learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 32
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
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0	0	1.1855	0.5909	0.5603	0.5909	0.5667
0.8449	0.1136	10	0.7082	0.7102	0.7023	0.7102	0.6896
0.8398	0.2273	20	0.5703	0.7216	0.7262	0.7216	0.6911
0.6942	0.3409	30	0.6016	0.6989	0.6881	0.6989	0.6864
0.7332	0.4545	40	0.6146	0.6307	0.6924	0.6307	0.6361
0.636	0.5682	50	0.5402	0.7557	0.8095	0.7557	0.7170
0.5157	0.6818	60	0.5080	0.7159	0.7088	0.7159	0.7099
0.6613	0.7955	70	0.5060	0.7330	0.7274	0.7330	0.7182
0.6174	0.9091	80	0.5203	0.7443	0.7538	0.7443	0.7190
0.5021	1.0227	90	0.5441	0.7216	0.7134	0.7216	0.7101
0.4124	1.1364	100	0.5618	0.7330	0.7286	0.7330	0.7161
0.3623	1.25	110	0.5811	0.7159	0.7080	0.7159	0.7084
0.3416	1.3636	120	0.5897	0.6932	0.6912	0.6932	0.6921
0.2837	1.4773	130	0.5869	0.7443	0.7388	0.7443	0.7338
0.3153	1.5909	140	0.5608	0.7330	0.7323	0.7330	0.7116
0.272	1.7045	150	0.5676	0.7386	0.7409	0.7386	0.7166
0.3459	1.8182	160	0.5586	0.7273	0.7241	0.7273	0.7067
0.368	1.9318	170	0.5576	0.7273	0.7241	0.7273	0.7067

AmirMohseni/router-qwen3-0.6b-text-only-v4

router-qwen3-0.6b-text-only-v4