add model

.gitignore

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

README.md

@@ -0,0 +1,79 @@
+---
+license: cc-by-4.0
+tags:
+- generated_from_trainer
+datasets:
+- null
+model-index:
+- name: nbailab-base-ner-scandi-unbalanced
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+---
+
+<!-- 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. -->
+
+# nbailab-base-ner-scandi-unbalanced
+
+This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0666
+- Micro F1: 0.8693
+- Micro F1 No Misc: 0.8925
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 90135.90000000001
+- num_epochs: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Micro F1 | Micro F1 No Misc |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------------:|
+| 0.6682        | 1.0   | 2816  | 0.0872          | 0.6916   | 0.7306           |
+| 0.0684        | 2.0   | 5632  | 0.0464          | 0.8167   | 0.8538           |
+| 0.0444        | 3.0   | 8448  | 0.0367          | 0.8485   | 0.8783           |
+| 0.0349        | 4.0   | 11264 | 0.0316          | 0.8684   | 0.8920           |
+| 0.0282        | 5.0   | 14080 | 0.0290          | 0.8820   | 0.9033           |
+| 0.0231        | 6.0   | 16896 | 0.0283          | 0.8854   | 0.9060           |
+| 0.0189        | 7.0   | 19712 | 0.0253          | 0.8964   | 0.9156           |
+| 0.0155        | 8.0   | 22528 | 0.0260          | 0.9016   | 0.9201           |
+| 0.0123        | 9.0   | 25344 | 0.0266          | 0.9059   | 0.9233           |
+| 0.0098        | 10.0  | 28160 | 0.0280          | 0.9091   | 0.9279           |
+| 0.008         | 11.0  | 30976 | 0.0309          | 0.9093   | 0.9287           |
+| 0.0065        | 12.0  | 33792 | 0.0313          | 0.9103   | 0.9284           |
+| 0.0053        | 13.0  | 36608 | 0.0322          | 0.9078   | 0.9257           |
+| 0.0046        | 14.0  | 39424 | 0.0343          | 0.9075   | 0.9256           |
+
+
+### Framework versions
+
+- Transformers 4.10.3
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "NbAiLab/nb-bert-base",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "I-LOC",
+    "2": "B-ORG",
+    "3": "I-ORG",
+    "4": "B-PER",
+    "5": "I-PER",
+    "6": "B-MISC",
+    "7": "I-MISC",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-MISC": 6,
+    "B-ORG": 2,
+    "B-PER": 4,
+    "I-LOC": 1,
+    "I-MISC": 7,
+    "I-ORG": 3,
+    "I-PER": 5,
+    "O": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": "4.10.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6431f1d8fa2383bef0a83ea660dec09fd15dbfb9766a6cc16347d5df42451bb
+size 709162481

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, "special_tokens_map_file": null, "name_or_path": "NbAiLab/nb-bert-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db68c7bf76cfd21c0f70c0ed31dbc2277bf061d0bf39ff2967bf2bc6d8d7dbe
+size 2671