learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 6
total_train_batch_size: 48
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
num_epochs: 30

Training Loss	Epoch	Step	Validation Loss
1.4421	0.996	83	1.3987
0.9271	1.992	166	0.7992
0.6591	3.0	250	0.5874
0.5797	3.996	333	0.4766
0.5308	4.992	416	0.4747
0.4441	6.0	500	0.3578
0.3555	6.996	583	0.3452
0.319	7.992	666	0.3231
0.2794	9.0	750	0.3032
0.2817	9.996	833	0.2769
0.2337	10.992	916	0.2796
0.2344	12.0	1000	0.2497
0.1966	12.996	1083	0.2579
0.2119	13.992	1166	0.2385
0.1604	15.0	1250	0.2364
0.1207	15.996	1333	0.2336
0.1452	16.992	1416	0.2250
0.1255	18.0	1500	0.2282
0.1294	18.996	1583	0.2304
0.1016	19.992	1666	0.2202
0.1195	21.0	1750	0.2245
0.1382	21.996	1833	0.2202
0.1201	22.992	1916	0.2178
0.1185	24.0	2000	0.2150
0.1149	24.996	2083	0.2264
0.1011	25.992	2166	0.2190
0.1046	27.0	2250	0.2215

bustamiyusoef/nougatArbic_AHRXjawi

_finetunned_nougat_AHR_jawi