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: 3

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.436	0.3042	10	0.9576	0.5765
0.14	0.6084	20	1.1787	0.6071
0.146	0.9125	30	0.8044	0.5561
0.0376	1.2433	40	1.5338	0.5714
0.0054	1.5475	50	1.1432	0.6020
0.0353	1.8517	60	1.0350	0.6173
0.0009	2.1825	70	1.1095	0.5867
0.0004	2.4867	80	1.1308	0.5867
0.0005	2.7909	90	1.1530	0.5918

Jennny/llama3_8b_helpsteer_coherence_rm

llama3_8b_helpsteer_coherence_rm