learning_rate: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Use 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
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.3399	1.3909	50	0.0722
0.0379	2.7818	100	0.0320
0.0291	4.1675	150	0.0308
0.0303	5.5585	200	0.0310
0.0265	6.9494	250	0.0306
0.0245	8.3351	300	0.0326
0.023	9.7260	350	0.0337
0.0218	11.1117	400	0.0369
0.0209	12.5026	450	0.0369
0.0202	13.8935	500	0.0388
0.0197	15.2792	550	0.0411
0.019	16.6702	600	0.0418
0.0186	18.0558	650	0.0442
0.0178	19.4468	700	0.0454
0.0174	20.8377	750	0.0473
0.0167	22.2234	800	0.0499
0.0161	23.6143	850	0.0492
0.0155	25.0	900	0.0508
0.0145	26.3909	950	0.0564
0.0138	27.7818	1000	0.0566
0.0131	29.1675	1050	0.0621
0.0122	30.5585	1100	0.0633
0.0115	31.9494	1150	0.0675
0.0105	33.3351	1200	0.0736
0.0098	34.7260	1250	0.0740
0.009	36.1117	1300	0.0807
0.0081	37.5026	1350	0.0832
0.0076	38.8935	1400	0.0855
0.007	40.2792	1450	0.0911
0.0064	41.6702	1500	0.0946
0.0061	43.0558	1550	0.0972
0.0056	44.4468	1600	0.1019
0.0055	45.8377	1650	0.1036
0.0053	47.2234	1700	0.1064
0.0051	48.6143	1750	0.1084
0.005	50.0	1800	0.1092

yilunhao/algsteer

algsteer