Add model

README.md

@@ -0,0 +1,73 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: Ernie-3.0-base-chinese-finetuned-ner
+  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. -->
+
+# Ernie-3.0-base-chinese-finetuned-ner
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3548
+- Precision: 0.6193
+- Recall: 0.7467
+- F1: 0.6771
+- Accuracy: 0.9069
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3645        | 1.0   | 126  | 0.3654          | 0.5452    | 0.6712 | 0.6017 | 0.8951   |
+| 0.2821        | 2.0   | 252  | 0.3639          | 0.5748    | 0.7127 | 0.6364 | 0.8961   |
+| 0.2378        | 3.0   | 378  | 0.3561          | 0.5801    | 0.7263 | 0.6451 | 0.8991   |
+| 0.217         | 4.0   | 504  | 0.3531          | 0.6027    | 0.7397 | 0.6642 | 0.9030   |
+| 0.2083        | 5.0   | 630  | 0.3640          | 0.5991    | 0.7435 | 0.6635 | 0.8999   |
+| 0.1956        | 6.0   | 756  | 0.3488          | 0.6218    | 0.7299 | 0.6715 | 0.9064   |
+| 0.18          | 7.0   | 882  | 0.3457          | 0.6207    | 0.7442 | 0.6769 | 0.9072   |
+| 0.1696        | 8.0   | 1008 | 0.3543          | 0.6191    | 0.7460 | 0.6766 | 0.9061   |
+| 0.1618        | 9.0   | 1134 | 0.3548          | 0.6193    | 0.7467 | 0.6771 | 0.9069   |
+| 0.1568        | 10.0  | 1260 | 0.3553          | 0.6180    | 0.7462 | 0.6761 | 0.9063   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[UNK]": 39979
+}

config.json

@@ -0,0 +1,89 @@
+{
+  "_name_or_path": "Ernie-3.0-base-chinese-finetuned-ner",
+  "architectures": [
+    "ErnieForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-position",
+    "2": "I-position",
+    "3": "B-name",
+    "4": "I-name",
+    "5": "B-movie",
+    "6": "I-movie",
+    "7": "B-organization",
+    "8": "I-organization",
+    "9": "B-company",
+    "10": "I-company",
+    "11": "B-book",
+    "12": "I-book",
+    "13": "B-address",
+    "14": "I-address",
+    "15": "B-scene",
+    "16": "I-scene",
+    "17": "B-mobile",
+    "18": "I-mobile",
+    "19": "B-email",
+    "20": "I-email",
+    "21": "B-game",
+    "22": "I-game",
+    "23": "B-government",
+    "24": "I-government",
+    "25": "B-QQ",
+    "26": "I-QQ",
+    "27": "B-vx",
+    "28": "I-vx"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-QQ": 25,
+    "B-address": 13,
+    "B-book": 11,
+    "B-company": 9,
+    "B-email": 19,
+    "B-game": 21,
+    "B-government": 23,
+    "B-mobile": 17,
+    "B-movie": 5,
+    "B-name": 3,
+    "B-organization": 7,
+    "B-position": 1,
+    "B-scene": 15,
+    "B-vx": 27,
+    "I-QQ": 26,
+    "I-address": 14,
+    "I-book": 12,
+    "I-company": 10,
+    "I-email": 20,
+    "I-game": 22,
+    "I-government": 24,
+    "I-mobile": 18,
+    "I-movie": 6,
+    "I-name": 4,
+    "I-organization": 8,
+    "I-position": 2,
+    "I-scene": 16,
+    "I-vx": 28,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "ernie",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task_type_vocab_size": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 4,
+  "use_cache": true,
+  "use_task_id": true,
+  "vocab_size": 40000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f91d99026ad7954852a1bf8906f5684f148bbc78e529fa615cf3bd2d48adf68
+size 469529812

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39979": {
+      "content": "[UNK]",
+      "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": true,
+  "ignore_mismatched_sizes": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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:ee9bbc5e1c4471260f7c6f5e9be8823e910dec16b7f30b6aae9835e038263833
+size 4600