add model

.gitignore

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

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-base-uncased-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9281908990011098
+    - name: Recall
+      type: recall
+      value: 0.9355632621098557
+    - name: F1
+      type: f1
+      value: 0.9318624993035824
+    - name: Accuracy
+      type: accuracy
+      value: 0.9837641190207635
+---
+
+<!-- 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. -->
+
+# distilbert-base-uncased-finetuned-ner
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0629
+- Precision: 0.9282
+- Recall: 0.9356
+- F1: 0.9319
+- Accuracy: 0.9838
+
+## 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: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2406        | 1.0   | 878  | 0.0721          | 0.9072    | 0.9172 | 0.9122 | 0.9801   |
+| 0.0529        | 2.0   | 1756 | 0.0637          | 0.9166    | 0.9318 | 0.9241 | 0.9826   |
+| 0.0315        | 3.0   | 2634 | 0.0629          | 0.9282    | 0.9356 | 0.9319 | 0.9838   |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153bea2aec0f28bd17a045d2fcc0a485e24723a758932230f958e3a98076d1c2
+size 265518581

runs/Sep22_10-15-33_949ab5c64c25/1632305750.6199079/events.out.tfevents.1632305750.949ab5c64c25.77.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e40f1d3731272a755b986d72d0b989e1077fea23631bf811c53a4c0ca7736b3
+size 4198

runs/Sep22_10-15-33_949ab5c64c25/events.out.tfevents.1632305750.949ab5c64c25.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3935298ebd27d6ef0230411c690e0af10b3eb48dbac9fbc44850930b1e1e1fa7
+size 5784

runs/Sep22_10-15-33_949ab5c64c25/events.out.tfevents.1632306283.949ab5c64c25.77.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38835ec30a006f4580556daf0b0dfa86461741894ef4d9a8da7d9f07fe6ea08a
+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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b67db46f7252303176ba0940ef7f3705b4f4eaf00ab074712f6ef2e99ab9dd
+size 2671