End of training

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: kor-naver-ner-name-v2.1
+  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. -->
+
+# kor-naver-ner-name-v2.1
+
+This model was trained from scratch 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: 5e-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: 3.0
+
+### Framework versions
+
+- Transformers 4.32.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "/home/evidnet/work/joon09/transformers-pytorch/finetune/ckpt/kor-bert-for-name-ner-ckpt/checkpoint-3",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "embedding_size": 768,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "PER-B",
+    "2": "PER-I",
+    "3": "FLD-B",
+    "4": "FLD-I",
+    "5": "AFW-B",
+    "6": "AFW-I",
+    "7": "ORG-B",
+    "8": "ORG-I",
+    "9": "LOC-B",
+    "10": "LOC-I",
+    "11": "CVL-B",
+    "12": "CVL-I",
+    "13": "DAT-B",
+    "14": "DAT-I",
+    "15": "TIM-B",
+    "16": "TIM-I",
+    "17": "NUM-B",
+    "18": "NUM-I",
+    "19": "EVT-B",
+    "20": "EVT-I",
+    "21": "ANM-B",
+    "22": "ANM-I",
+    "23": "PLT-B",
+    "24": "PLT-I",
+    "25": "MAT-B",
+    "26": "MAT-I",
+    "27": "TRM-B",
+    "28": "TRM-I"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AFW-B": 5,
+    "AFW-I": 6,
+    "ANM-B": 21,
+    "ANM-I": 22,
+    "CVL-B": 11,
+    "CVL-I": 12,
+    "DAT-B": 13,
+    "DAT-I": 14,
+    "EVT-B": 19,
+    "EVT-I": 20,
+    "FLD-B": 3,
+    "FLD-I": 4,
+    "LOC-B": 9,
+    "LOC-I": 10,
+    "MAT-B": 25,
+    "MAT-I": 26,
+    "NUM-B": 17,
+    "NUM-I": 18,
+    "O": 0,
+    "ORG-B": 7,
+    "ORG-I": 8,
+    "PER-B": 1,
+    "PER-I": 2,
+    "PLT-B": 23,
+    "PLT-I": 24,
+    "TIM-B": 15,
+    "TIM-I": 16,
+    "TRM-B": 27,
+    "TRM-I": 28
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": "4.32.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 42000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c5ff4b7dee6a8a228249fe412344b268ff1d95d720fc4cb1be84fd9cc45bc2
+size 470983913

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 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "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 sha256:68b4c138c59b3c4259e983f53d1bd3e90fef6e0226229080f964b3baf7a56808
+size 4091