-
exp-a retrain era_a1_refinedweb
-
exp-a retrain era_a1_refinedweb
-
exp-a retrain era_a1_refinedweb
-
exp-a retrain era_a1_c4
-
exp-a retrain era_a1_c4
-
exp-a retrain era_a1_c4
-
exp-a retrain era_a0_refinedweb
-
exp-a retrain era_a0_refinedweb
-
exp-a retrain era_a0_refinedweb
-
exp-a retrain era_a0_c4
-
exp-a retrain era_a0_c4
-
exp-a retrain era_a0_c4
-
data-ladder: dl_smollm2_135m_dclm
-
data-ladder: dl_smollm2_135m_dclm
-
data-ladder: dl_smollm2_135m_dclm
-
data-ladder: dl_smollm2_135m_refinedweb
-
data-ladder: dl_smollm2_135m_refinedweb
-
data-ladder: dl_smollm2_135m_refinedweb
-
data-ladder: dl_smollm2_135m_c4
-
data-ladder: dl_smollm2_135m_c4
-
data-ladder: dl_smollm2_135m_c4
-
data-ladder: dl_pythia160m_dclm
-
data-ladder: dl_pythia160m_dclm
-
data-ladder: dl_pythia160m_dclm
-
data-ladder: dl_pythia160m_refinedweb
-
data-ladder: dl_pythia160m_refinedweb
-
data-ladder: dl_pythia160m_refinedweb
-
data-ladder: dl_pythia160m_c4
-
data-ladder: dl_pythia160m_c4
-
data-ladder: dl_pythia160m_c4
-
data-ladder tokenized: c4_neox/train.bin
-
data-ladder tokenized: c4_neox/val_text.jsonl
-
data-ladder tokenized: c4_neox/val.bin
-
data-ladder tokenized: c4_neox/meta.json
-
data-ladder tokenized: c4_smollm2/train.bin
-
data-ladder tokenized: c4_smollm2/val_text.jsonl
-
data-ladder tokenized: c4_smollm2/val.bin
-
data-ladder tokenized: c4_smollm2/meta.json
-
data-ladder tokenized: refinedweb_neox/train.bin
-
data-ladder tokenized: refinedweb_neox/val_text.jsonl
-
data-ladder tokenized: refinedweb_neox/val.bin
-
data-ladder tokenized: refinedweb_neox/meta.json
-
data-ladder tokenized: refinedweb_smollm2/train.bin
-
data-ladder tokenized: refinedweb_smollm2/val_text.jsonl
-
data-ladder tokenized: refinedweb_smollm2/val.bin
-
data-ladder tokenized: refinedweb_smollm2/meta.json
-
data-ladder tokenized: dclm_smollm2/train.bin
-
data-ladder tokenized: dclm_smollm2/val_text.jsonl
-
data-ladder tokenized: dclm_smollm2/val.bin
-
data-ladder tokenized: dclm_smollm2/meta.json