NER Training complete

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: bert-large-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-lg-cased-ms-ner-v3-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert-lg-cased-ms-ner-v3-full
+
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 1.12.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,102 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-BOSS",
+    "2": "I-BOSS",
+    "3": "B-MOB",
+    "4": "I-MOB",
+    "5": "B-MAP",
+    "6": "I-MAP",
+    "7": "B-JOB",
+    "8": "I-JOB",
+    "9": "B-INGAME_ITEM",
+    "10": "I-INGAME_ITEM",
+    "11": "B-QUEST",
+    "12": "I-QUEST",
+    "13": "B-CHANNEL",
+    "14": "I-CHANNEL",
+    "15": "B-SALE_ITEM",
+    "16": "I-SALE_ITEM",
+    "17": "B-EVENT",
+    "18": "I-EVENT",
+    "19": "B-MECHANIC",
+    "20": "I-MECHANIC",
+    "21": "B-FEATURE",
+    "22": "I-FEATURE",
+    "23": "B-NPC",
+    "24": "I-NPC",
+    "25": "B-GAME",
+    "26": "I-GAME",
+    "27": "B-SKILL",
+    "28": "I-SKILL",
+    "29": "B-UPDATE",
+    "30": "I-UPDATE",
+    "31": "B-MISC",
+    "32": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-BOSS": 1,
+    "B-CHANNEL": 13,
+    "B-EVENT": 17,
+    "B-FEATURE": 21,
+    "B-GAME": 25,
+    "B-INGAME_ITEM": 9,
+    "B-JOB": 7,
+    "B-MAP": 5,
+    "B-MECHANIC": 19,
+    "B-MISC": 31,
+    "B-MOB": 3,
+    "B-NPC": 23,
+    "B-QUEST": 11,
+    "B-SALE_ITEM": 15,
+    "B-SKILL": 27,
+    "B-UPDATE": 29,
+    "I-BOSS": 2,
+    "I-CHANNEL": 14,
+    "I-EVENT": 18,
+    "I-FEATURE": 22,
+    "I-GAME": 26,
+    "I-INGAME_ITEM": 10,
+    "I-JOB": 8,
+    "I-MAP": 6,
+    "I-MECHANIC": 20,
+    "I-MISC": 32,
+    "I-MOB": 4,
+    "I-NPC": 24,
+    "I-QUEST": 12,
+    "I-SALE_ITEM": 16,
+    "I-SKILL": 28,
+    "I-UPDATE": 30,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "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 sha256:73c91e2f0cfb91630156ce84797ce9ccd5c3b7f17f664889e25869c6dba9744b
+size 1330300772

runs/May15_22-10-48_standardnc24adsa100v4al/events.out.tfevents.1715811055.standardnc24adsa100v4al.4736.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e669849b378ebb81cbb9ab4aa3fa691c691ed025848dc3b22ebe1cfd95ef43a5
+size 13243

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 +1,55 @@
+{
+  "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_lower_case": 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:cfed33b965166d0c266fb1624dc44220985e8d5c6a37e22f15ecf3c97dc86f8a
+size 4527