NER Training complete

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: bert-large-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-lg-cased-ms-ner-v3-test
+  results: []
+---
+
+<!-- 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. -->
+
+# bert-lg-cased-ms-ner-v3-test
+
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1288
+- Precision: 0.8909
+- Recall: 0.9094
+- F1: 0.9001
+- Accuracy: 0.9804
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1394        | 1.0   | 3615  | 0.1234          | 0.8374    | 0.8269 | 0.8321 | 0.9695   |
+| 0.0736        | 2.0   | 7230  | 0.1110          | 0.8618    | 0.8742 | 0.8679 | 0.9756   |
+| 0.0385        | 3.0   | 10845 | 0.1019          | 0.8844    | 0.8968 | 0.8906 | 0.9787   |
+| 0.019         | 4.0   | 14460 | 0.1193          | 0.8859    | 0.9048 | 0.8953 | 0.9798   |
+| 0.0094        | 5.0   | 18075 | 0.1288          | 0.8909    | 0.9094 | 0.9001 | 0.9804   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 1.12.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2