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: 20

Training Loss	Epoch	Step	Validation Loss
7.7857	1.0	84	1.2320
5.7315	2.0	168	1.0987
4.6512	3.0	252	1.0728
3.894	4.0	336	1.0901
3.8545	5.0	420	1.0915
2.9066	6.0	504	1.1346
2.3597	7.0	588	1.1675
1.9387	8.0	672	1.1842
1.7872	9.0	756	1.2136
1.3412	10.0	840	1.2311
1.3814	11.0	924	1.2475
1.047	12.0	1008	1.2613
0.9478	13.0	1092	1.2710
1.1476	14.0	1176	1.2813
0.7796	15.0	1260	1.2862
0.9022	16.0	1344	1.2898
0.9488	17.0	1428	1.2923
0.7874	18.0	1512	1.2943
0.8132	19.0	1596	1.2941
0.8164	19.768	1660	1.2944

bustamiyusoef/_Nougat_MixGerEng_01

_Nougat_MixGerEng_01