Training in progress, epoch 1

config.json

@@ -0,0 +1,172 @@
+{
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 768,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-B\u00e3i b\u1ecf",
+    "2": "I-B\u00e3i b\u1ecf",
+    "3": "B-B\u1ed5 sung",
+    "4": "I-B\u1ed5 sung",
+    "5": "B-B\u1ed9 lu\u1eadt",
+    "6": "I-B\u1ed9 lu\u1eadt",
+    "7": "B-Ch\u01b0\u01a1ng",
+    "8": "I-Ch\u01b0\u01a1ng",
+    "9": "B-C\u0103n c\u1ee9",
+    "10": "I-C\u0103n c\u1ee9",
+    "11": "B-C\u01a1 quan ban h\u00e0nh",
+    "12": "I-C\u01a1 quan ban h\u00e0nh",
+    "13": "B-Hi\u1ebfn ph\u00e1p",
+    "14": "I-Hi\u1ebfn ph\u00e1p",
+    "15": "B-H\u01b0\u1edbng d\u1eabn thi h\u00e0nh",
+    "16": "I-H\u01b0\u1edbng d\u1eabn thi h\u00e0nh",
+    "17": "B-Kho\u1ea3n",
+    "18": "I-Kho\u1ea3n",
+    "19": "B-K\u00e9o d\u00e0i th\u1eddi h\u1ea1n",
+    "20": "I-K\u00e9o d\u00e0i th\u1eddi h\u1ea1n",
+    "21": "B-Lu\u1eadt",
+    "22": "I-Lu\u1eadt",
+    "23": "B-M\u1ee5c",
+    "24": "I-M\u1ee5c",
+    "25": "B-Ngh\u1ecb quy\u1ebft",
+    "26": "I-Ngh\u1ecb quy\u1ebft",
+    "27": "B-Ngh\u1ecb \u0111\u1ecbnh",
+    "28": "I-Ngh\u1ecb \u0111\u1ecbnh",
+    "29": "B-Ng\u00e0y ban h\u00e0nh",
+    "30": "I-Ng\u00e0y ban h\u00e0nh",
+    "31": "B-Ng\u00e0y c\u00f3 hi\u1ec7u l\u1ef1c",
+    "32": "I-Ng\u00e0y c\u00f3 hi\u1ec7u l\u1ef1c",
+    "33": "B-Ng\u01b0\u1eddi k\u00fd",
+    "34": "I-Ng\u01b0\u1eddi k\u00fd",
+    "35": "B-Ph\u00e1p l\u1ec7nh",
+    "36": "I-Ph\u00e1p l\u1ec7nh",
+    "37": "B-Ph\u1ea1m vi \u00e1p d\u1ee5ng",
+    "38": "I-Ph\u1ea1m vi \u00e1p d\u1ee5ng",
+    "39": "B-Ph\u1ea7n",
+    "40": "I-Ph\u1ea7n",
+    "41": "B-Quy\u1ebft \u0111\u1ecbnh",
+    "42": "I-Quy\u1ebft \u0111\u1ecbnh",
+    "43": "B-S\u1ed1 v\u0103n b\u1ea3n",
+    "44": "I-S\u1ed1 v\u0103n b\u1ea3n",
+    "45": "B-S\u1eeda \u0111\u1ed5i",
+    "46": "I-S\u1eeda \u0111\u1ed5i",
+    "47": "B-Tham chi\u1ebfu",
+    "48": "I-Tham chi\u1ebfu",
+    "49": "B-Thay th\u1ebf",
+    "50": "I-Thay th\u1ebf",
+    "51": "B-Th\u00f4ng t\u01b0",
+    "52": "I-Th\u00f4ng t\u01b0",
+    "53": "B-Th\u1eddi h\u1ea1n thi h\u00e0nh",
+    "54": "I-Th\u1eddi h\u1ea1n thi h\u00e0nh",
+    "55": "B-Th\u1ef1c hi\u1ec7n theo",
+    "56": "I-Th\u1ef1c hi\u1ec7n theo",
+    "57": "B-Ti\u1ec3u m\u1ee5c",
+    "58": "I-Ti\u1ec3u m\u1ee5c",
+    "59": "B-\u0110i\u1ec1u",
+    "60": "I-\u0110i\u1ec1u",
+    "61": "B-\u0110i\u1ec1u kho\u1ea3n chuy\u1ec3n ti\u1ebfp",
+    "62": "I-\u0110i\u1ec1u kho\u1ea3n chuy\u1ec3n ti\u1ebfp",
+    "63": "B-\u0110i\u1ec3m",
+    "64": "I-\u0110i\u1ec3m",
+    "65": "B-\u0110\u00ecnh ch\u1ec9 thi h\u00e0nh",
+    "66": "I-\u0110\u00ecnh ch\u1ec9 thi h\u00e0nh",
+    "67": "B-\u0110\u1ed1i t\u01b0\u1ee3ng \u00e1p d\u1ee5ng",
+    "68": "I-\u0110\u1ed1i t\u01b0\u1ee3ng \u00e1p d\u1ee5ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-B\u00e3i b\u1ecf": 1,
+    "B-B\u1ed5 sung": 3,
+    "B-B\u1ed9 lu\u1eadt": 5,
+    "B-Ch\u01b0\u01a1ng": 7,
+    "B-C\u0103n c\u1ee9": 9,
+    "B-C\u01a1 quan ban h\u00e0nh": 11,
+    "B-Hi\u1ebfn ph\u00e1p": 13,
+    "B-H\u01b0\u1edbng d\u1eabn thi h\u00e0nh": 15,
+    "B-Kho\u1ea3n": 17,
+    "B-K\u00e9o d\u00e0i th\u1eddi h\u1ea1n": 19,
+    "B-Lu\u1eadt": 21,
+    "B-M\u1ee5c": 23,
+    "B-Ngh\u1ecb quy\u1ebft": 25,
+    "B-Ngh\u1ecb \u0111\u1ecbnh": 27,
+    "B-Ng\u00e0y ban h\u00e0nh": 29,
+    "B-Ng\u00e0y c\u00f3 hi\u1ec7u l\u1ef1c": 31,
+    "B-Ng\u01b0\u1eddi k\u00fd": 33,
+    "B-Ph\u00e1p l\u1ec7nh": 35,
+    "B-Ph\u1ea1m vi \u00e1p d\u1ee5ng": 37,
+    "B-Ph\u1ea7n": 39,
+    "B-Quy\u1ebft \u0111\u1ecbnh": 41,
+    "B-S\u1ed1 v\u0103n b\u1ea3n": 43,
+    "B-S\u1eeda \u0111\u1ed5i": 45,
+    "B-Tham chi\u1ebfu": 47,
+    "B-Thay th\u1ebf": 49,
+    "B-Th\u00f4ng t\u01b0": 51,
+    "B-Th\u1eddi h\u1ea1n thi h\u00e0nh": 53,
+    "B-Th\u1ef1c hi\u1ec7n theo": 55,
+    "B-Ti\u1ec3u m\u1ee5c": 57,
+    "B-\u0110i\u1ec1u": 59,
+    "B-\u0110i\u1ec1u kho\u1ea3n chuy\u1ec3n ti\u1ebfp": 61,
+    "B-\u0110i\u1ec3m": 63,
+    "B-\u0110\u00ecnh ch\u1ec9 thi h\u00e0nh": 65,
+    "B-\u0110\u1ed1i t\u01b0\u1ee3ng \u00e1p d\u1ee5ng": 67,
+    "I-B\u00e3i b\u1ecf": 2,
+    "I-B\u1ed5 sung": 4,
+    "I-B\u1ed9 lu\u1eadt": 6,
+    "I-Ch\u01b0\u01a1ng": 8,
+    "I-C\u0103n c\u1ee9": 10,
+    "I-C\u01a1 quan ban h\u00e0nh": 12,
+    "I-Hi\u1ebfn ph\u00e1p": 14,
+    "I-H\u01b0\u1edbng d\u1eabn thi h\u00e0nh": 16,
+    "I-Kho\u1ea3n": 18,
+    "I-K\u00e9o d\u00e0i th\u1eddi h\u1ea1n": 20,
+    "I-Lu\u1eadt": 22,
+    "I-M\u1ee5c": 24,
+    "I-Ngh\u1ecb quy\u1ebft": 26,
+    "I-Ngh\u1ecb \u0111\u1ecbnh": 28,
+    "I-Ng\u00e0y ban h\u00e0nh": 30,
+    "I-Ng\u00e0y c\u00f3 hi\u1ec7u l\u1ef1c": 32,
+    "I-Ng\u01b0\u1eddi k\u00fd": 34,
+    "I-Ph\u00e1p l\u1ec7nh": 36,
+    "I-Ph\u1ea1m vi \u00e1p d\u1ee5ng": 38,
+    "I-Ph\u1ea7n": 40,
+    "I-Quy\u1ebft \u0111\u1ecbnh": 42,
+    "I-S\u1ed1 v\u0103n b\u1ea3n": 44,
+    "I-S\u1eeda \u0111\u1ed5i": 46,
+    "I-Tham chi\u1ebfu": 48,
+    "I-Thay th\u1ebf": 50,
+    "I-Th\u00f4ng t\u01b0": 52,
+    "I-Th\u1eddi h\u1ea1n thi h\u00e0nh": 54,
+    "I-Th\u1ef1c hi\u1ec7n theo": 56,
+    "I-Ti\u1ec3u m\u1ee5c": 58,
+    "I-\u0110i\u1ec1u": 60,
+    "I-\u0110i\u1ec1u kho\u1ea3n chuy\u1ec3n ti\u1ebfp": 62,
+    "I-\u0110i\u1ec3m": 64,
+    "I-\u0110\u00ecnh ch\u1ec9 thi h\u00e0nh": 66,
+    "I-\u0110\u1ed1i t\u01b0\u1ee3ng \u00e1p d\u1ee5ng": 68,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 62000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd25e4d07acef237cd25289f404b9c5f68d48404fa83dc0cf54b4d543370320b
+size 532503188

runs/Sep14_15-48-59_18d407548951/events.out.tfevents.1757864943.18d407548951.857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe24ddbfc9c87bd02e8dafafd035e269435ce2d3e7e181919b49c2fce6553c6
+size 11227

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f59c5660bdd92275e14040a53608b46855179c7069ff35839bb863f64e670b
+size 5841