learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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
training_steps: 2000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.7809	0.5587	100	0.7240
0.7682	1.1173	200	0.6956
0.7216	1.6760	300	0.6608
0.7083	2.2346	400	0.6578
0.6839	2.7933	500	0.6375
0.6805	3.3520	600	0.6369
0.6587	3.9106	700	0.6269
0.6786	4.4693	800	0.6252
0.6561	5.0279	900	0.6192
0.6553	5.5866	1000	0.6159
0.6477	6.1453	1100	0.6108
0.6537	6.7039	1200	0.6121
0.6635	7.2626	1300	0.6106
0.6409	7.8212	1400	0.6059
0.6503	8.3799	1500	0.6066
0.6391	8.9385	1600	0.6033
0.6388	9.4972	1700	0.6039
0.6407	10.0559	1800	0.6010
0.6388	10.6145	1900	0.6016
0.6415	11.1732	2000	0.6022

KevinCRB/speecht5_ft_french

speecht5_ft_french