Upload 8 files

README.md

@@ -1,19 +1,91 @@
 ---
-title: AutoTrain Advanced
-emoji: 🚀
-colorFrom: blue
-colorTo: green
-sdk: docker
-pinned: false
-hf_oauth: true
-hf_oauth_expiration_minutes: 36000
-hf_oauth_scopes:
-- read-repos
-- write-repos
-- manage-repos
-- inference-api
-- read-billing
-license: mit
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: dark-bert-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: train
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.928300642821823
+    - name: Recall
+      type: recall
+      value: 0.9478290138000673
+    - name: F1
+      type: f1
+      value: 0.9379631942709634
+    - name: Accuracy
+      type: accuracy
+      value: 0.9859009831047272
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<!-- 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. -->
+
+# dark-bert-finetuned-ner
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0639
+- Precision: 0.9283
+- Recall: 0.9478
+- F1: 0.9380
+- Accuracy: 0.9859
+
+## 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
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0881        | 1.0   | 1756 | 0.0716          | 0.9172    | 0.9322 | 0.9246 | 0.9817   |
+| 0.0375        | 2.0   | 3512 | 0.0610          | 0.9275    | 0.9455 | 0.9364 | 0.9857   |
+| 0.0207        | 3.0   | 5268 | 0.0639          | 0.9283    | 0.9478 | 0.9380 | 0.9859   |
+
+
+### Framework versions
+
+- Transformers 4.22.1
+- Pytorch 1.10.0
+- Datasets 2.5.1
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81344e728f5a18bf527fc1c141e71c6554ae790d2c2fc5e068fee0713ac1e19
+size 134

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ea86c3e8509c5fef6d6b91a39c5f8e73fb0cc9bca85d28f63529a95d83a912
+size 129