Training in progress, epoch 0

config.json

@@ -1,35 +1,33 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "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": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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 sha256:0660bfa6aa04b40c43655cac3ff61db8346cfbd2d6ff2ee3c9f308460b622191
-size 437958648
+oid sha256:745927def156b1f2528c8f0b9ab1c0ca28eb3723ee1a8d0bdb60590b9f2eb6b4
+size 267832560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7bf38f4ec974582e2a753f7eecb2074a2763d298b588b3a8e24ec8a007ea8f
+oid sha256:f88ed6e21f8e73c354a58088d1015db951b1e711d6eea5f5ef4715e38a28b852
 size 5176