add model

README.md

@@ -0,0 +1,64 @@
+---
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+
+model-index:
+- name: distilbert-base-multilingual-cased-finetuned-conll2003-ner
+---
+
+<!-- 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-multilingual-cased-finetuned-conll2003-ner
+
+This model was trained from scratch on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0635
+- Precision: 0.9269
+- Recall: 0.9337
+- F1: 0.9303
+- Accuracy: 0.9835
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2338        | 1.0   | 878  | 0.0753          | 0.9188    | 0.9089 | 0.9138 | 0.9795   |
+| 0.0541        | 2.0   | 1756 | 0.0681          | 0.9362    | 0.9278 | 0.9320 | 0.9830   |
+| 0.031         | 3.0   | 2634 | 0.0635          | 0.9269    | 0.9337 | 0.9303 | 0.9835   |
+
+
+### Framework versions
+
+- Transformers 4.6.1
+- Pytorch 1.8.1+cu101
+- Datasets 1.6.2
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.6.1",
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790c1d8f79c4a1b09b3836462f3be2a7a741284977d99a353812d499693d61c7
+size 539006405

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": false, "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-multilingual-cased"}