End of training

README.md

@@ -22,12 +22,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) on the speaker-segmentation dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4833
-- Model Preparation Time: 0.014
-- Der: 0.1592
-- False Alarm: 0.0257
-- Missed Detection: 0.0139
-- Confusion: 0.1196
+- Loss: 0.3831
+- Model Preparation Time: 0.0038
+- Der: 0.1279
+- False Alarm: 0.0209
+- Missed Detection: 0.0105
+- Confusion: 0.0965
 
 ## Model description
 
@@ -58,11 +58,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
-| 0.4966        | 1.0   | 104  | 0.5339          | 0.014                  | 0.1742 | 0.0272      | 0.0153           | 0.1317    |
-| 0.4372        | 2.0   | 208  | 0.4908          | 0.014                  | 0.1606 | 0.0257      | 0.0139           | 0.1210    |
-| 0.4143        | 3.0   | 312  | 0.4868          | 0.014                  | 0.1607 | 0.0251      | 0.0146           | 0.1211    |
-| 0.3953        | 4.0   | 416  | 0.4840          | 0.014                  | 0.1600 | 0.0258      | 0.0138           | 0.1204    |
-| 0.3828        | 5.0   | 520  | 0.4833          | 0.014                  | 0.1592 | 0.0257      | 0.0139           | 0.1196    |
+| 0.4394        | 1.0   | 570  | 0.4349          | 0.0038                 | 0.1462 | 0.0209      | 0.0115           | 0.1138    |
+| 0.3989        | 2.0   | 1140 | 0.4134          | 0.0038                 | 0.1385 | 0.0211      | 0.0107           | 0.1067    |
+| 0.3797        | 3.0   | 1710 | 0.3871          | 0.0038                 | 0.1302 | 0.0211      | 0.0104           | 0.0986    |
+| 0.3518        | 4.0   | 2280 | 0.3817          | 0.0038                 | 0.1263 | 0.0209      | 0.0106           | 0.0948    |
+| 0.3269        | 5.0   | 2850 | 0.3831          | 0.0038                 | 0.1279 | 0.0209      | 0.0105           | 0.0965    |
 
 
 ### Framework versions

runs/Apr09_06-39-05_cfa6223c5491/events.out.tfevents.1744180768.cfa6223c5491.1850.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b8fd814c803b17797536362a0accbac94996eb79a486bad6f8134f9170956e
-size 26586
+oid sha256:95d85e9e148b4c8831083e338448e5b852d25c2bdf75d8ba3b92d24f90dc985a
+size 32345