End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.867180490309176
+      value: 0.8735358948028765
     - name: Accuracy
       type: accuracy
-      value: 0.8532342509711197
+      value: 0.8549231548724877
     - name: Precision
       type: precision
-      value: 0.8696655508234792
+      value: 0.8764387775530592
     - name: Recall
       type: recall
-      value: 0.8656878738444806
+      value: 0.870763095885445
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,12 +45,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mateiaassAI/teacher_ag-news](https://huggingface.co/mateiaassAI/teacher_ag-news) on the moroco dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0973
-- F1: 0.8672
+- Loss: 0.0951
+- F1: 0.8735
 - Roc Auc: None
-- Accuracy: 0.8532
-- Precision: 0.8697
-- Recall: 0.8657
+- Accuracy: 0.8549
+- Precision: 0.8764
+- Recall: 0.8708
 
 ## Model description
 
@@ -75,15 +75,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:---------:|:------:|
-| 0.1162        | 1.0   | 1358 | 0.0977          | 0.8660 | None    | 0.8537   | 0.8786    | 0.8559 |
-| 0.0803        | 2.0   | 2716 | 0.0955          | 0.8687 | None    | 0.8588   | 0.8777    | 0.8608 |
-| 0.0561        | 3.0   | 4074 | 0.0973          | 0.8672 | None    | 0.8532   | 0.8697    | 0.8657 |
+| 0.1163        | 1.0   | 1358 | 0.0982          | 0.8669 | None    | 0.8505   | 0.8830    | 0.8523 |
+| 0.0812        | 2.0   | 2716 | 0.0951          | 0.8735 | None    | 0.8549   | 0.8764    | 0.8708 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ef65f4b342d695aff8bce62c47f49566aec32a172064ffda87f5a5b19b2123
+oid sha256:7fdbe8c74ff72534814c3eedf3915735265b0b59bc8ba6dfe932859d4b27a6a0
 size 497807376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5566eb6cbf0abd7ce5611e31734b2c80ce984cbc68d8352154f6c544ad81ec39
+oid sha256:69b8b1fd70458e9d57dafacefe93818cff1ba35ee5c12c7c0fb9939f15ec8777
 size 5240