learning_rate: 0.0001
train_batch_size: 256
eval_batch_size: 256
seed: 13
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: 500
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
4.8939	1.0	495	3.9290
3.6468	2.0	990	3.5378
3.3754	3.0	1485	3.3858
3.2248	4.0	1980	3.2939
3.1189	5.0	2475	3.2257
3.0357	6.0	2970	3.1881
2.9645	7.0	3465	3.1580
2.9035	8.0	3960	3.1353
2.8468	9.0	4455	3.1218
2.7951	10.0	4950	3.1151
2.7449	11.0	5445	3.1136
2.6994	12.0	5940	3.1114
2.6552	13.0	6435	3.1170
2.6143	14.0	6930	3.1238
2.5771	15.0	7425	3.1313
2.5442	16.0	7920	3.1412
2.5148	17.0	8415	3.1452
2.4885	18.0	8910	3.1524
2.467	19.0	9405	3.1597
2.4502	20.0	9900	3.1630

fpadovani/cds_sh1_13

cds_sh1_13