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_FUSED 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: 5000

Training Loss	Epoch	Step	Validation Loss
4.8142	0.1364	100	0.5158
4.4829	0.2729	200	0.5417
4.2847	0.4093	300	0.4858
4.1648	0.5457	400	0.4760
4.1417	0.6821	500	0.4716
4.2032	0.8186	600	0.4722
4.1184	0.9550	700	0.4868
4.0658	1.0914	800	0.4759
4.0502	1.2278	900	0.4640
4.0098	1.3643	1000	0.4575
3.9671	1.5007	1100	0.4547
3.9913	1.6371	1200	0.4676
3.9387	1.7735	1300	0.4522
3.8744	1.9100	1400	0.4534
3.9864	2.0464	1500	0.4611
3.9376	2.1828	1600	0.4563
3.8866	2.3192	1700	0.4475
3.9037	2.4557	1800	0.4476
3.8385	2.5921	1900	0.4477
3.8257	2.7285	2000	0.4489
3.7905	2.8649	2100	0.4466
3.8109	3.0014	2200	0.4447
3.7939	3.1378	2300	0.4450
3.8064	3.2742	2400	0.4432
3.7764	3.4106	2500	0.4404
3.7865	3.5471	2600	0.4419
3.7751	3.6835	2700	0.4385
3.7756	3.8199	2800	0.4401
3.7690	3.9563	2900	0.4395
3.7346	4.0928	3000	0.4365
3.7100	4.2292	3100	0.4382
3.7393	4.3656	3200	0.4390
3.7059	4.5020	3300	0.4330
3.7070	4.6385	3400	0.4366
3.7473	4.7749	3500	0.4343
3.6961	4.9113	3600	0.4317
3.6602	5.0477	3700	0.4318
3.6724	5.1842	3800	0.4306
3.6902	5.3206	3900	0.4318
3.7066	5.4570	4000	0.4321
3.6924	5.5935	4100	0.4284
3.6851	5.7299	4200	0.4265
3.6385	5.8663	4300	0.4272
3.6388	6.0027	4400	0.4271
3.6214	6.1392	4500	0.4272
3.6388	6.2756	4600	0.4263
3.6027	6.4120	4700	0.4286
3.6368	6.5484	4800	0.4266
3.5963	6.6849	4900	0.4264
3.6028	6.8213	5000	0.4255

iamwille/speecht5_finetuned_iamwille_ig

speecht5_finetuned_iamwille_ig