update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9278042298748754
+      value: 0.9211136890951276
     - name: Recall
       type: recall
-      value: 0.9373531714956931
+      value: 0.93265465935787
     - name: F1
       type: f1
-      value: 0.9325542570951586
+      value: 0.9268482490272373
     - name: Accuracy
       type: accuracy
-      value: 0.9840818466328817
+      value: 0.9823978902886555
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0614
-- Precision: 0.9278
-- Recall: 0.9374
-- F1: 0.9326
-- Accuracy: 0.9841
+- Loss: 0.0639
+- Precision: 0.9211
+- Recall: 0.9327
+- F1: 0.9268
+- Accuracy: 0.9824
 
 ## Model description
 
@@ -67,8 +67,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -78,14 +78,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2348        | 1.0   | 878  | 0.0676          | 0.9123    | 0.9215 | 0.9169 | 0.9813   |
-| 0.053         | 2.0   | 1756 | 0.0615          | 0.9239    | 0.9334 | 0.9287 | 0.9830   |
-| 0.0296        | 3.0   | 2634 | 0.0614          | 0.9278    | 0.9374 | 0.9326 | 0.9841   |
+| No log        | 1.0   | 439  | 0.0788          | 0.8907    | 0.9098 | 0.9002 | 0.9785   |
+| 0.2157        | 2.0   | 878  | 0.0639          | 0.9130    | 0.9297 | 0.9213 | 0.9813   |
+| 0.0586        | 3.0   | 1317 | 0.0639          | 0.9211    | 0.9327 | 0.9268 | 0.9824   |
 
 
 ### Framework versions
 
 - Transformers 4.26.0
-- Pytorch 1.13.1+cu116
+- Pytorch 1.13.0a0+d321be6
 - Datasets 2.9.0
 - Tokenizers 0.13.2