diff --git a/.gitattributes b/.gitattributes index 4d5d6025c4d36ac55ba720769dc11e8de83a88f0..534198f1f8b491613950b4e3bdaea1df6320f4e4 100644 --- a/.gitattributes +++ b/.gitattributes @@ -177,3 +177,4 @@ fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_ fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/eos/step_025000/combined_eos_analysis.png filter=lfs diff=lfs merge=lfs -text fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/eos/step_001000/losses_lr.png filter=lfs diff=lfs merge=lfs -text fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/eos/step_003500/losses_lr.png filter=lfs diff=lfs merge=lfs -text +fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.png filter=lfs diff=lfs merge=lfs -text diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/losses_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..161da6c466db825b820145bd87b6457fc4d765fb --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b45cf5e910ffcffb81afca58fe748860192bd1bf1ce3e1e675c162eff0e22f +size 3575 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/norms_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..df4de98d7f0e9bdf2ba644e4cca782d6866bf67e --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_001000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a515940906bc1d4c768246d64e27a5a7e3757735465cdf59733be534d5b22b6 +size 3568 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/losses_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..34119a4d596b1acdaa2406fd90765c9efcc88656 --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd27a8ca837b608ec6f3614fc63bc61e182f25f2b94997949502043fa75b0d8 +size 3575 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/norms_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee3ae5c43fb29ab7ec154c7e2151bd1ed245d797 --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_002000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e485b742884ec23554366f53f9f725842997b7cf934f6b8acbb5eaa4e47e9e92 +size 3568 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.png b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.png new file mode 100644 index 0000000000000000000000000000000000000000..6f64a272ccbd58199192f155c856a9498178b29e --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3a0ff341eed85d340d6ed9829ee0f74ff92189d6d0fb672d2b1052772e6f04 +size 121352 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2d4ed0e2aaffadadd14ed52edb6b16029f4b113 --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c1f66aaf25cccef12aed41e83e817cb4aed1cea590f9e2bab139f92f7aeee5 +size 3575 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/norms_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..565023f9bdaffaae4625424a6405904292f9711f --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_007000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17211def3299e895c0e8d9d88c9cad47029c5844bcf2dc3e693ca93b014be3cf +size 3568 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/losses_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..4687710baa8cca78c7fea93ff001cec542cd485e --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a38b3a6ed9897004c946ec312b69f5d6841c2b3f02a61cac8ca39c5989b284 +size 3575 diff --git a/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/norms_lr.pt b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c879c74703de29801a40cba7b4500bbe7f5eba3 --- /dev/null +++ b/fineweb-10B/gpt2/eos/adam/linear/linear-256-2048-15000-0.1/lr_0.0018-wd_0.1-betas_0.9_0.95-bs_32-seq_1024-iters_15000/250622_035242/eos/step_010000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ff8e38650a039885ba6e2d8f6bd3ccd2390150a6d98db5b9b6b51ef93e3c97 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_001000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_001000.pt new file mode 100644 index 0000000000000000000000000000000000000000..eadcd65c463a586f37ef944a682b6c128c7e6a42 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_001000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581f791ec827e2b336d9f687e19b9e1415831332682702f6fabe4a281ff42acb +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_006000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_006000.pt new file mode 100644 index 0000000000000000000000000000000000000000..87269d148db085ff3d0672e70f1df7d1e1ce3fe3 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_006000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7061df12b77b3b9b5df6e08e1ff16b1d88188d7552003d52186cbda9a50de5c4 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_018000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_018000.pt new file mode 100644 index 0000000000000000000000000000000000000000..67ae2300bdd3c79def84b288bf64d034f0287f07 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_018000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1bc4ac24eec284ef4242de349d3981cda8fe519d32550c976aa990afa21ab8 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_021000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_021000.pt new file mode 100644 index 0000000000000000000000000000000000000000..464c6719a9e9c22652cb54cebc4af1ae742a845b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_021000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130d2bcae971d70d23e22545d0a2bb2d4f2b7c42664350958e7604d43c2eaa37 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_022000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_022000.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dfc7019b4357afe757fd39aac4602f0863b2d58 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_022000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51849bfa5b0f78afdcea5dff2036442a3c86a070a919c585f8ec81ec436b4f11 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_023000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_023000.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdbdfe95df44bb9ff7e3b338e1f6fb464b32aef0 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_023000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f4164bad305b8a02dd7b39552feeb8317c5706788c4c4785befd71ceaaa435 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_024000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_024000.pt new file mode 100644 index 0000000000000000000000000000000000000000..82c161a6c68ce1d813fda308ac3595e01b192973 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_024000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00bd52f8b2028b576a106ab3dde5a1ce2e23b10b77a9f95647997b48426dbbe +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_025000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_025000.pt new file mode 100644 index 0000000000000000000000000000000000000000..2fa43880e2cb090a7fde0cf70f7e121b8ff16a24 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250730_000401/checkpoints/step_025000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b20dff63d44fbcee77bd0c4989145e37bb2a219606f6e76bb0baba9e223ea54 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_016000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_016000.pt new file mode 100644 index 0000000000000000000000000000000000000000..4375bd4bb631ddcc104849935b22ac7ce1735c4c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_016000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e462008010f39e5c114e9219240b6070f60fdb550398c90cdff95f1a69715a +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_022000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_022000.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd931d4718030f7faba8f644571a06c2f102eb83 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_022000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1236ea7170f272a12a56a4f27486d086994aa9c2d15bdd83121ab162935e4ed6 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_024000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_024000.pt new file mode 100644 index 0000000000000000000000000000000000000000..251986245b668e255d24ede295392101a666e8f3 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.01-wd_0.0001-m_0.98-bs_32-seq_1024-iters_25000/250730_022725/checkpoints/step_024000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36784e29ce772f4c5f93992073cb4255458be1cef9c7697304498bf9185b8924 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_001000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_001000.pt new file mode 100644 index 0000000000000000000000000000000000000000..476362125511a052a1a3e95321a1584d82e00566 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_001000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203aad999bd05a913b30accf499818e75dce07c48ac90a8f16faa63c2ceaf68b +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_003500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_003500.pt new file mode 100644 index 0000000000000000000000000000000000000000..49b58e7297a1d8658aab70ce4d242b7dced6e2ba --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_003500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9b64f045978413a8fba8d402112ce97d545e96a7be7869e73822070b805aca +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_004000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_004000.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d3580c6e5f535b214ea42d2c0569ccd993d4cff --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_004000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa40822968d1380e7f164129b36fe4a3f0c5a15934828cca428e97db7733931 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_005500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_005500.pt new file mode 100644 index 0000000000000000000000000000000000000000..1dfd0bb666bdce0885be94989823cfb8c4b20849 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_005500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b30e82e1e8e81e6b38b0b3b19a7c48dc0183305a37190309ae7fd14939d94c68 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007000.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c6b80bf5befedaef655b9dd954152026d559ee0 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fd14e23dedce640e1741687e02fb0581b242ab7cb48d7a72ef5316ded67f4c +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007500.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb86154936a388ca3dc239c57e11f05cca3ab282 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_007500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afdb34bc5ca64dab9e8ee7b34bbc4cf3428eec96c471d0855a6ee49a2a40fbe +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_009500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_009500.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b989caeeb92ab6f75a25a76c6190ca9305ea698 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.0-bs_32-seq_1024-iters_9536/250622_011417/checkpoints/step_009500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2a30db2f8924ec6354fcf0dfe3262444e46ef197b78d9ac9d8ea43b43078a0 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_000000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_000000.pt new file mode 100644 index 0000000000000000000000000000000000000000..80dd2a64ef3bc3c6790790641e0fe342d675a620 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_000000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aabdd09acc5b62e5e5d5db14a64bbabb6abbf4d317cbd71586f216789f529a79 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_001000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_001000.pt new file mode 100644 index 0000000000000000000000000000000000000000..6634fe5861f4cfe324b09c165ba368187ae6efce --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_001000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41606eac264c2bdfffb1be001b3da354b969dba111b20d3aacc0f8ccfebd1a14 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_002000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_002000.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3f62c6627e8c5c23fb69ab039f7be27585d4d49 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_002000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cba2bdccb4a2578232493b90568d0b388eb041d91c7759c324162e896805214 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_003000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_003000.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1ae770186529679cd508fbbeed1475c771a3617 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_003000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6190cba24e14507d20f7551a13df43b7d7445863f7de1f3bc9635ed3ace2486 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_004000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_004000.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4339e4cdd5c7cd3505383397ef5e8af00a9dd3e --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_004000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af277026895b518859222979fd7f6b52aed9966b637e5a957b87af90c2f1f5dc +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_005000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_005000.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f86038e570fbecd027fa38ee2c7a30cd02c20f3 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_005000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54060533c57addb7a25087dbea440717f773ca8ee998efa1820b729c5d38e6a +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_006000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_006000.pt new file mode 100644 index 0000000000000000000000000000000000000000..a53ca0e5b6ffdf3e1180dbd5ab85b4419d7273de --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_006000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58706634ea5f18cad2b11f810f378b91453027202e85d645146fd1a4ae27494d +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_007000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_007000.pt new file mode 100644 index 0000000000000000000000000000000000000000..f86f501e952036d5a8aa61fc3fee8a88d552fb57 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_007000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a7eb6e26bfe1c8bc208c941b81aa58d05dec75396b29236a6722a52f63f7023 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_008000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_008000.pt new file mode 100644 index 0000000000000000000000000000000000000000..41f1ef0a3118d4e7edd2917d6bf1da0a0a70b34c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_008000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1097a4fa65ab13da10f3e51a0ad500e030f7dcd7bf738f9397adfe85edae5b1f +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_010000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_010000.pt new file mode 100644 index 0000000000000000000000000000000000000000..c34c1e8866bb9eb33318152b9584b2cbeb5cf4df --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_010000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040efc888b7d2b3aa6368334dfceed53bc1ceb391665b0b60933aba0837a0859 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_013000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_013000.pt new file mode 100644 index 0000000000000000000000000000000000000000..16f6d5687fdd74b3fde74dc0b2d5a4502f65f50b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_013000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67913a3cc27a7ef67ecd6ebf6871cc1bfc4545fe89f674e50a3622ef529446be +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_014000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_014000.pt new file mode 100644 index 0000000000000000000000000000000000000000..12d839fb1330a11982c90d4bcd01bf724dacc60b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_014000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10469afa9f03c302e7c3683ebf046701161e0093c4ba872887f885f1ec6ae52 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_015000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_015000.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae8d7453488f7f42e5d8668be3deac4f10535809 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_015000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2f49c396f10184510511c04d1612136d2346c6c64cc6c93e54d28073d609fe +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_017000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_017000.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fe5341a622ab18c43684fbe4d11fdea6d7f201b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_017000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97169153364a3968ff481425961624e46bd8fbc3d240428eb67966bc66822eb7 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_018000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_018000.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a0ccd95deda6d38de0707133819e6a442af16a7 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_018000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214330c363ed2c20f307408b07e521f7ca8bd2bfc5fb574f99584d839e44a66a +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_019000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_019000.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5f6dbe2f169a2f02b0b1dad3d6ba53b328c08d1 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_019000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54aaf8990033639264a13bb495494294e366b705638b80b6b3c4fddec7b8da6b +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_020000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_020000.pt new file mode 100644 index 0000000000000000000000000000000000000000..d99f206205c560929104b147693b95e94338537b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_020000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b438479d03d90312ee866349d7bb334ad9cc3554ccc1484a0bbfa23258b5ce7 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_022000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_022000.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d2b391e64d74eb5e05281f8c4c373097daee25c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_022000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3375eb1ab2da45e9b8b17322fee824bba7c82ed6868df9eba2c5fccdeba107c7 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_023000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_023000.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b293e181d555bfd84387ed5ccb8df03bf643829 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_023000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c52ebc03bd780c64a3f76f255dc4a356bf32ca21973d4c8e38d3d81c7e68185 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_024000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_024000.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c0f7481153d7442bf0e4376fe5a2f7c03b33018 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_024000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426c27142843ea8280de2a09d69ea492be75382011168eae96d446577d7477dd +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_025000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_025000.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e8e027c1526b9647c0824c3379f672105ceb8f1 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.03-wd_0.0001-m_0.95-bs_32-seq_1024-iters_25000/250729_212048/checkpoints/step_025000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f4be880e089960cf832a8f30a0cf56530f9194b634ae4f08ed1744c4d44127 +size 1297616507 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_003000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_003000.pt new file mode 100644 index 0000000000000000000000000000000000000000..32bb4f686bdd33ffce915115fb73a90a3b06eb51 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_003000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9148c49891ccdaf172d347687f00cacdabdaccd194f1d972687b0ff5b7f03821 +size 1297607995 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_004500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_004500.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8463823f9ea93bbe3a2011e14aa83a1d28aff15 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.95-bs_32-seq_1024-iters_9536/250702_163449/checkpoints/step_004500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38eaa98d2cb6d4ff05e7c97474bf74ee982a30e6ba689f0c490fc0684fb3034 +size 1297607995 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000000.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000000.pt new file mode 100644 index 0000000000000000000000000000000000000000..699598cdfaa9dabea685e74b04969b24ac8d83db --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc065d0b52a098d1dcfa1a3ecd838894788ef828cd22bcafbf086c25fecdea05 +size 1297607995 diff --git a/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000500.pt b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000500.pt new file mode 100644 index 0000000000000000000000000000000000000000..ceab8a5dd35191da4a83b2932a18e4f5671ad78d --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/constant/lr_0.06-wd_0.0001-m_0.98-bs_32-seq_1024-iters_9536/250702_174110/checkpoints/step_000500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6cbdda94b406cfce28cb9373dd209c4c3cc4b1c29b7ba73a414c92ce4f2da18 +size 1297607995 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000000.pt new file mode 100644 index 0000000000000000000000000000000000000000..e773456f80cf43a56786d4d67a964966fad36f45 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b68d289885c620d5a29055f7081313381698f28ed6769e98a34eb89a75b478 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000500.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000500.pt new file mode 100644 index 0000000000000000000000000000000000000000..64b0bb36f4e72cd648d2c25ef8075254baf6f05f --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_000500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f7cb574dd82d5ac80cc5936cc596b0f29e9cc3b3bf85b485db13a2f7489a9f +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002000.pt new file mode 100644 index 0000000000000000000000000000000000000000..d38e35d71253189133d51a59940a3917fad9b967 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6841a68a11b4c498ce19ffafd79c849963c709b2dd9a1dffa4886f68d51d27a +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002500.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002500.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfec734f9f4199707be69baebc5bb3b84b6a4085 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_002500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeb9426e8c70163548a04b9e0e60ea2552efa9b5c5326616a0f006126a274d3 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_003000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_003000.pt new file mode 100644 index 0000000000000000000000000000000000000000..7922160a914307bd023d0cdc8c9643c479311faa --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_003000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c3e68ffcd68a57f874f62ff361f5bbcc0c716c493c1f5421eda26d310dfc28 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_007000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_007000.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b00852c97c70ebfcab63d285aeaae5735ada631 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_007000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039e212b0846df29a89bb88d0b036e287cca14016fa173c36aa358157df8315c +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_008000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_008000.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb2ea7b2480316daf478361a468ad3a1320c8285 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_008000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c7f842bd3f1434f40a15dfe844bbed79e09439c385553140888b60afd62dcc +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009000.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5fcefb0e3d9330d65b5252f468e8572308b2a5b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9625d67e45cacc654abbb4363e3f92089b85eddf56bc3873e46b5039bd6f7ba4 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009500.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009500.pt new file mode 100644 index 0000000000000000000000000000000000000000..1afa727adde740eea257c39c5ae58228ce2293cf --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_009500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c148c4c61615c97ed68b708caf191c94b02dafcf90521cb53cc5851fea8fcd75 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_010000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_010000.pt new file mode 100644 index 0000000000000000000000000000000000000000..76bbfd9d5ceefe61c2ad26c496e7162de39a389d --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_010000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1da720d452d2a9ba4c9e931c01a37c013c752dfa302d714b5b3b8d90e74ff88 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_011000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_011000.pt new file mode 100644 index 0000000000000000000000000000000000000000..84db69d66cac60bf1051053acf5d95218f442654 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_011000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10550fe96d52bbc7c7b631253d9d96b4b76f867ab3819687252ec03942827f14 +size 648822165 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012000.pt new file mode 100644 index 0000000000000000000000000000000000000000..eac347f99bb6857c6ac80d7233ee68ca83ba5eca --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9a61ae861273d2f0c1989386f3a0c15d0f38ceb1772a8c689439677ba9e420 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012500.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012500.pt new file mode 100644 index 0000000000000000000000000000000000000000..655c5f738555563c22f784311ec243fe7107d88c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_012500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc6ccb597230eca6dfbfeb154db65b8da8f9af3aa6cae3964ff819606582430 +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013000.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013000.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6c13343fb5ba358a11016b805b7f3b322663f64 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013000.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2727b3686258fbec170c6a89fb68ce6d53c1f7a4dbcbc772ad81953d61668d +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013500.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013500.pt new file mode 100644 index 0000000000000000000000000000000000000000..108412e8e223114dca9a46f18dd57322fba2a3b9 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/checkpoints/step_013500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22cdd43efb08c76a91fa8c6a397882a14b00d5969494d9bd00a1c29ca1c83ec +size 648821973 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a52a348762b4197207d082cb122dbf4834b4eab2 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7f065187948ea272ce5c14eb803c48630252924c9b57c51b09ff1f648b2851 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed26179a91e9ca837a728ee8e17b8b1b9dc92d30 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_001000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e2a35ea7c237ec60eea6dfbb26273f53626bc320e9a1d5f9d46d522252a6c9 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6e59aa076a7bb5e343e8604163d29bae087f7fc --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88ce176d6d290a3b25e913cee79995e0f434f93ca5ede5e79f928b73721f479 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..355ba36a11347d07f7e50585ea5c18de97fcc0ff --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_002000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78476725d4a5e9b706e099a8c2c1af4904e269bffa27dc601b40a768e342230e +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e8729db86ccdc4c00bdd231e3788893b98403b9 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8eec2edfa95899a17ae45dcc69a5015240a5062b015bc9721b0f1bc53a1870 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..200d844a35eba853317250606f3663b193c1fd88 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_003000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7425b0df6e269252d407a704df4033ec6aca3f2c0232c7fe1d07aa81a59eb3 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2b3dd74b368be4e9d2ebfebb5cf425a674f970d --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4204e4a5938b74ada46809016c40dc258d4698a9a858b01cf4b156cecb108588 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..656dec694dc5d2f0f5c87c9dd5cbb3d099938025 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_005000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8937427638ac82de86f9c92a2813ca186a0c4a7032bc5dea39182854e9d422 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d7e973cc75140da34eed468cd3a19af4246cbf8 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b407e9fcc5fb247bba6b38fd12171fbf8bbc87695739d0f53c6ac21e323f605 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..326003cc83af45d88cbf94d806fefff792d1a12d --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_007000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ced8281aed71f90ec24498cda51b7e31132a967a271ebaf091844a085d7abf5 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..358d21f35e4b89dac8293510d55c17251540faf5 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88412f0a1ffcd43d3a9279b8b80d6a5c135f398d92076ef7ca8633dd51152e53 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e38f5ac07b5b86cbaf55cab31f874e8cbe7fdb5 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_009000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0cd13020b5c50e57dc5f60bac36ec8120e8b6ca54732d33fa39d7da6c1402e8 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..75c380e95b80f33296f3d41fb0e875d9016047ac --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608dab9e495785726d97b6345a9c62ff26f2172006beb01760d03f5845a30aa2 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..663dce02f71c645ddff0dd8c4b45cef530ffb183 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_011000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb2b4bcc3b0ab8b0f50c60fc99b0740bc9f61a1f6673a28b06c24b176435a721 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..423618a98e5a9e440df90530f5c40c2cbe19ad87 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951ab20807c716badc692c22d0d762d9040510152dda6575efd7dca29ac652e8 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a24109eeb43807818182d250ca028d2536380f03 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_013000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e9e2adc5aa78817ea01a7f26c2a4fa3a5733da489f8cc340e92793dda05565 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e5a3e6d05259550655982b32670367d19e6bf34 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a052b355ca44e3dd5b81042a911ddc07d80e0635d24d103b6daddfdbadd3f6 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9174f27b5a2fcd27668138feda2a020bef3019af --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos/step_014000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be5edaea20ff7390fd8619db20b19c69c28531ce18fb75a3018fa55a3a5b78f +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2166824b039e0a1f09fd3ad87a129fd4eb1bc74 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea824d570d06d7811036f9a75c61ebde20a9ec5c607bfc536959cf58b47c3f8 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..48dda076cd99aab50bb8bdd71855187b0192c5d9 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_001000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2375bf44c1d5a5c9bdf02a348c63aa6af3d0809430894607a877a5fb3f1bf8cf +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_006000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_006000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fa7b6f17eceb095afa1990c4dafd8db32718fb1 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_006000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f37719f82027ec76616e7e7bb6f36dc962be5780b8363794b7d8762d05b2ded +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..8158986b3b6ab71298917ed5657e323e2565f11e --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c0c7b3ff1fb64f0aec1c1d74c1826b2cfc777266329f4c65fbdf758d6d744e +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d045b6d71035906d8a09e61b279c6abda0e5e29 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_009000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcc7164e710f7f1c969ed4be5bbafd43248ef90ebe5509cfa3737093a174fcf +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..544827379371bd9d6c18a32a8f4c478473e55be9 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86f99f8089250a6841decb289245292982f3ae7a3e72c5ed895b9029b3b68d4 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..09100ce36051a90e8bf58eb0e27d8d6bb92791f6 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_011000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c538d647f43ecedd2893f28a461aecbe17adf4798aa5b0ab05c286533a0e0f +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..c83aae44e1919c006bc3b049a14e089f0588e8a4 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2e130c3f9dde2cd4d72383c247ee346a7661752efcedf985ce522b582c7c82d +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..08731be4f141ee32e852d61ab3e359af34cdd518 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_012000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d23336ef4ef5eb68147099ec6b8bc1a378326adc2c0031a0b0ccc865bdb793 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..26d48ed5a5d8739674cea03d7605aec3cddfd9e7 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43eae1a856dd8799ad7fd6fa24bb0ee5bae97e9cd986dfc63f5b691d55edabdc +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc957b790f4d51dee61b4272248aee803887e9a6 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_013000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc114b6a32d63963f6d2659a1438c48d6258112cd23d7234215dc52db4a285fe +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7db4613120246b0d6824c8ac2d3b217b9877921 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc823f6c380da1a6dd0c59b2edd7e19438a8373ac09ecf5d0ad2810f8c04c260 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3e017ba0aae8faa8328822e46246c1e625de52c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.0-bs_32-seq_1024-iters_15000/250622_051646/eos_original/step_014000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a42509280e6592800cf72da2761ab3a84918ae86926e283df476b793d35d4d4 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5471138b090ca3b2cc33de71e7cc34b67956bdc --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a0fd1b913a1212f15ffa26951c8cf1e438dab9d85fc7381b23b4579d1ae6e7 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5593a412cd9d8b5b4cac8e1b5e14a02c6e21843 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_001000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361c12ef28b2f82fcdae583047e9ce090a08dabf3b143c22123e1d1ff0e82893 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d8f6045bd678f0caa720df7d9fb562695a38517 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b157e9b1cf2537f35881dff15f27b1081fb446fa0aadeb2c8574447ebe8621b +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..86b7b1ad34fa44071a99870dbcec2c0f4f5d3b9b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_002000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2b6388131b11a252e3d2f5ac69a051162f4ff5228252ef815520217ef9d2ae +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..8cb09207e7d5927ddeddaa543d854bfd1776762c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ce1b4556688e6f82833fd413b4df4d84d38677fdc955b25db361d5a56ad52f +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..d00988efca7f6ffa18207ee3bddd41eb54800a5a --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_003000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eddffa6293c14ff9d97c563b376f94c3cd5058b441c22102498f61e2a5ef239d +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f826d0acd8ecb2fe3245a3ce7737de25a6f0672 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e2c497a9b907a708f60cbc3310dbf7280dcde3cadf3a063d384b467317ec68 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..469d169e4ec9a6fd73b07b8de827dc0e452f697e --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_004000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24ddb40c7923d9bc48d44b42ca401ab10a1a05ad4c105b5554f6a17202e6d68 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f40d39b8785733e6cc92d38b73a8b3f74ad5b1c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89925392e83884d136e2e18aa69a30525e3bb402092e1e991be005c754fa4dc +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..6373822af18772383b78d47f1d3b8b884610c2c9 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_005000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9feeafe4b01408239022fca3bd269202cbbba8c49dbda65fab3120f7c3cdb9b7 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..af5866de95f51ed4311fcd92bb04366bd8d6cb27 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8fee5df9c167230f4f681789e32471d793c89c92580cd60785a49932bcd69b +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..da80bbca03ed89572a3d08bcc13b01b6519ce6af --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_006000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3439061be2f5badf718b9a866005dc448bf37b8b1bfd8121b8a09370e855ecf +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..d08b5dbb4c0dbea1d11db2c1abd9a06e4e6fd373 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce6d2d8cfe0fb8986842af35282b4c122fe43ce5b6dd7bf0d744bc40facf1a4 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..926b5e6ab27b996c4ecf4b9467060d440fbdd66f --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_007000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383514d99c6a4ceefe056e6e1efe51ca7632e7b19afe593da07289191ad6c91e +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..91987f4242c69565e640815fc7fecc5b680132fd --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e175034470e6553d6ae356e6a4831aa3e0c254f63e82d738c62364c813be583 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..766e7a5247af820ef7c01056ee2959b0eab4f746 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_008000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801ef7741b1a9bb793037e856a3cbd881f02e7adf09e1bcb60c9e9ef36d022f2 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..56fdde89ae323c14568cfd4d44df4e69850c319c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2852cfde8aabfd58fac1d2205a87ef4b4d8b675c21cf4a2313198c920ed7135c +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b06e1c16fff46dd62634ce6e4359de348ec56ca --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_009000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751d9d4ac393e889a8fd4b3d67e8b28fdd7134c51f9f5786e60f151c02ea1dc8 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a84bb24207c82469a12b8464d9fda73c57450b0 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8ce0c2183d670f081d6de24ad53c106c5f85f5159dd16437f84764113f66b5 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..7608e9157b8c25c7e84b3ae4c3ab9d650c094a86 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_010000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04eb3a68768e906b31aea1f336318585df5878d62d5cff169f52ebf5d69ea119 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..73be15855231df2a43e3fea3c38ac29bc63d0e3d --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543fde67e446eec1712900bac3851b668411f8ff17e2b57b2b3d2b0dd8f8e351 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea628d7a13f8c492de65861c429e31172e30a6ed --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_011000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a069b7e4f5fa1c759dad8ed1cda8131bb83f07240d523c848e66ea7a81cfe08b +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..4edebd83793e067402c09ab7a24abf87b3e4366b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa960298fe31d4eb211f0d5bb6fab58d199abbb3cb4ca982a4cb4794230c53e4 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..85fbee0f707101e2d85ae985693a4599b0fe89a8 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_012000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51daf0f1ec6cabb7b274359eec02c16c2b843338626af2912e4aa2758db59d0 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9053fa498c23ebdaa0855ff2362de884e5d3c89 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdb0d6914587b81b7cfbd662f54236e19e2f8a07f76d5e3d3a06a4a3e03537e +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..492dab9365d08f23a93fe8d7c594992919f20998 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_013000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5fa9e819273010db130259978271ed2ed281f1f7c3ae1cfbfed7a6755f05d2 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..22f2690df2d0c737d5243fa5094497689ad2498b --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fddbf8a7c7dad8595a50f6304c2379b33848ce059b3f29f5f727da7518639c0 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2936d45bf6f98b2b69450a52aadaa06d7232d41 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_014000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33ca4227c977e2f1a6f78e63ce78d48726d0c99444090b2d73f8ca30222e46c +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9af215c088670ea4bf4b02102252720198d93a75 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b553b63f4866a68ff8ca9d2782763b247198107270ab9330aac39c3de12e5b5d +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecb323eaa6db585d002d88bf60a486687c6ec242 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos/step_015000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c622aba1398ff610ec0bba0fbdc0cd50edbe87ed3879ef8b627cc22ae6de9d +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..65d62045255e7101b89fcf91458fb7f203fd5c1e --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf775026ad8e6d3eb34d0c15f54505830e80c26b46333be9ebe58fe08fc27ad +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b77edb1ce4014c903e9a7e21dc3437e1a34d582 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_001000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8739b9a10ffd25b602fa13c8ba39aacbf61fa98af521e2540690e4033b4349 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..54705be7e299ccab14ef5962f44acd72f3f5b139 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da09361a4433ac4c2a885ec7db5c02fc8f092d27a5ea5e151ab4317d313854a2 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..b39bbd108b5cc6895f8fc7e24aed1da43a26d1e2 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_002000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d168374e30dba8d1b4aeb9c2671ccdd88364c55f22904ed95bdf9f323ae69c +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbe586d2e8be3fb5bf78e5339cea8e1b85e043ac --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322d0f6e0ccbf0803bfb6ec31554352a1c8862b9eb20d100cd0b8e625468d954 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..3eb332cd76ea5f88e2ce60e82c8fa96c3bcdf0ac --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_003000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a763dda08cb62be7543fa053d4ac6cb9cdec9ce64d599df8a5c0e31a933b9e07 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..63d160ec75319b4822cab1d3ade2b5254a529a30 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba69b3fec46d1ac8c4fcffb72cbb799b530b3a10ab1c3e15f541e7df7895e7a8 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..20c6748440bb4573ed4c750f4daf006ec707c373 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_004000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e822d26f68943989085b3a57792a21e85bf24801e1ace8a1451a1a94cb65e411 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a133fd64c386caafb143b4c3cb98536d3f2e830 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e4a9d51fe2975725ce6f1a32f9b365b107e6ba37f54ac9673eccddacdbf9cb +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..179943022bd491111715234a3fafd282bed14598 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_005000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02b677ee667ed68e9df4fc1d59074ba52a9afdce3bda8c2aa3f1eb027ed6e78 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a66b70de4870239417dff20611e06892bcf4e27 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c7fe3d1ad911c28e79a97519bcef339e1913a1261e58e4942b5f2586957cfc +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa969ec999d350515f02c075924defc4cb2e3bf2 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_006000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b2d9963a2d8de60664e8a743bfd6734604f8b622bc47d23fa35289ac84e003 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..f96ba90a814b5071a708be253dc7837fed5eec74 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0605ba65b089eaaa67873c8ca538301963cffcbc067a28e40b1b7586339bc1 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f80835ad0836f85719c57c8b9118df0e66ddc06 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_007000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8f823fb733597ef91ee2138fcf0e502ac259b1a53725da1d414bd11f844e6d +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..b177c072d81c0561ecd1a0af28cff60a183c8981 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454cb4d7fe2d7ffb5a55768a593f083955ffdcc136ee3056a2c41f78d12e2cd4 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..375a256b22fdc0a875b561eba809a521a077314a --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_008000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c71202f0ca176aa690175d03e93bfc8917e189fc043e37120bb64844934c616 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..125cc611e924d208303962e54040a0e6021d2099 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8b6c9dd19edcc6dedd97dfe29280dbf77aa9eaf19c2571682c752c33fbe30e +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..c56ac40219fb405aa4a1a484a8af8897a4eee85c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_009000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3301ff8983e5a7117c29a8197620a199402a1a33c4c44fd230962906be44734 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..7950846e1058a2b170560c00841d7378a75614ce --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762e0f02d09c4f53b3e9bcdcbded0b8696f3e1117a87ff788aa391c698ce7e45 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a0c60bf625434d536c241f06f8b1b7a541f9730 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_010000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42e8bb47daaf5cbee97a5b19377f54470c5fb6530fa4a8c1505d1834bac5d01 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a2e44d841fdd7b545c856e320c7ee6dd417865a --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111ec7cae238861953f45ed55f7e9b6dcca1a049cea9db47e3c319494e67c799 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bfb2119a97e6fe513e51467c3e06c58c5dcc846 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_011000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d581a1b94a091b52a504c99b5ddcf94a8bd19e984f0e42fa379b93f2d0017408 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..08fcbb85042e7010e7589c4d9f01ad3f66f69351 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891fed6dcd5569323fdb7826b85b792791fbc7cc43635cd5eaf2966d4dcb2798 +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c4c4d18ab921e40dcd0417506a4396afecb3132 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_012000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41cd12878fb195b17c6f1db41c4aa1169071672ba6a9c63c068a2910d10ac05d +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..70c0d7d1b3ddb6296ed69a8c62a678393591a33c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129942586c9f12997b4f1a5b471c1e6474f48a8ca0f7d57b77e4941e681b6dcd +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..282b997c243cbd9a83996d36594d62435ebfb884 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_013000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbff27c8eb119b6757688d03bab32c4b34c869b61250f8fe6908770a6d7038d2 +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9234eaec140bdb42a003023b575cb2a656bce4d8 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e8dcd9196b2f9180e2838251f0cf10860035736a4f0f28358b4a6f50a7677e +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..60e25b9a25ea688f9bc5c7465c7a18d073c82232 --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_014000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc81c139ee8316e7dafa1f8abb2e7422ab72032f7278f0f82695f355844ad13f +size 3568 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/losses_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/losses_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d5a8671aa250f44832c414739d0c882d359550c --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/losses_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bd7bb30c84f7f4f20e5c5298f1f03bf05c18ae4ec962ee8d5f4135457218ac +size 3575 diff --git a/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/norms_lr.pt b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/norms_lr.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8c4c1cd692778f21bbecfdf61d661675930f4db --- /dev/null +++ b/fineweb-10B/gpt2/eos/sgd/cosine/cosine-2048-12000-15000-0.1/lr_0.1-wd_0.0001-m_0.95-bs_32-seq_1024-iters_15000/250622_063840/eos_original/step_015000/norms_lr.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5a26962e09bb46dc9d170615e793071b83e22f88737bcb8ec9c9e0f371406cd +size 3568