learning_rate: 5e-06
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: 3

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.616	0.2424	10	0.6253	0.69
0.0111	0.4848	20	1.6194	0.6267
0.0199	0.7273	30	1.3252	0.6667
0.0151	0.9697	40	2.5704	0.6467
0.0084	1.1939	50	2.2932	0.6633
0.0235	1.4364	60	2.2684	0.6333
0.0264	1.6788	70	1.5395	0.6767
0.0322	1.9212	80	1.2030	0.6767
0.0018	2.1455	90	1.2336	0.69
0.0001	2.3879	100	1.4934	0.6667
0.0004	2.6303	110	1.5528	0.67
0.0	2.8727	120	1.5700	0.67

Jennny/qwen25_7b_rm_acc_5e6_2ep

qwen25_7b_rm_acc_5e6_2ep