sartifyllc/swahili-prompt-classifier

README.md

@@ -18,7 +18,7 @@ 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: 0.8786
+- Loss: 1.1803
 - F1: 0.64
 
 ## Model description
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1   |
 |:-------------:|:-----:|:----:|:---------------:|:----:|
-| No log        | 1.0   | 1    | 0.7738          | 0.64 |
-| No log        | 2.0   | 2    | 0.6932          | 0.64 |
-| No log        | 3.0   | 3    | 0.6529          | 0.64 |
-| No log        | 4.0   | 4    | 0.7746          | 0.64 |
-| No log        | 5.0   | 5    | 0.8786          | 0.64 |
+| No log        | 1.0   | 1    | 0.9308          | 0.64 |
+| No log        | 2.0   | 2    | 0.9615          | 0.64 |
+| No log        | 3.0   | 3    | 1.0317          | 0.64 |
+| No log        | 4.0   | 4    | 1.1136          | 0.64 |
+| No log        | 5.0   | 5    | 1.1803          | 0.64 |
 
 
 ### Framework versions

runs/Dec29_15-56-57_ai4d-Lambda-Vector/events.out.tfevents.1735477018.ai4d-Lambda-Vector.137875.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670dd1d21f339367199ff6e0f094c34f9cd3c79f9cb24f565c19456720b2026f
-size 6427
+oid sha256:ab36dc012310422dba958a3fc5d02e2eb549a5da7004f1564b66d77c0d09503b
+size 7708