learning_rate: 0.001
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Der	False Alarm	Missed Detection	Confusion
0.4003	1.0	304	0.4970	0.1927	0.0734	0.0675	0.0518
0.3686	2.0	608	0.4730	0.1799	0.0552	0.0778	0.0469
0.3446	3.0	912	0.4606	0.1718	0.0535	0.0763	0.0419
0.3520	4.0	1216	0.4732	0.1764	0.0661	0.0666	0.0438
0.3379	5.0	1520	0.4742	0.1773	0.0688	0.0662	0.0424
0.3186	6.0	1824	0.4669	0.1719	0.0520	0.0758	0.0441
0.3164	7.0	2128	0.4656	0.1696	0.0586	0.0689	0.0420
0.3013	8.0	2432	0.4661	0.1711	0.0564	0.0713	0.0434

mhdp-africa/speaker-segmentation-fine-tuned-callhome-MHDP-diarization-v1

speaker-segmentation-fine-tuned-callhome-MHDP-diarization-v1