End of training

README.md

@@ -25,12 +25,12 @@ 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: 0.3798
-- Model Preparation Time: 0.0039
-- Der: 0.1196
-- False Alarm: 0.0617
-- Missed Detection: 0.0232
-- Confusion: 0.0346
+- Loss: 0.3564
+- Model Preparation Time: 0.0016
+- Der: 0.1151
+- False Alarm: 0.0629
+- Missed Detection: 0.0211
+- Confusion: 0.0312
 
 ## Model description
 
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
-| 0.6461        | 1.0   | 47   | 0.4005          | 0.0039                 | 0.1328 | 0.0651      | 0.0212           | 0.0465    |
-| 0.5243        | 2.0   | 94   | 0.3903          | 0.0039                 | 0.1253 | 0.0615      | 0.0236           | 0.0402    |
-| 0.4921        | 3.0   | 141  | 0.3782          | 0.0039                 | 0.1203 | 0.0622      | 0.0226           | 0.0355    |
-| 0.4775        | 4.0   | 188  | 0.3828          | 0.0039                 | 0.1202 | 0.0615      | 0.0236           | 0.0350    |
-| 0.4764        | 5.0   | 235  | 0.3798          | 0.0039                 | 0.1196 | 0.0617      | 0.0232           | 0.0346    |
+| 0.6452        | 1.0   | 47   | 0.3749          | 0.0016                 | 0.1243 | 0.0629      | 0.0220           | 0.0394    |
+| 0.5163        | 2.0   | 94   | 0.3950          | 0.0016                 | 0.1329 | 0.0619      | 0.0249           | 0.0461    |
+| 0.4782        | 3.0   | 141  | 0.3613          | 0.0016                 | 0.1173 | 0.0633      | 0.0215           | 0.0324    |
+| 0.4698        | 4.0   | 188  | 0.3567          | 0.0016                 | 0.1154 | 0.0625      | 0.0216           | 0.0312    |
+| 0.4726        | 5.0   | 235  | 0.3564          | 0.0016                 | 0.1151 | 0.0629      | 0.0211           | 0.0312    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1964234d849316d10ae50eb6537710b463e54548bda9d78ca7f9d0020c92fbe5
+oid sha256:78a0a8406ad5c578bc6aa8ffc3b95d62c0ab5c5797de07df4f503a59142a7468
 size 5899124

runs/Mar17_05-56-38_92410cff8b4e/events.out.tfevents.1742191030.92410cff8b4e.172.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536036cc4e0872e2581116216c0314dd7f9b2f6b60eb897f8b188ea0962b2764
-size 9218
+oid sha256:0efad4aa541321e5cf6fa6a58afc84226898ff396b151b3aa295c157629cd259
+size 10124

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3ff3f9e36cfe86ceb03c932878dc223b966a6aea196cb79b6b55b104dd7cf4
+oid sha256:914fe3641f51b5cee004f31ef7d9b438791ca7f2d02cd1bfa09a1e912cf1f41b
 size 5304