- Model-B-16_Data-2B_Samples-13B_lr-1e-3_bs-88k
- Model-B-16_Data-2B_Samples-34B_lr-1e-3_bs-88k
- Model-B-16_Data-2B_Samples-3B_lr-1e-3_bs-88k
- Model-B-16_Data-400M_Samples-34B_lr-1e-3_bs-88k
- Model-B-16_Data-400M_Samples-3B_lr-1e-3_bs-88k
- Model-B-16_Data-80M_Samples-13B_lr-1e-3_bs-88k
- Model-B-16_Data-80M_Samples-34B_lr-1e-3_bs-88k
- Model-B-16_Data-80M_Samples-3B_lr-1e-3_bs-88k
- Model-B-32_Data-2B_Samples-13B_lr-5e-4_bs-32k
- Model-B-32_Data-2B_Samples-3B_lr-1e-3_bs-88k
- Model-B-32_Data-400M_Samples-13B_lr-1e-3_bs-86k
- Model-B-32_Data-400M_Samples-34B_lr-5e-4_bs-32k
- Model-B-32_Data-400M_Samples-3B_lr-1e-3_bs-88k
- Model-B-32_Data-80M_Samples-13B_lr-5e-4_bs-32k
- Model-B-32_Data-80M_Samples-34B_lr-1e-3_bs-88k
- Model-B-32_Data-80M_Samples-3B_lr-5e-4_bs-32k
- Model-H-14_Data-2B_Samples-34B_lr-5e-4_bs-79k
- Model-L-14_Data-2B_Samples-13B_lr-1e-3_bs-86k
- Model-L-14_Data-2B_Samples-3B_lr-1e-3_bs-88k
- Model-L-14_Data-400M_Samples-13B_lr-1e-3_bs-86k
- Model-L-14_Data-400M_Samples-34B_lr-1e-3_bs-86k
- Model-L-14_Data-400M_Samples-3B_lr-1e-3_bs-88k
- Model-L-14_Data-80M_Samples-13B_lr-1e-3_bs-88k
- Model-L-14_Data-80M_Samples-34B_lr-1e-3_bs-88k
- Model-L-14_Data-80M_Samples-3B_lr-1e-3_bs-88k