Add model trained for query classification (v6.0)

README.md

@@ -22,11 +22,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1422
-- Accuracy: 0.9796
-- F1: 0.9796
-- Precision: 0.9797
-- Recall: 0.9796
+- Loss: 0.1256
+- Accuracy: 0.9759
+- F1: 0.9759
+- Precision: 0.9763
+- Recall: 0.9759
 
 ## Model description
 
@@ -51,22 +51,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| No log        | 1.0   | 315  | 0.1323          | 0.9704   | 0.9704 | 0.9705    | 0.9704 |
-| 0.2136        | 2.0   | 630  | 0.1504          | 0.9722   | 0.9723 | 0.9739    | 0.9722 |
-| 0.2136        | 3.0   | 945  | 0.1670          | 0.9722   | 0.9723 | 0.9730    | 0.9722 |
-| 0.075         | 4.0   | 1260 | 0.1422          | 0.9796   | 0.9796 | 0.9797    | 0.9796 |
-| 0.0211        | 5.0   | 1575 | 0.1496          | 0.9741   | 0.9741 | 0.9742    | 0.9741 |
-| 0.0211        | 6.0   | 1890 | 0.1505          | 0.9741   | 0.9740 | 0.9741    | 0.9741 |
-| 0.012         | 7.0   | 2205 | 0.1661          | 0.9778   | 0.9778 | 0.9779    | 0.9778 |
-| 0.0038        | 8.0   | 2520 | 0.1558          | 0.9778   | 0.9778 | 0.9779    | 0.9778 |
-| 0.0038        | 9.0   | 2835 | 0.1557          | 0.9741   | 0.9740 | 0.9741    | 0.9741 |
-| 0.0049        | 10.0  | 3150 | 0.1574          | 0.9741   | 0.9740 | 0.9741    | 0.9741 |
+| No log        | 1.0   | 315  | 0.1474          | 0.9648   | 0.9647 | 0.9649    | 0.9648 |
+| 0.1965        | 2.0   | 630  | 0.1226          | 0.9704   | 0.9704 | 0.9718    | 0.9704 |
+| 0.1965        | 3.0   | 945  | 0.1192          | 0.9741   | 0.9742 | 0.9757    | 0.9741 |
+| 0.0426        | 4.0   | 1260 | 0.1250          | 0.9741   | 0.9741 | 0.9742    | 0.9741 |
+| 0.0042        | 5.0   | 1575 | 0.1256          | 0.9759   | 0.9759 | 0.9763    | 0.9759 |
 
 
 ### Framework versions

runs/Apr30_06-49-46_68be676fb8aa/events.out.tfevents.1745996410.68be676fb8aa.447.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e20480d9fc5adfa992d8cd49060be52f934da7b7c9a554d446ddf7cc14f0c68
+size 1032