learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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: linear
lr_scheduler_warmup_steps: 100
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.5178	0.8909	100	0.4322
0.4641	1.7751	200	0.4237
0.4453	2.6592	300	0.3944
0.4269	3.5434	400	0.3915
0.4145	4.4276	500	0.3878
0.4142	5.3118	600	0.3844
0.406	6.1960	700	0.3721
0.3908	7.0802	800	0.3709
0.4063	7.9710	900	0.3725
0.4023	8.8552	1000	0.3662
0.395	9.7394	1100	0.3665
0.3948	10.6236	1200	0.4014
0.3884	11.5078	1300	0.3655
0.3897	12.3920	1400	0.3776
0.384	13.2762	1500	0.3640
0.3698	14.1604	1600	0.3656
0.3692	15.0445	1700	0.3624
0.3809	15.9354	1800	0.3683
0.3804	16.8196	1900	0.3596
0.3744	17.7038	2000	0.3543
0.375	18.5880	2100	0.3558
0.3688	19.4722	2200	0.3673
0.3697	20.3563	2300	0.3617
0.3669	21.2405	2400	0.3596
0.3504	22.1247	2500	0.3556
0.3527	23.0089	2600	0.3550
0.3645	23.8998	2700	0.3523
0.3588	24.7840	2800	0.3519
0.3609	25.6682	2900	0.3514
0.362	26.5523	3000	0.3533
0.366	27.4365	3100	0.3515
0.355	28.3207	3200	0.3593
0.343	29.2049	3300	0.3695
0.3421	30.0891	3400	0.3580
0.3521	30.9800	3500	0.3518
0.3525	31.8641	3600	0.3521
0.3511	32.7483	3700	0.3521
0.3525	33.6325	3800	0.3544
0.3483	34.5167	3900	0.3520
0.3463	35.4009	4000	0.3567
0.3436	36.2851	4100	0.3547
0.3315	37.1693	4200	0.3647
0.3307	38.0535	4300	0.3534
0.3415	38.9443	4400	0.3520
0.3436	39.8285	4500	0.3504
0.3433	40.7127	4600	0.3542
0.3423	41.5969	4700	0.3556
0.3401	42.4811	4800	0.3565
0.3392	43.3653	4900	0.3550
0.3363	44.2494	5000	0.3539
0.3292	45.1336	5100	0.3563
0.3273	46.0178	5200	0.3514
0.3352	46.9087	5300	0.3590
0.3458	47.7929	5400	0.3576
0.3351	48.6771	5500	0.3567
0.3382	49.5612	5600	0.3555

Danetuk/speecht5_finetuned_emirhan_tr

speecht5_finetuned_emirhan_tr