End of training

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: RoBERTa-ext-large-crf-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. -->
+
+# RoBERTa-ext-large-crf-chinese-finetuned-ner
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 93.6921
+- eval_precision: 0.6788
+- eval_recall: 0.7538
+- eval_f1: 0.7143
+- eval_accuracy: 0.9634
+- eval_runtime: 23.7231
+- eval_samples_per_second: 21.203
+- eval_steps_per_second: 2.656
+- step: 0
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,96 @@
+{
+  "_name_or_path": "./RoBERTa-ext-large-chinese-finetuned-ner",
+  "architectures": [
+    "BertCrfForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "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": 4096,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": "4.35.2",
+  "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 sha256:74054eb7525f1811fa4d9eb645e99008be1db9a50cf9a058f271ef4bbf641458
+size 1298060872

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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "ignore_mismatched_sizes": true,
+  "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 sha256:1dca0bbb1c7d575f8c093b1d4826a8230a7cb1937f36a0f5b4f0536003486723
+size 4600