{"stage": "eval_set", "split": "val", "n": 500, "sha256": "c7e7203f7a98b7330c2123b44b7ec0dcf7e46ac8fc484f8f49d4fdfa9f7caa19", "t": 1793743474.79383} {"stage": "get_info", "arm": "sel_adamw_lr5e-05_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743479.3154309} {"stage": "init_saved", "group": "s0", "path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "by": "sel_adamw_lr5e-05_s0", "t": 1793743484.1809795} {"stage": "initial_output", "arm": "sel_adamw_lr5e-05_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 0, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743485.5117865} {"stage": "get_info", "arm": "sel_adamw_lr0.0001_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743488.5540414} {"stage": "get_info", "arm": "sel_adamw_lr0.0001_s0", "restores": 1, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743491.299017} {"stage": "initial_output", "arm": "sel_adamw_lr0.0001_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743492.4497533} {"stage": "get_info", "arm": "sel_adamw_lr0.0002_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743495.1814528} {"stage": "get_info", "arm": "sel_adamw_lr0.0002_s0", "restores": 1, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743497.9414043} {"stage": "initial_output", "arm": "sel_adamw_lr0.0002_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743499.042234} {"stage": "get_info", "arm": "sel_dimuon_lr0.0003_s0", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743502.1410964} {"stage": "get_info", "arm": "sel_dimuon_lr0.0003_s0", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743504.7654526} {"stage": "initial_output", "arm": "sel_dimuon_lr0.0003_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743505.9719884} {"stage": "get_info", "arm": "sel_dimuon_lr0.001_s0", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743508.9036634} {"stage": "get_info", "arm": "sel_dimuon_lr0.001_s0", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743511.485621} {"stage": "initial_output", "arm": "sel_dimuon_lr0.001_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743512.613078} {"stage": "get_info", "arm": "sel_dimuon_lr0.003_s0", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743515.4513211} {"stage": "get_info", "arm": "sel_dimuon_lr0.003_s0", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793743518.1089733} {"stage": "initial_output", "arm": "sel_dimuon_lr0.003_s0", "init": "s0", "init_path": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793743519.2583187} {"stage": "setup_done", "seconds": 48.95686173439026, "t": 1793743519.2597637} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "AdamParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.34653854370117, "t": 1793743569.484668} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "AdamParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.34677505493164, "t": 1793743570.6008499} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "AdamParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.345829010009766, "t": 1793743570.723108} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "DimuonParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.34832763671875, "t": 1793743570.7239501} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "DimuonParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.34993362426758, "t": 1793743570.7258542} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 1, "batch_sha256": "d9ce572e4cf770c21e54e31f0cd523d578343475316b862f1453171ae1c3c6eb", "params_type": "DimuonParams", "train_nll_sum": 15620.10640398725, "train_tokens": 6619.0, "train_token_mean_nll": 2.359889168150363, "grad_norm": 36.34648513793945, "t": 1793743570.830836} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 14117.908327949895, "train_tokens": 6073.0, "train_token_mean_nll": 2.324700860851292, "grad_norm": 39.80023193359375, "t": 1793743577.0800276} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13891.563357736912, "train_tokens": 6073.0, "train_token_mean_nll": 2.287430159350718, "grad_norm": 32.78599548339844, "t": 1793743577.8370168} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13537.728051586564, "train_tokens": 6073.0, "train_token_mean_nll": 2.229166483053938, "grad_norm": 24.17935562133789, "t": 1793743577.9738822} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14230.552639882488, "train_tokens": 6073.0, "train_token_mean_nll": 2.343249240883005, "grad_norm": 51.980224609375, "t": 1793743577.9746609} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14221.990011789423, "train_tokens": 6073.0, "train_token_mean_nll": 2.341839290595986, "grad_norm": 48.243499755859375, "t": 1793743577.9753585} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14159.370122556846, "train_tokens": 6073.0, "train_token_mean_nll": 2.3315280952670583, "grad_norm": 43.12493896484375, "t": 1793743578.1590781} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 13126.506307923913, "train_tokens": 5852.0, "train_token_mean_nll": 2.2430803670409967, "grad_norm": 50.97428894042969, "t": 1793743604.2314765} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12718.70646968531, "train_tokens": 5852.0, "train_token_mean_nll": 2.173394817102753, "grad_norm": 45.95807647705078, "t": 1793743605.3801968} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12364.768389588791, "train_tokens": 5852.0, "train_token_mean_nll": 2.112913258644701, "grad_norm": 27.224336624145508, "t": 1793743605.4162557} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13452.28726589535, "train_tokens": 5852.0, "train_token_mean_nll": 2.2987503872001622, "grad_norm": 52.358070373535156, "t": 1793743605.416983} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13440.43842012258, "train_tokens": 5852.0, "train_token_mean_nll": 2.296725635701056, "grad_norm": 52.68422317504883, "t": 1793743605.4177} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13301.239306962918, "train_tokens": 5852.0, "train_token_mean_nll": 2.2729390476696714, "grad_norm": 52.364383697509766, "t": 1793743605.4192371} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16745.71765305976, "train_tokens": 7125.0, "train_token_mean_nll": 2.350276161832949, "grad_norm": 25.562355041503906, "t": 1793743611.154377} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16268.204131931838, "train_tokens": 7125.0, "train_token_mean_nll": 2.283256720271135, "grad_norm": 18.643417358398438, "t": 1793743612.154182} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16038.389005998015, "train_tokens": 7125.0, "train_token_mean_nll": 2.2510019657541074, "grad_norm": 14.987004280090332, "t": 1793743612.2393515} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17334.557239286303, "train_tokens": 7125.0, "train_token_mean_nll": 2.432920314285797, "grad_norm": 30.673614501953125, "t": 1793743612.2401226} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17305.954452854552, "train_tokens": 7125.0, "train_token_mean_nll": 2.428905888119937, "grad_norm": 30.66706657409668, "t": 1793743612.2408175} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17061.051630038008, "train_tokens": 7125.0, "train_token_mean_nll": 2.3945335621105976, "grad_norm": 28.965316772460938, "t": 1793743612.2415361} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 16277.88208473403, "train_tokens": 6823.0, "train_token_mean_nll": 2.3857367850995206, "grad_norm": 25.210365295410156, "t": 1793743659.9126196} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15815.669024470099, "train_tokens": 6823.0, "train_token_mean_nll": 2.3179934082471196, "grad_norm": 16.505630493164062, "t": 1793743661.0528684} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15762.017248025293, "train_tokens": 6823.0, "train_token_mean_nll": 2.3101300378169856, "grad_norm": 15.786903381347656, "t": 1793743661.0542815} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 17039.531625234733, "train_tokens": 6823.0, "train_token_mean_nll": 2.4973664993748694, "grad_norm": 34.097984313964844, "t": 1793743661.0550478} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16984.521180321713, "train_tokens": 6823.0, "train_token_mean_nll": 2.489303998288394, "grad_norm": 33.784854888916016, "t": 1793743661.0557601} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16650.73899320923, "train_tokens": 6823.0, "train_token_mean_nll": 2.440383847751609, "grad_norm": 29.55232810974121, "t": 1793743661.0564554} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13583.670948392615, "train_tokens": 6097.0, "train_token_mean_nll": 2.2279270048208324, "grad_norm": 32.58718490600586, "t": 1793743707.1619241} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13281.06646999611, "train_tokens": 6097.0, "train_token_mean_nll": 2.178295304247353, "grad_norm": 16.68855094909668, "t": 1793743707.7274795} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13268.194277998165, "train_tokens": 6097.0, "train_token_mean_nll": 2.1761840705261877, "grad_norm": 20.321489334106445, "t": 1793743707.7282336} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 14450.373152326883, "train_tokens": 6097.0, "train_token_mean_nll": 2.3700792442720817, "grad_norm": 45.55159378051758, "t": 1793743707.9355803} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 14370.494099048985, "train_tokens": 6097.0, "train_token_mean_nll": 2.356977874208461, "grad_norm": 45.62739562988281, "t": 1793743707.936355} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 13925.178374677284, "train_tokens": 6097.0, "train_token_mean_nll": 2.2839393758696547, "grad_norm": 40.17916488647461, "t": 1793743708.2211177} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 13233.892139185362, "train_tokens": 6602.0, "train_token_mean_nll": 2.0045277399553716, "grad_norm": 20.78732681274414, "t": 1793743714.2970297} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 13005.557077924681, "train_tokens": 6602.0, "train_token_mean_nll": 1.969941999079776, "grad_norm": 15.472272872924805, "t": 1793743714.664574} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 12953.973979810557, "train_tokens": 6602.0, "train_token_mean_nll": 1.9621287458059007, "grad_norm": 14.831717491149902, "t": 1793743714.66546} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 14373.817362877124, "train_tokens": 6602.0, "train_token_mean_nll": 2.1771913606296764, "grad_norm": 34.6500358581543, "t": 1793743714.6662705} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 14259.12889753867, "train_tokens": 6602.0, "train_token_mean_nll": 2.1598195846014345, "grad_norm": 33.998477935791016, "t": 1793743715.258822} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 13644.702344350531, "train_tokens": 6602.0, "train_token_mean_nll": 2.0667528543396747, "grad_norm": 27.023025512695312, "t": 1793743715.2870548} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13818.708997938975, "train_tokens": 6404.0, "train_token_mean_nll": 2.157824640527635, "grad_norm": 19.58180046081543, "t": 1793743741.2793803} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13697.928331089088, "train_tokens": 6404.0, "train_token_mean_nll": 2.1389644489520747, "grad_norm": 18.490076065063477, "t": 1793743741.8238525} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13565.11111484351, "train_tokens": 6404.0, "train_token_mean_nll": 2.1182247212435215, "grad_norm": 14.859199523925781, "t": 1793743741.8246884} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14844.936950477802, "train_tokens": 6404.0, "train_token_mean_nll": 2.3180726031351973, "grad_norm": 53.65563201904297, "t": 1793743742.4497244} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14716.965165289766, "train_tokens": 6404.0, "train_token_mean_nll": 2.2980895011383144, "grad_norm": 54.69393539428711, "t": 1793743742.450519} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14102.83981941278, "train_tokens": 6404.0, "train_token_mean_nll": 2.20219235156352, "grad_norm": 30.223114013671875, "t": 1793743742.4515557} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10843.841559655968, "train_tokens": 5225.0, "train_token_mean_nll": 2.0753763750537737, "grad_norm": 23.804109573364258, "t": 1793743747.450061} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10795.757763652236, "train_tokens": 5225.0, "train_token_mean_nll": 2.0661737346702846, "grad_norm": 17.474946975708008, "t": 1793743747.8707108} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10709.20271328438, "train_tokens": 5225.0, "train_token_mean_nll": 2.0496081747912687, "grad_norm": 14.954314231872559, "t": 1793743748.021226} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11875.670599785923, "train_tokens": 5225.0, "train_token_mean_nll": 2.2728556171839087, "grad_norm": 42.85848617553711, "t": 1793743748.022127} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11738.736734722776, "train_tokens": 5225.0, "train_token_mean_nll": 2.246648178894311, "grad_norm": 42.449806213378906, "t": 1793743748.0229716} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11143.612709139807, "train_tokens": 5225.0, "train_token_mean_nll": 2.1327488438545084, "grad_norm": 29.467618942260742, "t": 1793743748.420145} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14693.509891397147, "train_tokens": 7976.0, "train_token_mean_nll": 1.8422153825723604, "grad_norm": 17.251319885253906, "t": 1793743754.8335001} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14606.630341605593, "train_tokens": 7976.0, "train_token_mean_nll": 1.83132276098365, "grad_norm": 15.92687702178955, "t": 1793743754.9232514} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14492.914730182922, "train_tokens": 7976.0, "train_token_mean_nll": 1.8170655378865248, "grad_norm": 13.466239929199219, "t": 1793743754.924156} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 15932.470883962997, "train_tokens": 7976.0, "train_token_mean_nll": 1.997551515040496, "grad_norm": 34.11865997314453, "t": 1793743754.9249442} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 15704.151159031184, "train_tokens": 7976.0, "train_token_mean_nll": 1.9689256718945818, "grad_norm": 31.99302101135254, "t": 1793743754.9257536} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 14957.442956019113, "train_tokens": 7976.0, "train_token_mean_nll": 1.8753062883674916, "grad_norm": 21.72764778137207, "t": 1793743755.5235214} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10364.519709994504, "train_tokens": 5826.0, "train_token_mean_nll": 1.7790112787494856, "grad_norm": 17.058795928955078, "t": 1793743762.6394486} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10302.1309079362, "train_tokens": 5826.0, "train_token_mean_nll": 1.7683025931919327, "grad_norm": 15.94118881225586, "t": 1793743762.7766588} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10239.881846051048, "train_tokens": 5826.0, "train_token_mean_nll": 1.7576178932459747, "grad_norm": 14.674591064453125, "t": 1793743762.7774663} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 11380.52361957635, "train_tokens": 5826.0, "train_token_mean_nll": 1.953402612354334, "grad_norm": 39.95533752441406, "t": 1793743762.7781808} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 11147.560380135334, "train_tokens": 5826.0, "train_token_mean_nll": 1.9134157878708091, "grad_norm": 35.086917877197266, "t": 1793743762.7788804} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 10501.21425452666, "train_tokens": 5826.0, "train_token_mean_nll": 1.802474125390776, "grad_norm": 20.259084701538086, "t": 1793743762.9634292} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13184.088874798077, "train_tokens": 6074.0, "train_token_mean_nll": 2.170577687651972, "grad_norm": 18.017545700073242, "t": 1793743804.1114144} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13113.779910951525, "train_tokens": 6074.0, "train_token_mean_nll": 2.159002290245559, "grad_norm": 16.591930389404297, "t": 1793743805.0117927} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13016.66559042261, "train_tokens": 6074.0, "train_token_mean_nll": 2.143013762005698, "grad_norm": 15.15014362335205, "t": 1793743805.0135639} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 14261.600468971414, "train_tokens": 6074.0, "train_token_mean_nll": 2.3479750525142267, "grad_norm": 38.53030014038086, "t": 1793743805.0144334} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13970.18555877942, "train_tokens": 6074.0, "train_token_mean_nll": 2.2999976224529832, "grad_norm": 34.556941986083984, "t": 1793743805.015278} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13255.58115682899, "train_tokens": 6074.0, "train_token_mean_nll": 2.182347902013334, "grad_norm": 19.352481842041016, "t": 1793743805.182963} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10807.271818016277, "train_tokens": 5144.0, "train_token_mean_nll": 2.1009470874837244, "grad_norm": 19.519594192504883, "t": 1793743876.8889773} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10698.236406299075, "train_tokens": 5144.0, "train_token_mean_nll": 2.079750467787534, "grad_norm": 16.97209930419922, "t": 1793743877.4678013} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10642.088188776548, "train_tokens": 5144.0, "train_token_mean_nll": 2.0688351844433415, "grad_norm": 16.958202362060547, "t": 1793743877.5015225} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 11804.356064979942, "train_tokens": 5144.0, "train_token_mean_nll": 2.2947815056337366, "grad_norm": 38.82902908325195, "t": 1793743877.5023448} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 11514.876840131376, "train_tokens": 5144.0, "train_token_mean_nll": 2.238506384162398, "grad_norm": 33.31524658203125, "t": 1793743877.7748325} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 10890.674456052559, "train_tokens": 5144.0, "train_token_mean_nll": 2.1171606640848677, "grad_norm": 20.18088150024414, "t": 1793743877.7756774} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10681.738780252417, "train_tokens": 4753.0, "train_token_mean_nll": 2.247367721492198, "grad_norm": 20.823719024658203, "t": 1793743897.796053} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10564.810169126486, "train_tokens": 4753.0, "train_token_mean_nll": 2.2227667092628836, "grad_norm": 17.5511531829834, "t": 1793743899.003356} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10496.899904430418, "train_tokens": 4753.0, "train_token_mean_nll": 2.208478835352497, "grad_norm": 16.57472038269043, "t": 1793743899.043964} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 11849.304030797335, "train_tokens": 4753.0, "train_token_mean_nll": 2.4930157859872364, "grad_norm": 47.367496490478516, "t": 1793743899.044633} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 11466.215321617408, "train_tokens": 4753.0, "train_token_mean_nll": 2.4124164362754907, "grad_norm": 43.76386260986328, "t": 1793743899.0452082} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 10729.363653544473, "train_tokens": 4753.0, "train_token_mean_nll": 2.257387682210072, "grad_norm": 20.414339065551758, "t": 1793743899.0457678} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 14112.73677710041, "train_tokens": 6492.0, "train_token_mean_nll": 2.1738658005391884, "grad_norm": 14.496214866638184, "t": 1793743905.56146} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13942.497089948793, "train_tokens": 6492.0, "train_token_mean_nll": 2.14764280498287, "grad_norm": 12.387145042419434, "t": 1793743906.6751566} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13880.873441371097, "train_tokens": 6492.0, "train_token_mean_nll": 2.138150560901278, "grad_norm": 11.533429145812988, "t": 1793743906.896891} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 15449.661500399408, "train_tokens": 6492.0, "train_token_mean_nll": 2.3797999846579496, "grad_norm": 44.2022590637207, "t": 1793743906.8977485} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 15001.953475514503, "train_tokens": 6492.0, "train_token_mean_nll": 2.3108369494014944, "grad_norm": 37.488346099853516, "t": 1793743906.8995335} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 14187.97022963314, "train_tokens": 6492.0, "train_token_mean_nll": 2.1854544407937677, "grad_norm": 15.118793487548828, "t": 1793743906.9003315} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14401.64777606076, "train_tokens": 7021.0, "train_token_mean_nll": 2.0512245799830167, "grad_norm": 18.091909408569336, "t": 1793743912.983844} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14277.723514731866, "train_tokens": 7021.0, "train_token_mean_nll": 2.033574065621972, "grad_norm": 15.775825500488281, "t": 1793743914.0284853} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14218.71339266268, "train_tokens": 7021.0, "train_token_mean_nll": 2.025169262592605, "grad_norm": 14.793211936950684, "t": 1793743914.1249514} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 15683.691362251857, "train_tokens": 7021.0, "train_token_mean_nll": 2.233825859884896, "grad_norm": 37.46642303466797, "t": 1793743914.1258664} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 15181.49550697431, "train_tokens": 7021.0, "train_token_mean_nll": 2.162298177891228, "grad_norm": 32.666015625, "t": 1793743914.1266658} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 14425.653832926766, "train_tokens": 7021.0, "train_token_mean_nll": 2.054643759140687, "grad_norm": 17.29377555847168, "t": 1793743914.1274407} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13721.525085295829, "train_tokens": 6222.0, "train_token_mean_nll": 2.205323864560564, "grad_norm": 16.08574676513672, "t": 1793743959.5401595} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13642.994170227777, "train_tokens": 6222.0, "train_token_mean_nll": 2.192702373871388, "grad_norm": 14.368327140808105, "t": 1793743960.689373} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13631.238959066932, "train_tokens": 6222.0, "train_token_mean_nll": 2.1908130760313296, "grad_norm": 14.790725708007812, "t": 1793743960.690095} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 14803.44431994603, "train_tokens": 6222.0, "train_token_mean_nll": 2.379209951775318, "grad_norm": 60.190399169921875, "t": 1793743960.6907673} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 14347.310847397717, "train_tokens": 6222.0, "train_token_mean_nll": 2.305900168337788, "grad_norm": 46.936946868896484, "t": 1793743960.6914017} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 13746.959787266765, "train_tokens": 6222.0, "train_token_mean_nll": 2.2094117305153915, "grad_norm": 15.953351020812988, "t": 1793743960.6920195} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11950.40565533017, "train_tokens": 5713.0, "train_token_mean_nll": 2.0917916428024106, "grad_norm": 18.97173500061035, "t": 1793743988.2889833} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11845.128165526008, "train_tokens": 5713.0, "train_token_mean_nll": 2.073363935852618, "grad_norm": 16.98499298095703, "t": 1793743988.289699} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11784.95733416919, "train_tokens": 5713.0, "train_token_mean_nll": 2.0628316706054943, "grad_norm": 15.419076919555664, "t": 1793743988.3730345} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 13267.113615691536, "train_tokens": 5713.0, "train_token_mean_nll": 2.3222673929094233, "grad_norm": 40.558738708496094, "t": 1793743988.3737519} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 12701.229916393544, "train_tokens": 5713.0, "train_token_mean_nll": 2.2232154588471107, "grad_norm": 34.4290657043457, "t": 1793743988.3744078} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 11989.919554543889, "train_tokens": 5713.0, "train_token_mean_nll": 2.0987081313747398, "grad_norm": 19.15751075744629, "t": 1793743988.604976} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12889.9682699133, "train_tokens": 6187.0, "train_token_mean_nll": 2.0833955503334898, "grad_norm": 15.68832778930664, "t": 1793743995.1359332} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12805.043643745528, "train_tokens": 6187.0, "train_token_mean_nll": 2.069669249029502, "grad_norm": 14.644673347473145, "t": 1793743995.1370442} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12786.955666596457, "train_tokens": 6187.0, "train_token_mean_nll": 2.0667457033451524, "grad_norm": 13.420042991638184, "t": 1793743995.2733605} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 14095.788612515555, "train_tokens": 6187.0, "train_token_mean_nll": 2.2782913548594723, "grad_norm": 43.74186325073242, "t": 1793743995.2742522} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 13544.218774803543, "train_tokens": 6187.0, "train_token_mean_nll": 2.1891415508006373, "grad_norm": 29.616777420043945, "t": 1793743995.274916} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 12920.969085166898, "train_tokens": 6187.0, "train_token_mean_nll": 2.0884061880017617, "grad_norm": 15.490583419799805, "t": 1793743995.2755418} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15218.264674816652, "train_tokens": 6765.0, "train_token_mean_nll": 2.249558710246364, "grad_norm": 14.400379180908203, "t": 1793744001.2070935} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15117.774721917898, "train_tokens": 6765.0, "train_token_mean_nll": 2.234704319573969, "grad_norm": 13.338794708251953, "t": 1793744002.2029197} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15082.580083342236, "train_tokens": 6765.0, "train_token_mean_nll": 2.2295018600653713, "grad_norm": 12.368941307067871, "t": 1793744002.3373737} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 16650.0942847718, "train_tokens": 6765.0, "train_token_mean_nll": 2.4612112763890317, "grad_norm": 32.86234664916992, "t": 1793744002.3382666} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 16004.482506878117, "train_tokens": 6765.0, "train_token_mean_nll": 2.3657771628792488, "grad_norm": 26.772563934326172, "t": 1793744002.3402069} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 15273.282746095265, "train_tokens": 6765.0, "train_token_mean_nll": 2.2576914628374376, "grad_norm": 14.803545951843262, "t": 1793744002.3410485} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12154.132102724932, "train_tokens": 5786.0, "train_token_mean_nll": 2.100610456744717, "grad_norm": 18.522306442260742, "t": 1793744008.8440897} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12101.212551574336, "train_tokens": 5786.0, "train_token_mean_nll": 2.091464319318067, "grad_norm": 17.372081756591797, "t": 1793744008.8449056} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12069.942763291287, "train_tokens": 5786.0, "train_token_mean_nll": 2.0860599314364476, "grad_norm": 16.131948471069336, "t": 1793744008.8456733} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 13364.0344951882, "train_tokens": 5786.0, "train_token_mean_nll": 2.309719062424507, "grad_norm": 37.29854965209961, "t": 1793744008.8467987} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12739.925557157838, "train_tokens": 5786.0, "train_token_mean_nll": 2.2018537084614307, "grad_norm": 30.078834533691406, "t": 1793744008.8478022} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12173.929917090009, "train_tokens": 5786.0, "train_token_mean_nll": 2.104032132231249, "grad_norm": 19.27552604675293, "t": 1793744008.8494186} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10729.16232071045, "train_tokens": 4783.0, "train_token_mean_nll": 2.243186769958279, "grad_norm": 16.997995376586914, "t": 1793744016.4270658} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10663.39927772612, "train_tokens": 4783.0, "train_token_mean_nll": 2.2294374404612416, "grad_norm": 16.293163299560547, "t": 1793744016.4296591} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10654.584039814887, "train_tokens": 4783.0, "train_token_mean_nll": 2.227594405146328, "grad_norm": 14.252575874328613, "t": 1793744016.4304461} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 11926.901144423231, "train_tokens": 4783.0, "train_token_mean_nll": 2.4936025808955113, "grad_norm": 40.97806167602539, "t": 1793744016.4312844} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 11282.765748532107, "train_tokens": 4783.0, "train_token_mean_nll": 2.358930743995841, "grad_norm": 29.608644485473633, "t": 1793744016.7381718} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 10761.504824835434, "train_tokens": 4783.0, "train_token_mean_nll": 2.24994874029593, "grad_norm": 17.30105209350586, "t": 1793744016.739035} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15468.972480917817, "train_tokens": 7466.0, "train_token_mean_nll": 2.071922378906753, "grad_norm": 13.814292907714844, "t": 1793744063.8986197} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15418.035488435542, "train_tokens": 7466.0, "train_token_mean_nll": 2.065099851116467, "grad_norm": 12.939115524291992, "t": 1793744064.4958978} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15384.11476102667, "train_tokens": 7466.0, "train_token_mean_nll": 2.060556490895616, "grad_norm": 12.113972663879395, "t": 1793744064.496972} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 16620.732599853065, "train_tokens": 7466.0, "train_token_mean_nll": 2.2261897401356903, "grad_norm": 27.876880645751953, "t": 1793744064.5252626} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15934.884695838444, "train_tokens": 7466.0, "train_token_mean_nll": 2.134326908095157, "grad_norm": 19.59009552001953, "t": 1793744064.526224} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15498.187248408036, "train_tokens": 7466.0, "train_token_mean_nll": 2.075835420360037, "grad_norm": 14.520601272583008, "t": 1793744064.5284085} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10865.28685216241, "train_tokens": 6100.0, "train_token_mean_nll": 1.781194565928264, "grad_norm": 15.144591331481934, "t": 1793744072.017618} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10788.096132232973, "train_tokens": 6100.0, "train_token_mean_nll": 1.768540349546389, "grad_norm": 13.925117492675781, "t": 1793744072.0184548} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10772.161505211037, "train_tokens": 6100.0, "train_token_mean_nll": 1.7659281156083668, "grad_norm": 13.20409107208252, "t": 1793744072.1469471} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 12008.531799241004, "train_tokens": 6100.0, "train_token_mean_nll": 1.9686117703673776, "grad_norm": 51.353607177734375, "t": 1793744072.1484673} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 11359.280826263945, "train_tokens": 6100.0, "train_token_mean_nll": 1.8621771846334336, "grad_norm": 21.97066879272461, "t": 1793744072.1492534} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 10909.477696364696, "train_tokens": 6100.0, "train_token_mean_nll": 1.7884389666171634, "grad_norm": 15.575742721557617, "t": 1793744072.1500056} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12406.888195836591, "train_tokens": 6108.0, "train_token_mean_nll": 2.0312521604185645, "grad_norm": 13.264731407165527, "t": 1793744080.062913} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12332.370275947256, "train_tokens": 6108.0, "train_token_mean_nll": 2.019052108046375, "grad_norm": 12.581259727478027, "t": 1793744080.090158} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12285.650838586662, "train_tokens": 6108.0, "train_token_mean_nll": 2.0114032152237495, "grad_norm": 11.78349781036377, "t": 1793744080.0910225} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 13651.544851107532, "train_tokens": 6108.0, "train_token_mean_nll": 2.235026989375824, "grad_norm": 35.257869720458984, "t": 1793744080.3615017} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12906.310446852054, "train_tokens": 6108.0, "train_token_mean_nll": 2.113017427447946, "grad_norm": 21.36964225769043, "t": 1793744080.3622537} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12430.782549484242, "train_tokens": 6108.0, "train_token_mean_nll": 2.035164137112679, "grad_norm": 13.624150276184082, "t": 1793744080.3631482} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11292.820248103555, "train_tokens": 5073.0, "train_token_mean_nll": 2.22606352219664, "grad_norm": 16.940473556518555, "t": 1793744086.5011766} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11232.648738364363, "train_tokens": 5073.0, "train_token_mean_nll": 2.2142023927388848, "grad_norm": 15.872090339660645, "t": 1793744086.5019195} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11220.7222831213, "train_tokens": 5073.0, "train_token_mean_nll": 2.211851425807471, "grad_norm": 14.479732513427734, "t": 1793744086.5026078} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 12470.255245999302, "train_tokens": 5073.0, "train_token_mean_nll": 2.458161885669092, "grad_norm": 36.776283264160156, "t": 1793744086.5779703} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11799.928794294594, "train_tokens": 5073.0, "train_token_mean_nll": 2.3260257824353623, "grad_norm": 25.846176147460938, "t": 1793744086.5786777} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11310.900243614626, "train_tokens": 5073.0, "train_token_mean_nll": 2.229627487406786, "grad_norm": 17.70415496826172, "t": 1793744086.5793147} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13514.022986868284, "train_tokens": 6392.0, "train_token_mean_nll": 2.1142088527641243, "grad_norm": 17.310335159301758, "t": 1793744093.387582} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13457.166495102587, "train_tokens": 6392.0, "train_token_mean_nll": 2.105313907243834, "grad_norm": 16.174997329711914, "t": 1793744093.388346} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13406.488920691656, "train_tokens": 6392.0, "train_token_mean_nll": 2.097385625890434, "grad_norm": 14.872056007385254, "t": 1793744093.3900354} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 14856.237316402143, "train_tokens": 6392.0, "train_token_mean_nll": 2.324192321089196, "grad_norm": 36.6722297668457, "t": 1793744093.3907263} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 13999.772776139649, "train_tokens": 6392.0, "train_token_mean_nll": 2.1902022490831743, "grad_norm": 22.885515213012695, "t": 1793744093.3913794} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 13539.514617686904, "train_tokens": 6392.0, "train_token_mean_nll": 2.11819690514501, "grad_norm": 17.309043884277344, "t": 1793744093.392032} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14645.312610084144, "train_tokens": 7271.0, "train_token_mean_nll": 2.0142088584904614, "grad_norm": 16.973661422729492, "t": 1793744100.9251091} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14594.810421076705, "train_tokens": 7271.0, "train_token_mean_nll": 2.0072631578980475, "grad_norm": 16.456941604614258, "t": 1793744100.9262292} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14574.98312676163, "train_tokens": 7271.0, "train_token_mean_nll": 2.0045362572908307, "grad_norm": 14.993814468383789, "t": 1793744100.9320517} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 16012.632324637028, "train_tokens": 7271.0, "train_token_mean_nll": 2.20225998138317, "grad_norm": 33.985469818115234, "t": 1793744101.234898} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 15165.26952934141, "train_tokens": 7271.0, "train_token_mean_nll": 2.0857199187651507, "grad_norm": 24.5267391204834, "t": 1793744101.235751} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 14650.134543180196, "train_tokens": 7271.0, "train_token_mean_nll": 2.014872031794828, "grad_norm": 17.24635887145996, "t": 1793744101.2365282} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11174.440231064455, "train_tokens": 5476.0, "train_token_mean_nll": 2.0406209333572782, "grad_norm": 15.459827423095703, "t": 1793744128.395343} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11128.142331423132, "train_tokens": 5476.0, "train_token_mean_nll": 2.032166240216058, "grad_norm": 14.541557312011719, "t": 1793744128.4009585} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11111.03736626772, "train_tokens": 5476.0, "train_token_mean_nll": 2.0290426161920596, "grad_norm": 13.612245559692383, "t": 1793744128.4022143} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 12232.762676330438, "train_tokens": 5476.0, "train_token_mean_nll": 2.2338865369485825, "grad_norm": 31.05768585205078, "t": 1793744128.4029028} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11565.66379175688, "train_tokens": 5476.0, "train_token_mean_nll": 2.112064242468386, "grad_norm": 21.55319595336914, "t": 1793744128.6548328} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11191.85249087826, "train_tokens": 5476.0, "train_token_mean_nll": 2.043800674009909, "grad_norm": 16.12084197998047, "t": 1793744128.6560955} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16854.517514729225, "train_tokens": 7466.0, "train_token_mean_nll": 2.257503015634774, "grad_norm": 13.346217155456543, "t": 1793744157.1772096} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16810.76961848256, "train_tokens": 7466.0, "train_token_mean_nll": 2.251643399207415, "grad_norm": 11.838857650756836, "t": 1793744157.2051044} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16808.055295781138, "train_tokens": 7466.0, "train_token_mean_nll": 2.2512798413850974, "grad_norm": 11.319619178771973, "t": 1793744157.2098498} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 18171.98502791889, "train_tokens": 7466.0, "train_token_mean_nll": 2.4339653131420964, "grad_norm": 52.322227478027344, "t": 1793744157.210737} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 17288.899481844746, "train_tokens": 7466.0, "train_token_mean_nll": 2.3156843667083775, "grad_norm": 21.49834632873535, "t": 1793744157.2116337} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 16866.235135193605, "train_tokens": 7466.0, "train_token_mean_nll": 2.259072479934852, "grad_norm": 13.828866958618164, "t": 1793744157.5107539} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11655.476538013154, "train_tokens": 5656.0, "train_token_mean_nll": 2.060727817894829, "grad_norm": 14.564947128295898, "t": 1793744164.2163827} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11623.247650859346, "train_tokens": 5656.0, "train_token_mean_nll": 2.055029641241044, "grad_norm": 13.425950050354004, "t": 1793744165.132989} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11592.209165029346, "train_tokens": 5656.0, "train_token_mean_nll": 2.049541931582275, "grad_norm": 12.966630935668945, "t": 1793744165.1730962} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 12833.752736849645, "train_tokens": 5656.0, "train_token_mean_nll": 2.269051049655171, "grad_norm": 35.24012756347656, "t": 1793744165.1739824} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11996.287781661926, "train_tokens": 5656.0, "train_token_mean_nll": 2.1209844026983604, "grad_norm": 19.439258575439453, "t": 1793744165.400994} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11656.633017146833, "train_tokens": 5656.0, "train_token_mean_nll": 2.0609322873314766, "grad_norm": 15.376518249511719, "t": 1793744165.4020143} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9926.896750371096, "train_tokens": 5681.0, "train_token_mean_nll": 1.7473854515703389, "grad_norm": 16.33611488342285, "t": 1793744171.136661} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9862.926244879354, "train_tokens": 5681.0, "train_token_mean_nll": 1.736125021101805, "grad_norm": 14.307494163513184, "t": 1793744172.1256926} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9852.139284285828, "train_tokens": 5681.0, "train_token_mean_nll": 1.734226242613242, "grad_norm": 14.146724700927734, "t": 1793744172.1295636} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 11167.293266564919, "train_tokens": 5681.0, "train_token_mean_nll": 1.9657266795572819, "grad_norm": 34.57700729370117, "t": 1793744172.1793568} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 10311.348957841634, "train_tokens": 5681.0, "train_token_mean_nll": 1.815058785045174, "grad_norm": 21.44632339477539, "t": 1793744172.2452204} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 9919.012398195668, "train_tokens": 5681.0, "train_token_mean_nll": 1.7459976057376638, "grad_norm": 17.59262466430664, "t": 1793744172.2460275} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11709.624740908323, "train_tokens": 6193.0, "train_token_mean_nll": 1.8907839077843247, "grad_norm": 15.317557334899902, "t": 1793744178.4812272} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11660.5860266661, "train_tokens": 6193.0, "train_token_mean_nll": 1.8828654976047312, "grad_norm": 13.315007209777832, "t": 1793744178.4839516} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11632.965746504744, "train_tokens": 6193.0, "train_token_mean_nll": 1.8784055783149918, "grad_norm": 12.96823787689209, "t": 1793744178.5733118} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 12906.294903898024, "train_tokens": 6193.0, "train_token_mean_nll": 2.0840133867104833, "grad_norm": 35.40910720825195, "t": 1793744178.5741246} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 12043.76837666256, "train_tokens": 6193.0, "train_token_mean_nll": 1.944738959577355, "grad_norm": 20.790185928344727, "t": 1793744178.8373923} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 11705.71564898337, "train_tokens": 6193.0, "train_token_mean_nll": 1.8901526964287696, "grad_norm": 15.381157875061035, "t": 1793744178.838189} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10277.948817891936, "train_tokens": 4524.0, "train_token_mean_nll": 2.2718719756613477, "grad_norm": 16.941303253173828, "t": 1793744185.1889415} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10225.246224730265, "train_tokens": 4524.0, "train_token_mean_nll": 2.2602224192595632, "grad_norm": 15.117447853088379, "t": 1793744185.1896653} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10212.91590165822, "train_tokens": 4524.0, "train_token_mean_nll": 2.257496883655663, "grad_norm": 14.367066383361816, "t": 1793744185.2878637} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 11312.0516762307, "train_tokens": 4524.0, "train_token_mean_nll": 2.500453509334814, "grad_norm": 37.83354568481445, "t": 1793744185.2885807} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10557.685499568852, "train_tokens": 4524.0, "train_token_mean_nll": 2.3337059017614616, "grad_norm": 22.17982292175293, "t": 1793744185.2893243} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10271.901592276654, "train_tokens": 4524.0, "train_token_mean_nll": 2.270535276807395, "grad_norm": 17.289791107177734, "t": 1793744185.2900543} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11984.394161172053, "train_tokens": 5628.0, "train_token_mean_nll": 2.1294232695757023, "grad_norm": 20.23248863220215, "t": 1793744191.1568377} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11945.527185390776, "train_tokens": 5628.0, "train_token_mean_nll": 2.1225172681931017, "grad_norm": 18.126243591308594, "t": 1793744191.2004511} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11937.34332614126, "train_tokens": 5628.0, "train_token_mean_nll": 2.1210631354195555, "grad_norm": 15.140250205993652, "t": 1793744191.2011185} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 13104.277171782609, "train_tokens": 5628.0, "train_token_mean_nll": 2.328407457672816, "grad_norm": 40.834991455078125, "t": 1793744191.3430245} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 12227.342454545107, "train_tokens": 5628.0, "train_token_mean_nll": 2.1725910544678584, "grad_norm": 21.11305046081543, "t": 1793744191.343695} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 11989.21095151311, "train_tokens": 5628.0, "train_token_mean_nll": 2.1302791313989182, "grad_norm": 18.06437873840332, "t": 1793744191.3442717} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13054.83788231798, "train_tokens": 6703.0, "train_token_mean_nll": 1.9476112013006086, "grad_norm": 12.702638626098633, "t": 1793744239.9296699} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13018.255812640447, "train_tokens": 6703.0, "train_token_mean_nll": 1.942153634587565, "grad_norm": 11.394512176513672, "t": 1793744240.5644534} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13002.949641018466, "train_tokens": 6703.0, "train_token_mean_nll": 1.939870153814481, "grad_norm": 11.352031707763672, "t": 1793744241.135557} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 14283.05722703793, "train_tokens": 6703.0, "train_token_mean_nll": 2.130845476210343, "grad_norm": 36.08739471435547, "t": 1793744241.1364596} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13322.20271043614, "train_tokens": 6703.0, "train_token_mean_nll": 1.9874985395250098, "grad_norm": 15.076483726501465, "t": 1793744241.1716685} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13047.094826790706, "train_tokens": 6703.0, "train_token_mean_nll": 1.9464560386081913, "grad_norm": 13.24396800994873, "t": 1793744241.1725323} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11526.682193365985, "train_tokens": 5733.0, "train_token_mean_nll": 2.0105847188847, "grad_norm": 14.897379875183105, "t": 1793744247.7677822} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11519.653398516375, "train_tokens": 5733.0, "train_token_mean_nll": 2.009358695014194, "grad_norm": 13.417112350463867, "t": 1793744247.7685184} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11497.04370372706, "train_tokens": 5733.0, "train_token_mean_nll": 2.0054149143078774, "grad_norm": 12.869767189025879, "t": 1793744247.7692358} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 12500.446284382095, "train_tokens": 5733.0, "train_token_mean_nll": 2.1804371680415304, "grad_norm": 39.26414489746094, "t": 1793744247.770151} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11734.032602570223, "train_tokens": 5733.0, "train_token_mean_nll": 2.046752590715197, "grad_norm": 17.820634841918945, "t": 1793744247.770837} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11523.047269189292, "train_tokens": 5733.0, "train_token_mean_nll": 2.009950683619273, "grad_norm": 15.247292518615723, "t": 1793744247.799302} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14731.43053308451, "train_tokens": 6763.0, "train_token_mean_nll": 2.17823902603645, "grad_norm": 12.31108283996582, "t": 1793744254.6378837} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14714.454026367894, "train_tokens": 6763.0, "train_token_mean_nll": 2.1757288224704854, "grad_norm": 11.018026351928711, "t": 1793744254.6386623} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14684.640932470369, "train_tokens": 6763.0, "train_token_mean_nll": 2.171320557810198, "grad_norm": 10.476949691772461, "t": 1793744254.6393905} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 15989.25620612007, "train_tokens": 6763.0, "train_token_mean_nll": 2.364225374259954, "grad_norm": 29.52715301513672, "t": 1793744254.6771662} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 15044.641196756098, "train_tokens": 6763.0, "train_token_mean_nll": 2.2245514116155696, "grad_norm": 15.388391494750977, "t": 1793744254.677935} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 14714.235704770323, "train_tokens": 6763.0, "train_token_mean_nll": 2.1756965407023987, "grad_norm": 12.565555572509766, "t": 1793744254.6795015} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10469.240131273104, "train_tokens": 5394.0, "train_token_mean_nll": 1.9409047332727296, "grad_norm": 18.20193862915039, "t": 1793744261.0811691} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10424.344711149486, "train_tokens": 5394.0, "train_token_mean_nll": 1.932581518566831, "grad_norm": 16.634563446044922, "t": 1793744262.3175745} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10417.558921398766, "train_tokens": 5394.0, "train_token_mean_nll": 1.931323493029063, "grad_norm": 15.379270553588867, "t": 1793744262.3193283} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 11428.784492383676, "train_tokens": 5394.0, "train_token_mean_nll": 2.1187957902083197, "grad_norm": 38.028358459472656, "t": 1793744262.320102} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10672.541817268842, "train_tokens": 5394.0, "train_token_mean_nll": 1.978595071796226, "grad_norm": 20.33094596862793, "t": 1793744262.331974} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10443.051577135539, "train_tokens": 5394.0, "train_token_mean_nll": 1.9360496064396624, "grad_norm": 18.67282485961914, "t": 1793744262.3348777} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8547.556337532606, "train_tokens": 4573.0, "train_token_mean_nll": 1.8691354335299815, "grad_norm": 17.605714797973633, "t": 1793744268.9468179} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8526.195497147786, "train_tokens": 4573.0, "train_token_mean_nll": 1.8644643553789166, "grad_norm": 15.736421585083008, "t": 1793744268.9475536} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8523.647163958154, "train_tokens": 4573.0, "train_token_mean_nll": 1.8639070990505475, "grad_norm": 15.194826126098633, "t": 1793744268.9482672} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 9560.544739268073, "train_tokens": 4573.0, "train_token_mean_nll": 2.090650500605308, "grad_norm": 54.28580093383789, "t": 1793744268.9489934} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8710.244386031503, "train_tokens": 4573.0, "train_token_mean_nll": 1.9047112149642473, "grad_norm": 20.201091766357422, "t": 1793744268.9497225} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8527.551675879953, "train_tokens": 4573.0, "train_token_mean_nll": 1.8647609175333377, "grad_norm": 17.85403060913086, "t": 1793744268.950439} {"stage": "train_done", "seconds": 749.6906819343567, "steps": 40, "arms": 6, "t": 1793744268.950469} {"stage": "eval", "arm": "sel_adamw_lr5e-05_s0", "split": "val", "step": 40, "nll_sum": 195317.96888038135, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.0706255712024144, "example_mean": 1.9349980029887375, "per_example": [[157.64626324461005, 104], [783.210276849044, 423], [280.5853212586444, 219], [1393.6089729132655, 467], [62.03043776879895, 53], [284.9742087270133, 151], [4.707577953597138, 20], [28.577956232088127, 27], [33.121636592842606, 32], [476.5852413153061, 247], [331.5628684955518, 223], [687.4043117537294, 280], [1003.7000013229408, 365], [74.57982590037864, 54], [397.86797729134014, 159], [377.8247375349529, 265], [672.8833360271165, 330], [223.21255727348034, 110], [302.85597844524455, 120], [88.26678084368541, 114], [214.88786879553663, 132], [80.33972388786697, 67], [104.5574291828575, 57], [134.59140760554874, 100], [568.5828491419379, 345], [2.2083957120439663, 14], [1265.3110650489107, 788], [1157.785829499222, 469], [240.12680477361573, 65], [265.54739451288333, 158], [832.8853416344646, 356], [66.30366422846055, 26], [329.8140918258796, 109], [225.4517071080445, 105], [266.2770679292298, 233], [182.9759532995231, 69], [133.20714111007692, 61], [105.88757440102654, 86], [275.6464879220639, 105], [222.67071280935306, 88], [1496.5263004344088, 519], [494.32038184619887, 157], [68.25028084082533, 78], [158.32644694507326, 102], [424.09194989515163, 209], [1161.1135109305087, 484], [236.2874358704321, 233], [191.2201277941349, 118], [92.96366190636377, 91], [30.890408400345677, 34], [330.6993819351992, 177], [67.36415356861107, 39], [67.5301027314622, 50], [104.55150260617302, 84], [183.4759897378317, 152], [288.62871051694674, 115], [463.80531736391094, 302], [398.48517932964023, 242], [584.8027388404589, 268], [55.491338598930724, 19], [299.1026344038746, 131], [533.7066831136726, 248], [260.870418422538, 261], [615.2784659226581, 328], [99.79147824443135, 56], [273.78020489160554, 104], [71.6869552553162, 62], [379.69291295425865, 179], [1546.6369798617961, 389], [97.18210283616281, 132], [90.25092547412169, 24], [255.24386980551344, 122], [66.31790409957466, 39], [81.65559509743252, 59], [3.6709936542320065, 18], [223.37671367498479, 124], [442.83000716100287, 269], [144.62435509030183, 69], [23.057572643709136, 23], [419.7580618788634, 202], [663.2009890673216, 255], [134.90478670697485, 52], [235.5937639575459, 138], [165.49767052800598, 99], [1.0996033960291243, 19], [740.4236297924144, 313], [558.1938396834466, 270], [60.06714174035005, 34], [606.943841880864, 256], [98.8789156703715, 64], [54.089651284615684, 28], [294.4942968237483, 135], [479.0282573767181, 217], [178.44991280553222, 73], [179.89426237269072, 62], [269.29869480816797, 520], [542.3871108776075, 193], [400.9664378881007, 110], [1003.9225609155728, 319], [31.6671355555045, 56], [355.68040794603803, 276], [221.28586127550807, 121], [157.70931293892863, 71], [139.5719166072381, 81], [76.42840258843717, 38], [203.38436485392594, 100], [199.8165509880855, 97], [107.52655167834746, 69], [962.2544015913663, 328], [52.09722159376088, 44], [342.5581929359605, 128], [99.93134990776184, 66], [804.4070477614587, 306], [133.46218497702284, 78], [614.5425345946715, 242], [447.77006024480215, 201], [74.95949586234383, 52], [54.49616790951768, 40], [800.3903707413847, 246], [271.6062594438986, 125], [8.572352159048023, 89], [936.3138628307352, 446], [131.74887798523469, 106], [450.0515283730456, 200], [557.007809288576, 266], [574.9723694579989, 288], [158.97769250049168, 106], [238.18440407837625, 86], [666.6371152626234, 341], [618.2850744304251, 258], [75.3702676234534, 52], [848.5982773228461, 448], [368.5904903038172, 168], [21.794192480360834, 47], [33.78782056779164, 43], [1233.0989813354827, 476], [97.19411956917793, 104], [149.98334199782403, 106], [218.90678923550752, 137], [1052.6352954958566, 491], [15.00369594264157, 20], [114.84630367607588, 66], [84.83985772448432, 54], [159.14461135151214, 92], [86.46519513394742, 42], [745.5343542380142, 425], [714.2699693277391, 231], [117.50588962842176, 96], [998.3309523448843, 417], [225.96015387008083, 96], [1405.822387721004, 582], [292.5446754067307, 146], [96.25669074198049, 98], [1465.1974454708397, 485], [78.0591434983653, 45], [599.5603953700847, 190], [46.349047710151346, 116], [4.107176158743641, 6], [161.14644400546422, 166], [337.3036920563318, 141], [431.8843482120228, 171], [989.4608740778567, 491], [10.310748690400942, 29], [139.8838070387028, 40], [708.1808233646952, 308], [279.9789496388621, 90], [215.73182209207152, 93], [200.16346393895583, 124], [177.4133663056782, 106], [349.96047229735086, 330], [42.56910493400619, 43], [230.00342527182238, 200], [103.36971188128518, 69], [276.11529407940293, 477], [59.95616240140657, 42], [308.70080939893523, 80], [206.97888737341782, 148], [558.5789476192804, 327], [517.781445351342, 231], [1506.7800444693748, 422], [6.48949454373178, 10], [319.1528797486244, 299], [488.8989507127844, 215], [250.75984388199004, 130], [64.48179666467695, 128], [335.2005406351236, 222], [269.7181514534632, 374], [1126.925879475064, 489], [154.6271418932174, 88], [237.34301084030085, 85], [1017.476241468119, 422], [85.0734725276443, 51], [317.68222328425236, 253], [758.7671935019862, 368], [325.99963549132553, 245], [205.06974740688338, 130], [189.55984229239402, 77], [1018.0212895259101, 408], [664.1556615274967, 268], [823.912794928241, 258], [476.9678359745667, 212], [230.0328918498417, 103], [115.89812875722941, 92], [144.77158536825846, 94], [161.7409812486003, 86], [150.1379246859142, 66], [320.68926006447964, 135], [249.71797627209708, 156], [474.3366325791285, 150], [128.30498115070304, 85], [471.1282573171484, 210], [99.0125487944315, 59], [592.8193551750082, 208], [821.8304852610454, 375], [21.651054181553263, 17], [1094.9107570192573, 457], [199.92573662485665, 88], [765.9571552691341, 319], [74.86719309241744, 27], [21.82326039572945, 39], [138.10969976977685, 73], [11.07142533764636, 36], [203.5357727126393, 119], [116.6586699497202, 68], [609.9308150235247, 321], [82.27647100517606, 71], [464.6112779878731, 192], [1268.4934476157432, 498], [84.22201453849948, 75], [655.6448306271368, 266], [426.2074184319463, 168], [84.03939267448732, 59], [41.432613500110165, 25], [576.8701255796332, 205], [1416.1560577303026, 478], [704.9054895773884, 377], [415.91273076274956, 181], [181.1856225003794, 47], [384.2629507634774, 195], [90.97538783753407, 54], [225.47287236296415, 120], [113.15269121404435, 169], [150.09890462240037, 495], [809.2442218093856, 361], [87.62020796698016, 41], [1239.8902397080801, 465], [80.96313924139395, 50], [105.19948384371492, 65], [215.12353933883742, 110], [50.169716648440954, 62], [668.244944985403, 306], [56.32122600944149, 44], [172.39091105577972, 52], [447.66329922950536, 194], [405.53334756765526, 197], [300.1855314268287, 105], [302.5506241559451, 148], [1163.1856377080876, 418], [335.08817482584254, 203], [913.1438789258536, 388], [402.2283242884878, 220], [11.21771556148451, 25], [63.38294742476137, 22], [836.120673061035, 645], [928.1005670725572, 375], [142.88267256066274, 76], [512.9096785734582, 198], [214.72796893724808, 221], [636.5497890063707, 272], [1638.4438875798514, 488], [10.902637478593533, 7], [7.175458116176742, 15], [162.94971096047084, 64], [424.4045596164522, 348], [605.4509452399216, 182], [178.64256154076566, 79], [82.1775474558309, 91], [1120.5601855216973, 479], [209.36570942973776, 96], [328.3245336863183, 140], [183.2234320149728, 65], [1133.440138763748, 504], [43.12245451255512, 50], [1058.8075045149162, 464], [103.51213854736216, 33], [305.22553748093014, 128], [242.36991739963923, 111], [93.3180852946989, 159], [250.90398453152739, 123], [39.30706677946, 40], [950.6002146516112, 470], [253.13340778296697, 143], [438.1171242707587, 120], [123.75558552059942, 93], [965.048862102667, 372], [316.89222538886315, 155], [69.29423399043935, 66], [545.8652798716867, 282], [41.25062897006319, 24], [23.01300228357286, 34], [123.6555793177904, 103], [92.02065794111695, 35], [667.9634874250623, 271], [52.27746889408172, 15], [927.8971118156226, 365], [761.6942103525216, 355], [159.34745831042528, 53], [143.54497280090436, 70], [2392.8325171712368, 1200], [509.2593249911515, 274], [593.8173824192199, 187], [306.93083000320075, 169], [707.8241979630038, 459], [278.44577833660696, 158], [495.2095749426353, 156], [213.72665950832152, 102], [107.91788104302395, 56], [999.1398813390006, 464], [672.2204175601073, 275], [550.6579894006172, 146], [276.32871827109557, 154], [157.9154491787558, 108], [913.4702425399519, 356], [1090.3335435257031, 423], [100.37812048239721, 80], [423.7803134802318, 342], [345.213875247784, 178], [1453.5384944445977, 697], [348.5235743005687, 136], [1068.0992774222977, 462], [89.10537536361153, 46], [271.11042334252124, 151], [8.482071155951417, 27], [223.79263176851964, 85], [156.1121364424198, 91], [1195.1947753396234, 441], [142.63064729309122, 135], [1204.5407476690016, 457], [218.8097618804968, 94], [100.12779357361251, 62], [475.3492257545731, 195], [236.87527988716465, 108], [23.537366847039266, 46], [340.99038789261976, 127], [1032.6949279352411, 412], [52.91600349413784, 38], [259.66670579022684, 192], [127.11208753946994, 89], [263.7099171728187, 119], [262.7758513150575, 138], [587.3344398948066, 248], [513.5542975020799, 247], [161.48869961802757, 172], [327.08541565949736, 187], [517.3371154798078, 222], [227.74929147836428, 119], [504.5134841369436, 222], [849.6953960714109, 388], [1338.0434112826915, 483], [662.1171426055735, 227], [156.14845772455737, 75], [190.8470392315494, 119], [298.06531495290074, 187], [819.4222977567115, 293], [643.0290801598558, 287], [1083.4439200743327, 593], [300.23303474515524, 107], [124.14709522631529, 56], [241.28359610368307, 97], [250.78238119471644, 124], [122.2842551673308, 101], [280.41532554957666, 91], [424.66539297600684, 155], [987.1248623471183, 388], [209.33420787195791, 78], [655.103664262133, 274], [1442.9414011936897, 508], [793.7831554691147, 303], [828.0250317329192, 543], [4.732156996663434, 18], [323.7955909535667, 172], [422.2947329164763, 189], [314.91722939644205, 168], [238.77264539584212, 154], [370.60635985703993, 182], [440.17842183342145, 205], [36.29975717103116, 18], [259.09091153930785, 204], [77.68430093652933, 57], [1117.985172629269, 467], [272.52820990961663, 123], [793.592659171336, 308], [246.2125112453059, 426], [1199.8889790104058, 496], [177.02543369642808, 60], [629.4454958075657, 204], [671.8736078980364, 298], [124.49053864332336, 181], [956.5090428850599, 300], [381.81769158945826, 127], [77.88214606776182, 31], [356.62262021128845, 132], [746.5334814969829, 325], [794.8291108279118, 418], [645.2524260112332, 270], [67.43200573490321, 54], [126.51008963353524, 64], [312.44832850418607, 140], [251.91709648969845, 105], [177.31081870979324, 112], [50.72224083398942, 32], [78.6990074460773, 78], [722.4521113865922, 324], [31.639139750292088, 22], [140.9707856937457, 64], [763.7074960071332, 354], [704.3283957525964, 284], [820.9210999723582, 381], [82.69573866068458, 59], [78.91262427673792, 57], [419.5298727044719, 172], [76.00209948815609, 63], [9.061887900672446, 47], [95.07786125159691, 47], [13.89528615856159, 47], [334.4320241949299, 117], [391.34852637701715, 159], [306.06130168688196, 142], [192.07094782165768, 160], [191.4178734434263, 123], [720.0937352576366, 318], [585.3115427093071, 312], [572.0622837722294, 240], [559.3306109069381, 235], [18.223921389709744, 69], [1003.3353473755124, 446], [317.0980944664989, 163], [812.0268204911115, 494], [553.3934482412733, 236], [26.523914185329545, 31], [671.5503777485528, 345], [714.8668145343945, 326], [9.898516311914136, 15], [152.23971757620893, 74], [262.4926897902915, 131], [309.26101602711424, 160], [511.8884585538726, 285], [81.86583679339674, 57], [307.8728600005561, 158], [126.30540783909237, 70], [71.25468413524504, 74], [180.38665947632398, 88], [500.4503488917908, 198], [488.90452776269376, 238], [406.06881479548247, 194], [117.90839855767058, 74], [2.6917737151397887, 10], [117.95316098874264, 68], [291.8693416558817, 96], [912.5370712916028, 399], [497.75075875512994, 236], [387.4081739191897, 147], [403.5648567694261, 174], [8.964161425956263, 40], [740.4987415507721, 351], [791.8894143950347, 356], [268.8399353660352, 107], [893.3791809627619, 449], [438.2903757150707, 176], [1442.624761912697, 650], [90.11231747199054, 56], [138.9664769736487, 84], [343.78413683801045, 141], [20.776472224741156, 21], [463.0973486168181, 1062], [1074.8323143447487, 405], [718.5079352345201, 279], [119.52946500046892, 75], [60.81083071586181, 31], [1145.8591577997722, 453], [136.82697597047627, 108], [634.9719661810923, 426], [195.86967347910286, 132], [297.8015903718624, 149], [74.4633125996661, 43], [291.25959062320544, 147], [894.4452648903098, 383], [242.07804190577554, 123], [767.8372344695672, 310], [360.2712471499399, 169], [289.70856076195196, 151], [49.386145337583, 44], [176.34736354542838, 66], [444.80842231521456, 157], [5.870457821867603, 28], [106.25292804866149, 64], [835.4811194513022, 471], [80.41954223787798, 60], [320.82204196765815, 292], [118.4207390088468, 71]], "final_state": "tinker://f23fad8a5cc3c0a7883ead5d7fb0188c/weights/select-sel_adamw_lr5e-05_s0-final", "t": 1793744290.8162816} {"stage": "eval", "arm": "sel_adamw_lr0.0001_s0", "split": "val", "step": 40, "nll_sum": 194894.05999439553, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.0661315833516616, "example_mean": 1.9274823314266618, "per_example": [[156.9554263815569, 104], [782.1033998410308, 423], [281.1972048885741, 219], [1391.0198650746065, 467], [62.2584929815107, 53], [285.2481172720245, 151], [4.266170250766663, 20], [27.938407055422203, 27], [32.371548911098046, 32], [473.22707156736885, 247], [330.5628148534556, 223], [683.6947460037675, 280], [1002.6531028414281, 365], [74.670601876197, 54], [399.51674722165967, 159], [372.1625519580866, 265], [669.604122721938, 330], [221.62253435978937, 110], [298.3619242178605, 120], [87.87866107866876, 114], [211.75715577476421, 132], [80.1587914830236, 67], [106.53268984427064, 57], [134.55285008695864, 100], [565.762888081607, 345], [2.431466590990567, 14], [1263.8164204645864, 788], [1158.7945343007027, 469], [238.77856034133856, 65], [263.6406111056058, 158], [831.835677957019, 356], [66.50572170591295, 26], [328.207334385113, 109], [224.55420145326093, 105], [263.10192952133957, 233], [180.5222052234726, 69], [133.29484862039317, 61], [103.55758624138457, 86], [273.88898563196335, 105], [221.32445163342322, 88], [1495.6592838465103, 519], [492.8523396589162, 157], [66.60530628952074, 78], [156.2159316379707, 102], [425.75998953886574, 209], [1159.9308327121516, 484], [239.0693505532936, 233], [193.14609408353635, 118], [92.44995333414406, 91], [30.213927532369325, 34], [328.413097285179, 177], [67.08778979404224, 39], [66.83866586097372, 50], [105.23744534901721, 84], [182.02437253323478, 152], [284.9801904740873, 115], [463.53188676156367, 302], [398.5985513335754, 242], [583.9986854931178, 268], [53.15989226990155, 19], [297.09469617780223, 131], [532.987068680527, 248], [262.9715081355373, 261], [615.3473665503325, 328], [98.7672309351683, 56], [272.7753198464188, 104], [71.78949314306283, 62], [378.1456404558387, 179], [1543.3615184569558, 389], [94.63073010359176, 132], [90.18420806276617, 24], [256.4988877029897, 122], [65.02580986675548, 39], [82.00903341720937, 59], [3.6921535889332517, 18], [222.43721607561702, 124], [437.7898408108764, 269], [146.3723880706625, 69], [23.601851115443424, 23], [418.514816632406, 202], [661.413418809808, 255], [132.97529930941255, 52], [233.39053517542743, 138], [165.0864341242036, 99], [1.046363388235136, 19], [733.6732039973062, 313], [561.2077440570483, 270], [59.82878792139945, 34], [605.9811999716391, 256], [97.01701422733095, 64], [54.51139602676767, 28], [294.08713805292007, 135], [477.4896217541145, 217], [176.04356165819786, 73], [175.12725021274582, 62], [267.9526792861027, 520], [540.3624289894308, 193], [397.4850382095369, 110], [1001.2481821026252, 319], [31.884043511424807, 56], [355.10213215173917, 276], [221.69592067154917, 121], [158.21602210334754, 71], [138.80265625682864, 81], [76.20970588295654, 38], [204.86139904150286, 100], [199.27047507275302, 97], [108.57373226609207, 69], [962.5443243698146, 328], [49.05750529943316, 44], [343.4170689293801, 128], [98.30740856246837, 66], [802.3496908663326, 306], [134.5372158277737, 78], [616.4664338143466, 242], [449.9330890594571, 201], [74.55489996939468, 52], [54.341267908227564, 40], [798.1879329811477, 246], [269.87216553507665, 125], [7.485375341580607, 89], [937.1905000348941, 446], [131.314408092402, 106], [447.99803569283404, 200], [555.7136560658253, 266], [572.5202135675933, 288], [157.19117441565868, 106], [238.85026542410878, 86], [658.6262366586288, 341], [613.1334461074578, 258], [74.83682468206507, 52], [843.6823743970217, 448], [369.00243009397764, 168], [21.53910981171157, 47], [33.30497808037944, 43], [1233.3198480745987, 476], [98.39088707026895, 104], [148.76941137241374, 106], [216.22107735815098, 137], [1054.0578405678962, 491], [13.416283575340458, 20], [114.58066791797091, 66], [85.22865231834226, 54], [159.63017556352315, 92], [86.80083951075358, 42], [742.9460672282545, 425], [710.6443751247061, 231], [114.93342001619692, 96], [1000.7391385147739, 417], [224.71655731886767, 96], [1399.8595559029618, 582], [292.37162347001504, 146], [94.78690994121553, 98], [1467.7939531273125, 485], [78.57863660438306, 45], [599.3692190526451, 190], [45.47505892798651, 116], [1.8065383429811845, 6], [162.12416407999228, 166], [337.9550368163591, 141], [429.4909149137509, 171], [984.59858051746, 491], [9.753851627397808, 29], [137.8894227851972, 40], [707.0579308736756, 308], [276.47622091977064, 90], [211.94598669654533, 93], [201.3108082695594, 124], [176.28462025400768, 106], [346.6601039607408, 330], [42.82044361306441, 43], [228.82549128623805, 200], [102.0086884421944, 69], [278.6341274338147, 477], [60.32892608301876, 42], [303.5877556937576, 80], [207.61659650692582, 148], [561.9731127330297, 327], [515.8113548566048, 231], [1504.4925025609991, 422], [5.358534691490149, 10], [320.51771075382794, 299], [487.0223165343382, 215], [248.68556216848685, 130], [63.50495500589841, 128], [336.70355043551433, 222], [269.7677986119696, 374], [1127.6683012820345, 489], [155.59038392938135, 88], [234.2479777376302, 85], [1013.4798373314682, 422], [85.10972149860231, 51], [318.1685678942242, 253], [759.2937709173439, 368], [324.8953841356645, 245], [201.93655925109022, 130], [189.21682999704672, 77], [1017.7052866808658, 408], [661.3357741539617, 268], [823.5200094889999, 258], [475.96710050906313, 212], [227.41594626786514, 103], [111.52604554531715, 92], [141.37749832041072, 94], [160.6253983244519, 86], [148.6056042266199, 66], [320.50140654402867, 135], [248.75070355902562, 156], [475.0322007822042, 150], [129.4166035491362, 85], [470.63955037498727, 210], [98.0631126581784, 59], [588.635748074495, 208], [818.7480922491488, 375], [21.180821092182896, 17], [1090.8536833051548, 457], [195.549909160487, 88], [760.976903817077, 319], [74.10106617422389, 27], [22.89589552813868, 39], [136.43680088923293, 73], [11.19408634851834, 36], [204.70838316509344, 119], [118.35989556771301, 68], [605.8003490843835, 321], [88.2493680289972, 71], [461.27497568338504, 192], [1269.0935232320307, 498], [84.51809637446604, 75], [653.683668693683, 266], [424.98965550955927, 168], [83.54610086344735, 59], [41.764643129663, 25], [578.595215475505, 205], [1414.004303456436, 478], [705.6873618026218, 377], [417.79448401334184, 181], [180.48118420116543, 47], [383.26110064237764, 195], [90.58588843763914, 54], [225.20148744900962, 120], [111.86216301969, 169], [144.96275634898302, 495], [809.0291491857661, 361], [87.15151338616033, 41], [1238.3802368338713, 465], [80.53618208833086, 50], [104.51978518262183, 65], [211.74085905328275, 110], [49.26119485249001, 62], [666.7587833126972, 306], [56.40004141002328, 44], [173.4922606597528, 52], [444.4854862347115, 194], [402.7097567880878, 197], [298.6876315817776, 105], [298.8797643349649, 148], [1161.5201327625832, 418], [331.7335782794148, 203], [912.4874725550029, 388], [402.9985888996341, 220], [10.24613936861806, 25], [63.500132162749196, 22], [831.5552291048743, 645], [925.2739521230535, 375], [140.05526559944997, 76], [510.0392375076958, 198], [213.1636296779552, 221], [637.2573316653775, 272], [1632.1001368024868, 488], [10.727664789282016, 7], [6.827442744180189, 15], [162.21247497956165, 64], [418.5907794671839, 348], [607.3058720421022, 182], [177.55741850393315, 79], [83.2941063843027, 91], [1122.231867614409, 479], [207.9899699746411, 96], [329.5898752216697, 140], [183.02563790425165, 65], [1129.3771839815558, 504], [43.27032415878534, 50], [1057.6379428994067, 464], [102.56535556118843, 33], [305.20944255937957, 128], [240.9652268571033, 111], [93.74282857703474, 159], [249.0893667459327, 123], [39.3568593291202, 40], [949.1645936521118, 470], [250.39738175765342, 143], [435.02306348475327, 120], [120.65964972145525, 93], [965.3237256955023, 372], [317.55765318224167, 155], [70.09057715381635, 66], [544.2740166421299, 282], [40.38608428229804, 24], [23.64639008762424, 34], [123.30365579483623, 103], [95.48917087590917, 35], [663.7698323980517, 271], [51.901402615917505, 15], [928.2336094934791, 365], [762.46120132024, 355], [159.1288601126612, 53], [142.60918675144035, 70], [2388.0888766848557, 1200], [510.27373400871625, 274], [592.7888152618709, 187], [304.3691059885914, 169], [707.1818537244321, 459], [280.6115368143212, 158], [490.75725112340933, 156], [213.75818143090078, 102], [109.25289694484854, 56], [994.6536325417555, 464], [668.5676216418115, 275], [549.3112736246721, 146], [276.70960435311076, 154], [157.26158650118577, 108], [914.4312722355671, 356], [1086.1279285222022, 423], [100.49555556914129, 80], [420.2609222244099, 342], [341.99113371113526, 178], [1451.7770547972204, 697], [349.1472660877216, 136], [1067.1314755534713, 462], [87.06546885147509, 46], [269.97055683291364, 151], [7.976504569809094, 27], [224.2604916587576, 85], [157.52805539864084, 91], [1192.7118442378844, 441], [136.67758657077127, 135], [1200.778669400299, 457], [217.86159636535422, 94], [100.57142250401466, 62], [477.81765454311085, 195], [236.84021268944684, 108], [24.023909906822155, 46], [340.5953591463881, 127], [1028.7163713417622, 412], [53.70105387683725, 38], [259.66982230884605, 192], [125.79338298302741, 89], [262.57439779405195, 119], [262.79682399243006, 138], [589.6919549587419, 248], [513.8819879535422, 247], [164.62999209963027, 172], [327.4769947554446, 187], [517.5576203292412, 222], [229.14290798855905, 119], [504.90846154455676, 222], [846.6785513123345, 388], [1332.5972599784018, 483], [662.8064482943646, 227], [155.07803002920673, 75], [190.29241521737913, 119], [294.3524654500857, 187], [819.2921471652485, 293], [635.5149497933364, 287], [1084.5862698710957, 593], [297.89776110502726, 107], [124.50556415902042, 56], [240.8008364315881, 97], [249.29373891826208, 124], [121.3663254717465, 101], [280.68209156634475, 91], [424.60904684528805, 155], [988.307035106051, 388], [207.9582451959318, 78], [657.1478534595194, 274], [1441.238776565439, 508], [791.8910439333174, 303], [828.0506454977617, 543], [4.7114182967739, 18], [322.71947299747535, 172], [421.6738269532202, 189], [313.85706040178775, 168], [236.20194351524538, 154], [367.73649849135586, 182], [442.2994099417531, 205], [34.318633734749255, 18], [257.32308502442356, 204], [79.65530764525079, 57], [1115.4380185051568, 467], [271.414028149562, 123], [791.5869639877483, 308], [244.37404866534962, 426], [1201.0205184035126, 496], [175.08450220322356, 60], [623.1006200619788, 204], [673.2157255926058, 298], [125.74792943039779, 181], [955.7146862851746, 300], [383.3194681556033, 127], [80.00022314368493, 31], [354.79267007510816, 132], [744.3125941370563, 325], [793.2073910703907, 418], [643.4520170481263, 270], [66.90554556347911, 54], [125.5419069778909, 64], [314.25252800066573, 140], [250.74247341439195, 105], [174.80649629596064, 112], [50.291523724261424, 32], [78.02839725176909, 78], [724.7713364246247, 324], [31.812840238056197, 22], [139.3488913694955, 64], [765.0967499504181, 354], [702.4579218884898, 284], [815.5784683874351, 381], [81.49809256867957, 59], [77.57274509726358, 57], [418.70260568901267, 172], [75.440408882665, 63], [9.936157056945376, 47], [93.7620371690607, 47], [13.885800281239312, 47], [333.85929334218076, 117], [387.3506426583567, 159], [307.66488717634616, 142], [193.24452016303349, 160], [191.75554973116323, 123], [721.5058696273773, 318], [587.9693721166132, 312], [575.1383415120858, 240], [561.0157298268864, 235], [16.697896602270674, 69], [1001.1456926260358, 446], [317.64363034841335, 163], [810.9247748210844, 494], [553.1504699193565, 236], [27.990059054369794, 31], [672.2178692741209, 345], [709.0842080548528, 326], [7.923605179146989, 15], [152.60690096129747, 74], [262.42545764298893, 131], [305.12025179978536, 160], [511.7471827761815, 285], [79.06458031879538, 57], [307.14672293230933, 158], [125.04840370681814, 70], [70.73682557029679, 74], [178.57278114637393, 88], [514.9667844795981, 198], [486.64665450337475, 238], [407.087269954976, 194], [117.84246483023145, 74], [1.5321333482052069, 10], [118.74453835899408, 68], [291.90404901228067, 96], [911.8339503223777, 399], [497.13150118243834, 236], [386.6501466541649, 147], [404.1859285327623, 174], [9.350184511586576, 40], [740.0756727535542, 351], [792.6375272151072, 356], [269.7094558989752, 107], [892.3123684356999, 449], [435.58606039280403, 176], [1438.300415960468, 650], [88.81155737206223, 56], [139.6558490055644, 84], [344.6744973335144, 141], [20.05281658537831, 21], [465.24255722761785, 1062], [1079.1983322020747, 405], [716.7705561051688, 279], [118.65765060717604, 75], [61.43488619051186, 31], [1144.7415894725345, 453], [137.2527775561539, 108], [628.1970546245229, 426], [197.33471201862676, 132], [298.4617440906136, 149], [73.55590155143909, 43], [291.60730480163966, 147], [894.0730020401511, 383], [239.42831956751297, 123], [770.1868057573568, 310], [362.6126621356166, 169], [288.8628046830704, 151], [48.999302989197986, 44], [177.03067604697958, 66], [445.07950172586834, 157], [5.150335179167087, 28], [107.17648945617975, 64], [837.1690550496253, 471], [79.01593311018132, 60], [321.72309403295185, 292], [117.53906684653816, 71]], "final_state": "tinker://34671def1a8e798b05dd051092ac4307/weights/select-sel_adamw_lr0.0001_s0-final", "t": 1793744312.0866346} {"stage": "eval", "arm": "sel_adamw_lr0.0002_s0", "split": "val", "step": 40, "nll_sum": 194619.27323100422, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.063218484765968, "example_mean": 1.921903435317206, "per_example": [[156.4685007764656, 104], [783.1307346685207, 423], [281.4848097599397, 219], [1389.941557157164, 467], [62.27296646019386, 53], [289.9289478244873, 151], [4.324547018888552, 20], [27.589320276088074, 27], [32.24630213632372, 32], [470.51128868889646, 247], [330.34816084096326, 223], [684.8798080438319, 280], [1000.6746692639708, 365], [72.90420177720989, 54], [398.609100901323, 159], [373.22150492416995, 265], [667.9068171727599, 330], [221.59648852362807, 110], [300.5527853523363, 120], [87.79199456004972, 114], [210.3097162013346, 132], [80.39832941630686, 67], [106.54712893488613, 57], [134.96305289544398, 100], [565.0878352850325, 345], [2.4419656219615717, 14], [1260.2231417370458, 788], [1155.117655485491, 469], [236.96592861151566, 65], [264.5129153124508, 158], [837.1401059141185, 356], [65.66191914794581, 26], [328.9436705256676, 109], [225.7589704708571, 105], [264.304566553481, 233], [177.49021722306406, 69], [132.34639986159345, 61], [102.73905871862098, 86], [272.62369186323986, 105], [221.73359978767803, 88], [1497.6106474969588, 519], [493.5270336115391, 157], [64.73311164393726, 78], [157.08321789011552, 102], [426.667484339182, 209], [1156.4711445743842, 484], [236.9353483236555, 233], [194.40029447835877, 118], [91.1175445676771, 91], [29.951286332435302, 34], [324.917515835652, 177], [68.28551830633478, 39], [66.09442790654543, 50], [102.29881629844476, 84], [183.35096227197573, 152], [283.6482307932438, 115], [464.7680680840904, 302], [397.69099751470276, 242], [582.0970534486601, 268], [53.21660473137854, 19], [297.0723534671479, 131], [532.9478568967033, 248], [263.1394929646285, 261], [617.4895439886932, 328], [96.63798298919937, 56], [269.99031623888277, 104], [71.19010280896327, 62], [377.09184960847415, 179], [1543.5952072083091, 389], [93.69322719989032, 132], [89.8799305986031, 24], [255.7789941516453, 122], [65.77434250766328, 39], [82.42956606292319, 59], [3.7741621253017, 18], [221.32277665773654, 124], [435.4579930752243, 269], [144.9143050122766, 69], [24.049631902596957, 23], [418.641335216058, 202], [662.1964664414036, 255], [133.01848908133252, 52], [232.40609951791703, 138], [163.40493473539755, 99], [0.8779396827810615, 19], [733.2794278138699, 313], [564.2928221770744, 270], [60.633466540552035, 34], [606.8397350887976, 256], [97.43537121344525, 64], [55.74996296946847, 28], [295.353107542262, 135], [478.2612125118603, 217], [177.19753655158206, 73], [176.78567102712668, 62], [263.8148267914403, 520], [537.2960286506059, 193], [395.1307209218012, 110], [1004.3283497153952, 319], [28.96571453625961, 56], [351.63464808057324, 276], [221.2559739742578, 121], [158.3406365957535, 71], [139.09755948837847, 81], [76.95226060755795, 38], [205.84589094656644, 100], [199.68778378886418, 97], [108.43308686862565, 69], [967.1130202019267, 328], [46.96555164125357, 44], [345.07770898304807, 128], [99.38465633770613, 66], [802.4274180044204, 306], [135.16009483858397, 78], [616.2786028653959, 242], [449.7807008691875, 201], [73.89309444432365, 52], [54.028888601423205, 40], [800.0138194730312, 246], [271.93165878774016, 125], [7.537455439268797, 89], [939.2065532087681, 446], [129.7512502966265, 106], [446.05471719966954, 200], [552.9108306678193, 266], [571.8510093820096, 288], [157.19269978834382, 106], [239.00487954863456, 86], [657.8674689788986, 341], [607.5671020008986, 258], [74.07706581386356, 52], [840.9895252963652, 448], [373.4382672856427, 168], [21.291301302764623, 47], [32.71756384283981, 43], [1233.94847988135, 476], [99.53290664926317, 104], [146.60569231876616, 106], [214.97784281912436, 137], [1047.6324356843015, 491], [11.270078110519535, 20], [113.84655388248484, 66], [84.4373539572407, 54], [160.07040611240154, 92], [85.20157020233137, 42], [738.818449881263, 425], [710.1921752350027, 231], [114.673653177902, 96], [997.437219847986, 417], [224.4722412017345, 96], [1396.8325976839878, 582], [292.8102410711617, 146], [94.00873435545418, 98], [1470.3489035565362, 485], [77.33496854308123, 45], [600.4480322155905, 190], [42.84033432027434, 116], [0.5406180847671749, 6], [161.85329074733795, 166], [339.6860284081813, 141], [429.4622132134855, 171], [985.6825796972398, 491], [9.001048224105034, 29], [135.8189662244995, 40], [707.2276107484322, 308], [277.1306648866048, 90], [210.48977746641322, 93], [201.5079068092823, 124], [174.98704373488818, 106], [344.10602951309284, 330], [43.58988578902881, 43], [227.77119768934335, 200], [101.3978902817289, 69], [278.0451601079411, 477], [61.91181599695051, 42], [302.62939981455384, 80], [206.6498652834298, 148], [562.6044608352399, 327], [514.3564674562231, 231], [1503.3694539104672, 422], [3.941647032504079, 10], [314.4187688547245, 299], [488.9960668405247, 215], [246.5197201632236, 130], [64.68528613433227, 128], [337.79465451132273, 222], [268.6237444747626, 374], [1128.1602219118176, 489], [155.65097719970618, 88], [232.0030451728726, 85], [1012.9932826408185, 422], [85.3987106313482, 51], [319.2169240930398, 253], [756.36873288061, 368], [324.83155371246085, 245], [199.03894729583817, 130], [188.03692614908277, 77], [1016.7384943461584, 408], [662.0806065319184, 268], [823.5079922153363, 258], [474.4261296164814, 212], [229.69376064712287, 103], [107.10450854332322, 92], [137.98152875053074, 94], [159.0400966244315, 86], [147.47830499559916, 66], [322.2429010610913, 135], [248.4439587646175, 156], [474.69646146133255, 150], [128.02854641695376, 85], [469.6219940832798, 210], [96.98644716451236, 59], [590.9666612438104, 208], [813.5383136860742, 375], [21.940068491841885, 17], [1087.673518448315, 457], [193.3747602169492, 88], [758.9753040534674, 319], [70.72511150054015, 27], [20.22090555820978, 39], [134.43288198883693, 73], [8.856225830871608, 36], [204.90132735181624, 119], [111.26545256365534, 68], [605.2576699462406, 321], [88.7748630961778, 71], [460.4646535146512, 192], [1270.1078833632246, 498], [83.3666614063618, 75], [650.1806533561407, 266], [427.53717113959556, 168], [83.11089111988804, 59], [42.49672167259632, 25], [578.2836985519589, 205], [1411.0104457697144, 478], [704.0799095376385, 377], [418.80714686529427, 181], [182.2370063189328, 47], [384.6074499512961, 195], [89.16331999977092, 54], [227.75089641440354, 120], [112.26261620560274, 169], [141.8256208311368, 495], [804.083494905397, 361], [86.78687519622144, 41], [1239.487273095444, 465], [80.73389901324208, 50], [103.64214545444156, 65], [210.25256411891132, 110], [48.70886310097558, 62], [665.9641187920242, 306], [54.82224413367658, 44], [174.60133914783546, 52], [446.67431290002605, 194], [398.5359840261374, 197], [299.2649839519013, 105], [296.82203645164645, 148], [1157.5037904515502, 418], [329.73735100101976, 203], [913.4679721977823, 388], [405.07692428293285, 220], [9.792973537678336, 25], [63.56058106026194, 22], [831.8303534192478, 645], [923.4601939904678, 375], [139.42739016066434, 76], [510.1676332224415, 198], [213.83472027616426, 221], [633.9383415605826, 272], [1633.9965757058826, 488], [10.577550227377287, 7], [7.900853027582343, 15], [163.60493377988223, 64], [416.1539394869138, 348], [607.1859232188381, 182], [176.71600895110896, 79], [80.70266680619523, 91], [1124.0860807751378, 479], [207.18902605872245, 96], [329.5488975390763, 140], [181.49165095350213, 65], [1129.4586885871959, 504], [42.4356492036668, 50], [1055.5678295609268, 464], [101.9169526544074, 33], [302.21817700016527, 128], [241.5997298092193, 111], [93.72046328517263, 159], [246.9043701135488, 123], [39.08719734624901, 40], [950.187417417108, 470], [251.0829555182463, 143], [438.1459383267993, 120], [119.75098997399459, 93], [965.4962506812599, 372], [314.7038140268314, 155], [70.03944144661568, 66], [544.7352093501522, 282], [39.98700327766255, 24], [24.228588350357313, 34], [123.04716604006535, 103], [96.24393546433657, 35], [660.8755225994018, 271], [51.4182881785332, 15], [927.0668452519772, 365], [760.5242487143632, 355], [160.8327811547315, 53], [141.04545139017773, 70], [2399.33891572271, 1200], [507.1842800121394, 274], [591.1417312439844, 187], [302.396085571776, 169], [707.8819813245409, 459], [279.31297034759837, 158], [489.9506844346306, 156], [209.69374689921824, 102], [109.968827617834, 56], [995.2835258137366, 464], [669.5924216879921, 275], [546.5113952477786, 146], [275.4146206884798, 154], [155.7814854873759, 108], [917.0717066422749, 356], [1080.835791091622, 423], [99.6818597381498, 80], [419.82682083095517, 342], [338.8005139051238, 178], [1450.1179535289084, 697], [348.17772523609074, 136], [1072.177589814025, 462], [85.2550973491625, 46], [268.87759693717817, 151], [6.84475207693049, 27], [222.16281877155507, 85], [156.32567503354585, 91], [1190.462784974583, 441], [132.24141142454573, 135], [1198.1386286246343, 457], [215.90621948835724, 94], [99.72716407980352, 62], [476.6716516383158, 195], [235.7452702454966, 108], [24.02576857045733, 46], [339.88807492498745, 127], [1025.4400698214104, 412], [52.67749879270923, 38], [259.2037734807218, 192], [123.88148407324661, 89], [261.2180864976308, 119], [259.33914316717846, 138], [590.7076421668226, 248], [513.8049845046316, 247], [166.01124172053142, 172], [327.5806301343723, 187], [514.8582267136055, 222], [230.48626171678916, 119], [503.80040525169716, 222], [845.4467099765361, 388], [1336.4520469200843, 483], [662.0243884469483, 227], [154.0927583009543, 75], [186.4953218572782, 119], [291.8397368218193, 187], [815.2554986727218, 293], [632.0566686600773, 287], [1085.0922718635084, 593], [299.0420988795279, 107], [123.76174718646962, 56], [242.51810140039743, 97], [248.51902956764388, 124], [120.52058916686838, 101], [282.700089424583, 91], [426.07819232496695, 155], [987.4877498328333, 388], [207.28278869397673, 78], [654.7840366138807, 274], [1442.7088566422053, 508], [793.7108413574479, 303], [827.5743741376418, 543], [4.351129498769296, 18], [321.97575680604314, 172], [419.97645310444204, 189], [309.48475386313476, 168], [235.28986333707053, 154], [366.94309747126226, 182], [440.57663378892653, 205], [32.61555217542082, 18], [258.5273414912099, 204], [80.11436929264346, 57], [1115.0301989991494, 467], [274.0611695359312, 123], [786.8794280184356, 308], [242.55376652949417, 426], [1204.7580580418562, 496], [174.44303509031943, 60], [620.4574793063857, 204], [673.6838008344221, 298], [126.99772394767479, 181], [957.8244607729084, 300], [381.87002939096965, 127], [81.48682274300427, 31], [353.03697103637023, 132], [742.0571364770431, 325], [792.265764814113, 418], [640.5614851860369, 270], [65.85578019070908, 54], [125.26197078203768, 64], [314.4238946440255, 140], [248.89623549100725, 105], [176.20131765836413, 112], [49.748937986048986, 32], [76.8351568822145, 78], [724.4184155820294, 324], [31.795654279697374, 22], [139.16088153052442, 64], [767.0263400343974, 354], [700.6635596363712, 284], [815.3664929226052, 381], [82.61457056455902, 59], [76.63327232882511, 57], [422.78140563232137, 172], [74.89171500584598, 63], [9.544975034829804, 47], [93.61556350190403, 47], [14.88604372792679, 47], [329.8149569460438, 117], [385.50934175310215, 159], [309.4301204214098, 142], [193.7480267026076, 160], [191.91760352567144, 123], [718.3933579584591, 318], [583.9474591200442, 312], [574.7997940997639, 240], [559.49879080549, 235], [17.76480175405436, 69], [999.5466058081765, 446], [319.10085127674483, 163], [812.0529969306085, 494], [558.5945498151978, 236], [28.72451530239414, 31], [674.3747375136263, 345], [705.6451581114561, 326], [7.141306645766235, 15], [149.61021909053488, 74], [262.41378949157115, 131], [305.2673701335607, 160], [512.8522869877961, 285], [79.90758388491304, 57], [308.9462812026177, 158], [124.35958099190066, 70], [70.00103550386211, 74], [176.47044862144685, 88], [493.49542834296153, 198], [485.69219993299885, 238], [404.4874964172127, 194], [116.58072546743097, 74], [1.4229550241807374, 10], [118.66141666801741, 68], [293.1001445728789, 96], [912.5143165387276, 399], [492.98130256283366, 236], [385.0260966693304, 147], [407.2427418817333, 174], [9.241323222396204, 40], [736.8980658035371, 351], [793.5826164929649, 356], [268.53934953937414, 107], [893.8560865035561, 449], [437.16168684025433, 176], [1436.31927888875, 650], [86.68314738451636, 56], [139.178002388398, 84], [344.19313062165565, 141], [21.786969541268206, 21], [468.3130789841242, 1062], [1082.770625486476, 405], [717.0803044464501, 279], [117.22122709797031, 75], [61.358045831123036, 31], [1144.0122464083242, 453], [137.4585617133789, 108], [626.4354214232953, 426], [197.80587146798916, 132], [299.5949375816772, 149], [73.11691903074416, 43], [290.61567010797626, 147], [889.2922473257131, 383], [238.16799574895367, 123], [769.6072947589341, 310], [360.72299516933253, 169], [287.69756437266915, 151], [49.3415513982618, 44], [176.06100895068175, 66], [444.86392191786035, 157], [5.212694116886269, 28], [106.5885526879847, 64], [839.9152608423265, 471], [78.72426112808171, 60], [321.57499980323337, 292], [118.30891367821914, 71]], "final_state": "tinker://99ddc7356a2150f7dbafc5262693978b/weights/select-sel_adamw_lr0.0002_s0-final", "t": 1793744333.0424273} {"stage": "eval", "arm": "sel_dimuon_lr0.0003_s0", "split": "val", "step": 40, "nll_sum": 212278.3997532398, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.250428290149688, "example_mean": 2.2014211871263685, "per_example": [[169.36369168124133, 104], [835.5390345780006, 423], [316.0188910990646, 219], [1445.202430409373, 467], [80.3249541955231, 53], [295.5439077044048, 151], [19.265792266348853, 20], [38.92245898892361, 27], [49.93981486211396, 32], [515.4506011302092, 247], [358.29420807159113, 223], [735.043877482811, 280], [1073.5402288120113, 365], [86.77809404555, 54], [409.0178514975769, 159], [430.3037012981729, 265], [760.9775594560235, 330], [239.7532686366626, 110], [326.68775293001073, 120], [109.45524566330596, 114], [243.0847924823347, 132], [101.83643166452293, 67], [130.5312516774785, 57], [178.37796771189528, 100], [599.2650071566231, 345], [1.7154836943154805, 14], [1335.037524674422, 788], [1197.6479302955713, 469], [271.492271883933, 65], [307.3725504328454, 158], [885.9409072956842, 356], [74.56909988123482, 26], [350.99956502169516, 109], [250.27354977600112, 105], [300.9979354033085, 233], [227.82248375604036, 69], [163.67692026655732, 61], [127.17706826514063, 86], [293.56724990697694, 105], [237.72783537947316, 88], [1527.1112084109561, 519], [543.766591157048, 157], [90.90083428338585, 78], [194.246283092255, 102], [466.87807312245013, 209], [1242.619787261267, 484], [237.49792672102308, 233], [188.66768459492414, 118], [156.0507906257953, 91], [46.21927000117182, 34], [355.686514222783, 177], [85.51566223020131, 39], [83.06030407370764, 50], [122.88525922475492, 84], [228.480915162163, 152], [337.7645380278773, 115], [516.3170400727645, 302], [449.7455042002699, 242], [634.9617628866815, 268], [61.20214063674871, 19], [328.37799290338853, 131], [575.074561011777, 248], [279.57431431213377, 261], [670.5845131498195, 328], [103.95851272154505, 56], [308.1212298634323, 104], [87.27014580430478, 62], [406.87928096906285, 179], [1602.6174796586638, 389], [124.57829446573373, 132], [101.07472669983292, 24], [274.84092328892496, 122], [90.0066355483649, 39], [126.61806615436399, 59], [8.95818439303389, 18], [247.24063327976455, 124], [490.36805170557045, 269], [163.95460622581686, 69], [52.63113045368004, 23], [472.8877006491814, 202], [686.7459117130525, 255], [152.8149594331312, 52], [267.7279834558435, 138], [181.05494488945192, 99], [3.6588301331394177, 19], [781.0245967100614, 313], [608.1871406782943, 270], [74.01039154725459, 34], [639.6457296692543, 256], [122.60696595440277, 64], [55.57758847459934, 28], [334.4191933820109, 135], [505.2909070408573, 217], [209.58815709904593, 73], [201.85339650569495, 62], [328.59692859580434, 520], [560.0969425841624, 193], [428.7548238028901, 110], [1070.904640143178, 319], [39.976223650719476, 56], [403.77705804189213, 276], [263.66954865486514, 121], [167.66171215297055, 71], [157.7355019839788, 81], [93.2528670132142, 38], [220.07777606189165, 100], [228.70783532252608, 97], [121.91869075860996, 69], [1005.5794207043641, 328], [79.73447743571114, 44], [366.4302542315353, 128], [119.02522776064131, 66], [846.2933947010179, 306], [168.33683695072972, 78], [667.1848793320801, 242], [485.6305487625925, 201], [114.17416345083984, 52], [78.9634235354248, 40], [835.3015761083624, 246], [292.8247373235579, 125], [29.53951491022906, 89], [1003.9754865640466, 446], [161.19070766824962, 106], [486.1637803960962, 200], [616.5702665249363, 266], [623.9462912379983, 288], [168.26097242439937, 106], [269.2852182925635, 86], [698.7025006938752, 341], [638.3192468097129, 258], [92.92690179662668, 52], [884.4045359888737, 448], [404.15621084363033, 168], [47.988290009689536, 47], [53.5508366039644, 43], [1283.852990715532, 476], [150.7118140052105, 104], [185.61196564134752, 106], [238.39825267518984, 137], [1092.8323009581436, 491], [24.657973153472994, 20], [137.98291167823209, 66], [140.68903615918862, 54], [174.0922234429072, 92], [115.49140395648828, 42], [806.3280809698645, 425], [762.6546320032121, 231], [140.08200743723455, 96], [1051.036399028816, 417], [236.18905651910427, 96], [1468.0697676919451, 582], [335.10044766995543, 146], [125.74215683703324, 98], [1523.7121854688426, 485], [97.23755183376443, 45], [682.0483952025827, 190], [75.46096098992615, 116], [12.568686038148911, 6], [169.6000029142425, 166], [348.7578795999764, 141], [456.2304270422542, 171], [1030.9484733393463, 491], [12.230560100981393, 29], [163.83982290510994, 40], [748.541107974389, 308], [311.4264787115285, 90], [248.53960456290736, 93], [229.09813865065098, 124], [207.916443705843, 106], [378.55154257550237, 330], [53.281443865462734, 43], [252.13883206267155, 200], [120.80147535813012, 69], [327.9556956842814, 477], [80.24747465791, 42], [346.58930338332254, 80], [243.1878470912202, 148], [599.3533143610371, 327], [543.3466699677729, 231], [1550.1666903089358, 422], [14.716771162042107, 10], [426.70926311792505, 299], [537.1464650051075, 215], [291.14297693724257, 130], [91.10506683368044, 128], [401.86610630134214, 222], [294.6236580119055, 374], [1142.259089588516, 489], [178.48999963207098, 88], [260.4659487742001, 85], [1065.7500529298827, 422], [96.43502125841758, 51], [350.40812079769194, 253], [813.7006967305706, 368], [381.73073935942125, 245], [225.5669205654956, 130], [230.9297101688701, 77], [1047.26198205145, 408], [704.5428101302919, 268], [902.1388255340664, 258], [508.8003710477519, 212], [269.3407160304755, 103], [134.8358476072109, 92], [178.23984300446136, 94], [187.42961029843536, 86], [169.27159679377837, 66], [350.0485865096357, 135], [261.12784629892576, 156], [521.5141351980715, 150], [159.3031650504293, 85], [529.9097191489614, 210], [128.8710169982719, 59], [643.8140704884952, 208], [866.6017724609437, 375], [24.637573476007503, 17], [1138.7922642168633, 457], [221.4766571164671, 88], [798.0910454280273, 319], [101.98299096232495, 27], [27.679289749695727, 39], [164.78544764949947, 73], [33.77654101288135, 36], [214.8726474560999, 119], [152.21763336365711, 68], [665.0429927213402, 321], [102.88302372845465, 71], [508.1290402027955, 192], [1332.4367224770333, 498], [115.78383238634433, 75], [716.4429105254235, 266], [458.33359479660703, 168], [121.79606871840684, 59], [49.584373481454804, 25], [619.2902734114248, 205], [1462.5057471003597, 478], [741.5460063040246, 377], [448.89426743418835, 181], [204.30442810203658, 47], [439.42159078876284, 195], [126.63067285407578, 54], [267.78928262704676, 120], [133.39566351539997, 169], [146.65667602868052, 495], [844.5397183511859, 361], [105.08507082265669, 41], [1275.9503071062618, 465], [93.89943854570356, 50], [127.3253337844086, 65], [239.4538458603256, 110], [69.2036442300041, 62], [699.9184526563877, 306], [70.71828143711787, 44], [196.095944701794, 52], [488.627010918741, 194], [427.8003077294452, 197], [319.81011798102554, 105], [352.6256526539803, 148], [1236.1159135544863, 418], [365.9412328729943, 203], [960.6207018036287, 388], [444.96576801448737, 220], [27.35971162388887, 25], [72.99585567264785, 22], [949.9735089787584, 645], [953.9622640712292, 375], [172.03402268908144, 76], [559.370783205596, 198], [274.6770648083593, 221], [655.388593130961, 272], [1696.5002667554222, 488], [23.542739987307414, 7], [23.89673377425993, 15], [192.34867788610063, 64], [460.4057665260159, 348], [637.8053555853253, 182], [186.26296118073515, 79], [91.47422039951255, 91], [1181.521039100209, 479], [235.3031434469449, 96], [352.3377654719393, 140], [199.60015325631673, 65], [1194.49874404826, 504], [54.605503157631574, 50], [1107.3365543445807, 464], [154.1707423622425, 33], [333.3005244070381, 128], [271.10973176177595, 111], [116.60305075681197, 159], [283.2404949297097, 123], [68.58670773935955, 40], [979.4590859010098, 470], [287.25834109427524, 143], [471.6892247441514, 120], [146.52535387853595, 93], [1014.6294397399681, 372], [339.79199377847954, 155], [73.28045762753732, 66], [591.9401730849306, 282], [51.00959587579189, 24], [44.98090070082549, 34], [135.78385882063958, 103], [113.64565910121541, 35], [735.468267304183, 271], [58.13254879017296, 15], [963.8498005071259, 365], [796.60853813229, 355], [172.44230044108963, 53], [161.63115262030033, 70], [2477.578975855765, 1200], [603.1706141633338, 274], [628.5389194610293, 187], [346.2140325576761, 169], [766.6116014224713, 459], [300.78142718005233, 158], [531.7320135584932, 156], [243.14705126472268, 102], [119.17482382148341, 56], [1051.1260745285183, 464], [732.8222601955304, 275], [590.4831925800836, 146], [325.97921908230524, 154], [189.01071763778805, 108], [980.5600794498664, 356], [1173.312818134778, 423], [134.35203967128155, 80], [460.47776444458054, 342], [384.03794404822384, 178], [1517.1411200213417, 697], [381.6598492348703, 136], [1127.388133484399, 462], [108.39510308663262, 46], [299.02502789460357, 151], [29.30981647631893, 27], [254.2344064970771, 85], [197.14020820201313, 91], [1243.3690858432492, 441], [194.85021426617425, 135], [1258.53366161845, 457], [226.5924714581281, 94], [106.04390481600694, 62], [521.8356924000659, 195], [241.76488766308034, 108], [44.27494528365435, 46], [367.5991114214926, 127], [1089.7259276906716, 412], [70.4318836608436, 38], [312.04987997903606, 192], [164.7472416237675, 89], [327.41738699444704, 119], [294.58823473081975, 138], [622.4535056104914, 248], [543.4219545817159, 247], [178.3265933256181, 172], [382.3912616449386, 187], [545.1358075959183, 222], [259.8396126256265, 119], [564.823759346205, 222], [905.4308723259203, 388], [1392.9514312120805, 483], [688.6570676771407, 227], [206.64755378848554, 75], [229.58331879712568, 119], [347.29218801309617, 187], [903.7942180915938, 293], [708.6091305144441, 287], [1186.0718444513723, 593], [324.75118618755164, 107], [147.34842710426517, 56], [261.05419902637243, 97], [294.9067522740079, 124], [158.52381379268422, 101], [278.87318739367424, 91], [446.0228882938154, 155], [1028.1583316742995, 388], [242.33022580309398, 78], [698.199441655262, 274], [1483.7005471729135, 508], [826.4981734894662, 303], [888.8773172678348, 543], [16.415573619734232, 18], [378.54434056895616, 172], [472.23333106652296, 189], [353.7159712287921, 168], [281.1966990655942, 154], [410.1671528205047, 182], [479.4533417498301, 205], [46.80130974732538, 18], [283.9035376288002, 204], [105.27352791058536, 57], [1172.9438954676189, 467], [322.36085363764596, 123], [830.6551698944584, 308], [269.6309543904895, 426], [1245.7151498108278, 496], [219.47657842782223, 60], [688.1535834809947, 204], [721.3224484227958, 298], [152.25499298441036, 181], [1002.2846494158644, 300], [408.5108939399952, 127], [75.6390152142393, 31], [382.7770244125559, 132], [801.3763108478202, 325], [845.5740230780043, 418], [692.6402196956737, 270], [77.63688299457135, 54], [158.04404188081935, 64], [370.962920411758, 140], [275.76635454153757, 105], [209.21421343967359, 112], [78.06960160985227, 32], [96.0296515052828, 78], [785.5299499554446, 324], [43.69538756443001, 22], [171.55442915438857, 64], [802.5858965114448, 354], [738.6029301589952, 284], [875.7374842961472, 381], [107.52233876391074, 59], [96.26357824867864, 57], [475.0241353679403, 172], [91.24190622147671, 63], [8.459918110102024, 47], [100.10200967306719, 47], [15.087576197468934, 47], [379.04764410861185, 117], [437.1981422918657, 159], [318.7295806868924, 142], [235.87182917269638, 160], [226.60562770378044, 123], [774.5380913086315, 318], [655.8752502546909, 312], [600.4165800803985, 240], [594.4570261940446, 235], [26.820595115896822, 69], [1067.4593313144283, 446], [350.1301811855085, 163], [850.8077756155138, 494], [589.8514696536522, 236], [36.44260833091306, 31], [815.8760772674502, 345], [771.3703952147034, 326], [17.1172474471241, 15], [189.36947461106138, 74], [296.9307879424259, 131], [328.8400013296596, 160], [538.978275993049, 285], [109.22400678584563, 57], [322.142222993647, 158], [155.02168386641642, 70], [111.8884035359697, 74], [220.87327280880334, 88], [565.9692642874015, 198], [528.3710791359572, 238], [455.4489889640953, 194], [136.20726481143834, 74], [12.146818459369115, 10], [156.19351496641923, 68], [326.7994488800359, 96], [954.348169569972, 399], [576.5010297948324, 236], [432.3904091404147, 147], [432.21916937317826, 174], [20.319198040022115, 40], [766.5253474677938, 351], [858.16728336506, 356], [287.3307132320548, 107], [942.1726832088598, 449], [459.79337875161093, 176], [1507.022956968869, 650], [126.66030533412925, 56], [160.61102036838747, 84], [365.72890419308897, 141], [39.58393868142042, 21], [487.87690191992283, 1062], [1154.420961888286, 405], [760.6947462493349, 279], [149.9041900694874, 75], [66.55533712311058, 31], [1217.104227236504, 453], [191.5304437434886, 108], [664.4537170306035, 426], [221.40365041652785, 132], [333.19177168239617, 149], [91.21083556298754, 43], [315.16342945907854, 147], [963.1987182510147, 383], [266.6294301555854, 123], [802.7921090138937, 310], [384.0428295022002, 169], [318.55036757962625, 151], [65.96664800381905, 44], [217.15083251220335, 66], [463.5386070930256, 157], [13.359978606814366, 28], [141.64464630661723, 64], [878.1592601922971, 471], [97.49969494566949, 60], [362.7893505320535, 292], [135.97293327581622, 71]], "final_state": "tinker://3f4f84e3c9c6567b09cde46deae56415/weights/select-sel_dimuon_lr0.0003_s0-final", "t": 1793744355.5018857} {"stage": "eval", "arm": "sel_dimuon_lr0.001_s0", "split": "val", "step": 40, "nll_sum": 198681.98552384428, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.1062885413010375, "example_mean": 1.9812850549290002, "per_example": [[161.86228314280015, 104], [793.8653581800331, 423], [286.86374145341097, 219], [1409.1748966916348, 467], [62.76820615823726, 53], [288.47397183840985, 151], [5.337010819856914, 20], [29.36556378055002, 27], [34.024185551062146, 32], [482.4257993519109, 247], [340.2839661929746, 223], [705.9131215646914, 280], [1018.6142908582381, 365], [77.49194868386098, 54], [401.2281880394439, 159], [386.27245577375163, 265], [687.3726144216621, 330], [221.75375569593325, 110], [314.1601910899657, 120], [88.54951417124994, 114], [220.62576771276235, 132], [80.16109809649424, 67], [105.27912475561243, 57], [137.46816397663497, 100], [561.6723129633715, 345], [1.9416010938221007, 14], [1288.580209956831, 788], [1164.737957734105, 469], [246.13258760701683, 65], [262.30253795588624, 158], [834.581975793823, 356], [65.73501649970399, 26], [332.9509115346432, 109], [222.71848809981566, 105], [274.3257480391653, 233], [197.89444394549298, 69], [136.70141583528448, 61], [108.75558951321818, 86], [279.0600195148668, 105], [228.4132867211, 88], [1505.7456776910108, 519], [504.388127379116, 157], [72.47189995918211, 78], [161.93741943302302, 102], [433.50570709186604, 209], [1176.950977121938, 484], [226.57900707250383, 233], [194.03667284086987, 118], [101.05259151695395, 91], [32.92731025069611, 34], [334.7756446574258, 177], [69.20930895995059, 39], [70.28842725731306, 50], [104.51021513516935, 84], [184.3208698417726, 152], [297.4910693340307, 115], [477.2315921099971, 302], [408.5336017023874, 242], [598.8909614742099, 268], [55.73193603823768, 19], [305.18339966921303, 131], [549.9258789736737, 248], [268.0659327799199, 261], [631.7840473254464, 328], [98.31565191636037, 56], [281.627755566411, 104], [76.15002635878045, 62], [384.7668498214324, 179], [1557.8790130410327, 389], [98.26779023851827, 132], [92.33764602988902, 24], [263.61969404574427, 122], [67.57878463953784, 39], [84.09976745172628, 59], [7.23078023603739, 18], [224.6997225461878, 124], [455.78176764354225, 269], [151.67803915286459, 69], [25.32962831288387, 23], [430.5018674034177, 202], [669.1377733297702, 255], [138.32678462867216, 52], [244.90010696261697, 138], [167.95390024964036, 99], [0.6307038315680984, 19], [737.8127133196763, 313], [563.6713215518989, 270], [63.18709253705401, 34], [613.026515184581, 256], [100.17103335302818, 64], [52.25458487239621, 28], [299.8254103062786, 135], [483.25455742310623, 217], [192.75403262484906, 73], [186.0206068072457, 62], [275.0553368424554, 520], [552.290407935039, 193], [406.71681739063297, 110], [1025.2792764897451, 319], [33.716183253790405, 56], [362.20206773107475, 276], [229.07859257674045, 121], [156.93692739796802, 71], [141.17690088566405, 81], [84.33631504070559, 38], [203.1995902664412, 100], [202.28475099829848, 97], [105.60031317244102, 69], [969.1839036563365, 328], [57.78460902716688, 44], [353.48543880862167, 128], [102.65246076494032, 66], [813.900786411715, 306], [137.4611753377867, 78], [629.219856607594, 242], [455.05626290509804, 201], [84.34388556851832, 52], [58.4167776185659, 40], [807.9767798029345, 246], [276.0194063505549, 125], [11.999865576906814, 89], [945.8175891214768, 446], [138.84829426874057, 106], [454.8811739587436, 200], [566.9010183815772, 266], [581.617967419166, 288], [159.86576178912674, 106], [245.93628453084875, 86], [668.9575382479179, 341], [624.2352472780453, 258], [77.46762796304893, 52], [858.2503967096695, 448], [372.43510039737066, 168], [27.673728578367445, 47], [34.54657076051808, 43], [1252.6864900734315, 476], [103.17386192788263, 104], [149.48534794482566, 106], [224.3517073217954, 137], [1066.6347001013912, 491], [13.926466534189672, 20], [119.5780532053841, 66], [94.57162565990893, 54], [167.91531337216657, 92], [89.95701481399601, 42], [753.5687989536669, 425], [724.5636142803116, 231], [117.78965229700657, 96], [1017.3837085831876, 417], [226.53874408118554, 96], [1421.648903086036, 582], [302.0469507519233, 146], [103.93551122921053, 98], [1483.7011905484808, 485], [82.30485297415862, 45], [607.0858522007454, 190], [52.155567738071085, 116], [2.8297476191339683, 6], [163.00419493173968, 166], [340.75897977326474, 141], [436.58933406067047, 171], [996.4694196332164, 491], [9.134729340667718, 29], [148.65835050912096, 40], [721.2572487209252, 308], [285.78500082343726, 90], [227.53935583755583, 93], [213.2095920893421, 124], [182.36807126459416, 106], [353.4246727248774, 330], [46.08160573378882, 43], [233.64542081286527, 200], [104.55737578956541, 69], [287.00860546239437, 477], [62.15729958555221, 42], [317.24847833067054, 80], [213.33738669175273, 148], [573.6230750464858, 327], [522.8716663321179, 231], [1515.8072662548448, 422], [8.495536974586003, 10], [337.4722872789416, 299], [505.17893215536446, 215], [258.64413476522714, 130], [68.12895793811913, 128], [345.94174594088304, 222], [264.6791046764263, 374], [1128.9417816330051, 489], [158.04918181489575, 88], [236.0327221838479, 85], [1029.216433136286, 422], [87.27930555111374, 51], [318.48040561986136, 253], [773.3872925510786, 368], [339.29063567767287, 245], [205.86311547598052, 130], [198.89517410075678, 77], [1024.1834222772136, 408], [677.0453491913033, 268], [835.647877225186, 258], [489.1614155150785, 212], [241.80518806915188, 103], [119.49842890028822, 92], [154.42326695137308, 94], [166.00628906918064, 86], [156.30428851675208, 66], [327.41763831417666, 135], [252.0137675162132, 156], [480.4254856114235, 150], [132.28633166398868, 85], [485.35384661853186, 210], [104.39072527548433, 59], [605.0601843332394, 208], [835.2539584324984, 375], [21.410623838426318, 17], [1103.2320996188128, 457], [205.41956761549227, 88], [772.1736976367241, 319], [81.09518327737896, 27], [24.093687308133667, 39], [143.80978454102205, 73], [14.425214245756479, 36], [212.62409459153196, 119], [115.30015857162289, 68], [613.8316108662821, 321], [82.63524937824832, 71], [471.96755612327183, 192], [1288.7628766141113, 498], [93.45412964709249, 75], [668.4792414886465, 266], [432.335986888673, 168], [90.56652330257862, 59], [42.508871690544595, 25], [582.9775499750376, 205], [1424.9843059393966, 478], [714.7404989643101, 377], [421.63909201873946, 181], [182.74329509632503, 47], [395.04257475619124, 195], [98.30938323354246, 54], [232.9529998381131, 120], [116.70331276882007, 169], [143.2054401928849, 495], [829.1518690783657, 361], [88.2015228858179, 41], [1243.485717409698, 465], [81.97581688661921, 50], [111.27276710223578, 65], [222.01535631853903, 110], [53.12703397808946, 62], [678.1269274252227, 306], [61.177346489438605, 44], [181.18611145624868, 52], [456.66772840451347, 194], [412.7382854182206, 197], [295.9450326341308, 105], [308.3765110940958, 148], [1187.3316305505575, 418], [337.6123188562028, 203], [928.6988000248368, 388], [413.02237838564906, 220], [11.487258181354264, 25], [62.3901844453643, 22], [866.8409006134577, 645], [929.4822772726835, 375], [144.6632886674538, 76], [529.3382729936395, 198], [217.50300966668556, 221], [638.9157914443344, 272], [1647.678282146322, 488], [12.413904299252408, 7], [11.13968515808665, 15], [168.11140367522785, 64], [433.23976883846944, 348], [615.1383722696899, 182], [178.248462353567, 79], [83.0571714360583, 91], [1136.462886125085, 479], [216.5405496949902, 96], [330.0831906914193, 140], [187.44839618261847, 65], [1145.861107259257, 504], [45.45097127858753, 50], [1063.8639108850757, 464], [117.63198879896538, 33], [311.05194887984453, 128], [252.10533814453538, 111], [94.22181168506904, 159], [254.22108036529107, 123], [41.22219681753813, 40], [957.5369930041988, 470], [270.7920654263198, 143], [444.66298444452445, 120], [125.89727986157436, 93], [978.9906513633026, 372], [325.0158828344132, 155], [70.26578304357031, 66], [553.3516966605337, 282], [41.87216910207633, 24], [26.017816908832174, 34], [126.53795505193648, 103], [100.14516243011894, 35], [687.4998579875648, 271], [52.00909020238396, 15], [933.4233869208375, 365], [770.4917962264863, 355], [161.08773697079937, 53], [148.33797688718505, 70], [2412.1653573882822, 1200], [528.7661652606303, 274], [598.1765389320781, 187], [322.03284428245286, 169], [719.7278409288613, 459], [283.2628959019744, 158], [498.14309896725854, 156], [211.0903849233871, 102], [109.97408745737266, 56], [1014.2094699525255, 464], [681.8686423858139, 275], [558.910527518789, 146], [285.32832837046, 154], [165.25005684546113, 108], [935.3691864925759, 356], [1112.8350231774875, 423], [101.21961731007832, 80], [434.48679931658864, 342], [348.9487405104096, 178], [1475.669215508543, 697], [349.22730303143453, 136], [1068.34540685414, 462], [89.48968851405516, 46], [277.32722832355466, 151], [11.229950645136341, 27], [230.00494409468047, 85], [160.82647210897903, 91], [1203.178793438934, 441], [159.55758125397415, 135], [1221.037751250883, 457], [218.61085756984482, 94], [100.02302550778495, 62], [480.5738123358604, 195], [236.1314366492436, 108], [30.133670931481902, 46], [349.40479268808076, 127], [1047.8449252607138, 412], [53.25671573177897, 38], [267.47733757661763, 192], [136.79623488091693, 89], [277.4025247385566, 119], [269.55406456257276, 138], [599.0775921054756, 248], [519.7331568614245, 247], [157.90593168948203, 172], [331.78024812991487, 187], [529.3358369126713, 222], [237.80173392267534, 119], [519.7536078667017, 222], [858.9027013242726, 388], [1349.2459230635936, 483], [660.5704172916776, 227], [166.19172334030395, 75], [199.834897800406, 119], [312.20212411990224, 187], [844.3643158099089, 293], [656.683169379347, 287], [1097.7834229958662, 593], [307.0964574301612, 107], [128.32246091269144, 56], [247.7293470706789, 97], [262.6499076332493, 124], [128.22399819385407, 101], [279.2820902958008, 91], [429.8590158501165, 155], [1001.4878167448862, 388], [217.07118899840737, 78], [661.5731947461722, 274], [1453.3441021218207, 508], [799.5772959802086, 303], [844.1728129080639, 543], [5.933565916715452, 18], [338.86112129140383, 172], [430.2417743359101, 189], [320.938589503462, 168], [247.3599472024357, 154], [375.2382953123878, 182], [452.6936871139329, 205], [36.58621483847128, 18], [261.6654201163616, 204], [79.67938376177332, 57], [1126.5240000604654, 467], [283.90669339939814, 123], [803.1004406711434, 308], [247.26711054282896, 426], [1210.4979203139942, 496], [184.35130451433224, 60], [635.8988198758445, 204], [689.1732533210884, 298], [130.68735911057138, 181], [965.8531279613871, 300], [388.6537482767292, 127], [74.53596376278426, 31], [362.2028992096888, 132], [756.2136298861578, 325], [805.3216852317785, 418], [659.605931994736, 270], [67.91271350234092, 54], [128.75936727780027, 64], [322.32956745396586, 140], [253.4261223058602, 105], [180.70284871936656, 112], [57.08579515844394, 32], [80.41151438262386, 78], [735.3964535380105, 324], [33.98224669171009, 22], [151.85824209774273, 64], [784.74950264582, 354], [714.7014636422678, 284], [835.6461120414572, 381], [89.66681658472498, 59], [80.7307449342743, 57], [426.9835400040606, 172], [78.24690469217512, 63], [7.0753885304666255, 47], [96.66800937545418, 47], [17.716496541292145, 47], [343.09729197620936, 117], [405.1741508309474, 159], [311.6849598850963, 142], [196.29654239999127, 160], [199.53667091777243, 123], [740.7827114968468, 318], [595.5268382049667, 312], [575.5922968059701, 240], [577.9192908707755, 235], [20.689486604420154, 69], [1006.7953355324546, 446], [321.6921999751854, 163], [817.1823587807844, 494], [561.7524384937701, 236], [25.28783516067415, 31], [680.6696815877367, 345], [726.9140465449727, 326], [10.140850305266213, 15], [167.02302521978254, 74], [269.2778076340903, 131], [310.95455761602534, 160], [517.4073951896526, 285], [85.22906369330713, 57], [308.73063695685687, 158], [128.53432954285017, 70], [79.068544474394, 74], [189.75368054047954, 88], [511.6102666683382, 198], [492.78796638559834, 238], [419.2427772963416, 194], [121.79930839243207, 74], [3.6485780592265655, 10], [122.96058723650617, 68], [303.9587143449967, 96], [916.9384729019471, 399], [511.0960131080345, 236], [399.9848566641426, 147], [415.7680239318843, 174], [8.167546068041702, 40], [751.8016776549391, 351], [806.2110945410632, 356], [272.3990815954744, 107], [902.5854578771455, 449], [438.9894337842006, 176], [1461.7804911263777, 650], [102.60687093524484, 56], [143.92156088411343, 84], [348.0453566358176, 141], [21.87654817718976, 21], [460.266909290306, 1062], [1092.6870080138992, 405], [732.6852837100105, 279], [123.03337732852742, 75], [61.366929435635825, 31], [1159.147451326655, 453], [147.73658062517438, 108], [633.974307340387, 426], [201.06086583504612, 132], [305.3614760109615, 149], [78.86833642329862, 43], [296.01528991199575, 147], [912.698600553935, 383], [259.3977139159024, 123], [772.8735048931846, 310], [364.4058109413552, 169], [291.5890500141195, 151], [53.6166729372635, 44], [193.5208811205805, 66], [447.36421940563, 157], [4.709690318748471, 28], [109.78026545164118, 64], [841.5185851021588, 471], [82.49531721888343, 60], [332.8370528775449, 292], [117.72108214541345, 71]], "final_state": "tinker://4d27e2e59c33df3015a266e8878b457d/weights/select-sel_dimuon_lr0.001_s0-final", "t": 1793744373.9308076} {"stage": "eval", "arm": "sel_dimuon_lr0.003_s0", "split": "val", "step": 40, "nll_sum": 195006.4643987574, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.0673232168471443, "example_mean": 1.9287302029516677, "per_example": [[157.0736934242468, 104], [785.6978923283841, 423], [282.72594347330596, 219], [1390.6758642604436, 467], [61.71591949185495, 53], [286.91624354117084, 151], [3.8063537378329784, 20], [27.94517000844189, 27], [32.266116781018354, 32], [473.7234725249664, 247], [334.03460322316096, 223], [687.178957129915, 280], [1001.4211319786009, 365], [74.07309534639717, 54], [397.8598313376897, 159], [378.6822813908457, 265], [670.5295495111459, 330], [222.41851955187485, 110], [302.28161770408315, 120], [87.17660942177599, 114], [213.81029801521072, 132], [79.74423178418385, 67], [105.37689674105104, 57], [134.95082066965733, 100], [567.4649870219355, 345], [2.6596309997762546, 14], [1261.7453493392015, 788], [1156.5742328117922, 469], [239.00290376238615, 65], [264.49622623145115, 158], [829.9786862108595, 356], [66.8789956674832, 26], [330.8909391980196, 109], [225.23456376828562, 105], [266.52827622303084, 233], [179.0871690435506, 69], [132.9860871742585, 61], [104.70227412752183, 86], [273.5858475120767, 105], [222.23244072754457, 88], [1496.605197558294, 519], [495.39412761761923, 157], [67.17522490529973, 78], [158.12640780714537, 102], [423.53471212471777, 209], [1158.9373435608122, 484], [238.7495331286118, 233], [192.486017011086, 118], [92.2879525103051, 91], [31.04585077525917, 34], [332.3920209342032, 177], [66.67545083426376, 39], [66.56943662693948, 50], [105.83531154642151, 84], [183.61827951104442, 152], [286.99644351218103, 115], [463.53332142057934, 302], [395.81196590563195, 242], [584.9704373380782, 268], [55.00120270009438, 19], [298.16375663053077, 131], [530.846109376349, 248], [261.5013251673481, 261], [611.4690383655197, 328], [98.43934669422742, 56], [271.83568532770005, 104], [70.9868751019294, 62], [380.0831997820692, 179], [1545.1667547394945, 389], [96.38649645605437, 132], [88.28381394250073, 24], [256.2559108013411, 122], [65.87591490078557, 39], [81.39800678747997, 59], [3.269239533529003, 18], [222.76492498549487, 124], [439.1864021894198, 269], [142.79527099512052, 69], [24.448060116124907, 23], [419.6272709152995, 202], [662.5941179699712, 255], [137.0031358066226, 52], [235.46255917819872, 138], [164.1140268521931, 99], [1.2449446947834986, 19], [738.2830050901994, 313], [560.6968849234245, 270], [60.3615933774563, 34], [606.9134273371346, 256], [97.77003632315063, 64], [55.01215781617475, 28], [293.4824502241763, 135], [480.5227389700826, 217], [178.43655382388351, 73], [178.3255604894739, 62], [264.95740993730897, 520], [539.1598937883828, 193], [399.44058636703795, 110], [1003.9223638472413, 319], [29.67123519771485, 56], [354.9328412814741, 276], [221.53491567990022, 121], [159.34615477483658, 71], [140.08132279156052, 81], [75.44513498218294, 38], [204.08749561428021, 100], [199.82333626720174, 97], [107.99923828787541, 69], [963.1490086119538, 328], [49.32434947358888, 44], [344.04420401587413, 128], [98.78771319351063, 66], [803.2817257273666, 306], [135.70596231589616, 78], [615.4908176841582, 242], [446.956425361775, 201], [75.80709671869954, 52], [54.314820272004, 40], [798.6450377587744, 246], [269.3641368786857, 125], [8.126084469082343, 89], [937.5990068557074, 446], [131.35856758959346, 106], [449.4068138158909, 200], [555.0830559162573, 266], [573.9637260336749, 288], [158.36734972485374, 106], [239.76176280201526, 86], [663.9279935036111, 341], [612.0395700140562, 258], [75.11270662244351, 52], [847.0161732597335, 448], [368.78335766266173, 168], [22.959694767089786, 47], [33.75251324144847, 43], [1236.5280937461412, 476], [97.13159808853197, 104], [146.9584996006961, 106], [217.36271242085238, 137], [1050.5939538246075, 491], [14.057234365443946, 20], [113.58979201166221, 66], [84.8138164537595, 54], [159.22673751890397, 92], [84.46700237540517, 42], [749.1894853845588, 425], [710.0672761669102, 231], [115.25403251909302, 96], [998.1948989689708, 417], [224.6396258105524, 96], [1402.4911413758782, 582], [291.7781302299354, 146], [95.03758799037496, 98], [1463.8734579146949, 485], [79.41436159125806, 45], [596.9569887992129, 190], [43.5389338977393, 116], [3.0213613276537217, 6], [162.1288732301182, 166], [338.40807207520356, 141], [430.1366880279729, 171], [988.2370474556265, 491], [9.80804095133135, 29], [139.0088700256797, 40], [708.880985370587, 308], [277.8582353406872, 90], [214.70167572296668, 93], [199.45917641305823, 124], [174.96228110676384, 106], [346.8808388715697, 330], [43.419668688567526, 43], [229.14604675543052, 200], [103.6551750892695, 69], [277.73180881416465, 477], [59.79365778545798, 42], [304.7507252237938, 80], [205.97229815560058, 148], [558.9975316888922, 327], [520.4006916283761, 231], [1506.297699550093, 422], [5.380805835335195, 10], [321.491811828163, 299], [489.7446829331693, 215], [251.42646848590448, 130], [65.99240988329075, 128], [335.66096671234686, 222], [270.0559510071216, 374], [1124.9880249572361, 489], [154.99746319655833, 88], [234.63997634027567, 85], [1015.464116355759, 422], [85.64321409873264, 51], [320.19161551113575, 253], [757.3171581854931, 368], [327.49595929096904, 245], [202.12935837180385, 130], [188.81708212201806, 77], [1018.4792303398153, 408], [660.5208370877556, 268], [822.0019275256018, 258], [476.8169872737044, 212], [232.06550722739667, 103], [110.74514728620625, 92], [141.5945179821456, 94], [160.83899896827006, 86], [147.8306664794418, 66], [318.8184717048516, 135], [250.3481696442068, 156], [471.6613933813178, 150], [128.32395058673228, 85], [469.2291960378061, 210], [98.16320401558005, 59], [587.1249494866224, 208], [817.9847717278026, 375], [20.451136369265896, 17], [1095.6248106426792, 457], [199.82104351953603, 88], [765.4553396971828, 319], [73.04159109233296, 27], [20.502255967988958, 39], [136.86790715989446, 73], [9.365839340164712, 36], [203.9995214817245, 119], [112.2102564247889, 68], [603.1211775196201, 321], [83.3136617212831, 71], [462.13641864439705, 192], [1264.0707403768592, 498], [84.66773192285109, 75], [653.0635840372961, 266], [428.26091581545916, 168], [82.89358965034978, 59], [43.41012844536294, 25], [579.6961830029522, 205], [1415.2498613982534, 478], [706.2446961948854, 377], [416.0488035231633, 181], [181.89857281748118, 47], [381.23306720455, 195], [89.12750429635526, 54], [225.51711470266218, 120], [112.16916356799993, 169], [151.12838594333698, 495], [806.8324314424244, 361], [86.20921480595462, 41], [1239.7763984961348, 465], [79.63399147946984, 50], [106.72413902177095, 65], [215.40645932481902, 110], [49.11346863005565, 62], [667.4484461824031, 306], [55.97745953514641, 44], [173.71434481852828, 52], [445.3567506754616, 194], [404.1957277364618, 197], [299.23599046224444, 105], [299.05077907499253, 148], [1160.6849496661869, 418], [332.26779011148574, 203], [912.6231745075384, 388], [403.0226436813791, 220], [11.036917822165378, 25], [64.62375861340297, 22], [832.823160008425, 645], [928.4139005287616, 375], [138.3802353003266, 76], [511.904827466049, 198], [214.34359304396276, 221], [633.6222612116107, 272], [1637.69678694311, 488], [11.165639393342644, 7], [7.7414372205766995, 15], [163.42299554259716, 64], [418.3797603246485, 348], [602.5366648298914, 182], [177.62683758271288, 79], [80.52256969255461, 91], [1120.9995398862402, 479], [210.28871457211426, 96], [329.05783517440614, 140], [181.79991164205376, 65], [1130.7373707355637, 504], [43.822537062182164, 50], [1060.4161768530062, 464], [101.98370989276191, 33], [302.2123115622421, 128], [242.46038512183713, 111], [93.19006898346902, 159], [248.21001195245117, 123], [38.94207512422872, 40], [956.5916033842041, 470], [256.133906334122, 143], [434.0787705604466, 120], [122.8472367465206, 93], [966.4472029626595, 372], [316.73657188295056, 155], [69.6678619635436, 66], [545.7187003966537, 282], [39.78804087553169, 24], [22.741993648965035, 34], [121.89747572187116, 103], [95.65390924801159, 35], [665.2411214456079, 271], [51.02888875671488, 15], [928.4210908376117, 365], [761.0291907765368, 355], [158.76031235046048, 53], [144.03099817255588, 70], [2398.46250894423, 1200], [508.7448732998512, 274], [594.0230143689623, 187], [304.17068664957696, 169], [708.2067094135309, 459], [278.7125506392895, 158], [490.10882422239763, 156], [214.010556327612, 102], [107.32161368675224, 56], [995.5559588337155, 464], [671.9136652792752, 275], [546.2878508183048, 146], [276.34559016629055, 154], [158.39781084316564, 108], [916.4183390666849, 356], [1091.1118226649587, 423], [99.50344064561068, 80], [421.45934017223635, 342], [343.8825101190396, 178], [1455.2373407135801, 697], [348.14649616299903, 136], [1069.806435548664, 462], [88.23372001975349, 46], [269.49691753436855, 151], [6.918680962786311, 27], [222.43034855345286, 85], [155.83908839142896, 91], [1192.2300346787815, 441], [143.00522861414083, 135], [1206.067173110372, 457], [217.72260696654484, 94], [98.46790636730475, 62], [477.3544658965002, 195], [236.48505663858066, 108], [23.89306671440454, 46], [339.09482219353595, 127], [1029.2687939561365, 412], [53.3729400542652, 38], [257.3436569688092, 192], [127.53481941426435, 89], [260.76623002874476, 119], [260.53617991405554, 138], [586.8056223649801, 248], [512.3027585063542, 247], [162.70893861409058, 172], [326.1523082639742, 187], [516.3512777599858, 222], [228.26372596419424, 119], [506.92644562038186, 222], [846.6103182528041, 388], [1341.3473445576092, 483], [662.7292732983697, 227], [157.2675338937206, 75], [187.14428276727858, 119], [296.3998796321948, 187], [818.916209830888, 293], [638.1771600904158, 287], [1081.229329992966, 593], [300.2711399239597, 107], [124.20354961169232, 56], [239.1093778549125, 97], [250.7684660426894, 124], [121.05192123396591, 101], [280.6216997949575, 91], [424.4570418524072, 155], [986.0148512695487, 388], [209.87231514992527, 78], [655.3165350888139, 274], [1443.4344319506963, 508], [793.0772313864527, 303], [829.4914131226215, 543], [3.777411931547249, 18], [325.0482886861464, 172], [423.3535761314268, 189], [314.3921027422729, 168], [237.77096882145725, 154], [369.42572512845754, 182], [439.59651021545324, 205], [35.18611944507029, 18], [262.2068096886078, 204], [79.15699842116555, 57], [1117.1807970552654, 467], [274.184683021449, 123], [792.7254810192244, 308], [242.49321102439308, 426], [1200.7771782630964, 496], [174.91830824127942, 60], [627.0047012825817, 204], [670.0596228272098, 298], [124.86822486248138, 181], [954.7644782835337, 300], [382.6117528973191, 127], [79.10783648174197, 31], [352.9124552510525, 132], [745.8069224605206, 325], [793.9788141627832, 418], [645.3513948893997, 270], [68.54115691122115, 54], [123.63891516179137, 64], [313.26102769875615, 140], [252.46841197130288, 105], [174.18388397319723, 112], [49.69845294915922, 32], [77.85448641437506, 78], [726.2466916662215, 324], [32.756395965337106, 22], [141.0518341311472, 64], [760.593878314583, 354], [707.1956501357781, 284], [822.2170476486317, 381], [82.08327611822733, 59], [77.93682871378405, 57], [419.12975435456246, 172], [76.32894601923726, 63], [10.271705306443437, 47], [94.54953820471246, 47], [13.845396890656048, 47], [332.03691254297155, 117], [390.39859283971236, 159], [308.16200923582346, 142], [192.11030109165586, 160], [189.36787396541786, 123], [718.8310052398007, 318], [584.5152495949108, 312], [572.4932432156347, 240], [557.7976720211009, 235], [17.11320264197434, 69], [1002.2083005193449, 446], [317.4839499358641, 163], [814.2478876275422, 494], [555.5043371734564, 236], [26.742239587783843, 31], [669.0224451912, 345], [710.9565625068462, 326], [7.238626931922681, 15], [150.73572357978446, 74], [262.63416782161767, 131], [306.153748914483, 160], [511.8654833338096, 285], [79.1272784438903, 57], [308.8242799619038, 158], [124.22430523677394, 70], [70.20994412192977, 74], [180.83921122089305, 88], [497.8477291376221, 198], [490.3554901507341, 238], [404.7274740875364, 194], [117.93108911901697, 74], [2.2115437393013053, 10], [118.9714482862837, 68], [292.3711837318406, 96], [911.7880660022142, 399], [498.0465015075217, 236], [389.4554487180021, 147], [402.9816497266109, 174], [8.530860895952628, 40], [740.827607691388, 351], [792.2043839509417, 356], [268.2336921011529, 107], [893.6615247175505, 449], [436.07948201296676, 176], [1441.5793087190086, 650], [90.5058541770004, 56], [137.92626224202195, 84], [344.53688869524694, 141], [20.872071940004844, 21], [461.93119752290045, 1062], [1076.4476243595127, 405], [715.8019488639093, 279], [119.63801545789829, 75], [61.055902178419274, 31], [1144.330622186495, 453], [136.32803574969716, 108], [627.3747522317644, 426], [196.59289160629214, 132], [299.4664360218958, 149], [73.27175949079628, 43], [290.7048288723854, 147], [890.6413060879222, 383], [241.8480541778863, 123], [769.4472415139535, 310], [359.06533811733243, 169], [288.3143697150226, 151], [48.207859345697216, 44], [175.2420891322172, 66], [443.9965446429742, 157], [5.4136078206302045, 28], [105.71366306300115, 64], [835.3556247742072, 471], [78.95969337341012, 60], [319.6472465307743, 292], [116.48392520346079, 71]], "final_state": "tinker://38efef6933464782c8204a61c7fec196/weights/select-sel_dimuon_lr0.003_s0-final", "t": 1793744396.7129443} {"stage": "eval_done", "seconds": 127.7629702091217, "total_seconds": 926.41055560112, "t": 1793744396.7134569}