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:fc48d8c0a6404952dfc03ee8dc781216e0f729c440dfa7ac1719a2d0686b9911
-size 267832560
+oid sha256:479a315b0da1fd2fc81b7fd3b76c78ba179d61cf55616282c50d48a840ca9886
+size 437958648

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88ed6e21f8e73c354a58088d1015db951b1e711d6eea5f5ef4715e38a28b852
+oid sha256:8ab316eef5e56b5938169b2690dbf540e2a6661d8d3c232c9d8e889a5b4f6492
 size 5176