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: 0.3692
-- Model Preparation Time: 0.004
-- Der: 0.1171
-- False Alarm: 0.0608
-- Missed Detection: 0.0237
-- Confusion: 0.0326
+- Loss: 0.3670
+- Model Preparation Time: 0.0069
+- Der: 0.1186
+- False Alarm: 0.0629
+- Missed Detection: 0.0202
+- Confusion: 0.0355
 
 ## Model description
 
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der    | False Alarm | Missed Detection | Confusion |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:-----------:|:----------------:|:---------:|
-| 0.6458        | 1.0   | 47   | 0.3909          | 0.004                  | 0.1246 | 0.0619      | 0.0247           | 0.0380    |
-| 0.5198        | 2.0   | 94   | 0.3743          | 0.004                  | 0.1243 | 0.0596      | 0.0267           | 0.0379    |
-| 0.4773        | 3.0   | 141  | 0.3716          | 0.004                  | 0.1189 | 0.0616      | 0.0230           | 0.0343    |
-| 0.4667        | 4.0   | 188  | 0.3707          | 0.004                  | 0.1175 | 0.0600      | 0.0245           | 0.0330    |
-| 0.4657        | 5.0   | 235  | 0.3692          | 0.004                  | 0.1171 | 0.0608      | 0.0237           | 0.0326    |
+| 0.6461        | 1.0   | 47   | 0.3966          | 0.0069                 | 0.1309 | 0.0634      | 0.0233           | 0.0442    |
+| 0.5228        | 2.0   | 94   | 0.3730          | 0.0069                 | 0.1171 | 0.0607      | 0.0232           | 0.0332    |
+| 0.4746        | 3.0   | 141  | 0.3697          | 0.0069                 | 0.1204 | 0.0630      | 0.0207           | 0.0368    |
+| 0.4577        | 4.0   | 188  | 0.3724          | 0.0069                 | 0.1205 | 0.0624      | 0.0211           | 0.0370    |
+| 0.4609        | 5.0   | 235  | 0.3670          | 0.0069                 | 0.1186 | 0.0629      | 0.0202           | 0.0355    |
 
 
 ### Framework versions
 
 - Transformers 4.48.3
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.0
-- Tokenizers 0.21.0
+- Datasets 3.4.1
+- Tokenizers 0.21.1

runs/Mar18_02-28-15_37c115ce7e54/events.out.tfevents.1742264909.37c115ce7e54.3375.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3ea3175c6220213669f6c6f30bb90cff859e78ef3342b84aa6604e94ac7ffd
-size 9218
+oid sha256:d2cfbd90f0623cbd4d7a699c5b3bbbcddabf727b75f674aacb40de6c63ba0bcd
+size 10124