Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.5067114093959731
+      value: 0.44208809135399674
     - name: Recall
       type: recall
-      value: 0.2798887859128823
+      value: 0.2511584800741427
     - name: F1
       type: f1
-      value: 0.36059701492537316
+      value: 0.32033096926713944
     - name: Accuracy
       type: accuracy
-      value: 0.9394638963703988
+      value: 0.938480612201274
 ---
 
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0770
-- Precision: 0.5067
-- Recall: 0.2799
-- F1: 0.3606
-- Accuracy: 0.9395
+- Loss: 0.0759
+- Precision: 0.4421
+- Recall: 0.2512
+- F1: 0.3203
+- Accuracy: 0.9385
 
 ## Model description
 
@@ -79,8 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 213  | 0.0859          | 0.4361    | 0.1297 | 0.2000 | 0.9336   |
-| No log        | 2.0   | 426  | 0.0770          | 0.5067    | 0.2799 | 0.3606 | 0.9395   |
+| No log        | 1.0   | 213  | 0.0822          | 0.4343    | 0.1501 | 0.2231 | 0.9341   |
+| No log        | 2.0   | 426  | 0.0759          | 0.4421    | 0.2512 | 0.3203 | 0.9385   |
 
 
 ### Framework versions