diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de2bc05a4c9bc2e323bc1a9b8d1c8a95c27109b9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4293ea7826965fe65d7186ec34d7c6ec49fd98064cf9d643ffae455c9122f2c3 +size 52568791 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..baf236a15702fc90c8d343d0bdff313283ea20a5 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bdf3c820ed72f141681a8c5cd9fc0d0f4922d1950e4dd6a4668099fc493acb +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85f791026f73b5eb62ffd365f631ef534258b7c9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5242104eb3633f0859fd450b493dcbe1355fe2321c0e8d076ca3a89d6bd48f81 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9971144cfa73b3a2e2abd05f45641614abfff77d --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed02791aa03b23c05cf0dd0f085cea9c73c7f927b549183494b75c34fcc42e3f +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fff33c9c35ff215e353685ff69f888d54b8cb246 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e9dd0f02780efe3981c0a650d3ed0f24c2155744c068a3726b71e08415d6b1 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41786e271662aa3060d37fdafda12739490baca4 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade36467d0e41b50f1656c5997f15079c12121337a1f4584c7844d4191e06758 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7088bef1a4fa0e08196f7859df0e917f1cfbb293 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b3c8d832485ab0b3d7ea41abbd6d0da49d0ee8628db927b680c2253d1c3ccb +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da535657c659375c4234b0906d0376b316e2eaad --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e86ac156a4b30487608d7c9bc8420a66b5440fc8548f5568d9064d4740f670 +size 52568738 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e1580726792ba9a4025c26c45f3871a2121d5f7 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19abd66e43363cddd320b05f3ebbe54aa8bb8b7696a3af0c41e55689f960567b +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5283e6610af8cf7387446019929aba50f75b7965 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252da7de057d27d80c03e5aef8742870e7795f588006faa9f49c963fa8e62959 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..897e3b8053deb37d985fd61639d00950d2826c9d --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b4af5e4a85ef58aaa23a26974cc88cc35e2842594c1db664f2037c2cdcc57c8 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91cbcf769f40c24f87900a43be84bf3e0b9aa371 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcf65aac7cd79a9ce3cb3a08903340a999064ea448b99830754ec158522cf8d +size 52568855 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..891aea25c7cb14f27147b54e5c4ad5023f1ee4b8 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48df2cc295be33245ca8b4136c9db91488aff1bfb4d39e40c68c42faef194243 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a802b43a0d564488818ce2a95b2658b8b322de0 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90890d5d146cdd0fbbc2fe13b21b2963997bec23f9e8a4b9263aa8d35a07aa93 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f183b0b1a860715ff2c9ef5999877b67d12cdb6 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f4f4a0358fa3a92d074566cc72b386a890ef669634497838593982467ac9e9 +size 52568994 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..403dedcbb91a10c1a7afbab548adaeea1be32445 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfbac35b0de46a72af2e29f0174aacf08898591c7f768805c1af89e6890efaf1 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd81fca663fc6e339198a3dd8cbad5befbc9c455 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee038dc5e8854c08217afc97ed3654643519e58c4395a23ddccd0f133034b581 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3bb6fd512cc89afd33c736b406f4305ab60dfc9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9184203c4c44eddceed3b5850077dd419ac0740e90ef2673aa4015cc231677 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc0aa0553905611bc6fcf6393a90a9b14fee40e9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa26e2a054e4df83de7ec3b6dedfaa9d12ab48ebc16d11be8e09ab45a12139ff +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8787762d4f42230ffae9dae6db4b4d2d575543f9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d83444008a8bb688ec9dcf594f5c3e6d7969600fa766db303c03f8fe79f92dfd +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27e5f7adf9d695375f5214596b5ecec461e28602 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0fec8b03c13594ea50e443ec247a5898aba8a287b40b893999078289a923b1 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..069fdaa23c9535f3fa213bf45d0a4c83107d59ce --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690d5a09084699be618e1178ec865922a6af3e31928082215195161d60df8fd9 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8593e3a4476ea46da3b94bf36e4848bd2a30f31e --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35527d7b9f59f3aadacdc9486a0dc7201bf799bb44215986b36194d9c260274a +size 52568791 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d48f25f09db91e51aaf75f12d56c79a221893724 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64562543e618a7f4c28b5fb2e9d66bf81dcb88874399e3fbfcb97040d3ed5c8a +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95f4bf46c19b62a2b12803d333bfc9d89b1af1bf --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b5391a4ee2aa889dac89c6adadc96fb24bd946e97bf30ecc0eda781530c9ab +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd9e676d34105eb806868c0a3d3e133796d0f91b --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab054943dcce1b759cd71c556ae9283ae272c5e2e7f453aa92a6742d7101c7c +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaafc9024fde4099e04110da6f217fac457b3a00 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b653912c0b77bbb2f4fba1b4bd9d25b8f9e87ef1fd8895a44f28c7b6535bb70 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b21510619b2eb29b08b09fa6731ea7ea5cce6b9 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f340669cd074d250eeb70d45e6e1a739926f644496835bd30a617375d4013fe +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69ce6b97ac3e932ac647ceef13dbe7c58ec6965c --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6f08cb5935edb933e920939b95c55f50736dedc0ff47d9320c9c94cc9a2432 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b31fa419513eb22ad454989a3d564d748018a8c --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d00d57702fbced623f1f95cca4a6f8cc3eaae99d6c4666cd958dcb937f2dce2 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f11e5bda72852b672b9e255d196c64ab649bbeec --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ac2df41ff8b425b4345147747908608726a3dff33954841194c7faf538a490 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60d053d5d55231f42fa863e27e98a902e88b9fda --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309f69c131511c28beb58cb871b58b419d80bc0c009e8aef7682751c4f60a31d +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e12b092e0f5ba369aaa85af3c09c932b93fb157 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e109b748719229b461a3a198b9d05cc5735972ed09d9c1d321eea3ca405e52 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3f9a0e4acd80bee20d38a45556e56899c67b8d1 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57563975a4d19737e670c691cd209b0f223371a2e28ce28ac3b1d6154911e504 +size 52568791 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fccd0231a03fca3bc610da6713d4527dc6124ece --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bf4bea4c45d387fc044d5b04e9de93c394b035b2f5c8e05480274a4e743491 +size 52568994 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbb7d0fda97bde9baae9915e268c3bdb979394c8 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8310df5d1a6769ec0d3f1d23cec4690cc68eeeefd816b138276fe9e859aafba0 +size 52568738 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f85c981c58d0b3935b72abd49dbb5675d62dfcc --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3c2e622cdb05e152e201eb5029cdb2d59bf6b83e2dd8d7ebb9cbcfc124bdf0 +size 52568994 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae639c0f2f056137aa14960247d8f032f621cc78 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2768910ec3f6b4791b6a15895682edad56b7c3047b545593ff6bac6d115dfd +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7c2445b3e88a58920a49ad4ebff00f85fdfa508 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba554faf9b02573ef287cbbb4c0f17cbaa1bef49d62ddad9386731a54cfcb3b +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecd02227b4122a961b99576a7c5cfc41a73ece64 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e804ad87f7d1904a69fa611820373f97354d6dad336acb1c36a5ea188bc0dfc4 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..10616de516b6c760bc7f245300a1b21156e21c00 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa257bab85f87cfabb7bf08a490cb6e0114e8014247054824877460f59f6616 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49c77fcb497d76133abb2cabc0018875a27f8e1b --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04bb4018ca5a78735cdbb43c2b2bb51be08791d1460641966cb067a59ab3f3b +size 52568994 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..496332d2b1d75ca6ea59f869d91b17f14272d744 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a433093c1b6794c03edb9cc6dfe4508252eb09fdeb822bab4fef285f0c16cf5 +size 52568610 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa2423462411009c1932b917138b61cd070fea25 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43aa0e2365190dead12225668fce60b4a3ea9b901dc2c30e2dda07caecca104b +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe9a6700e2ec1f0adf7cf5e14b671c77d80bf44f --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4e55949ffc71188c3d45432df3b68e4c515c02e833b55c863032eea3c7fe70 +size 52568855 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38c59a4951451e9a3da1f9d7b54fe15491f054fb --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6ecfbc31959f3135e433c787c71389871cc33a5ec70da85f363bb8e379c9ba +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..974ac22b2fd08e401869a8ff618be14a15308cc4 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1903ad2c882a205ec62c6548c2043f55ba91e26cc7334c28c89e319ca22edab +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38301c5d435e26c502e1b631d49592ad750387e1 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b528403436595cf6954a72c7e0d95e364ab3da3bc96088b5819a034891edf32e +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..858501f6e2a889ef7fd2c56da47d26aad999d118 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a41a3a853e4c962dc450180cfa12217342347a888c4c68638bba05d10c29147 +size 52568738 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d273c87aafc664f4e1c55b9c6b4af5073cddec35 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4ff00cd4036bf925cdb18803061fa0401a4c874528af3de4b6388f39e856c3 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23414700610fd8193097766c551825aacf5cb15d --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddc721df3f3e30daf585317b938d2fa4348cc43035d2c965f50bb0d2b6cee7f +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e834978fd0ca0bd2e9113c0cbcbf31537efa26c3 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36712347522970a6439309a6f9b188d0415ac55af582d7321ed42b6723978118 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..097775aea6c4a71a9db910041bbb3fbc55bbcc32 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988499b0cc92940b8a8ddb533e2bdfbc1debeb6fe65ef58524ea92d99b87f525 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f02759dcd633f9eea4d02aa75f4e15cfb4722e4a --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78120d7eca5bf83619b817c7f7121e6b8e265ff74e9cb4b2a558e3979a8fca47 +size 52568930 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a6e5764639fc21431aaab991ba0c5ac27dadc10 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec923a5707f3a8eaa30899b4e7c67ac8f51eacab7166a42ed3c7b4a92c13e6c4 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..986962d2527d9a2441843f0137733d075cd3da93 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1764c86fb57f1e2166c25218fb2b907040f915603cc41db5f9f6bd07ae851339 +size 52568791 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cdf5afba8762c5dc87d5c4448933fee7e87eafe --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535c2ce442b3f8be47df13f670da80241a7bcc5b023eabb5c2c88f71b4c5c7a3 +size 52568866 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ce86df1b3e5fb6972e69ab8e09227401a00120a --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955496c594a36f1b2503335af875c747abdb2a8de1d6050d7ef9d270ea180c9f +size 52568994 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..983ee754a79160534f3b261403758d9fd4f2a99f --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ebcd94476c71aaa41c91a6926e596f3c8e40a68f6d0a45d26f16b5d5a70df4 +size 52568738 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3e16d322aa9e2a77733c9facc6a332468f01496 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac74de4a54d4bf9ddc509a9d976e927d302de38f5de901342967c40949bdd2c2 +size 52568802 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..663bfb00ae48ce7d6fd8cbfb22c4328012aa4731 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b6f17bb6de163b9177effb281670d104e120762528acb3e7509a0a0feefc8a +size 52568727 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e4dd188179084e2cd5fc25dccb864e4355a46ef --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f400d6e7415abf965b574590c750b109a96346e305920b8bfecb9aea33ec2a +size 52568791 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4807d3458c5aba63af02c137499229e80ee2a99 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5a6a42482fa7ebc5f2954a613a7462a1ca1171db5383f537dc09636f44a39d +size 52568855 diff --git a/280m5b91b5/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/280m5b91b5/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1ca27fe3890df1234c8ceec63aa2048f572a597 --- /dev/null +++ b/280m5b91b5/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7392985b1196d0e66f5d486fa2deaf31042ff3885977735cb2bb4735f8c097d6 +size 52568791 diff --git a/280m5b91b5/global_step11269/layer_01-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80a491cb547faf6427782bc7e7770d0f9065444b --- /dev/null +++ b/280m5b91b5/global_step11269/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33d7816a4c93e76a1d4254380d6759abbf1bcc54219a040b0034fc3671e719b +size 107218179 diff --git a/280m5b91b5/global_step11269/layer_03-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aee493d4198a63e8589f6b2e81be878e6f5b8cc --- /dev/null +++ b/280m5b91b5/global_step11269/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595b0d59802f0e4963694be1d5c1492b76810b49663fa0644f34269d376dcd6c +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_04-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f2e69b2cf402733d44434dbd19d43470be83071 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be7016bede2a52053e23ac8d39b4aadf847aed43aeb6229955cdba6e92e2566 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_05-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..614f9d417bc8f07bd38d673ff9242bda33724ab4 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26ec8e416ff7ce828a132499512cf68a693a89a26fd57142e3e635841501462 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_06-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bc273bce33d9686b358d588f6cd1df40914fc06 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb99adb20b55867e9a19857b43a6b74e58c47438a63ec5aafe2d5411d7f8d585 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_07-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..97f9fc5e6f6b2ee41ea17afd3bc6c2c62983049a --- /dev/null +++ b/280m5b91b5/global_step11269/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8778ae6ea260e93b0823ca4a868c08dab5335ab6dbe8832061ee20097683179e +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_08-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8782dd0d8ecfa9829e86c13ddde86785af6324f --- /dev/null +++ b/280m5b91b5/global_step11269/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc397d056fd91efad136a9e5a99e5337bf85714b713d51d004d324caf20a7a2d +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_09-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0325ea205775b0ef10d81516b74a1b21a9f12465 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d921791e622274e0e48cdb0850deecc036bcee8fe80e858c21f4b1e822914921 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_10-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e65ea45b4556185a1e3c07e2efe7ee9e8f3636a --- /dev/null +++ b/280m5b91b5/global_step11269/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52d3d6d9b6c4090d239959cb9d08fe1cd11712a6751b61e5cde170996e9ed5d +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_11-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e8b81030db8784ba300434199c0fd38ac8cb36c --- /dev/null +++ b/280m5b91b5/global_step11269/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f714e27e03bfebd1dbcaa4539812a7254b8bb1599bb0c8d5566b1a198533a8 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_12-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..453455df50f1a0db11553d28c0bac431ae592164 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167e9783827a2a249d99ed8d06f5111c878f6b83a7f89a58d2abc6d8a384148b +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_13-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..28919fbca444cdcc7f545fcda4710fd85690bf44 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76346323b4454ae0b79c83314286bf97564276a8eb63fac54aab5f0252742b57 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_14-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd8304a9ea11eb5658e60a31fecb2bed804bd654 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b30fc951ab16cc154e9b25c0b49e6c1dba74e8dd33a806c2d8ae4117b8775c +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_15-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8afe002f82f5abb66a08c5daeb3b4472edeb9f2d --- /dev/null +++ b/280m5b91b5/global_step11269/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597fc6c8b41231cb7eae3e8b76bc7b27b20260c5717df0eec37ecaf46e989eb2 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_16-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..486a331edc81fc4edc8319f04b49fd30f5511a8e --- /dev/null +++ b/280m5b91b5/global_step11269/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eaabf39f2ce7e22c617b7e2ed2e8049abd071695f21a9ff6e53af568a0f46c7 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_17-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9b17b8de7bcd158befe2b382fb527b41bdde750 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea82cf7aa5701ebb87c8b7e0ee61d5628dad18415b039afb1dd24934f34f9b9 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_18-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c89378b2773ee5614ec438c80cf7eff1e5ad00c5 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567e987f1640cead4121384d3c896be4bd09886d5df12b340c51468056e66db8 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_19-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98de65e1b3c3900a3d82bb41cc9985716a7a2627 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1a078fe67291d134e8381795d2927801e3baee9d8cbd7572dae5729300d694 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_20-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2ac9bbc776293910ac13370d8c536ee97f2d705 --- /dev/null +++ b/280m5b91b5/global_step11269/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230bafb8e05208725047be1b99b3587376ce225a56ef2616da82b7827a3571f8 +size 25196803 diff --git a/280m5b91b5/global_step11269/layer_22-model_00-model_states.pt b/280m5b91b5/global_step11269/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..540107c282779b6297d176222d1ba856dadd72bf --- /dev/null +++ b/280m5b91b5/global_step11269/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3367117fd5534cb2160c22eefe3a3294693dfb3e76d106a7d6a2bdea9c3f8b48 +size 5315 diff --git a/280m5b91b5/global_step11269/mp_rank_00_model_states.pt b/280m5b91b5/global_step11269/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b4cfa9b6bccc39551c63d750ee8df5042d45fc0 --- /dev/null +++ b/280m5b91b5/global_step11269/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d5c03238375efa99e4d0f74856dbe45fe8c2c4422f4fa5f9d3039ef7dfeed2 +size 37747 diff --git a/280m5b91b5/transformers/config.json b/280m5b91b5/transformers/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d490cd9dfd31d4b6a7b98fda75952b0196dea7be --- /dev/null +++ b/280m5b91b5/transformers/config.json @@ -0,0 +1 @@ +{"vocab_size": 50304, "n_positions": 2048, "n_embd": 1024, "n_layer": 18, "n_head": 16, "n_inner": 4096, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"} \ No newline at end of file diff --git a/280m5b91b5/transformers/pytorch_model.bin b/280m5b91b5/transformers/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ebe78482fa5d4c9b5e9ccbabf4a3d43e30c8ce6 --- /dev/null +++ b/280m5b91b5/transformers/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ec2ee5e826d6924190d0ecf4151cd408793725158143cab764cf988a5cb94f +size 711759757 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e972479e7471736e0e9bb0adc6bcb5a0e91f4a18 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb13f6c92306879bd56edbf2b26cf44eca8958156712a0644b567ebc7a17ba0b +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f83aa6d531d2cb93b9ed1ea819c9e33a8b3664b --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca1be08a1a0287c9d8ce7f8348cbdb92582f2ac424555f12c6fe1dcc56bfa29 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2feacaa66a78239888d67a7c17032f3d26891164 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af443f8364eeee39f41f1f3a7459c26117f800619ba49387b8092673f735cb6 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..096712c36acd51b3b3130aa585a683b0f51bded3 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11273a0e361773e3c76a22f9e7862c0696fc9132cf70d9279838ce002dc1f39 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..177f0bb97eae6f51683ffd326956f782a8c3152e --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b536eb95a1d3d057d153b4db010b3c616801fe184831a16d579e0f214e304f2 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b468939e030d67765454f9c8a2021bc66c949d2 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebf17a2eb1ee14b9e86357a9c738b59d9b2ca3797999b911fbc650e7a772263 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f4b36ab791be610081a153f481359a2d363eada --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4b14e1c9c73d03e14c79db48eecb483641b14ca6a0c108c89cdb93e86f7bdd +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..178f63e7bc5be033bdfb02d73f0908df99c91f66 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98e4c8eb87aecc49ffa9cb44fc8bd9b777d8b43779d6fd29df65069003afaad +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73694fc1eb8de2a81c71c6e1e2cff591af86dbbb --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634779a3809bfc4fbcd19be83d86567c6b592e1dbb76c2f056b10b45db30abb2 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..360049162a4060848986b0425c2bc123ea3ae9dd --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9acb5dd15a39a6b98d5ec83e96afc371d9f0f87ed267b1ca7b586734d92e51cd +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5153beda4b66bc984f19552710d7afa351f91e7 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fb78f25b30b4cc5c517145ccc7af91b6f1c858bd18a35531ba61ba724f0204 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cada9fac4d79d09aad3d03409bb5ee5fd8208b1c --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3b2d3dab0d18a7463a97a15f8d476b281b3869d4fb795d8436ef4680057d56 +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4c0736fdc8bc73b2040564a971836d20e68f161 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fcfa62bc90333197bce2ba6af6963a2e2ec41e5c442034f8aa3e5bbe76a891f +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ef3efd50d0094a80410d1ca4dabb4a96226b330 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5b7b03f21a40b15b82cc6ed5557ea685e0640a262374ceea66ce3aac7400b8 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce73312b1356fd67fb6cfc7cce6fcad0059f1858 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f95bbf204d374d8f1f285cfecb3d9de5317bb9cd7438ed984cdb6adc32b6c2 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90ba2d6184d0aba14d7d0a682e29a180eeb25ee1 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38062fa3e1e907f4c3d783aa74f812ebc065388b21d6318ee9dfc97c804dddb5 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e62abf21a4be73a447ed14cf0cd0bb17bc4933c --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e71479bd0b97a17182daa4ca910ef7295a9f8a5f490704a05d7ee5bd8e22f5 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5814865d1d8e4fd4c49797be449110f3fb8c9076 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0717e1521dbf33f934b7bfe3a503336de3b6e9b66a1c1f882e10949b9f8b1490 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ef9151c4a38d7ce913960613e7681121d7268da --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2266e5e628fedb1d3d47a8c42c149d560b5a8382b740abb06e0b1709d2375b64 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50b8bdaf8708ef766dbe3ab31fb2750e13c7bfab --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a81af1ff7d3b980f207b66f557ebf4970ac450150e819d767f16c554a1edeb +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aca894edec9eef62638450f89cde93cd17bd1e8b --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c683b74b28893654d0cf80564af9b723179c8a05b5e9ab4225450b4de1ed2d0 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..520f51767ec6891a9c300a927d32328883f7d679 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285a3451292c2208065621f8c60054cbcd0f4fdce9fdbfc0467435956d733b78 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77bddff24eb8d586d897a76010cce50c3f98853c --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f2ce3cb43b57046dda8a563297ab6f9c2a2d501d21cd6e3eb12a0bfb30aa66 +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..632da99d0a101acc8d1d413103cf21aae784f68d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71292f5bb3d8276f66940f809e1dd3b2e7dddd66559e1e52855deb9110dc7e53 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8608b49341ae9f937274a48d67c9f7b456d0612 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66841db011c76a310676b56df320a65904967968f5eb48fbaa50f35919bee1e3 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14e2d4ffdcb099b2399cab7ce9849e6b04a05d05 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7215508951b643a65426a873ebbdc70d614dd0e878b5b3de1a8ad6364c15735b +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0ae05ddcef52059fafc8b4b81cfd378c503eccd --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231d92be01b201cb6a30b4e3613a40111a8a079b1efd1102db86a7c5cc407fc0 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01cfe1832b04336cbdd3bba55a0dd871c24a379c --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37bce23ef7033646835be19008a956738b648c0e7132b32c2809bd5177ab86f9 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f0fe198eeda7300d4a8eb2a3f48dbeea81ff787 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea7fa4db561ec70edd9f0c59ade6d693ad16ba651ac57e1ac55bbc7eff65444 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c23c21ef46112b204c348609320a19d58dd8b9a --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8368672bc16539abc288441717e503172760420a0fc4c69c5b8b56d70007cbbd +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31b91a26bf94b385acc2bc4c8c8674f562ec587d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b020075f560de99feab25bcff93c1ca11d1996fa737188e039918cd57122a4 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2659167182791e2a5d86a3214545aaaf73727cd --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6fa280521c02b7c40da8ec13bb48aa0f506c7eb62d031390e7e67a66e459bb +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0329246c87b706b5491d18ee4128c943f2bc7b71 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa0feff7b4ad93485cd850cf04ba4951708d1f2b037129324c9fee4a2ee3152 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81e067c33200870ab4764de74dc31346cecd3684 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96c615ff115ba31539eac2ccd73a32d54e411d96ab0925e122e315135df47fc +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c1d93b30747d3268915fd7c89ee1189f0409a15 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b6755c2998d315d36778353a24bfb3d0cd6754a73deb1a9a5daa6d7b101865 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be77a28921336f99b46752d076bf6b584fb20094 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc86506fa63c2447e7590c8f1a98ab08b5948075fba467471362e02179b4be18 +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c42d2c0c6f5198b92425b8893c43e33419abfe6 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587e076a0948356399bb35e3bb11f84dd11fc29434401acac8cd886b429a6d4c +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c461cdc8b5f66838e128f8c0a7b4d03e0971f62 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751f75f148ba85c213af05fad3e7bbbaee9180a9db1b94609d406198ddd4c9b9 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d52d0c7581b529b68c96e5fc94512d107d1c294 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ccc8ba6d60ed203d4522368a489cc780cc27217982116e767a83b948cba2c70 +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e1cfc01e1808630953dcee9994dc57021281f3c --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1fe6b3351c74a4ab3aa39ee8ef83f733c70ce873b9ee6ce707a1c205e8d4e7 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfb748ee11409c7410f6c31c3fae969af52ce51b --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437fc068206be276f9b5b11d4360e883d0019b8630a7dac93c77372aa7146244 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..113894a92305b2f7fbc9427d3203bb20c27ea165 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddde2aea8af88031eb09b723de69e7ec7709efa2b39a0d5703b696c59a34f59a +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fed4ef4fbcc05829ffa92fcb6e08c33357a244d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f217ccaf67f395772e317c0a6271a8e268eea739e32628f67481fd82d36a0bbc +size 52568610 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf5595d0d7ac359a7177eeb518a3e06aa4235ab2 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f4ae5f3da261f6d811ed6d08914e435d08f80ddba1773d7777532d9418b70c +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cb293823e98ec87fda8a8b4df2d17aebbc2d84f --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121d5237fea7a06dba79579267017c5ef52256d4bbcb463de762b6bf5f5641ff +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..139dcf5e9318ab8dd1b840ef2b7b04312c9e05d9 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f663ea380ca4fb13f3d67e1c6cdd98e107f27b8f96e798ec9706483e409c78f +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bca6784ac113ee734eb437ee56b0533342b98153 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b083354b553a6657ca81ba7cc1221633520e95cfcf3cd06ee4a9656c2ec155 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbe12fdffd9cb13d7bada36264f59ab1187b9d0e --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4bfe2d4e0fc4ef7fcae54e4f7f73dfdfe31b817282b5207f79be52f628f06e +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1dd78dc8d0a8a3a70a2c51b9dbefeda81e849b9 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c240219a8a01bbeb322ae582890f8883e082c3b61d05c313772c32ca5a839b90 +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d13dbffc8594650aea8166e5f49a8db2c5d3eb3 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1de93338821a77816ce621429eb4aa68e13dfd0643b75cfe8a4a745e3fb77e +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1f1a0e7a4926468b633bfa442db9367ef688c2f --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b524bf5ae9287ed7df427715c2a7a313587a780b457b667f8a53824e7a4a45 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc1b03a9d090956bebcf82340fdb3eab89674a64 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcb39ca7162056922282ef844c5fe9f80c119c33abe788514ab28909a08fde1 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7d988dc207dafc921838bc54c5b7bb5ed7e89ba --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441db2b9d5399a68afe392a8d10f22817638d61c37f800469799de728408799a +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..11cb5e6a559474c0521ba116bfdf843f34d6e388 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47be845e9dfd7e0661ee63d0502343958afb2a2712f4b750eafecff2700f9762 +size 52568930 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d242857ba124e8f0a62d3246a855568f6ef9e30 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d29ed0e76424626f4477e787be093e20f949bb9392bdf8d68fe76201ae357c +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2fed38bf0421e1037c0eccd1191b64de98459a60 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97caf818c927c61fd43671500996086886ca7a21eec330e3d5ce396127cf5bc +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4630a8eb943ada583669425c493a300f643fac9b --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03083c1038660be5be345f3d09c2cead19d459bbd4dbb6f606fe2b88218e764c +size 52568866 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98d008bb8d1202822db8c60e6a2d8748ae0c82c8 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9901146a81913b8b449bb3fbc8c3ebfe57eb2d2412585957307157de03b54929 +size 52568994 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6e45f0eeb42e8b98bf9bd4b36a70347c0e72ebd --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9af3864dd3e552d2e99a907fd967164fc228ac11744082d6b58bfece9d62f855 +size 52568738 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50ac54114b64f0586a1a04f62048e44f908b6e23 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78e46d1e4c8511cdfcd467ba8b234f2456b378079916191319c25601b8a1bc5 +size 52568802 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbd9c76dbec9a90c894d08761a86be2706e1b84d --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a0126225c02fa1f8f220f5db128e79c300d13f268200e693135b9123e1bb4c +size 52568727 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb16d95471645168d242ea6a9e3857cab26021ca --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9815860f3addbdb625fa36324848a865f570d0bbddf0b87b5d02ba09e30ce2 +size 52568791 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1caf16c161712384bcde0232710b9f56a2b7c056 --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7cfc985fdeaa9373f8f8beadcd06a539ce03333e38fe4ff4bbad1c5edee175 +size 52568855 diff --git a/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0102948f1505577c8c09e0708ffb8e857fe405ee --- /dev/null +++ b/280m5b95b9/global_step11269/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33d401408fae6df1e9d18afe4a2cf692caa0d473122347a7097935db06d83d0 +size 52568791 diff --git a/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e244b36372baa26da50644ad8fb4f0a2a8e4b30e --- /dev/null +++ b/280m5b95b9/global_step11269/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed1dc38cd0f7c5abc12f9b119b645779dccddd6339d518dd77bcdd3e9a2d2e6 +size 107218179 diff --git a/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b314a5643befc675da7b3c203024b4a710f9477f --- /dev/null +++ b/280m5b95b9/global_step11269/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09dd6d3eb89fdb18095e0b3e4afee31e27c5a1a9c165a9e12f9b334c52d6e4c3 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3910a0a31cf90b85fce97732c22d7eeb66a83729 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de844f48f5fe32bbc18f3cbe473311427cb07b9ba22fee6cb39bfbf03cc3d5f +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c42a33e69bd7befec2d8a2d2847cc197618318b --- /dev/null +++ b/280m5b95b9/global_step11269/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d8677b4e0ca5a0f71aa6b4c162fe9a53f0008207fd5b910c4cc466627f234f +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dffd7ea2193de5670ac92c77e46482abd1ee84d --- /dev/null +++ b/280m5b95b9/global_step11269/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141035edc16f0cc12c9870f371315ae3b8b649ebf26bb6333d2fa110635ac339 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cca40d426e5874fddd86c0aa6932733f7f1fa10 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c88bea7b20ad7020eefcc762d45fe3f6fb75ec1f569985bdeb1b3c20c6d2768 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2dc5bf2b23a1105ee6e6fddbd3a5a02a14ca075 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cba5eb59578daa92b40267980512fad72770f6b4cc5446dfbcd5eebbc272321 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d131cb9eff3e17ba71fca107679aa3cad79d8308 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc273487914e058cd30bd478d8e6f8136f23a2bbf2684980b0d4c733af5fe5df +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07a567e709cbabd6db26a30bb105af084c0f9e37 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7533c6ba1634ba4f209f67dce48f41770e9d4671039ba3e26cbd9888e8cbdb9d +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e29537e699315827948eca2298cb84e756562a5c --- /dev/null +++ b/280m5b95b9/global_step11269/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72a188925b9d44da43685f02fdcb58bfaad64edc31d54a93c69bcff53d18ecf +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e59d0af3166c6770816c0e27ce46bd58aa4a1fc5 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55cbbc7b5f3c5fbdc1de65d5d09ee0d059a8328321dffae077556ac7d743e3fd +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47716a14408ddcd231d1507cba28563f436c8fa6 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b88f35c496be12a90ea82b1bd5e5cd066c5f064a8cb7c6e9ed138f0b6325eb +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..106a566fa3e34e9f5a5993fc43bfddad7e0a7ad2 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c896483e017a9d4203e2fef9eb6ff1fcba1c6781ed077490b7f25e2b349d8358 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77ac53c1e52f5ca6f2062115e000980e95a5233c --- /dev/null +++ b/280m5b95b9/global_step11269/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac7567de79b59bfe486b0b212d96ed7fa17979f9e85a6c776e02abf3bbf089e +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22d6dd2a5a4bdba8eef663fec19b3f83e7348b8e --- /dev/null +++ b/280m5b95b9/global_step11269/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce8f0b4f1285b04197e470835a6e056677d27e25be45d0d46b51d410c246222 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8dc24890c1cd5143293befbbb9bf7f2f7ad5bf2 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18fbecfcf17738827420421c65671ce0709acebdb0e2df47774eea3f90582600 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c0501d9e6fd0b1ebe56cb6f914108a3f12fb1c1 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128993600dd1672d3016443f029969d6e1b4230a372750215f2ccee898002db2 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d80a0c8c9645355a71e308d6c623926f22d75575 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2812c8637f7ea8e2827269bf483597c9b6f6c253076ebfeb1889b9e28a0205 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5ec8ce259a543e516969284d6b6c8047fe4f100 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13312054c5e7b21b1f23dfe12f018bb8330ffbd830a4234c8ab92f67577eb634 +size 25196803 diff --git a/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt b/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b73cdb8e021f2f3048410d832baa5a1b399c6e37 --- /dev/null +++ b/280m5b95b9/global_step11269/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280639544068436229caca5df698f0ecbac7f23fa66e877ac6d611b96594d3b0 +size 5315 diff --git a/280m5b95b9/global_step11269/mp_rank_00_model_states.pt b/280m5b95b9/global_step11269/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..efd0431fa72f59bce6555d30023780957264621e --- /dev/null +++ b/280m5b95b9/global_step11269/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652cdde43579b96b8d963d9692b0069feff4165c8ccdfd24c7b0cc9e1627b0ed +size 37747 diff --git a/280m5b95b9/transformers/config.json b/280m5b95b9/transformers/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d490cd9dfd31d4b6a7b98fda75952b0196dea7be --- /dev/null +++ b/280m5b95b9/transformers/config.json @@ -0,0 +1 @@ +{"vocab_size": 50304, "n_positions": 2048, "n_embd": 1024, "n_layer": 18, "n_head": 16, "n_inner": 4096, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"} \ No newline at end of file diff --git a/280m5b95b9/transformers/pytorch_model.bin b/280m5b95b9/transformers/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..77d7e5a2d6a43966dea40d0a4837cdf1515edfc7 --- /dev/null +++ b/280m5b95b9/transformers/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e132d4dae83ba7a736d71e859d9587bce78a10f9f6800b73924af28ca567103a +size 711759757