End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.539708265802269
+      value: 0.5676100628930818
     - name: Recall
       type: recall
-      value: 0.3086190917516219
+      value: 0.3345690454124189
     - name: F1
       type: f1
-      value: 0.392688679245283
+      value: 0.4209912536443149
     - name: Accuracy
       type: accuracy
-      value: 0.9407464409388226
+      value: 0.9413449617374203
 ---
 
 <!-- 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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2868
-- Precision: 0.5397
-- Recall: 0.3086
-- F1: 0.3927
-- Accuracy: 0.9407
+- Loss: 0.2739
+- Precision: 0.5676
+- Recall: 0.3346
+- F1: 0.4210
+- Accuracy: 0.9413
 
 ## Model description
 
@@ -79,13 +79,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 213  | 0.3043          | 0.5144    | 0.2484 | 0.335  | 0.9381   |
-| No log        | 2.0   | 426  | 0.2868          | 0.5397    | 0.3086 | 0.3927 | 0.9407   |
+| No log        | 1.0   | 213  | 0.2898          | 0.6165    | 0.2697 | 0.3752 | 0.9388   |
+| No log        | 2.0   | 426  | 0.2739          | 0.5676    | 0.3346 | 0.4210 | 0.9413   |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.3.0+cpu
+- Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1