acd91fa05cadda4fce1372eb2185c7025c784c0
-size 5841
+oid sha256:2465565c97b29f018134eae1a817aa0f196a94105e71890871adc8378313026c
+size 5201