Training in progress, epoch 1

config.json

@@ -1,56 +1,54 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
-    "0": "I-URL_PERSONAL",
-    "1": "B-PHONE_NUM",
-    "2": "B-URL_PERSONAL",
+    "0": "B-USERNAME",
+    "1": "B-STREET_ADDRESS",
+    "2": "B-NAME_STUDENT",
     "3": "I-ID_NUM",
-    "4": "B-NAME_STUDENT",
-    "5": "B-EMAIL",
-    "6": "I-STREET_ADDRESS",
+    "4": "I-PHONE_NUM",
+    "5": "I-STREET_ADDRESS",
+    "6": "B-URL_PERSONAL",
     "7": "B-ID_NUM",
-    "8": "I-PHONE_NUM",
-    "9": "I-NAME_STUDENT",
-    "10": "B-STREET_ADDRESS",
+    "8": "I-URL_PERSONAL",
+    "9": "B-PHONE_NUM",
+    "10": "B-EMAIL",
     "11": "O",
-    "12": "B-USERNAME"
+    "12": "I-NAME_STUDENT"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "label2id": {
-    "B-EMAIL": 5,
+    "B-EMAIL": 10,
     "B-ID_NUM": 7,
-    "B-NAME_STUDENT": 4,
-    "B-PHONE_NUM": 1,
-    "B-STREET_ADDRESS": 10,
-    "B-URL_PERSONAL": 2,
-    "B-USERNAME": 12,
+    "B-NAME_STUDENT": 2,
+    "B-PHONE_NUM": 9,
+    "B-STREET_ADDRESS": 1,
+    "B-URL_PERSONAL": 6,
+    "B-USERNAME": 0,
     "I-ID_NUM": 3,
-    "I-NAME_STUDENT": 9,
-    "I-PHONE_NUM": 8,
-    "I-STREET_ADDRESS": 6,
-    "I-URL_PERSONAL": 0,
+    "I-NAME_STUDENT": 12,
+    "I-PHONE_NUM": 4,
+    "I-STREET_ADDRESS": 5,
+    "I-URL_PERSONAL": 8,
     "O": 11
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97cb3ecba695104fa5858d432a25602be646a24467a48f9ce39839a7b31c97e
-size 1336469268
+oid sha256:b22da7496a9b097570953434d79dc3bdfc7f9f63e9753964809861d5fb7bf4f1
+size 265503852

runs/Mar29_03-29-18_341bed32227e/events.out.tfevents.1711682960.341bed32227e.152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf03ceb8a2466b4b8a7a6cbd348a2f257c2dbd33439a129ef9d4311a2ce2905
+size 5338

tokenizer_config.json

@@ -50,6 +50,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2092b81867d9594d639b09a6e0f1c006cee259c000191dc458f41a50eb1dab7
-size 4600
+oid sha256:17c20ad625e783bfbcb15b0a6cc3082ec8cc92a405060693325d39bc9ba630a3
+size 4920