Index of /open-courses-0923/50-6-7960-Deep-Learning/github/modded-nanogpt/records/track_1_short/


../
2024-06-06_AdamW/                                  04-Oct-2026 18:28       -
2024-10-09_SOAP/                                   04-Oct-2026 18:28       -
2024-10-10_Muon/                                   04-Oct-2026 18:28       -
2024-10-13_llmc/                                   04-Oct-2026 18:28       -
2024-10-14_ModernArch/                             04-Oct-2026 18:28       -
2024-10-17_DistributedMuon/                        04-Oct-2026 18:28       -
2024-10-18_PyTorch25/                              04-Oct-2026 18:28       -
2024-10-20_ScaleUp1B/                              04-Oct-2026 18:28       -
2024-10-29_Optimizers/                             04-Oct-2026 18:28       -
2024-11-03_UntieEmbed/                             04-Oct-2026 18:28       -
2024-11-04_50Bruns/                                04-Oct-2026 18:28       -
2024-11-06_ShortcutsTweaks/                        04-Oct-2026 18:28       -
2024-11-08_CastBf16/                               04-Oct-2026 18:28       -
2024-11-09_Replicateleloykun/                      04-Oct-2026 18:28       -
2024-11-10_ScaleShortcuts/                         04-Oct-2026 18:28       -
2024-11-10_UNetDoubleLr/                           04-Oct-2026 18:28       -
2024-11-14_QuantizedFP4/                           04-Oct-2026 18:28       -
2024-11-19_FlexAttention/                          04-Oct-2026 18:28       -
2024-11-24_WindowWarmup/                           04-Oct-2026 18:28       -
2024-12-04_ValueEmbed/                             04-Oct-2026 18:28       -
2024-12-08_UNetValueEmbedsTweaks/                  04-Oct-2026 18:28       -
2024-12-10_MFUTweaks/                              04-Oct-2026 18:28       -
2024-12-17_SparsifyEmbeds/                         04-Oct-2026 18:28       -
2025-01-04_SoftCap/                                04-Oct-2026 18:28       -
2025-01-13_Fp8LmHead/                              04-Oct-2026 18:28       -
2025-01-16_Sub3Min/                                04-Oct-2026 18:28       -
2025-01-26_BatchSize/                              04-Oct-2026 18:28       -
2025-02-01_RuleTweak/                              04-Oct-2026 18:28       -
2025-05-09_SkipMLPBlocks/                          04-Oct-2026 18:28       -
2025-05-24_FasterReduce/                           04-Oct-2026 18:28       -
2025-05-24_StableTorch/                            04-Oct-2026 18:28       -
2025-05-25_EvenFasterReduce/                       04-Oct-2026 18:28       -
2025-05-25_MuonWithAuxAdamExample/                 04-Oct-2026 18:28       -
2025-05-30_noallreduce/                            04-Oct-2026 18:28       -
2025-07-12_BosAlign/                               04-Oct-2026 18:28       -
2025-07-13_UpgradeTorch190/                        04-Oct-2026 18:28       -
2025-07-18_TritonMuon/                             04-Oct-2026 18:28       -
2025-08-23_SparseAttnGate/                         04-Oct-2026 18:28       -
2025-09-03_FA3/                                    04-Oct-2026 18:28       -
2025-09-05_SkipMLPBlocks/                          04-Oct-2026 18:28       -
2025-09-10_Yarn/                                   04-Oct-2026 18:28       -
2025-09-11_VectSigmoidBFloat16/                    04-Oct-2026 18:28       -
2025-09-15_AsyncDataLoadAttnFinalWindow/           04-Oct-2026 18:28       -
2025-09-18_Smear/                                  04-Oct-2026 18:28       -
2025-09-21_DropAttn/                               04-Oct-2026 18:28       -
2025-09-23_MuonCustomSizing/                       04-Oct-2026 18:28       -
2025-09-27_BF16CE/                                 04-Oct-2026 18:28       -
2025-09-29_PolarExpress/                           04-Oct-2026 18:28       -
2025-09-30_CustomBatching/                         04-Oct-2026 18:28       -
2025-10-04_Backout/                                04-Oct-2026 18:28       -
2025-10-24_NorMuon/                                04-Oct-2026 18:28       -
2025-10-27_FixMuonLR/                              04-Oct-2026 18:28       -
2025-10-31_AdamSyncGradientHook/                   04-Oct-2026 18:28       -
2025-11-10_CautiousWD/                             04-Oct-2026 18:28       -
2025-11-18_RefineSkip/                             04-Oct-2026 18:28       -
2025-11-29_BatchSizeSchedule/                      04-Oct-2026 18:28       -
2025-12-10_SALambdaOnWeights/                      04-Oct-2026 18:28       -
2025-12-11_NorMuonOptimsAndFixes/                  04-Oct-2026 18:28       -
2025-12-14_PartialKeyOffset/                       04-Oct-2026 18:28       -
2025-12-18_CautiousWDAdam/                         04-Oct-2026 18:28       -
2025-12-19_RetieLMHead/                            04-Oct-2026 18:28       -
2025-12-21_SmoothedScalars/                        04-Oct-2026 18:28       -
2025-12-22_MultiTokenPrediction/                   04-Oct-2026 18:28       -
2025-12-26_LogitRescale/                           04-Oct-2026 18:28       -
2025-12-29_VeSkipGates/                            04-Oct-2026 18:28       -
2025-12-31_GatesToCompiledAdam/                    04-Oct-2026 18:28       -
2026-01-04_MixedPrecisionInterweavedOptimizer/     04-Oct-2026 18:28       -
2026-01-07_PairedHeadAttention/                    04-Oct-2026 18:28       -
2026-01-10_FusedLinearReLUSquare/                  04-Oct-2026 18:28       -
2026-01-16_FusedSoftcappedEntropy/                 04-Oct-2026 18:28       -
2026-01-18_UnifiedOptimizers/                      04-Oct-2026 18:28       -
2026-01-19_BigramHashEmbedding/                    04-Oct-2026 18:28       -
2026-01-24_ImprovedLMHead/                         04-Oct-2026 18:28       -
2026-01-26-UntieValueEmbeddings/                   04-Oct-2026 18:28       -
2026-01-30_MimeticValueOutput/                     04-Oct-2026 18:28       -
2026-01-30_VeFused/                                04-Oct-2026 18:28       -
2026-01-31-BigramHashH2D/                          04-Oct-2026 18:28       -
2026-02-02_KernelTuning/                           04-Oct-2026 18:28       -
2026-02-03_VeTuned/                                04-Oct-2026 18:28       -
2026-02-06_SparseBigramGradient/                   04-Oct-2026 18:28       -
2026-02-10_ShortWindow/                            04-Oct-2026 18:28       -
2026-02-12_ParallelResiduals/                      04-Oct-2026 18:28       -
2026-02-16_FlattenForward/                         04-Oct-2026 18:28       -
2026-02-23_CrossEntropyKernel/                     04-Oct-2026 18:28       -
2026-02-28_TransposeCopyBackward/                  04-Oct-2026 18:28       -
2026-03-06_SimplifyHC/                             04-Oct-2026 18:28       -
2026-03-22_VarlenMaxDocs/                          04-Oct-2026 18:28       -
2026-04-04_FuseCEFwdAndBwd/                        04-Oct-2026 18:28       -
2026-04-08_PairedHeadMuon/                         04-Oct-2026 18:28       -
2026-04-22_MuddFormer/                             04-Oct-2026 18:28       -
2026-04-29_XSAGatedLayers/                         04-Oct-2026 18:28       -
2026-05-07_XSAGatedLayers/                         04-Oct-2026 18:28       -
2026-05-19_FP8MLPUpProj/                           04-Oct-2026 18:28       -
2026-05-20_BigramsSignTrick/                       04-Oct-2026 18:28       -
2026-05-27-MuddGatedAndDC/                         04-Oct-2026 18:28       -
2026-06-11_RecursiveFromBest/                      04-Oct-2026 18:28       -
2026-07-13_PrefixTokenPrediction/                  04-Oct-2026 18:28       -
2026-07-17_FP8DownProjection/                      04-Oct-2026 18:28       -
2026-07-22_AttentionPacking/                       04-Oct-2026 18:28       -
2026-08-03_FP8MLPBackwardPackedQKV/                04-Oct-2026 18:28       -
2026-08-06-CanonicalMasking/                       04-Oct-2026 18:28       -
2026-08-30_ANVIL2/                                 04-Oct-2026 18:28       -