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
0.6888	0.1001	320	0.6834	0.5905
0.6498	0.2003	640	0.6436	0.6396
0.6142	0.3004	960	0.6433	0.6359
0.6589	0.4005	1280	0.6341	0.6460
0.6498	0.5006	1600	0.6293	0.6473
0.6192	0.6008	1920	0.6289	0.6549
0.5904	0.7009	2240	0.6252	0.6575
0.6187	0.8010	2560	0.6202	0.6594
0.6027	0.9011	2880	0.6188	0.6622

licezhang/Qwen3-8B_17242432

Qwen3-8B_17242432