learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 1968
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.8571	3	1.1100	0.2414	0.1806
No log	2.0	7	1.2438	0.1724	0.1061
1.0564	2.8571	10	1.2948	0.2069	0.1287
1.0564	4.0	14	1.4553	0.3103	0.2008
1.0564	4.8571	17	1.6435	0.2759	0.1798
0.601	6.0	21	1.4658	0.3793	0.3412
0.601	6.8571	24	1.7203	0.3103	0.2597
0.601	8.0	28	1.8225	0.4138	0.4122
0.227	8.8571	31	1.7533	0.4483	0.4552
0.227	10.0	35	2.6984	0.3448	0.2730
0.227	10.8571	38	3.1588	0.2759	0.1850
0.0553	12.0	42	2.9259	0.4138	0.3870
0.0553	12.8571	45	2.9862	0.4483	0.4370
0.0553	14.0	49	3.2382	0.4483	0.4370
0.0072	14.8571	52	3.4094	0.4138	0.3870
0.0072	16.0	56	3.5602	0.4138	0.3870
0.0072	16.8571	59	3.6131	0.3793	0.3333
0.0034	17.1429	60	3.6195	0.3793	0.3333

sarasarasara/whisper-base-finetuned-bmd-V1-fp16-20241111_180200-LOSO-section-out1

whisper-base-finetuned-bmd-V1-fp16-20241111_180200-LOSO-section-out1