End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.5426356589147286
+      value: 0.5762987012987013
     - name: Recall
       type: recall
-      value: 0.38924930491195553
+      value: 0.3290083410565338
     - name: F1
       type: f1
-      value: 0.4533189422558014
+      value: 0.4188790560471976
     - name: Accuracy
       type: accuracy
-      value: 0.9463896370398871
+      value: 0.9424992518490017
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ 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: 0.2586
-- Precision: 0.5426
-- Recall: 0.3892
-- F1: 0.4533
-- Accuracy: 0.9464
+- Loss: 0.2703
+- Precision: 0.5763
+- Recall: 0.3290
+- F1: 0.4189
+- Accuracy: 0.9425
 
 ## Model description
 
@@ -80,13 +80,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 213  | 0.2486          | 0.4843    | 0.4004 | 0.4384 | 0.9443   |
-| No log        | 2.0   | 426  | 0.2586          | 0.5426    | 0.3892 | 0.4533 | 0.9464   |
+| No log        | 1.0   | 213  | 0.2797          | 0.5139    | 0.2567 | 0.3424 | 0.9385   |
+| No log        | 2.0   | 426  | 0.2703          | 0.5763    | 0.3290 | 0.4189 | 0.9425   |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
 - Tokenizers 0.19.1

runs/Sep19_23-48-38_1de0d8f41bd7/events.out.tfevents.1726789719.1de0d8f41bd7.677.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e62f53c5c90bc4e617e9da59b9b2bfc7d0cf17172a0c72124af5d9400d2f91
-size 5882
+oid sha256:f687a6ed269d2fe6e27d8e2f3b81a68601bf4fe5590a02502d81ca59ca568e8b
+size 6708