learning_rate: 8e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Use 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: 0.05
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
0.8842	1.0	12	0.8997
0.8086	2.0	24	0.8223
0.7502	3.0	36	0.7781
0.7287	4.0	48	0.7514
0.6899	5.0	60	0.7341
0.6934	6.0	72	0.7228
0.6727	7.0	84	0.7168
0.69	8.0	96	0.7134
0.6892	9.0	108	0.7124
0.6735	10.0	120	0.7120

effcot/Limo_qwen

Limo_qwen