add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: ner_conll2003
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      args: conll2003
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9769764744577354
+---
+
+<!-- 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_conll2003
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1551
+- Precision: 0.8966
+- Recall: 0.9065
+- F1: 0.9015
+- Accuracy: 0.9770
+
+## 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: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3068        | 1.0   | 877  | 0.0589          | 0.9200    | 0.9388 | 0.9293 | 0.9837   |
+| 0.0464        | 2.0   | 1754 | 0.0562          | 0.9298    | 0.9453 | 0.9375 | 0.9851   |
+| 0.0233        | 3.0   | 2631 | 0.0559          | 0.9408    | 0.9472 | 0.9440 | 0.9865   |
+| 0.0116        | 4.0   | 3508 | 0.0581          | 0.9421    | 0.9523 | 0.9472 | 0.9871   |
+| 0.0068        | 5.0   | 4385 | 0.0620          | 0.9439    | 0.9521 | 0.9480 | 0.9871   |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78429ee037a29820396fdfee6e6b08ffdf193e4741e93821887d6b45c9fdbe4f
+size 435677681

runs/Aug05_22-33-12_ip-172-31-23-147/1628202798.1075165/events.out.tfevents.1628202798.ip-172-31-23-147.6522.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13845b6a4d3d7f64e44696d4552b5f7895840f6a309b83ba39614e5135bd87bf
+size 4235

runs/Aug05_22-33-12_ip-172-31-23-147/events.out.tfevents.1628202798.ip-172-31-23-147.6522.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b5a9fa13a8d6a2bbb466ce09499fef775025a03dd620ed298ebd505385045f
+size 6801

runs/Aug05_22-33-12_ip-172-31-23-147/events.out.tfevents.1628203219.ip-172-31-23-147.6522.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafcbf1906c9f78efe314230f8c9aad7a4be3a3afd244e95311663a9faf6d65a
+size 512

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b05606cc4a361f1fa02aa2237857db792bd5d06103cb09f435c5567d586513
+size 2671