learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 8
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: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1.0

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6503	0.1003	244	0.6892	0.5896
0.6364	0.2006	488	0.6464	0.6412
0.6312	0.3009	732	0.6322	0.6508
0.6092	0.4012	976	0.6172	0.6696
0.6399	0.5014	1220	0.6155	0.6673
0.5885	0.6017	1464	0.6120	0.6746
0.6144	0.7020	1708	0.6100	0.6777
0.6014	0.8023	1952	0.6070	0.6782
0.5877	0.9026	2196	0.6066	0.6801

licezhang/Qwen3-8B_17646861

Qwen3-8B_17646861