Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[/E1]": 119548,
+  "[E1]": 119547
+}

config.json

@@ -4,11 +4,9 @@
     "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",
@@ -30,8 +28,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.3.0",
-  "use_cache": false,
+  "transformers_version": "4.56.0",
   "vocab_size": 119549
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c4465fb8624cc9cd898e578ca6f3399675db43b48662ac1ba283472eca5b29
+oid sha256:3c7d323402572abc3239c830de708d98fa4a99992b34436e66c09abe89e37ec5
 size 541323512

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[E1]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[/E1]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,18 +1,76 @@
 {
-  "backend": "tokenizers",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "extra_special_tokens": [
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "119547": {
+      "content": "[E1]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "119548": {
+      "content": "[/E1]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
     "[E1]",
     "[/E1]"
   ],
-  "is_local": false,
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "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:a3a0cd494c27eeaf6b6ec38699d3be62f1238c3acd0f0fecb215eeb9cba1d3fd
-size 5265
+oid sha256:84bce02998a399ce78ddea796fba6d834f7a0c05f49812681797f191f2d0182a
+size 5841