learning_rate: 0.0002
train_batch_size: 64
eval_batch_size: 64
seed: 42
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: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
0.5359	0.5236	100	0.5565
0.6126	1.0471	200	0.5504
0.509	1.5707	300	0.5592
0.431	2.0942	400	0.5757
0.4301	2.6178	500	0.5810
0.431	3.1414	600	0.6398
0.4047	3.6649	700	0.6208
0.3453	4.1885	800	0.7369
0.3393	4.7120	900	0.7307
0.1874	5.2356	1000	0.8825
0.2594	5.7592	1100	0.9202
0.1177	6.2827	1200	1.1571
0.1848	6.8063	1300	1.1725
0.1035	7.3298	1400	1.3685
0.0879	7.8534	1500	1.4279
0.0384	8.3770	1600	1.5605
0.0373	8.9005	1700	1.5722
0.0257	9.4241	1800	1.6143
0.0373	9.9476	1900	1.6194

dzhang019/20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora

20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora