update model card README.md

README.md

@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2036
-- Precision: 0.6420
-- Recall: 0.6613
-- F1: 0.6515
-- Accuracy: 0.9421
+- Loss: 0.1592
+- Precision: 0.7852
+- Recall: 0.8012
+- F1: 0.7931
+- Accuracy: 0.9701
 
 ## Model description
 
@@ -42,21 +42,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
+- learning_rate: 8e-05
+- train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 261  | 0.2696          | 0.5284    | 0.5958 | 0.5601 | 0.9222   |
-| 0.2809        | 2.0   | 522  | 0.2086          | 0.6354    | 0.6464 | 0.6408 | 0.9399   |
-| 0.2809        | 3.0   | 783  | 0.2036          | 0.6420    | 0.6613 | 0.6515 | 0.9421   |
+| No log        | 1.0   | 131  | 0.1607          | 0.6254    | 0.6801 | 0.6516 | 0.9538   |
+| No log        | 2.0   | 262  | 0.1188          | 0.7437    | 0.7695 | 0.7564 | 0.9670   |
+| No log        | 3.0   | 393  | 0.1264          | 0.7556    | 0.7750 | 0.7652 | 0.9675   |
+| 0.0923        | 4.0   | 524  | 0.1344          | 0.7622    | 0.7858 | 0.7738 | 0.9680   |
+| 0.0923        | 5.0   | 655  | 0.1442          | 0.7741    | 0.7835 | 0.7788 | 0.9694   |
+| 0.0923        | 6.0   | 786  | 0.1501          | 0.7892    | 0.8104 | 0.7997 | 0.9703   |
+| 0.0923        | 7.0   | 917  | 0.1584          | 0.7750    | 0.7964 | 0.7856 | 0.9694   |
+| 0.0133        | 8.0   | 1048 | 0.1592          | 0.7852    | 0.8012 | 0.7931 | 0.9701   |
 
 
 ### Framework versions