End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.5451327433628319
+      value: 0.5588235294117647
     - name: Recall
       type: recall
-      value: 0.28544949026876737
+      value: 0.3169601482854495
     - name: F1
       type: f1
-      value: 0.3746958637469586
+      value: 0.40449438202247195
     - name: Accuracy
       type: accuracy
-      value: 0.9414732161942627
+      value: 0.9422854944209311
 ---
 
 <!-- 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: 0.2722
-- Precision: 0.5451
-- Recall: 0.2854
-- F1: 0.3747
-- Accuracy: 0.9415
+- Loss: 0.2684
+- Precision: 0.5588
+- Recall: 0.3170
+- F1: 0.4045
+- Accuracy: 0.9423
 
 ## 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  | 0.2842          | 0.4646    | 0.2252 | 0.3034 | 0.9376   |
-| No log        | 2.0   | 426  | 0.2722          | 0.5451    | 0.2854 | 0.3747 | 0.9415   |
+| No log        | 1.0   | 213  | 0.2770          | 0.4932    | 0.2335 | 0.3170 | 0.9380   |
+| No log        | 2.0   | 426  | 0.2684          | 0.5588    | 0.3170 | 0.4045 | 0.9423   |
 
 
 ### Framework versions