learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 16
seed: 42
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
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.1933	1.0	24	0.9206
0.2084	2.0	48	0.8872
0.1692	3.0	72	0.8975
0.1341	4.0	96	0.8255
0.1333	5.0	120	0.8524
0.1217	6.0	144	0.8312
0.1132	7.0	168	0.8814
0.0767	8.0	192	0.8282
0.0798	9.0	216	0.8331
0.0939	10.0	240	0.9095
0.0736	11.0	264	0.8566
0.0733	12.0	288	0.7841
0.0351	13.0	312	0.8250
0.0571	14.0	336	0.8270
0.0398	15.0	360	0.7958
0.0383	16.0	384	0.8322
0.0282	17.0	408	0.8043
0.0375	18.0	432	0.8077
0.0392	19.0	456	0.7974
0.047	20.0	480	0.7974

vivek-pathania/donut-base-sroie

donut-base-sroie