update model card README.md

README.md

@@ -19,21 +19,21 @@ model-index:
       name: conll2003
       type: conll2003
       config: conll2003
-      split: train
+      split: validation
       args: conll2003
     metrics:
     - name: Precision
       type: precision
-      value: 0.9280336581045173
+      value: 0.9139204232337705
     - name: Recall
       type: recall
-      value: 0.9376887795055375
+      value: 0.9276205392102025
     - name: F1
       type: f1
-      value: 0.9328362361582551
+      value: 0.9207195203197868
     - name: Accuracy
       type: accuracy
-      value: 0.9842248240583348
+      value: 0.9817306623032075
 ---
 
 <!-- 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: 0.0593
-- Precision: 0.9280
-- Recall: 0.9377
-- F1: 0.9328
-- Accuracy: 0.9842
+- Loss: 0.0662
+- Precision: 0.9139
+- Recall: 0.9276
+- F1: 0.9207
+- Accuracy: 0.9817
 
 ## 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: 48
+- eval_batch_size: 48
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2474        | 1.0   | 878  | 0.0695          | 0.9205    | 0.9268 | 0.9236 | 0.9818   |
-| 0.0538        | 2.0   | 1756 | 0.0585          | 0.9266    | 0.9348 | 0.9307 | 0.9838   |
-| 0.0297        | 3.0   | 2634 | 0.0593          | 0.9280    | 0.9377 | 0.9328 | 0.9842   |
+| No log        | 1.0   | 293  | 0.0861          | 0.8786    | 0.9014 | 0.8899 | 0.9765   |
+| 0.1963        | 2.0   | 586  | 0.0682          | 0.9031    | 0.9218 | 0.9124 | 0.9805   |
+| 0.1963        | 3.0   | 879  | 0.0662          | 0.9139    | 0.9276 | 0.9207 | 0.9817   |
 
 
 ### Framework versions
 
-- Transformers 4.24.0
-- Pytorch 1.12.1
-- Datasets 2.9.0
+- Transformers 4.26.1
+- Pytorch 1.12.0
+- Datasets 2.10.1
 - Tokenizers 0.11.0