PolyPythias
- Preview • Updated • 639
EleutherAI/pile-preshuffled-seeds
Updated • 46 • 1Note Training data information for each seed.
EleutherAI/pythia-14m
Text Generation • 0.0B • Updated • 226k • 23EleutherAI/pythia-14m-seed1
Updated • 40EleutherAI/pythia-14m-seed2
Updated • 40EleutherAI/pythia-14m-seed3
Updated • 40EleutherAI/pythia-14m-seed4
Updated • 39EleutherAI/pythia-14m-seed5
Updated • 40EleutherAI/pythia-14m-seed6
Updated • 40EleutherAI/pythia-14m-seed7
Updated • 40EleutherAI/pythia-14m-seed8
Updated • 40EleutherAI/pythia-14m-seed9
Updated • 40EleutherAI/pythia-31m
Text Generation • 0.1B • Updated • 128k • 5EleutherAI/pythia-31m-seed1
Updated • 40EleutherAI/pythia-31m-seed2
Updated • 40EleutherAI/pythia-31m-seed3
Updated • 40EleutherAI/pythia-31m-seed4
Updated • 40EleutherAI/pythia-31m-seed5
Updated • 40EleutherAI/pythia-31m-seed6
Updated • 40EleutherAI/pythia-31m-seed7
Updated • 40EleutherAI/pythia-31m-seed8
Updated • 40EleutherAI/pythia-31m-seed9
Updated • 39EleutherAI/pythia-70m
0.1B • Updated • 186k • 71EleutherAI/pythia-70m-seed1
Updated • 412EleutherAI/pythia-70m-seed2
Updated • 393EleutherAI/pythia-70m-seed3
Updated • 400EleutherAI/pythia-70m-seed4
Updated • 391EleutherAI/pythia-70m-seed5
Updated • 300EleutherAI/pythia-70m-seed6
Updated • 612EleutherAI/pythia-70m-seed7
Updated • 300EleutherAI/pythia-70m-seed8
Updated • 300EleutherAI/pythia-70m-seed9
Updated • 299EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 130k • 32EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 1.38kEleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 1.4kEleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 1.38kEleutherAI/pythia-160m-seed4
Updated • 384 • 1EleutherAI/pythia-160m-seed5
Updated • 301EleutherAI/pythia-160m-seed6
Updated • 313EleutherAI/pythia-160m-seed7
Updated • 297EleutherAI/pythia-160m-seed8
Updated • 294EleutherAI/pythia-160m-seed9
Updated • 310EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 107k • 32EleutherAI/pythia-410m-seed1
Updated • 249EleutherAI/pythia-410m-seed2
Updated • 219EleutherAI/pythia-410m-seed3
Updated • 215EleutherAI/pythia-410m-seed4
Updated • 225EleutherAI/pythia-410m-seed5
Updated • 141EleutherAI/pythia-410m-seed6
Updated • 150EleutherAI/pythia-410m-seed7
Updated • 146EleutherAI/pythia-410m-seed8
Updated • 145EleutherAI/pythia-410m-seed9
Updated • 167
EleutherAI/pythia-160m-data-seed1
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-data-seed2
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-data-seed3
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed1
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed2
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed3
UpdatedNote Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
Paper • 2503.09543 • Published