Training in progress, epoch 1

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-T005",
+    "2": "I-T005",
+    "3": "B-T007",
+    "4": "I-T007",
+    "5": "B-T017",
+    "6": "I-T017",
+    "7": "B-T022",
+    "8": "I-T022",
+    "9": "B-T031",
+    "10": "I-T031",
+    "11": "B-T033",
+    "12": "I-T033",
+    "13": "B-T037",
+    "14": "I-T037",
+    "15": "B-T038",
+    "16": "I-T038",
+    "17": "B-T058",
+    "18": "I-T058",
+    "19": "B-T062",
+    "20": "I-T062",
+    "21": "B-T074",
+    "22": "I-T074",
+    "23": "B-T082",
+    "24": "I-T082",
+    "25": "B-T091",
+    "26": "I-T091",
+    "27": "B-T092",
+    "28": "I-T092",
+    "29": "B-T097",
+    "30": "I-T097",
+    "31": "B-T098",
+    "32": "I-T098",
+    "33": "B-T103",
+    "34": "I-T103",
+    "35": "B-T168",
+    "36": "I-T168",
+    "37": "B-T170",
+    "38": "I-T170",
+    "39": "B-T201",
+    "40": "I-T201",
+    "41": "B-T204",
+    "42": "I-T204"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-T005": 1,
+    "B-T007": 3,
+    "B-T017": 5,
+    "B-T022": 7,
+    "B-T031": 9,
+    "B-T033": 11,
+    "B-T037": 13,
+    "B-T038": 15,
+    "B-T058": 17,
+    "B-T062": 19,
+    "B-T074": 21,
+    "B-T082": 23,
+    "B-T091": 25,
+    "B-T092": 27,
+    "B-T097": 29,
+    "B-T098": 31,
+    "B-T103": 33,
+    "B-T168": 35,
+    "B-T170": 37,
+    "B-T201": 39,
+    "B-T204": 41,
+    "I-T005": 2,
+    "I-T007": 4,
+    "I-T017": 6,
+    "I-T022": 8,
+    "I-T031": 10,
+    "I-T033": 12,
+    "I-T037": 14,
+    "I-T038": 16,
+    "I-T058": 18,
+    "I-T062": 20,
+    "I-T074": 22,
+    "I-T082": 24,
+    "I-T091": 26,
+    "I-T092": 28,
+    "I-T097": 30,
+    "I-T098": 32,
+    "I-T103": 34,
+    "I-T168": 36,
+    "I-T170": 38,
+    "I-T201": 40,
+    "I-T204": 42,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d48316636ea99146af0b8f510787d45422fbfa782bebdb9e5a39dcaa2484dc
+size 431034324

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "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:c40bfd1c72a2a67c1dd55b435fe99d13aa4086dcff616db8726f41d86063abaa
+size 5240