RachelCX/ner_for_GJ

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: hfl/chinese-bert-wwm-ext
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ner_model_output
+  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. -->
+
+# ner_model_output
+
+This model is a fine-tuned version of [hfl/chinese-bert-wwm-ext](https://huggingface.co/hfl/chinese-bert-wwm-ext) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3016
+- Precision: 0.9999
+- Recall: 0.9999
+- F1: 0.9999
+- Accuracy: 1.0000
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3028        | 1.0   | 3900  | 0.3021          | 0.9999    | 0.9999 | 0.9999 | 1.0000   |
+| 0.3019        | 2.0   | 7800  | 0.3019          | 0.9999    | 0.9999 | 0.9999 | 1.0000   |
+| 0.3045        | 3.0   | 11700 | 0.3017          | 0.9999    | 0.9999 | 0.9999 | 1.0000   |
+| 0.3033        | 4.0   | 15600 | 0.3022          | 0.9998    | 0.9998 | 0.9998 | 0.9999   |
+| 0.3026        | 5.0   | 19500 | 0.3016          | 0.9999    | 0.9999 | 0.9999 | 1.0000   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "BertForNER"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-\u4e1a\u52a1\u7c7b\u578b",
+    "1": "B-\u4fe1\u606f\u7c7b\u578b",
+    "2": "B-\u533a\u57df\u7c7b\u578b",
+    "3": "B-\u5ba2\u6237\u7c7b\u578b",
+    "4": "B-\u6570\u503c\u7c7b\u578b",
+    "5": "B-\u65f6\u95f4\u7c7b\u578b",
+    "6": "B-\u6761\u4ef6\u7c7b\u578b",
+    "7": "B-\u72b6\u6001\u7c7b\u578b",
+    "8": "I-\u4e1a\u52a1\u7c7b\u578b",
+    "9": "I-\u4fe1\u606f\u7c7b\u578b",
+    "10": "I-\u533a\u57df\u7c7b\u578b",
+    "11": "I-\u5ba2\u6237\u7c7b\u578b",
+    "12": "I-\u6570\u503c\u7c7b\u578b",
+    "13": "I-\u65f6\u95f4\u7c7b\u578b",
+    "14": "I-\u6761\u4ef6\u7c7b\u578b",
+    "15": "I-\u72b6\u6001\u7c7b\u578b",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-\u4e1a\u52a1\u7c7b\u578b": 0,
+    "B-\u4fe1\u606f\u7c7b\u578b": 1,
+    "B-\u533a\u57df\u7c7b\u578b": 2,
+    "B-\u5ba2\u6237\u7c7b\u578b": 3,
+    "B-\u6570\u503c\u7c7b\u578b": 4,
+    "B-\u65f6\u95f4\u7c7b\u578b": 5,
+    "B-\u6761\u4ef6\u7c7b\u578b": 6,
+    "B-\u72b6\u6001\u7c7b\u578b": 7,
+    "I-\u4e1a\u52a1\u7c7b\u578b": 8,
+    "I-\u4fe1\u606f\u7c7b\u578b": 9,
+    "I-\u533a\u57df\u7c7b\u578b": 10,
+    "I-\u5ba2\u6237\u7c7b\u578b": 11,
+    "I-\u6570\u503c\u7c7b\u578b": 12,
+    "I-\u65f6\u95f4\u7c7b\u578b": 13,
+    "I-\u6761\u4ef6\u7c7b\u578b": 14,
+    "I-\u72b6\u6001\u7c7b\u578b": 15,
+    "O": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd5ca7e0bb6253e329076e4fcc15f628c1cb22e2ce2a06b70cdf7ebb0bac3d1
+size 409146380

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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:c8571ccf61a907a390cf7414ed0b6a327e28d027fd3644227804cf561c2b3ec5
+size 5304