End of training

README.md

@@ -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: 0.9730806713589605
+      value: 0.9783236696036152
     - name: Recall
       type: recall
-      value: 0.934681311366284
+      value: 0.9577025239110016
     - name: F1
       type: f1
-      value: 0.9534945409402952
+      value: 0.9679032760195776
     - name: Accuracy
       type: accuracy
-      value: 0.9711464290464158
+      value: 0.9800733834122645
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0672
-- Precision: 0.9731
-- Recall: 0.9347
-- F1: 0.9535
-- Accuracy: 0.9711
+- Loss: 0.1222
+- Precision: 0.9783
+- Recall: 0.9577
+- F1: 0.9679
+- Accuracy: 0.9801
 
 ## Model description
 
@@ -67,7 +67,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -79,11 +79,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0791        | 1.0   | 875  | 0.0848          | 0.9613    | 0.9226 | 0.9416 | 0.9643   |
-| 0.0565        | 2.0   | 1750 | 0.0814          | 0.9628    | 0.9272 | 0.9447 | 0.9659   |
-| 0.0519        | 3.0   | 2625 | 0.0794          | 0.9615    | 0.9276 | 0.9442 | 0.9656   |
-| 0.05          | 4.0   | 3500 | 0.0745          | 0.9625    | 0.9315 | 0.9467 | 0.9671   |
-| 0.0451        | 5.0   | 4375 | 0.0672          | 0.9731    | 0.9347 | 0.9535 | 0.9711   |
+| No log        | 1.0   | 438  | 0.1036          | 0.9894    | 0.9413 | 0.9647 | 0.9785   |
+| 0.0608        | 2.0   | 876  | 0.1149          | 0.9875    | 0.9466 | 0.9666 | 0.9795   |
+| 0.0527        | 3.0   | 1314 | 0.1188          | 0.9846    | 0.9470 | 0.9654 | 0.9787   |
+| 0.0413        | 4.0   | 1752 | 0.1200          | 0.9840    | 0.9535 | 0.9685 | 0.9805   |
+| 0.0316        | 5.0   | 2190 | 0.1222          | 0.9783    | 0.9577 | 0.9679 | 0.9801   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a29ce87177eeab73a7261b66306e0817185d85a59bd13d9822f0ba694762de1
+oid sha256:8001ab6ea27c0f225301f44343a1cccccd39681515ee247ff624696c3dffbd94
 size 435646633