diff --git a/.gitattributes b/.gitattributes index 7a57a52ae25ee807dc92b85063940ef35c0dda36..e725e2dc1c6a69f58c8b3f42940609415d276ec6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -120,3 +120,12 @@ train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/artifacts/models train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-1200/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1800/model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/13afe5124825b4f3751f836b40dafda64c1ed062/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_3_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/blobs/584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_shuffle_deterministic21_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/13afe5124825b4f3751f836b40dafda64c1ed062/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-600/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_5_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..c7e8bdcfa530a43cc81ab80f394d84c7fe3e2b0a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8684c9462d9fc3fb615b731881af04d8b16f65be4da19dc5a18ccfb1a6d504 +size 4417900 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..9ddde792089d80164c573846f5e44447020a47d6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8b3b5e1e25b38b8ee0f53b9d4918bdfeb5b33f56cce7aed26deaffa30797bb +size 17651860 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..6efa9191791716d19b27e28b5e8986e9fa6c811d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74659323de5b02fb3bd9fa1f31aaf574b954b0e354e9ef26613d324fbc318b4 +size 15127301 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..7f0f04b978e6a25ebc5c188a5c0d9238bdad124f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bd87152c93775c208fae2c5f037b8964a1b6f15596a031f46550100073856d +size 11026365 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..45ad5a1ce29592acd1d03f969759224d7083607f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f09903c9a9a87070cf9a597dce67a0f2df9b3749600bf2ad1c223a7d5281600 +size 9609434 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..60b83f12968e57f115f7ae83f37bba3a35b20dfe --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a53ef489760bf4b814b7a4a81c9a2b8517a9afb80239b9477a610adc7bb36f2 +size 808033 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..e3f609135d3490a2729c2a8affc47d10cbd79800 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1a76bacdd1fb6e8cea5eb76992383338f70a25ef32eb1a63400528aebf59cc +size 4304538 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..090bf25520fa531f4e4ea360778c711379931119 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a00c7debc157f33a44ce0ae100d1e05d8edbfdf6530419a90b54810cb86ec83 +size 1936128 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..b12f7569768ff67000bb84cf64dc2d8e6296a30c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdfab6ac3f7e34480f18507af3729adfb86130d385e1a8de40a4db93be693ee +size 6612672 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..915f6ed93e546e8a0255ca0307ce9f8c294c2c14 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa1583a706e368799e9ec2d9c06fab3659c998677300f9fc30b5dad85e5aa83 +size 3774128 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/switchboard_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/switchboard_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..90b1c94410ad9d61c680776ace5b8e082395521f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected_sents/switchboard_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74238735ec71f58fbc5685e640a7309801ffe2b24f593f705baa1262cdd4540a +size 337150 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..a5cef1fb80f3bb481fd745d34e609c5a5359558f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe9f94f47b24e03b2c07c1a4af77ccf3c96116d613997b452f59b238c7d22763 +size 3362470 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..ea740b8d85be2a5e9b192cc170d10198704dd8d2 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fa37dc4717741cece16428da16292c8d4fecfff4b356ec8068250f776c586a +size 2691936 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..4169567288269969030c7e1fbbf20b1fdc100551 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894447ae9b216856ce8ee1ac1da2598052e4cdfdbbe19a4ef0dd8d810ad67488 +size 4127354 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..090bf25520fa531f4e4ea360778c711379931119 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a00c7debc157f33a44ce0ae100d1e05d8edbfdf6530419a90b54810cb86ec83 +size 1936128 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..e22bf520538cb76b39dcf1bd1c46770849b20dbd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ab781c0931404c57d6102bd86edd7b9ef7100a432c94cd91f40d0784b14086 +size 9069569 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..c020cc17ad9eb358b739eb7308d46ef629ba6286 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d9c7f69dbb14d752a82e4c70899d14bdd7d737fd72d77b9f0a5452cc347826 +size 9907630 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..b12f7569768ff67000bb84cf64dc2d8e6296a30c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdfab6ac3f7e34480f18507af3729adfb86130d385e1a8de40a4db93be693ee +size 6612672 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..e24da90f7bc2f8baef42c40a10879a728ada2626 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5b1adc3fde86a5124e5400cd391983093633922eee4b60458f6379c7174630 +size 4417900 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..5470c247d0c07f64cb416f3e6079adfecc2e9e1a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae14858cb729cc08b6589030dabc9cfcd4a44002159dfa03513321d4c634008e +size 17651860 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..66694fb7358f34a5814d899367aaddffd523ac07 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7011d639d422fdb7c9f44aa36220d6bc89ea8f4e232923aa7ce4df039667c789 +size 11026365 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..91abd83fc8db480a9ee0cfc6a88ea1dc4844e863 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3c580156834a80e675a514eb7b44e3e1e3d42c99c8c03b400cd0768ae68bc0 +size 9609434 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..2de8f643ba44b586857d33deb1ce7a9f955b7576 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3208a42d7b40bed6dded6cb7b298dbec19afcc965c067e58f0e6a52359641007 +size 808033 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7a0e9feff36bd3e00a309bd4066e3e2cf18d0078 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394832e6d23e93b2df715e019de66c94f991e2f195a02c1b4a949b27427dc051 +size 4304538 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/bnc_spoken_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/bnc_spoken_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..50badb63e793a63d69f2ed03b941ebd63f32f196 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/bnc_spoken_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29015cda832f132dcc9d1ef48c7be789da1b75cf79fea382062d7665a784bfc +size 2138751 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/childes_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/childes_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..b6a77097d5d71a594a9e574c7d2b035a764d7495 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/childes_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2580792113c2d12b93f49cc13d09c718ccc6a01bb47f35013e6c4fcef212ce8e +size 11836414 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/gutenberg_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/gutenberg_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..ab67e1e53312272db1b0535bbc9b205383276f0c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/gutenberg_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3e284d8a5d241e864d7181b5119b8cffc756d1d4593d37326e065180baa1c1 +size 10822314 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/open_subtitles_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/open_subtitles_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..e7ad16723bb766df04f4a3bfbdd3f405e50fd1cf --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/open_subtitles_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d1b45c29a132f470a9b6408d667e5e68ddc5d3caa7c17633eb2d29d045cf6e +size 7839251 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/simple_wiki_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/simple_wiki_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..19971982499cd8b234d46ad91d4f90bded6dccb0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/simple_wiki_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b43fcc24d69158e04ae227db75c412e47fa8233f15ae59a8e8bbd74e560c70c +size 4473447 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/switchboard_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/switchboard_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..8f189bd544f4401a897fc821d1594d58dffbb784 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected/switchboard_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ffae1a946aab2bdd9ea6e6ddd0236acc4233409a3dfbf3962a019f8dfce38d +size 438728 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..90b1c94410ad9d61c680776ace5b8e082395521f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74238735ec71f58fbc5685e640a7309801ffe2b24f593f705baa1262cdd4540a +size 337150 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..8ba61ab52fe2522d1d4b71a307719958bd412686 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844791e847323d549119de4cf74bc399ecdb7b189581f8a8a7b28925cc4945c7 +size 15267499 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..943584bf1a000e2890dad484e9bac206debf5334 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f135362030c31ec5a3c610f37b5900552d065b9a07c3da5ed06b8ab2a2e97d +size 13877592 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..34d9ce7773fcf253bdb43d7c70a21dcf136f1ea6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a27b0fbf8df01c2cdbe6f66b81f3483a32c5640c885dbf9e348c7188bdfc16b +size 9365894 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..709c60a05cc666fd810cfbed1a8cecc885eac3ee --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:979fb1fcb7cb8fd26c6ef91c4053a40d55c42993dd95618e9c27a75a6ae7c0e6 +size 5542795 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..cbab30bd9f7e0bb98f5ca70381f3e1925a1343f0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e068700cf273c0669599acee218b35445f613f4cbfd1c12741dbdb5ac7abc63 +size 24499725 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..7020b4be9b4c0de222cc7d779a793eb5cf6410c6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f1d7be26017ee7b56f4b6e9b7528aa56caf5f2a9c8b381dd6b40beb29ce3b29 +size 14508573 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..d1e5ed242152b97da3872ce66a5008c711f21503 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126ce61d883a61ad1d0e76b9b4943eb1153b17c1ba517f8847965a3e4794493c +size 10406061 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..7bc5551b89d9b12a75627a78426cf92d28f0c59a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_full/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d604af54e73f061b35a4919181f320a37c71407eeac642aa437d4668285255e4 +size 960676 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..e359d12d3af7fbc1677b178d519e419366c0bc07 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a726f9a44a09f85165976d7ac56c0b9d6878a4426ca1cc5388c806476a3ec72d +size 885832 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..66a0dade51612ffe63438a231d49e56583527edf --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec415119918a2d06e5ee0655623a7ff3fff3055488b4947ce98d568d9b199450 +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..6b313bbd86ae9ec5352485cb02942976ddf4e13a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb531494ed5610122dda4b43330c260b4b3eb7838dc94f094f27705b7f34a63 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..2161c003834f0df11015937620c94aaeb13f0762 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ac2532a55b70452e65d7265b12acda6edb2f9dcc98a0130ab40279f959b4ff +size 21246382 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..aa026190f9bb33b3a8e03118417e7883c0b32c4a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f62117e37041df38b79376b191b157a44102d4565542ded737bb3101fbc97fd +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..820a2911501b376521b1c033790cef06311c5455 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08befde0681189c4ae598d80e925aca2eff7e33adfc0a5e8f494e80f5989fea6 +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..1ce907448f5e1f27bf22a8bf45ae109c883bfbbb --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a488aaaaab92e687ead3594c7c0353ad2f359a6feeb30e9a62e3844dc6f826e5 +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..00985246c5f62dd3030cb83fe2c66d7c5b521856 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6266129722feef61afb3d03c4debf3f46030f4bf83e05da4c1f65e8a7eec5b +size 885832 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..90cb811e2bacb41c9f8bbf033d233aa3f671f9bd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3387c7a2fcefc34f6c68fae6ca03845c06d2f03d3f7d59a65ad84f911956d181 +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7da4e19942d5bd9fdf702138add29fd1ef82a198 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2772295770aa504cfe8dbce51a856a6cb63b3756cab77609ea9e8117ef5c566 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..aae1b5802a1d4908e40ef8d2521c6e7e301215a0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03a2db48a21d39c113028d385f6ade35c4121b317532b2503894c82cad107d0d +size 4417900 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..6a8034a9ad08dc79b2152ea35b8857d9540be2e3 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f61ef38fdf29d40ea97849976f8c56e44c07f27de30ae406c6d56eb90f8a113 +size 17651860 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..764bd5b29c44385f15e2460671a4a2153068a62f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090cdbc0d6fbe4abe402437f8111ba4833b5210b430e7b981496ab69df875cdd +size 15127301 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..f8a991f00e3839a71d9c41ca119fb07d34498a6e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e306c246664ab85ce1cd6ed1d5ca1de1b1f97d5d0401117f110f4278ed916ad4 +size 9609434 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..11c8e499e8a0d17738c009d82cc8cb3ae457656c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9922b2abb2171d11728957932ce6f595270fe3076658faee77643e41899e13f8 +size 808033 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..57280d5f96f1b07a5fd0f62e3805035b4fe66af1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250e3032e11ffe48526225a7ed4bc42b5766be9d7531f1abe7b00dea348cf631 +size 2320164 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..9368d0bfd31abc4f7a6f3b36253176f934bc2f66 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be973489ca0aec0eab1b60f3e3213de2d1f299fe4e366de194e120352cf71bda +size 4304538 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..a5cef1fb80f3bb481fd745d34e609c5a5359558f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe9f94f47b24e03b2c07c1a4af77ccf3c96116d613997b452f59b238c7d22763 +size 3362470 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/bnc_spoken_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/bnc_spoken_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..50badb63e793a63d69f2ed03b941ebd63f32f196 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/bnc_spoken_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29015cda832f132dcc9d1ef48c7be789da1b75cf79fea382062d7665a784bfc +size 2138751 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/childes_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/childes_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..b6a77097d5d71a594a9e574c7d2b035a764d7495 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/childes_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2580792113c2d12b93f49cc13d09c718ccc6a01bb47f35013e6c4fcef212ce8e +size 11836414 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/gutenberg_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/gutenberg_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..ab67e1e53312272db1b0535bbc9b205383276f0c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/gutenberg_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3e284d8a5d241e864d7181b5119b8cffc756d1d4593d37326e065180baa1c1 +size 10822314 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/open_subtitles_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/open_subtitles_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..e7ad16723bb766df04f4a3bfbdd3f405e50fd1cf --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/open_subtitles_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d1b45c29a132f470a9b6408d667e5e68ddc5d3caa7c17633eb2d29d045cf6e +size 7839251 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/simple_wiki_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/simple_wiki_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..19971982499cd8b234d46ad91d4f90bded6dccb0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/simple_wiki_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b43fcc24d69158e04ae227db75c412e47fa8233f15ae59a8e8bbd74e560c70c +size 4473447 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/switchboard_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/switchboard_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..8f189bd544f4401a897fc821d1594d58dffbb784 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected/switchboard_unaffected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ffae1a946aab2bdd9ea6e6ddd0236acc4233409a3dfbf3962a019f8dfce38d +size 438728 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..090bf25520fa531f4e4ea360778c711379931119 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a00c7debc157f33a44ce0ae100d1e05d8edbfdf6530419a90b54810cb86ec83 +size 1936128 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..e22bf520538cb76b39dcf1bd1c46770849b20dbd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/childes_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ab781c0931404c57d6102bd86edd7b9ef7100a432c94cd91f40d0784b14086 +size 9069569 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..c020cc17ad9eb358b739eb7308d46ef629ba6286 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d9c7f69dbb14d752a82e4c70899d14bdd7d737fd72d77b9f0a5452cc347826 +size 9907630 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..b12f7569768ff67000bb84cf64dc2d8e6296a30c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdfab6ac3f7e34480f18507af3729adfb86130d385e1a8de40a4db93be693ee +size 6612672 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..915f6ed93e546e8a0255ca0307ce9f8c294c2c14 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa1583a706e368799e9ec2d9c06fab3659c998677300f9fc30b5dad85e5aa83 +size 3774128 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..90b1c94410ad9d61c680776ace5b8e082395521f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74238735ec71f58fbc5685e640a7309801ffe2b24f593f705baa1262cdd4540a +size 337150 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..66694fb7358f34a5814d899367aaddffd523ac07 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7011d639d422fdb7c9f44aa36220d6bc89ea8f4e232923aa7ce4df039667c789 +size 11026365 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..91abd83fc8db480a9ee0cfc6a88ea1dc4844e863 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3c580156834a80e675a514eb7b44e3e1e3d42c99c8c03b400cd0768ae68bc0 +size 9609434 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..975898b4abd7c82b3c70419d3cb9e11a28d90daa --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd9b8c04b859c0ae6ee6313260ac2cba6421a6446e5b3d021d92f3325fd1f4e +size 16386922 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..ca1d538297c66947b8f93a5673da4c3bc6e0f279 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f699f4c9b5fe1d6f2c9f07e040644e919f202d6986d0dbefa379e4834d5afc70 +size 14508573 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..becf3348332a5b6d4c10b68ff08d3818a3ea059a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07a5cf16f1665026d9ea7a274b3e0b1f630704ece30cc6c94a2eb8ba660ed17 +size 10406061 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..f5bca0e05b24e1e4209dfb154c50a3c19cb45e04 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e469d7580367c1e3a7932d9e280f73bd52bc2ad30ab2ad20d89ba4fe4026dc +size 960676 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..2ac334e339cb167b683a2689911708b315000755 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ad7855e180a12a81f0b1ce9f74acffd65a980f220e3bc7437bf67f5376876e +size 5595388 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..610600ca672b2263cdc28cc8b8e64abc5556d105 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2616faa79b968fc7e85d8696f0354351285072a8e378196897150560febb1e9c +size 22934709 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..8ba61ab52fe2522d1d4b71a307719958bd412686 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844791e847323d549119de4cf74bc399ecdb7b189581f8a8a7b28925cc4945c7 +size 15267499 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..34d9ce7773fcf253bdb43d7c70a21dcf136f1ea6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a27b0fbf8df01c2cdbe6f66b81f3483a32c5640c885dbf9e348c7188bdfc16b +size 9365894 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7bddc77c661e91bb24e2dde5538a168791e91b6f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a5162fd58503262890fdcc1b9359323f1b1e7d189bad3cee31571f6ba12679 +size 1086542 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..cbab30bd9f7e0bb98f5ca70381f3e1925a1343f0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e068700cf273c0669599acee218b35445f613f4cbfd1c12741dbdb5ac7abc63 +size 24499725 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..3c36c8f59bd5205e0e82fc558f4faf9c5de0fce4 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a259bdd2f6fd3f3ca1a6428397c772a35c9324c71d458ebc464bb11c53af67b7 +size 16386922 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..7bc5551b89d9b12a75627a78426cf92d28f0c59a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d604af54e73f061b35a4919181f320a37c71407eeac642aa437d4668285255e4 +size 960676 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..9063d2c959d14627357ebc4b9f15452fe2fdfd7b --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f79e95756e2e8aea832407135576329d8b948467e3b4facb9cd58d77f073d9a +size 9365894 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..c304779ccada7a6f0b79c7454952712f4e6225cd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26bc33eb1ed478a4175b3bc1e386e460e8fc723c9be0141476334fdfaef9df2d +size 5542795 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..e7b14f9ce26b0a46ee6a4eb829e912bdfe3d532d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edeb95e87575294af1602a2ca55e483558c8b26f2572a979ad81bd1df9d99a45 +size 10406061 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..e007b1a25ec9d7b4892c84b0bcf00335389aed79 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3a1f1d88eafd7d0daaa5e759407bc9cea7622d5ec53f4f793124944067b620 +size 960676 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..f1729faef1ecb811d0385523cbae1cd05db547be --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0377842499b65111dd992956ca437f776e3a0f25eee4c88544c265f4fd632021 +size 5595388 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..d608c58a6cb8b0559de9b5e53014856a143a25b7 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad635d3d6f77181b3df5f96e4009ceaf2752922f2b23aa191127a986894334e +size 22934709 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..2151899adba9ab51f00f5146735b738ebb9060d1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cad8fbbcc1fa843482813f98eb69b7c9a72bc0ad2c46d91be45800cc39cb647 +size 15267499 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..40131a186975b54ef473701f0dcc17319e929050 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8532e49103e21fc06fb3eb3ed720380797afe5cc8ee5aa5b2bc8231722376580 +size 13877592 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b7faaa7951fbeda8044e077c3ced0882c18798f1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa216d8af4f5e9b16132e49c8d4f7b4f66b615ba479068b97826fb78910eb0fd +size 9365894 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..6feb483ca6bd86cfa891b7f7fc3d44ba2221d8fb --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_partial/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ce388b9a9b3bf085dbdcbe62e7cbf9755d69af01917cfe3e039a69d00b03c1 +size 1086542 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..dc3aa7e3c30c38153adbadc9837940e6601065b7 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29a443cb8b2f89823b779721f8721a008d10933f9515b26dea597d04187d8d6 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..1fc7c725996d354b3d37202c269d2d99f33faa1f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5df252417ac47dba398877aeaacdafa86823a65a2cead1388d3dcf219a3674 +size 21246382 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..f712d43b2fab85299ec44ce1fbdb9b7fcfb44fe6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df601c8040219d364f26953730a1601dfd027c48425400891d6079cd28886523 +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..bdff14e124ec10a3ae316c43c9b86cd2a11200cc --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8575595e9e8ab5658a3edb1a9c3f582e9c641fc3f08731e0e8c9e659eb566bc8 +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..a839fe8a653e05f520feac4bd41b3a4ca137051e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561c77e78589ea1cee4242104281bcba9e9f3ebfa124f8752596f22e863492eb +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..bf68071530b4b59a2a38fa3d0c7bbff148e33554 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a72bb84f801a343fe841dfdc86a3bbdd860f818ec141763ec2b2cddc909131 +size 885832 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..85fbf911fdb53fee5e74460884b3c6791da8fca6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52222bb12834f20d2198efb03824ccb3ac4b48c0c85f9958b3ebb1db0cfca3e3 +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b25a7a308046f8e6a1f63335a6c4e1cb956b9ef3 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ac20364bb15908b9b9dcdd538d071b94c7aace1bcabda2f6483f2cd6dab247 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b5a8c12b6f53f238a8b575359fad1e88e6b53ee7 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed91d9ac26ca0b0d7e2e0a7c0345bd07c70b86e9a9b21f7f04fd87c5d1c09662 +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..f78af91c79d8a2675c82e24fbbf4d722378350d4 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ade608bce0ae083f7370e0400b50e69548352415b912180dca02514e6f7b13 +size 1005125 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..d66f50fbb41a30b1ade270c37c84814130b53e51 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557c53717431b9a6407a668fdc84b8ec016ffaf763ebd6a1e848b6b8b309a6e3 +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..5c7c62442f6dce5788d7ff51443d46cc3920f0a8 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4da4d514c08ecedf417a25eb1d639ad385ee8789314f06c24910782392aef55 +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..cf1c5b2ee4eaca4dd8cb2807394b0185af15ece1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic21/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d433a76f73723d6c79fd841a93f55073d84a5f02816278abcbea77d156bcb54 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..58c749c3f39d7b7ce4e0f1c530d045b8981fc5fe --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df50e7b64c7cc242a357120ae3a2a9118662aac788476ffeb1b8171b3e7dd549 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..7101b8d51a4e524657142bad0bf1a2665cd270dd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4a83031e81f8ccec642e1f75c79211a2fd6b1bf0080f5dadc79614c7bf164b +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..c243c24fae9246e76faad110a5c9b1af9ad97d56 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5caf4d6bc39387bd64dccac209f3938da34a36457a905a8ef831408ec5b1a7 +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..e2b18effcd14710f920359ae0db2400424ad65ad --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7179621dbd52f79accccdf46c5b6f3f945e5343be12a9cd024aa6916646193d6 +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..41e91c07b303e75c787255c6f019b3e51b036573 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02fdc40cce15dd18c51daf43c9fb65253fd332302c2ae3bcb935b08393295821 +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..bfd96cabf5b5e664e6125ac734ac9918e8005950 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33323418ba1e3df7f9570196af5b1f45308f724c1f9cf975315adef52cbbf77 +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..0168673d1fa62f83a0ff5c7d76c1eb7f2aded74d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf82fe8c50a8bf3ac977f67cbe6c57e78cee478ecf3f9bffcf99a700d87039d4 +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..340080e05fcb4d276315d5d887f4b70f1850520b --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic57/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e70ab37bcab6e8ea5328271ba71411f1f48db4738c50f455b51ace69a39ed8 +size 1005125 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..f237c1d02704463b3697b1ad40ebde636925e94d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a31bb704dead25bc6f61acc717f14d027dd60d84ddb0148ba209a45cf4715a +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..a6fb6d1639c468f4db3b6a43826cebbeec642772 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_deterministic84/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47de99520800d9c1b1100aa7769c6b8f1ace6c4153c8befb6eac981b6225f55 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..987e79024e2c6c657d89e77be8b4c024756d59d6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a7604cf107f039b7acdff49f784f7ac391f42b128470d961ad6444f46fbca7 +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..31d4c01059933000f7ef7221254d4bad4913202a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_even_odd/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8693b3217bdb9ea013d467e3e053bc8a431eaf6ba62912c9c777638b18606b +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..d24cd1a3292fda1f2241e0a377894d8c7f505cae --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27429c30205100a77f5c7e5bb35c480ce50dadb402cffc398a1ffd0c372d5962 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..683852bc00bcbe75adee7a272369625ee69a1179 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f650a99182c9d45c6e47fe8b4375d97d77ea55f272ac9f3990f7c84bb74385e +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..15f166f50387b93bf741441769d55df8cdca11ad --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded6dd27c83c8572e043bbc1e54981d4b63012538af8ede99b79f0438f72df1f +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..a1c3c868eb8d33dfd086118389044d7191d62776 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6200d25d54f13299ff66535dea68daedddd2f9a394a78ec4442c00379b60039e +size 1005125 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..615a3aed6b60d9a786c8943fa4f4db30b346cc2a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c65a5e3e225854e49be902373c7d63129cb91177d947c008e215ec6c361701 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..2a881951de3ddd72189d070ad26e14b6b562f897 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7ada17cd3385a5c62bbc758ee2de18390e88f432564ddd3b9aa407b8ce2fb4 +size 21246382 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..95012718320b63c6ed97d16d832ff4053ec0b41f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3deda7ff564ed59b5d60c0845cd75bcd1520966bcb208118bfd10289e19293c6 +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7002943ee6ec5879893368a7af354f8ae3a2c3f3 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ac582f47a47d174b4c6b84f4506981551c38e50c3fc625148e5c56355c69dd +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..cb0bd0794732c79ee799a3f2997dd2a5df54cd4a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f700e0be94adf0d1f1722a5779d76b46a18d0f1c2a63355f2e35775412103714 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b8e085bb4cfd0dbe93b35cb6ba52bae5786fe3d3 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae85bb2a8abb88c56dcc317f34b094ddd7049c8278b392eaceaa33194a7f34d6 +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..3958692eabc2cb0a1799d8b5f7ad7507d45b4779 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f1d9dcf5297be590b20ef40f7e254465b9e867052f3c07891724081dcb4c28 +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..681c3d3fa72b7011ab57b67f83136072bd678ed9 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47af98c328c0b7d76acddff7ae8a9b047337cbd4061b1197179389459dadfb90 +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..bf14f28198b1e600089726a7ae7a829dd8bb39e0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a4204c4cb3a11224e54ac5f438ed73849c557b1e6875c57d68e9da552080ff +size 1005125 diff --git a/data/babylm_data/babylm_10M/bnc_spoken.train b/data/babylm_data/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..e4ae42ee0f131f17ab1cd8cc6078bcfd4c344938 --- /dev/null +++ b/data/babylm_data/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e932ab5c552c8205aad28880c52a610d929c6f90f5b24d52b790f7e7d2df8d21 +size 4884146 diff --git a/data/babylm_data/babylm_10M/childes.train b/data/babylm_data/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..e157ad32d3a7006e8b3c4ad4c8e0460b8a100319 --- /dev/null +++ b/data/babylm_data/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8095a2aa318e51c40ee10fa28ea311025a5879f42b23289268cf00447b796bfc +size 15485295 diff --git a/data/babylm_data/babylm_10M/open_subtitles.train b/data/babylm_data/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..5f5b573ecc3d60c2441a39320214aeec6c865dda --- /dev/null +++ b/data/babylm_data/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a0be59362c41c8681a08403feead3b7d100f8a8a7e6ff664c6aae93e4dfa74 +size 10828244 diff --git a/data/babylm_data/babylm_10M/simple_wiki.train b/data/babylm_data/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..d9765889834df49b29079b89faeac7910011a912 --- /dev/null +++ b/data/babylm_data/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a80b05c9521c6080c2b30fa92870e0e02f7c23d15d73218043d2236db96e05 +size 8432882 diff --git a/data/babylm_data/babylm_10M/switchboard_parsed.json b/data/babylm_data/babylm_10M/switchboard_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..937cc6ed86e8f921426a225306b4e15ecfa7687e --- /dev/null +++ b/data/babylm_data/babylm_10M/switchboard_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448c6196c0e58c96cc6410d0e23265dffe12e467aae976175aefdfae64b4c49f +size 79619438 diff --git a/data/babylm_data/babylm_dev/gutenberg.dev b/data/babylm_data/babylm_dev/gutenberg.dev new file mode 100644 index 0000000000000000000000000000000000000000..80717cff502179608237b5f60a5fa8c5cfaa230f --- /dev/null +++ b/data/babylm_data/babylm_dev/gutenberg.dev @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760ebc4c697b91308dd21f643ae3c3071e3e1222960fcf8af04119addc50e99b +size 15605575 diff --git a/data/babylm_data/babylm_dev/open_subtitles.dev b/data/babylm_data/babylm_dev/open_subtitles.dev new file mode 100644 index 0000000000000000000000000000000000000000..e454f8333030a51915958c39a5e755642c05fc60 --- /dev/null +++ b/data/babylm_data/babylm_dev/open_subtitles.dev @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e8038d3216c28d7319d0cb564011061d64e093e426b0ca816a9def481481e6b +size 11029539 diff --git a/data/babylm_data/babylm_test/bnc_spoken_parsed.json b/data/babylm_data/babylm_test/bnc_spoken_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..c67cad9a6c86ae6e652995b4928640999f6edaca --- /dev/null +++ b/data/babylm_data/babylm_test/bnc_spoken_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e711cf5718a459423f3b3ea2ba11f53c539747eb3fde963795cfee94d684c49 +size 429502385 diff --git a/data/babylm_data/babylm_test/open_subtitles.test b/data/babylm_data/babylm_test/open_subtitles.test new file mode 100644 index 0000000000000000000000000000000000000000..6d28fe15eba1484588f9300064115b3c8e8a7b74 --- /dev/null +++ b/data/babylm_data/babylm_test/open_subtitles.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59cf3e496921fb89f2581cae4f91ce5d2009513ad10778eb4181381d7ea44066 +size 10388196 diff --git a/data/babylm_data/babylm_test/switchboard.test b/data/babylm_data/babylm_test/switchboard.test new file mode 100644 index 0000000000000000000000000000000000000000..eb5059888cf6b0dc80cddcf42f1870081d5706cf --- /dev/null +++ b/data/babylm_data/babylm_test/switchboard.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30501f856a0f63571f81716b2e7f7420cfc9ca4b4705671111063065792e713 +size 823158 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/blobs/584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/blobs/584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 new file mode 100644 index 0000000000000000000000000000000000000000..e362b81bf93cef8c6d96b08171bab63416808c70 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/blobs/584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 +size 4965799096 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..779d54e99b95431e723190dde81d0572bc55fe92 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d038cd53d957294564dacab9eb3b0fdbfd6fcf9bfc45f3f3dd77c235ad800527 +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef76b478f4ac5cbdd10da67d367f6791464f6832 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ae565b6ac569b08396502fe42938f93f7d664a80bc50a7b44f938975da8c45 +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00002-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6108c74fa48b30a203087d7bb3022402378d84e --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df2388bc9f8b1ef78d0d5442fb2efd51f69bb7034b8f9ce2a3271fc98c24aac9 +size 2247734920 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_3_mp_rank_00_optim_states.pt b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fffb06e42b04680bfc74d2b760d912663ebd926e --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e178a7ecd43866821b20685a490fb7a43567be642598fd680182fd884049c0c9 +size 5507578223 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_5_mp_rank_00_optim_states.pt b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a40433eeacbfa4e8d1c7fbdb6805f5df675a343 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90cb3d77ff5120fd7e4797571669d3fae216ba8160912191b34a4cd7dacb364 +size 5507578223 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-600/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-600/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14b5f9ad1ca9fe2ccdc741f1b7c35be0367dab4e --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-600/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c261b87afe9ca9dbb0e36ae6996c20d4d777304a81e26aa1641322073cd1e1ce +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e8569d18f46756fc962ac8d924c9ee10e905532 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4a0e65d3799580ce5a06586a7be8f5122e156d21bc5b154b554dc0a7fd520c +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_shuffle_deterministic21_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/13afe5124825b4f3751f836b40dafda64c1ed062/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_shuffle_deterministic21_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/13afe5124825b4f3751f836b40dafda64c1ed062/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e362b81bf93cef8c6d96b08171bab63416808c70 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_shuffle_deterministic21_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/13afe5124825b4f3751f836b40dafda64c1ed062/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 +size 4965799096