Training in progress, epoch 0

config.json

@@ -1,33 +1,35 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "Introduction",
     "1": "Greeting"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Greeting": 1,
     "Introduction": 0
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
+  "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:b3c9575687ce887cf723b6f8684dde1b483abf1499f4a6cefd00d74f9794d11c
-size 267832560
+oid sha256:a069a9a879e00a39117c79552110e92616eb70e4671982305685a3212b211945
+size 437958648

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bf057fe8a7cc719d6aee68ba9b82af35880ea1cd7bf83a354ed6ca68b1e205
+oid sha256:9a7bf38f4ec974582e2a753f7eecb2074a2763d298b588b3a8e24ec8a007ea8f
 size 5176