learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.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_steps: 0.1
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
2.6367	0.1507	171	2.5935
2.0299	0.3013	342	1.9835
1.8834	0.4520	513	1.8715
1.8843	0.6026	684	1.8319
1.7929	0.7533	855	1.8088
1.8340	0.9040	1026	1.7920
1.6984	1.0546	1197	1.7805
1.7795	1.2053	1368	1.7718
1.7848	1.3559	1539	1.7657
1.7373	1.5066	1710	1.7593
1.7183	1.6573	1881	1.7548
1.7889	1.8079	2052	1.7509
1.6819	1.9586	2223	1.7478
1.7535	2.1093	2394	1.7460
1.6669	2.2599	2565	1.7448
1.7614	2.4106	2736	1.7437
1.6935	2.5612	2907	1.7431
1.7186	2.7119	3078	1.7428
1.6719	2.8626	3249	1.7426
1.6835	3.0	3405	1.7426

stage-babylm/llama-256-12L-qa

llama-256-12L-qa