learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	Map@3
21.087	0.0623	20	1.4444	0.7169
9.8108	0.1246	40	1.1465	0.7859
7.6633	0.1868	60	0.9294	0.8218
7.0727	0.2491	80	0.7713	0.8514
6.1375	0.3114	100	0.6833	0.8680
5.8015	0.3737	120	0.6946	0.8675
4.9316	0.4360	140	0.6652	0.8726
5.0053	0.4982	160	0.6030	0.8796
4.5137	0.5605	180	0.5770	0.8903
4.4611	0.6228	200	0.6356	0.8779
4.8127	0.6851	220	0.5487	0.8906
4.5154	0.7474	240	0.5269	0.9004
3.9116	0.8097	260	0.5962	0.8855
4.3977	0.8719	280	0.4977	0.9028
3.6962	0.9342	300	0.4942	0.9084
3.2734	0.9965	320	0.4548	0.9119
3.2019	1.0561	340	0.4396	0.9157
3.1092	1.1183	360	0.5063	0.9056
3.0406	1.1806	380	0.4858	0.9101

prl90777/qwen3_4_20250809

qwen3_4_20250809