learning_rate: 0.0003
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: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
23.6951	0.2283	50	12.4335	1.0
10.0619	0.4566	100	7.2129	1.0
6.0237	0.6849	150	4.3896	1.0
3.7555	0.9132	200	3.4440	1.0
3.2614	1.1416	250	3.2118	1.0
3.1725	1.3699	300	3.1193	0.9995
3.0116	1.5982	350	2.7685	1.0
2.1438	1.8265	400	1.2964	0.7798
1.2369	2.0548	450	0.8161	0.5840
0.8896	2.2831	500	0.6958	0.5295
0.8004	2.5114	550	0.5918	0.4849
0.701	2.7397	600	0.4901	0.4161
0.6333	2.9680	650	0.4689	0.3978
0.4878	3.1963	700	0.4251	0.3819
0.501	3.4247	750	0.4009	0.3507
0.4599	3.6530	800	0.3477	0.3086
0.4426	3.8813	850	0.3219	0.2967
0.429	4.1096	900	0.3077	0.2722
0.3689	4.3379	950	0.2865	0.2609
0.3725	4.5662	1000	0.2880	0.2492
0.3478	4.7945	1050	0.2573	0.2293
0.336	5.0228	1100	0.2824	0.2536
0.2992	5.2511	1150	0.2744	0.2449
0.2775	5.4795	1200	0.2674	0.2464
0.274	5.7078	1250	0.2590	0.2387
0.2651	5.9361	1300	0.2678	0.2412
0.241	6.1644	1350	0.2602	0.2298
0.2539	6.3927	1400	0.2477	0.2246
0.2576	6.6210	1450	0.2346	0.2110
0.2626	6.8493	1500	0.2310	0.2138
0.2556	7.0776	1550	0.2365	0.2058
0.2271	7.3059	1600	0.2253	0.2003
0.1902	7.5342	1650	0.2013	0.1812
0.1633	7.7626	1700	0.1960	0.1706
0.1557	7.9909	1750	0.1920	0.1694
0.1555	8.2192	1800	0.1911	0.1680
0.1514	8.4475	1850	0.2003	0.1640
0.146	8.6758	1900	0.1860	0.1592
0.1269	8.9041	1950	0.1920	0.1569
0.1314	9.1324	2000	0.1872	0.1553
0.1247	9.3607	2050	0.1874	0.1549
0.1262	9.5890	2100	0.1852	0.1515
0.1201	9.8174	2150	0.1850	0.1513

sam422001/SuperSindhi

SuperSindhi