diff --git a/.gitattributes b/.gitattributes index e725e2dc1c6a69f58c8b3f42940609415d276ec6..f4136c4583d659e6d4136eefdd0f484edf118892 100644 --- a/.gitattributes +++ b/.gitattributes @@ -129,3 +129,17 @@ train/checkpoints/Llama-3.2-3B/babylm_shuffle_deterministic21_10M_seed0/artifact 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 +train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/5cc0ffe09ee49f7be6ca7c794ee6bd7245e84e60/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-150/global_step150/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_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_0_mp_rank_00_optim_states.pt 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_4_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-750/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-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-1950/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-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-1350/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-1650/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-900/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-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_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_reverse_full_10M_seed0/runs/checkpoint-450/model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..ebfa1e5c6a2e406a08ed788f61887230306febca --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5958129c0c967896e9c979ade685f9c5c71b346e2612974720dfb0879afa2065 +size 5546587 diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..c0f83fc1ee86812bfbca55084f0ac430a897fb0d --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d29fd2ef3468fe901b36fbc1b82f7717b9685d42c850ddec3e204aeab8b62e +size 9142615 diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..6670984869b7b0ac034634f7d91a870c0dcc08f4 --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_control/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd738a3f0a5922e440973d9130ee71ea41d72e5f3b46c5a64d68ed7a220898a +size 1087539 diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/childes.dev b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/childes.dev new file mode 100644 index 0000000000000000000000000000000000000000..6a4db3af191312647a6fcfdefd3f4f3c12c31353 --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/childes.dev @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372e210b5fbfd87854819ee0b4765be4cce5fbc8c614509d065d3fcdcf255b12 +size 23046068 diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/gutenberg.dev b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/gutenberg.dev new file mode 100644 index 0000000000000000000000000000000000000000..b07a807d263b19c944dca27496a26a49df6e1256 --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/gutenberg.dev @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e10af003ca32afdd708805067454b001c4f12737bc1c57681dedfe2e875707e +size 17909917 diff --git a/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/simple_wiki.dev b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/simple_wiki.dev new file mode 100644 index 0000000000000000000000000000000000000000..b3a5669e3a37903f49d063a2c09403a9c3757948 --- /dev/null +++ b/data/Perturbed_data/Llama-3.2-3B/babylm_shuffle_deterministic21/babylm_dev/simple_wiki.dev @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd078b14c04b5f8feaa1e95416145b6af88eb725badb11282d37b8e423c7a32d +size 9832550 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/babylm_test_unaffected/bnc_spoken_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/childes_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/gutenberg_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/open_subtitles_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/simple_wiki_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/switchboard_unaffected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_control/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_control/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_tokens4/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..aae1b5802a1d4908e40ef8d2521c6e7e301215a0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..6a8034a9ad08dc79b2152ea35b8857d9540be2e3 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..764bd5b29c44385f15e2460671a4a2153068a62f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..232e598c9656f2b0f88efdaccffdff1c4188dd6d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838847f6082640bdd97f32ad591f3c939dfd7ed620c4a4f587be8f0f92f7d344 +size 11026365 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..f8a991f00e3839a71d9c41ca119fb07d34498a6e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..57280d5f96f1b07a5fd0f62e3805035b4fe66af1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..9368d0bfd31abc4f7a6f3b36253176f934bc2f66 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..2c311f703cf00582626b995ac38889764bc6411e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ba81a79513825e9dac6be40c676b4aa6f384900b1c8641268c1bfacffeecc1 +size 474965 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..5c0d099e90f98652e3bed2325692c851c96d4fe5 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7c0735eb59669387765952a4b26a75a5c730eba14214c75a0ea153acae931f +size 15127301 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..eba51cd0e60f6239156b7c5c89111ac616bb703e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df452d4e8f630302872be9f1ac246c9544ab3dd39abc922fa9b96abcdf8096ce +size 2320164 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..0a071561858d80928506ecd87437065269bcfbf5 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e484099098f627a658d087c945b229873a1877b1aa992ed441329454094df4 +size 3362470 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..9090f1f271198e48541e60983e9dd80aed93dbb1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f69fa25b5ca5726179ddb39d8bd28fb45d9fde34e6bfa367b315b413368079c +size 2691936 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..0419ea27ce1a653234cb9ffb51357cc78002e76a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c3490804627a4071e96dd5ed36699246d5d0066caea56fdcd4813bd2b572b7 +size 4127354 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..d46ec96ae7931eb367116f4c51220999f91d49ef --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f04e10deb6fc573ae0cfcf51085ee47b0302dd900e7a153df06134508e33403 +size 474965 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/childes_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/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_words4/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_test_unaffected_sents/simple_wiki_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_hop_words4/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_words4/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_reverse_partial/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..f1729faef1ecb811d0385523cbae1cd05db547be --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..d608c58a6cb8b0559de9b5e53014856a143a25b7 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..2151899adba9ab51f00f5146735b738ebb9060d1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..40131a186975b54ef473701f0dcc17319e929050 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b7faaa7951fbeda8044e077c3ced0882c18798f1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_reverse_partial/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..6feb483ca6bd86cfa891b7f7fc3d44ba2221d8fb --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..1fc7c725996d354b3d37202c269d2d99f33faa1f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..f712d43b2fab85299ec44ce1fbdb9b7fcfb44fe6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..bdff14e124ec10a3ae316c43c9b86cd2a11200cc --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..a839fe8a653e05f520feac4bd41b3a4ca137051e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_control/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..bf68071530b4b59a2a38fa3d0c7bbff148e33554 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..034b5ce34c71042c2a3db7c0f8118305a213b8ae --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b484ab727b2a45cc1d5f47aa748e6b6f6df5b6e8f20f8533dee9b5864caf8fa2 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..830cafb26ce223b2db1d3eebb1cf1a506b8468a2 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a965db500286017bd61d8b57c61b068af8fbd8fcba5555c38ac23fd8e3d2f834 +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_deterministic21/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..cf1c5b2ee4eaca4dd8cb2807394b0185af15ece1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..bf971d11cfe1123d07f7db653c90afce53396693 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d343e5fcf4f9c459b26959e5860570c0d7c8e9849e20e3e4d579148ff7ddda1 +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..542cd27477bd74e2def80f0f69a881ba7752347f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e05bb4bfc783eef2bc838da32abdfa659fee54e8c69a2d63182bb436bf84b73 +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..987e79024e2c6c657d89e77be8b4c024756d59d6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..9ddb0fb515ef8ffdb10d92622d9b405766f90989 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09872ec379f52e37626f0e4dd3edd0ea3299235cc78fc39f494927556474da09 +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..5e87b4e43dec1551d419e34d5c0aa542d4f7a6ae --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e9f5b7e23050160b6e0b252a3b79608ad48ab20f2b6de2ff51ed76e0b6e8dc +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..f0519c34adf35b614b3f7eefe3f4629466d5f7c4 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_even_odd/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d23f24ccc94b88515a99f52493e7fadeb8db2c5bf0f161c15e9fd6c48afb56 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..d24cd1a3292fda1f2241e0a377894d8c7f505cae --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..f7ba27cbcfc3f081adb62a2c30e2c5c2afde6062 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc1ad693bdba69d69f1f2fd09f0c004dabaa0b70e73b36a6b30ea92fb5e71c3 +size 5048214 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..5d2b24b101617ed3488894f32bbb22904619df1d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda18400bf9922f1e8f1cd211c4a1ab66bc02dd9d077bb8afca32c4699c45d95 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..791bffd45f83b70a9d6d61aaa2825c4ede8c75ce --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038ad84aea587c5071779c99727e6fb3513358283cca420aaae0df1846cc48b9 +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..c1b31d18bce4942f1e3e525342f17d7ea36901f1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741e644e10a337ff961506a8822b37ebea9a1cf1cd8e20dc15f8278191dfbe57 +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..1b3aa1170ba0b3fd580fb08529c67e2204228faa --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a255231d511a1e218df3bae36f7087746f6c9c3ecd3e2f8ec440dd3dc6dc31ea +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local10/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..a1c3c868eb8d33dfd086118389044d7191d62776 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..29febc83f3d2c7eb6eaebe56550bac55ef6ef2d5 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/bnc_spoken.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ff8207258a324531f7d6e428f97dfae9dd7cccc605634f86606806e16fc45f +size 5023084 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..e714c28c811ae9cae63a06660362ce1f03a7a8ec --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/childes.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8646de39e316946796dc49dce9ef7ef40ef0010fb19608fc217e66861b76d2f9 +size 21246382 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..f6ef5891d5c854fa5aab1df62f63eebb9cb2a1ae --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3796ce9912258419f29c880fe07f63e647d68666cbdcc6c3d83720ff763c74 +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..2828f829639da800853d1a02db2e03f2e90f4805 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8535a8e970c0fb1190ae854cd9ef379863fbc2606147a52e0ad481165d454905 +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..a1c125f9c56172b19a863aeb85dd9e4ee23e465c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_10M/simple_wiki.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b266498ad07ab6f99dcf7030e75331be97a459c457400c4cff3171a6529b0cb +size 9711377 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..55281c0487a0757dca031c4ca7a2e24661ed00e9 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local3/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d108c0a01b3498715d3b90d50123d9e5d662667b4d43e385eab8c785ade46e99 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..08f62cc91be8c6c495d3fcd37976b4a2605f23f4 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effd9459a4aa545022e941b493c16ed345bf660173243bc31ba234822a1bb0ed +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b7bc5872af28befb1607670b342dbf34e38320ce --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4ccf236b87865e5678f7e894e66b53dea35b062872737469aef60a8ac6d93e +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..67c77cc845bab0cdbb955dc19365464b94e5a078 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c31d484d2d3daff4cf25886c91725069501e2d0814502546870ae7acf35e9c +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..49ce7f633ba2ff873afd14f9c44f8147d764c239 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8938c2ffa48dd2c3482d2a10eec051300127dad7f54345b984d5e7ff7f3dab +size 1005125 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..98231f912c4faf5f1e667ff51cd4c74492aa939f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7856df54a9c8e814f8c01019a4246b523b9711ff3c6acbd922e60a37c037280f +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..95012718320b63c6ed97d16d832ff4053ec0b41f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/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/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..628d4bd15b9c6caa10881c8f8a5b6893ed2eb410 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-0.5B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bf10a33b36b00381054a27cb8766f71a2c2fdafe0a8065e62036c7bd639630 +size 885832 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..9ddde792089d80164c573846f5e44447020a47d6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_control/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..6efa9191791716d19b27e28b5e8986e9fa6c811d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_control/babylm_test_unaffected/childes_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/babylm_test_unaffected/childes_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..b6a77097d5d71a594a9e574c7d2b035a764d7495 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/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_control/babylm_test_unaffected/gutenberg_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/babylm_test_unaffected/gutenberg_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..ab67e1e53312272db1b0535bbc9b205383276f0c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/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_control/babylm_test_unaffected/open_subtitles_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/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_control/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_control/babylm_test_unaffected/simple_wiki_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_control/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_control/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_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..232e598c9656f2b0f88efdaccffdff1c4188dd6d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838847f6082640bdd97f32ad591f3c939dfd7ed620c4a4f587be8f0f92f7d344 +size 11026365 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..ea740b8d85be2a5e9b192cc170d10198704dd8d2 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..2c311f703cf00582626b995ac38889764bc6411e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_tokens4/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ba81a79513825e9dac6be40c676b4aa6f384900b1c8641268c1bfacffeecc1 +size 474965 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..e24da90f7bc2f8baef42c40a10879a728ada2626 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..2de8f643ba44b586857d33deb1ce7a9f955b7576 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..eba51cd0e60f6239156b7c5c89111ac616bb703e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df452d4e8f630302872be9f1ac246c9544ab3dd39abc922fa9b96abcdf8096ce +size 2320164 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7a0e9feff36bd3e00a309bd4066e3e2cf18d0078 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..0a071561858d80928506ecd87437065269bcfbf5 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e484099098f627a658d087c945b229873a1877b1aa992ed441329454094df4 +size 3362470 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..9090f1f271198e48541e60983e9dd80aed93dbb1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f69fa25b5ca5726179ddb39d8bd28fb45d9fde34e6bfa367b315b413368079c +size 2691936 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..0419ea27ce1a653234cb9ffb51357cc78002e76a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c3490804627a4071e96dd5ed36699246d5d0066caea56fdcd4813bd2b572b7 +size 4127354 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..d46ec96ae7931eb367116f4c51220999f91d49ef --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f04e10deb6fc573ae0cfcf51085ee47b0302dd900e7a153df06134508e33403 +size 474965 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/bnc_spoken_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/bnc_spoken_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..50badb63e793a63d69f2ed03b941ebd63f32f196 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/childes_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/childes_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..b6a77097d5d71a594a9e574c7d2b035a764d7495 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/gutenberg_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/gutenberg_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..ab67e1e53312272db1b0535bbc9b205383276f0c --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/open_subtitles_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/open_subtitles_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..e7ad16723bb766df04f4a3bfbdd3f405e50fd1cf --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/simple_wiki_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/simple_wiki_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..19971982499cd8b234d46ad91d4f90bded6dccb0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/switchboard_unaffected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected/switchboard_unaffected.test new file mode 100644 index 0000000000000000000000000000000000000000..8f189bd544f4401a897fc821d1594d58dffbb784 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected_sents/bnc_spoken_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/childes_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/gutenberg_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/open_subtitles_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/simple_wiki_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/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_words4/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_words4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test b/data/Perturbed_data/Qwen2.5-7B/babylm_hop_words4/babylm_test_unaffected_sents/switchboard_unaffected_sents.test new file mode 100644 index 0000000000000000000000000000000000000000..90b1c94410ad9d61c680776ace5b8e082395521f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_control/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..943584bf1a000e2890dad484e9bac206debf5334 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_reverse_full/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..709c60a05cc666fd810cfbed1a8cecc885eac3ee --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_reverse_full/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..7020b4be9b4c0de222cc7d779a793eb5cf6410c6 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_reverse_full/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..d1e5ed242152b97da3872ce66a5008c711f21503 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..ed783f94da1e1bf535ef3f680470fb38e27ded55 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/bnc_spoken_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e173dfb7aa52e5595af9f37f89efb89233b86833d1a6f5324be9048deb8856b +size 5595388 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..5d24e92f2f34229fc316456bf31182f737478896 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9777f0623230371f9ddac7a36f761182a307d030b39252c612c5e3929d3a23b1 +size 13877592 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..fe7a25f245c6098e401e1472fe52ac0660911093 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_reverse_full/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f5737be9594b5406243212e63b6bf704b8e4099e3f046a2bf07d2e10241658 +size 1086542 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..3e7a695ddd2f129d4080190a99edf6c2f84af08e --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a921f5dcc67bf103627edbe7863ffae666b9b23ab32555546b357b38832a7c +size 885832 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..5d2b24b101617ed3488894f32bbb22904619df1d --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/childes_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda18400bf9922f1e8f1cd211c4a1ab66bc02dd9d077bb8afca32c4699c45d95 +size 19884703 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..c1b31d18bce4942f1e3e525342f17d7ea36901f1 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local10/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741e644e10a337ff961506a8822b37ebea9a1cf1cd8e20dc15f8278191dfbe57 +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/bnc_spoken.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/bnc_spoken.train new file mode 100644 index 0000000000000000000000000000000000000000..6b313bbd86ae9ec5352485cb02942976ddf4e13a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/childes.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/childes.train new file mode 100644 index 0000000000000000000000000000000000000000..2161c003834f0df11015937620c94aaeb13f0762 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..aa026190f9bb33b3a8e03118417e7883c0b32c4a --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..820a2911501b376521b1c033790cef06311c5455 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/simple_wiki.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/simple_wiki.train new file mode 100644 index 0000000000000000000000000000000000000000..1ce907448f5e1f27bf22a8bf45ae109c883bfbbb --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..00985246c5f62dd3030cb83fe2c66d7c5b521856 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/bnc_spoken_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/bnc_spoken_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..90cb811e2bacb41c9f8bbf033d233aa3f671f9bd --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/childes_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/childes_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..7da4e19942d5bd9fdf702138add29fd1ef82a198 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/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_shuffle_local5/babylm_test_affected/gutenberg_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/gutenberg_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..08f62cc91be8c6c495d3fcd37976b4a2605f23f4 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/gutenberg_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effd9459a4aa545022e941b493c16ed345bf660173243bc31ba234822a1bb0ed +size 14267044 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..b7bc5872af28befb1607670b342dbf34e38320ce --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/open_subtitles_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4ccf236b87865e5678f7e894e66b53dea35b062872737469aef60a8ac6d93e +size 11843211 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..67c77cc845bab0cdbb955dc19365464b94e5a078 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/simple_wiki_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c31d484d2d3daff4cf25886c91725069501e2d0814502546870ae7acf35e9c +size 8678323 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test new file mode 100644 index 0000000000000000000000000000000000000000..49ce7f633ba2ff873afd14f9c44f8147d764c239 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_local5/babylm_test_affected/switchboard_affected.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8938c2ffa48dd2c3482d2a10eec051300127dad7f54345b984d5e7ff7f3dab +size 1005125 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/gutenberg.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/gutenberg.train new file mode 100644 index 0000000000000000000000000000000000000000..8d2063a3b87f52a8bba3758945610b9ae61be2a0 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/gutenberg.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b004065adfa49653efe4ef5d8363859deafdccb06c6db4193088efe0468ff7 +size 15295716 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train new file mode 100644 index 0000000000000000000000000000000000000000..98231f912c4faf5f1e667ff51cd4c74492aa939f --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/open_subtitles.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7856df54a9c8e814f8c01019a4246b523b9711ff3c6acbd922e60a37c037280f +size 12358723 diff --git a/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..628d4bd15b9c6caa10881c8f8a5b6893ed2eb410 --- /dev/null +++ b/data/Perturbed_data/Qwen2.5-7B/babylm_shuffle_nondeterministic/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bf10a33b36b00381054a27cb8766f71a2c2fdafe0a8065e62036c7bd639630 +size 885832 diff --git a/data/babylm_data/babylm_10M/gutenberg_parsed.json b/data/babylm_data/babylm_10M/gutenberg_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..e4f95fc39818e57059e49e4fef5a3e3dd78b861a --- /dev/null +++ b/data/babylm_data/babylm_10M/gutenberg_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf6b893ba2a09361a0114540901afbfc54fabe66cf08dfdfd7a7744d2b8e35e +size 1252572862 diff --git a/data/babylm_data/babylm_10M/switchboard.train b/data/babylm_data/babylm_10M/switchboard.train new file mode 100644 index 0000000000000000000000000000000000000000..f68b1440c3582722392bafe0415183379490dc9c --- /dev/null +++ b/data/babylm_data/babylm_10M/switchboard.train @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d6dee919f28386a907842ada3bf56dde4eb961f4e6e56e1529500c1d6ec0a4 +size 719322 diff --git a/data/babylm_data/babylm_dev/open_subtitles_parsed.json b/data/babylm_data/babylm_dev/open_subtitles_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..ab2081025db09314c3e8790232b116251f30bb25 --- /dev/null +++ b/data/babylm_data/babylm_dev/open_subtitles_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0042de6c0a9c6dac9ff14760aadb5bceeb5493f31abad60fb92ebb76579999 +size 1160238920 diff --git a/data/babylm_data/babylm_dev/simple_wiki_parsed.json b/data/babylm_data/babylm_dev/simple_wiki_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..5fe1eb5ec0228d22accf359922230cb27ed0eafd --- /dev/null +++ b/data/babylm_data/babylm_dev/simple_wiki_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68860ac24b3a863ebb851fd41e92b4c0667df8c13b88903cbb80ab2cdabcb7f +size 677472005 diff --git a/data/babylm_data/babylm_dev/switchboard_parsed.json b/data/babylm_data/babylm_dev/switchboard_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..03047494b0528b9932b55681031048f76ce7810f --- /dev/null +++ b/data/babylm_data/babylm_dev/switchboard_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685475ae76160f1bbd5372dfe16c32553157bc3cc2e3579550ef788a6212b752 +size 84546588 diff --git a/data/babylm_data/babylm_test/bnc_spoken.test b/data/babylm_data/babylm_test/bnc_spoken.test new file mode 100644 index 0000000000000000000000000000000000000000..df71a44f39d698ac5321e9c228edb727080d16b9 --- /dev/null +++ b/data/babylm_data/babylm_test/bnc_spoken.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfc15bb70e1bd5f66d6a6113ef47995b7fe7fac247bd8afddfac87b86627b4b +size 4889225 diff --git a/data/babylm_data/babylm_test/childes.test b/data/babylm_data/babylm_test/childes.test new file mode 100644 index 0000000000000000000000000000000000000000..e77d00c3303071f10600663c5bc07c97d73e4049 --- /dev/null +++ b/data/babylm_data/babylm_test/childes.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b9e5d5479d003381a9a5ea8905ed82ac9c418cbc53395d4234bbb218ee8424 +size 14707424 diff --git a/data/babylm_data/babylm_test/open_subtitles_parsed.json b/data/babylm_data/babylm_test/open_subtitles_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..1d9266906329f36ebde019d987fcf02215880e2a --- /dev/null +++ b/data/babylm_data/babylm_test/open_subtitles_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd0aa583de68d7c30e6eb7632aefde0d155055301d7dcba8160dbaec4579e5c +size 1006023288 diff --git a/data/babylm_data/babylm_test/simple_wiki.test b/data/babylm_data/babylm_test/simple_wiki.test new file mode 100644 index 0000000000000000000000000000000000000000..a93f3235f98e1f38a056c37b5603c0c9344009fa --- /dev/null +++ b/data/babylm_data/babylm_test/simple_wiki.test @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b1dec6f381115c82630b229ba427edd0f79553ccb9b40fdfc965e31bc7da70 +size 7618762 diff --git a/data/babylm_data/babylm_test/simple_wiki_parsed.json b/data/babylm_data/babylm_test/simple_wiki_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..d5d8a4ce0a8da9decc9ffecc8947f86dc74978c5 --- /dev/null +++ b/data/babylm_data/babylm_test/simple_wiki_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c328b8ca5294cca309fa5dc4a77014bbff181319f447344fe0add8695a80bee +size 631896230 diff --git a/data/babylm_data/babylm_test/switchboard_parsed.json b/data/babylm_data/babylm_test/switchboard_parsed.json new file mode 100644 index 0000000000000000000000000000000000000000..bfaf2c2c2c0cf1b724a9f607e709abddc13e0a8d --- /dev/null +++ b/data/babylm_data/babylm_test/switchboard_parsed.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da05e6ba323c1cdf6b7d01d4877fa1e01e15ec2fbcd8efd6212f3aafb41a4be6 +size 90198801 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/5cc0ffe09ee49f7be6ca7c794ee6bd7245e84e60/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/snapshots/5cc0ffe09ee49f7be6ca7c794ee6bd7245e84e60/model-00001-of-00002.safetensors 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/snapshots/5cc0ffe09ee49f7be6ca7c794ee6bd7245e84e60/model-00001-of-00002.safetensors @@ -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-1200/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3f66b5533d6f697a60c6c7d2e5216c64662356c --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d28176ac4aecf3a3b21530c8ef0732f04c5aca6490adeaac983d1be29fb0eb +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1350/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1350/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9c09017b8b20804e8ba8231d861ec167dea7885 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1350/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11499c6e1555c614db1f9cc91e5deb7c263e246653201cddebd7ac8e96ecbd4a +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1650/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1650/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79a247313e63b56d365f97b7b3c9ebc3f8b55377 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1650/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7536147650b50a4cb96dc941afd124b7a37b263f4e21c30a79aa7ef959efb9ae +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1800/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1800/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04600e47c54fe446759e389e835392d39612de31 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1800/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61395a84a1cc49fefc4dcdeda8c652e34cba27188e78df3969c3a5786e178a91 +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1950/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1950/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28ff1b9b078cd886811f67030c55dbcc11578aa9 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-1950/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d559f3d47722a02a8e8b9d8c6b05c806c972f1e7b16a2bfc97f9441d342114 +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00002-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcdacf4df8c2d11c0af4215f9683ab898f08c7a2 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-450/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7606008a44917390d94066b864289ec3a77fa4f900ca3753cba00ae533d24b +size 2247734920 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..717faa9c9cb92e6237ff544e93520cc30bfc186f --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-750/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3040ca781f228d0e1c1bb105e4aff8785c16684b5e0fc22d2b116906c8a47367 +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08b911bb0775617f57fd487af6ddb5826d9b84bd --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_full_10M_seed0/runs/checkpoint-900/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad99caaca7623cdd62da7909a8fe45addfd787012e94809c2ae8b6fe06be7ee +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/artifacts/models--meta-llama--Llama-3.2-3B/blobs/584d8d3e3f82f7964955174dfe5e3b1cf117a9d859f022cfdf7fcb884856e002 b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_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_partial_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_partial_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8bafeae2cc6b500a8ab40ed1133a7de8dedaabd --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-1050/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe7d0c83d34f4f5ee89b26d1bc1cdf995ed88e9b3749c7720dffbe67d1b443f +size 4965798912 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-150/global_step150/zero_pp_rank_3_mp_rank_00_optim_states.pt b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-150/global_step150/zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7495edcc5f471228ae5a9928b5ecc4e6e0df0ee5 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-150/global_step150/zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07476d137601d6582523b4baf3e7bde60929f4e626fbfe879fde911ec4c4499c +size 5507578223 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_0_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_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..edbd5b0403c5c56540f94494bb2f6ca7aa72e10e --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c13e285cbb948c6180668a0064d66bfb0d7de19d7d66b70fa3de558e9582f60 +size 5507576303 diff --git a/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_4_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_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..182ec5235691d378c1522d7bb444da1ea19287c2 --- /dev/null +++ b/train/checkpoints/Llama-3.2-3B/babylm_reverse_partial_10M_seed0/runs/checkpoint-2080/global_step2080/zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b4b459b3272d66773033e6869ed1e9977a3626c77cada530ca4b3a3161b872 +size 5507578031