Training in progress, epoch 1

config.json

@@ -0,0 +1,37 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NON_PII",
+    "1": "VALID_PII"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NON_PII": 0,
+    "VALID_PII": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 119549
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13440ce570326e67d490c15bbea8be8d8c71e5cc59add6065f3a4f74d72ff35d
+size 541323512

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": [
+    "[E1]",
+    "[/E1]"
+  ],
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a0cd494c27eeaf6b6ec38699d3be62f1238c3acd0f0fecb215eeb9cba1d3fd
+size 5265