add model

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+tags:
+- token-classification
+datasets:
+- wikiann-conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+
+model-index:
+- name: distilroberta-base-ner-wikiann-conll2003-3-class
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wikiann-conll2003
+      type: wikiann-conll2003
+    metrics:
+      - name: Precision
+        type: precision
+        value: 0.9624757386241104
+      - name: Recall
+        type: recall
+        value: 0.9667497021553124
+      - name: F1
+        type: f1
+        value: 0.964607986167396
+      - name: Accuracy
+        type: accuracy
+        value: 0.9913626461292995
+---
+
+<!-- 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. -->
+
+# distilroberta-base-ner-wikiann-conll2003-3-class
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the wikiann-conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0520
+- Precision: 0.9625
+- Recall: 0.9667
+- F1: 0.9646
+- Accuracy: 0.9914
+
+## 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: 4.9086903597787154e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.6.1
+- Pytorch 1.8.1+cu101
+- Datasets 1.6.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04fe971151b3871aafe85511a85565218715f90c7c1e209861edae0a8aecc826
+size 326181207

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base"}