End of training

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cis-lmu/glot500-base](https://huggingface.co/cis-lmu/glot500-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5080
-- Precision: 0.8320
-- Recall: 0.8440
-- F1: 0.8380
-- Accuracy: 0.8655
+- Loss: 0.6304
+- Precision: 0.7752
+- Recall: 0.7796
+- F1: 0.7774
+- Accuracy: 0.8290
 
 ## Model description
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 375  | 0.6582          | 0.7848    | 0.7963 | 0.7905 | 0.8275   |
-| 1.0414        | 2.0   | 750  | 0.5080          | 0.8320    | 0.8440 | 0.8380 | 0.8655   |
+| No log        | 1.0   | 295  | 0.8056          | 0.7341    | 0.7346 | 0.7343 | 0.7913   |
+| 0.948         | 2.0   | 590  | 0.6304          | 0.7752    | 0.7796 | 0.7774 | 0.8290   |
 
 
 ### Framework versions

runs/Feb16_16-47-31_464128ad0710/events.out.tfevents.1739724458.464128ad0710.855.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e88bc9c47fb88a39794e7293ad8f4155b3a816dae743904e5403b7fc36e778e
-size 6328
+oid sha256:45517c0cd14d564f1cd95c1f26c3ca10c7952a4dd5e8a3b7fac59eddeb686693
+size 7154