learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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
0.2729	0.0747	50	0.3080
0.2717	0.1493	100	0.2636
0.2538	0.2240	150	0.2482
0.2415	0.2986	200	0.2399
0.2389	0.3733	250	0.2347
0.1839	0.4479	300	0.2321
0.1859	0.5226	350	0.2280
0.1969	0.5972	400	0.2271
0.1573	0.6719	450	0.2246
0.1698	0.7465	500	0.2241
0.1835	0.8212	550	0.2244
0.145	0.8959	600	0.2234
0.1717	0.9705	650	0.2232

kyleliu789/qwen3-14b-svamp14-sft-qlora-r8-a16

qwen3_14b_svamp14_sft_qlora_r8_a16