Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "BertForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
@@ -12,12 +12,16 @@
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "electra",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "type_vocab_size": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1b20825831bf82659276faf774e6899f7b7c1e7707d1c75d25bf5db8dbffbc
-size 442499064
+oid sha256:cec1680bafdc81650fbabb668ed485f57e458f50319052192ee071c5e443ebb8
+size 442499672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dad0e36d84adbb572d1c02d802bad9a42408ce4be2b9c4ba29fae3b3465657d
+oid sha256:45b991e9dd08ec6914bc8762b23f3391971d7c1c650b51e5590bcba9e7144283
 size 5304