JackHsieh/0.6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-2.best Updated Jun 8
JackHsieh/0.6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-3.best Updated Jun 8
JackHsieh/0.6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-4.best Updated Jun 8
JackHsieh/0.6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-5.best Updated Jun 8
JackHsieh/0.6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-6.best Updated Jun 8
JackHsieh/6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-1-master_weights_fp32.best Updated Jun 8
JackHsieh/6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.25.seed-2-master_weights_fp32.best Updated Jun 8
JackHsieh/6B.40M-20M.no-thoughts-r-0.0-k-8.lr-0.00015-epochs-2-replay-0.5.seed-0-master_weights_fp32.best Updated Jun 8
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0001-epochs-2-replay-0.25.seed-0.val-r-1.0.latest Updated Jun 10
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0001-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.25.seed-0.val-r-1.0.latest Updated Jun 10
JackHsieh/M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-7e-05-epochs-2-replay-0.25.seed-0.val-r-1.0.latest Updated Jun 10
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0001-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-7e-05-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-7e-05-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0002-epochs-2-replay-0.25.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0002-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 13
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.5.seed-2.val-r-1.0.latest Updated Jun 13
JackHsieh/0M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.5.seed-3.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.03125-k-8.lr-0.0002-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 12
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.125-k-8.lr-0.00015-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 15
JackHsieh/40M-20M.32B-predict-k-8-L-16-r-0.125-k-8.lr-0.0001-epochs-2-replay-0.75.seed-0.val-r-1.0.latest Updated Jun 14
JackHsieh/qwen3-predict-revise-k-8-L-512-r-0.03125-k-8.lr-1.5e-4-epochs-2-replay-0.5.seed-0.val-r-1.0 Updated Jun 20
JackHsieh/B-predict-revise-k-8-L-512-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.25.seed-0.val-r-1.0.latest Updated Jun 21
JackHsieh/0.6B.40M-20M.reason-predict-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 26
JackHsieh/0.6B.40M-20M.propose-choose-r-0.03125-k-8.lr-0.00015-epochs-2-replay-0.5.seed-0.val-r-1.0.latest Updated Jun 29
JackHsieh/prestar-4B-reason-only-k8-lr1e-05-replay0.75-epochs2-bs32-step2432 Text Generation • 4B • Updated Jul 31 • 9
JackHsieh/prestar-4B-reason-only-k8-r_train0.125-lr1e-05-replay0.75-epochs2-bs32-step2432 Text Generation • 4B • Updated Jul 31 • 15