learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
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: constant_with_warmup
lr_scheduler_warmup_steps: 30
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss
15.2427	0.128	10	0.3634
0.18	0.256	20	0.1202
0.1177	0.384	30	0.1100
0.1055	0.512	40	0.1040
0.1045	0.64	50	0.0994
0.0964	0.768	60	0.0965
0.0977	0.896	70	0.0948
0.0925	1.0128	80	0.0936
0.0914	1.1408	90	0.0930
0.0882	1.2688	100	0.0920
0.0868	1.3968	110	0.0919
0.0899	1.5248	120	0.0915
0.0862	1.6528	130	0.0914
0.0894	1.7808	140	0.0909
0.0891	1.9088	150	0.0910

wangwang0204/adl-hw2-qwen3

adl-hw2-qwen3