learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 192
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Disfluent Precision	Disfluent Recall	Disfluent F1	False Positive Rate
0.0079	0.1821	250	0.0090	0.9100	0.9259	0.9179	0.9833	0.9522	0.9633	0.9577	0.0117
0.0077	0.3642	500	0.0098	0.9118	0.9296	0.9206	0.9840	0.9595	0.9592	0.9594	0.0098
0.0059	0.5462	750	0.0146	0.9168	0.9287	0.9227	0.9836	0.9654	0.9508	0.9581	0.0083
0.0058	0.7283	1000	0.0109	0.9157	0.9242	0.9199	0.9837	0.9549	0.9623	0.9586	0.0110
0.0055	0.9104	1250	0.0116	0.9131	0.9279	0.9205	0.9834	0.9530	0.9632	0.9581	0.0115
0.0072	1.0925	1500	0.0093	0.8936	0.9201	0.9067	0.9815	0.9396	0.9679	0.9535	0.0150
0.0062	1.2746	1750	0.0103	0.9085	0.9226	0.9155	0.9822	0.9455	0.9652	0.9553	0.0134
0.0059	1.4567	2000	0.0088	0.9079	0.9225	0.9151	0.9816	0.9371	0.9715	0.9540	0.0157
0.0062	1.6387	2250	0.0093	0.9149	0.9306	0.9226	0.9841	0.9533	0.9667	0.9599	0.0115

Teloxico/deberta-4-disfluency

deberta-4-disfluency