End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-cased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -20,21 +20,21 @@ model-index:
       name: ner
       type: ner
       config: indian_names
-      split: test
+      split: train
       args: indian_names
     metrics:
     - name: Precision
       type: precision
-      value: 0.9779481031086752
+      value: 0.982625089167431
     - name: Recall
       type: recall
-      value: 0.950199700449326
+      value: 0.9665213251140179
     - name: F1
       type: f1
-      value: 0.96387423507069
+      value: 0.9745066828368578
     - name: Accuracy
       type: accuracy
-      value: 0.977337411889879
+      value: 0.9865003101950782
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Bert-NER
 
-This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the ner dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0518
-- Precision: 0.9779
-- Recall: 0.9502
-- F1: 0.9639
-- Accuracy: 0.9773
+- Loss: 0.0404
+- Precision: 0.9826
+- Recall: 0.9665
+- F1: 0.9745
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -67,7 +67,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -79,11 +79,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 438  | 0.0725          | 0.9691    | 0.9325 | 0.9505 | 0.9693   |
-| 0.0435        | 2.0   | 876  | 0.0635          | 0.9687    | 0.9392 | 0.9537 | 0.9711   |
-| 0.039         | 3.0   | 1314 | 0.0569          | 0.9790    | 0.9416 | 0.9599 | 0.9751   |
-| 0.0392        | 4.0   | 1752 | 0.0542          | 0.9744    | 0.9490 | 0.9615 | 0.9758   |
-| 0.0378        | 5.0   | 2190 | 0.0518          | 0.9779    | 0.9502 | 0.9639 | 0.9773   |
+| No log        | 1.0   | 469  | 0.0541          | 0.9760    | 0.9580 | 0.9669 | 0.9826   |
+| 0.0887        | 2.0   | 938  | 0.0503          | 0.9767    | 0.9620 | 0.9693 | 0.9839   |
+| 0.0519        | 3.0   | 1407 | 0.0464          | 0.9799    | 0.9627 | 0.9712 | 0.9849   |
+| 0.0467        | 4.0   | 1876 | 0.0430          | 0.9806    | 0.9652 | 0.9728 | 0.9856   |
+| 0.0427        | 5.0   | 2345 | 0.0404          | 0.9826    | 0.9665 | 0.9745 | 0.9865   |
 
 
 ### Framework versions
@@ -91,4 +91,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.14.0
+- Tokenizers 0.14.1