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
0.2222	0.1677	10	1.4139	0.5333
0.065	0.3354	20	0.9037	0.6067
0.0552	0.5031	30	0.7860	0.68
0.0371	0.6709	40	1.0758	0.7133
0.0731	0.8386	50	0.7435	0.7433
0.0534	1.0	60	0.6848	0.7467
0.0035	1.1677	70	1.2106	0.7433
0.0064	1.3354	80	1.2054	0.7467
0.0223	1.5031	90	1.3114	0.7367
0.0503	1.6709	100	0.9685	0.7467
0.0387	1.8386	110	0.8559	0.7567

Jennny/qwen25_math_eng_rm

qwen25_math_eng_rm