Model save

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.68
+      value: 0.71
     - name: Precision
       type: precision
-      value: 0.7035278154681139
+      value: 0.7228353140916808
     - name: Recall
       type: recall
-      value: 0.6799999999999999
+      value: 0.71
     - name: F1
       type: f1
-      value: 0.6704767789105138
+      value: 0.705762987012987
 ---
 
 <!-- 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 [MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli](https://huggingface.co/MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli) on the sem_eval_2024_task_2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5648
-- Accuracy: 0.68
-- Precision: 0.7035
-- Recall: 0.6800
-- F1: 0.6705
+- Loss: 0.6038
+- Accuracy: 0.71
+- Precision: 0.7228
+- Recall: 0.71
+- F1: 0.7058
 
 ## Model description
 
@@ -74,17 +74,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.7089        | 1.0   | 107  | 0.6638          | 0.635    | 0.6373    | 0.635  | 0.6335 |
-| 0.6762        | 2.0   | 214  | 0.6057          | 0.675    | 0.6831    | 0.675  | 0.6714 |
-| 0.69          | 3.0   | 321  | 0.6047          | 0.695    | 0.7059    | 0.6950 | 0.6909 |
-| 0.6251        | 4.0   | 428  | 0.5648          | 0.68     | 0.7035    | 0.6800 | 0.6705 |
+| 0.6794        | 1.0   | 107  | 0.6548          | 0.595    | 0.5978    | 0.595  | 0.5921 |
+| 0.6734        | 2.0   | 214  | 0.6038          | 0.71     | 0.7228    | 0.71   | 0.7058 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645e9df632419e44b1e6141cbd7e779a57a2f94fa58709e33d2d59f6a9452f9a
+oid sha256:ef0ebb4c50a5f0bf2905029c84ebf3527ac6f2f7f259f258eab59545ceb9a215
 size 737719272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9490f3a26120c09795c2cde7ad24009926377b287eb4f547b32ba1e7af3c1535
+oid sha256:d06ed329bbde18a4a7b9915772902e60753a0756949350e242ce7474246819ca
 size 4536