learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW 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: 2

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3308	0.2424	10	1.3608	0.66
0.0063	0.4848	20	1.4237	0.7167
0.0703	0.7273	30	2.4097	0.6267
0.0751	0.9697	40	0.9876	0.67
0.0047	1.1939	50	1.9047	0.68
0.0009	1.4364	60	2.5391	0.6267
0.1065	1.6788	70	2.4082	0.64
0.1204	1.9212	80	2.2156	0.65

Jennny/qwen25_math_acc_rm

qwen25_math_acc_rm