update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1079
-- Precision: 0.9141
-- Recall: 0.9076
-- F1: 0.9109
-- Accuracy: 0.9652
+- Loss: 0.0999
+- Precision: 0.9203
+- Recall: 0.9141
+- F1: 0.9172
+- Accuracy: 0.9672
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 20
-- eval_batch_size: 20
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1584        | 1.0   | 8806  | 0.1524          | 0.8780    | 0.8698 | 0.8739 | 0.9499   |
-| 0.1149        | 2.0   | 17612 | 0.1217          | 0.9032    | 0.8961 | 0.8996 | 0.9606   |
-| 0.0925        | 3.0   | 26418 | 0.1079          | 0.9141    | 0.9076 | 0.9109 | 0.9652   |
+| 0.1412        | 1.0   | 17611 | 0.1358          | 0.8961    | 0.8834 | 0.8897 | 0.9555   |
+| 0.1024        | 2.0   | 35222 | 0.1076          | 0.9133    | 0.9076 | 0.9104 | 0.9641   |
+| 0.076         | 3.0   | 52833 | 0.0999          | 0.9203    | 0.9141 | 0.9172 | 0.9672   |
 
 
 ### Framework versions