{"stage": "eval_set", "split": "val", "n": 500, "sha256": "c7e7203f7a98b7330c2123b44b7ec0dcf7e46ac8fc484f8f49d4fdfa9f7caa19", "t": 1793806744.3644636} {"stage": "get_info", "arm": "sel_adamw_lr5e-05_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793806752.7568896} {"stage": "init_saved", "group": "s0", "path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "by": "sel_adamw_lr5e-05_s0", "t": 1793806756.6784186} {"stage": "initial_output", "arm": "sel_adamw_lr5e-05_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 0, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806758.0312448} {"stage": "step0_saved", "arm": "sel_adamw_lr5e-05_s0", "path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-sel_adamw_lr5e-05_s0-step0", "before_first_update": true, "t": 1793806760.624526} {"stage": "get_info", "arm": "sel_adamw_lr0.0001_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793806763.178664} {"stage": "get_info", "arm": "sel_adamw_lr0.0001_s0", "restores": 1, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793806768.2996945} {"stage": "initial_output", "arm": "sel_adamw_lr0.0001_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806769.4848225} {"stage": "step0_saved", "arm": "sel_adamw_lr0.0001_s0", "path": "tinker://03adbc7870ed91f79da6f4176f6bc747/weights/select-sel_adamw_lr0.0001_s0-step0", "before_first_update": true, "t": 1793806773.5576339} {"stage": "get_info", "arm": "sel_adamw_lr0.0002_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793806776.0492327} {"stage": "get_info", "arm": "sel_adamw_lr0.0002_s0", "restores": 1, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793806780.1639366} {"stage": "initial_output", "arm": "sel_adamw_lr0.0002_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806781.3532538} {"stage": "step0_saved", "arm": "sel_adamw_lr0.0002_s0", "path": "tinker://bbaff5449c41db38914ac3f4523738b2/weights/select-sel_adamw_lr0.0002_s0-step0", "before_first_update": true, "t": 1793806785.3761387} {"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": 1793806787.907865} {"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": 1793806792.192664} {"stage": "initial_output", "arm": "sel_dimuon_lr0.0003_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806793.403589} {"stage": "step0_saved", "arm": "sel_dimuon_lr0.0003_s0", "path": "tinker://df15cdc0afbf74e50388cdfd5d48723d/weights/select-sel_dimuon_lr0.0003_s0-step0", "before_first_update": true, "t": 1793806799.7559972} {"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": 1793806802.4154675} {"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": 1793806806.4350505} {"stage": "initial_output", "arm": "sel_dimuon_lr0.001_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806807.7070515} {"stage": "step0_saved", "arm": "sel_dimuon_lr0.001_s0", "path": "tinker://07a741b9c4df208a09f7f0ba7592d096/weights/select-sel_dimuon_lr0.001_s0-step0", "before_first_update": true, "t": 1793806811.7248116} {"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": 1793806814.2696567} {"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": 1793806818.155267} {"stage": "initial_output", "arm": "sel_dimuon_lr0.003_s0", "init": "s0", "init_path": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-init-s0", "restores": 1, "output_sha256": "d7ba8bf1d6c57c98e0583ccf7b1768634e9973631561c4770d0e69e1e8fee0f7", "t": 1793806819.3339324} {"stage": "step0_saved", "arm": "sel_dimuon_lr0.003_s0", "path": "tinker://c1d1931de8c1fc62d30b56642bd6b4bf/weights/select-sel_dimuon_lr0.003_s0-step0", "before_first_update": true, "t": 1793806823.3617764} {"stage": "setup_done", "seconds": 82.80450391769409, "t": 1793806823.3634987} {"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": 36.344947814941406, "t": 1793806838.5843647} {"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": 36.3460693359375, "t": 1793806838.825915} {"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": 36.34831619262695, "t": 1793806838.8271635} {"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": 36.34547424316406, "t": 1793806838.827873} {"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": 36.34613037109375, "t": 1793806838.999884} {"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": 36.34757614135742, "t": 1793806839.6056848} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 14120.459785868732, "train_tokens": 6073.0, "train_token_mean_nll": 2.3251209922392118, "grad_norm": 41.10645294189453, "t": 1793806845.885762} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13894.709350384097, "train_tokens": 6073.0, "train_token_mean_nll": 2.2879481887673467, "grad_norm": 32.70993423461914, "t": 1793806845.8878477} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13537.599320121606, "train_tokens": 6073.0, "train_token_mean_nll": 2.2291452857107865, "grad_norm": 24.17645263671875, "t": 1793806846.6068916} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14229.188311533519, "train_tokens": 6073.0, "train_token_mean_nll": 2.343024586124406, "grad_norm": 55.18222427368164, "t": 1793806846.6085534} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14221.482341487625, "train_tokens": 6073.0, "train_token_mean_nll": 2.341755695947246, "grad_norm": 49.4034423828125, "t": 1793806846.6100624} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14152.955153228502, "train_tokens": 6073.0, "train_token_mean_nll": 2.3304717854813934, "grad_norm": 44.530574798583984, "t": 1793806847.0814357} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 13128.482862036537, "train_tokens": 5852.0, "train_token_mean_nll": 2.2434181240663937, "grad_norm": 50.87067794799805, "t": 1793806861.7539399} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12713.407370803525, "train_tokens": 5852.0, "train_token_mean_nll": 2.172489297813316, "grad_norm": 46.084228515625, "t": 1793806861.7551858} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12366.291228810653, "train_tokens": 5852.0, "train_token_mean_nll": 2.113173484075641, "grad_norm": 27.221729278564453, "t": 1793806861.8379254} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13453.19376048366, "train_tokens": 5852.0, "train_token_mean_nll": 2.2989052905816236, "grad_norm": 52.51587677001953, "t": 1793806861.838763} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13438.618698672506, "train_tokens": 5852.0, "train_token_mean_nll": 2.296414678515466, "grad_norm": 52.69249725341797, "t": 1793806861.8394566} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13300.109137680822, "train_tokens": 5852.0, "train_token_mean_nll": 2.272745922365144, "grad_norm": 52.28227233886719, "t": 1793806862.1479104} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16746.070580913853, "train_tokens": 7125.0, "train_token_mean_nll": 2.3503256955668563, "grad_norm": 25.63431167602539, "t": 1793806869.0316317} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16262.673068575361, "train_tokens": 7125.0, "train_token_mean_nll": 2.2824804306772437, "grad_norm": 18.562543869018555, "t": 1793806869.0323617} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16040.442222288906, "train_tokens": 7125.0, "train_token_mean_nll": 2.2512901364616007, "grad_norm": 15.010476112365723, "t": 1793806869.0330336} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17338.272046174134, "train_tokens": 7125.0, "train_token_mean_nll": 2.4334416906911063, "grad_norm": 30.708040237426758, "t": 1793806869.0336938} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17303.760951976477, "train_tokens": 7125.0, "train_token_mean_nll": 2.428598028347576, "grad_norm": 30.686674118041992, "t": 1793806869.0351696} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17061.589607350714, "train_tokens": 7125.0, "train_token_mean_nll": 2.3946090676983456, "grad_norm": 28.975685119628906, "t": 1793806869.140106} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 16280.149799555682, "train_tokens": 6823.0, "train_token_mean_nll": 2.386069148403295, "grad_norm": 25.332393646240234, "t": 1793806883.811886} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15811.410710881548, "train_tokens": 6823.0, "train_token_mean_nll": 2.3173692966263446, "grad_norm": 16.46901512145996, "t": 1793806884.975112} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15758.638896597993, "train_tokens": 6823.0, "train_token_mean_nll": 2.309634896174409, "grad_norm": 15.861392974853516, "t": 1793806884.977813} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 17042.73772012467, "train_tokens": 6823.0, "train_token_mean_nll": 2.497836394566125, "grad_norm": 34.18380355834961, "t": 1793806885.0375056} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16986.03489195498, "train_tokens": 6823.0, "train_token_mean_nll": 2.4895258525509276, "grad_norm": 33.69156265258789, "t": 1793806885.1731875} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16647.913463492627, "train_tokens": 6823.0, "train_token_mean_nll": 2.439969729370164, "grad_norm": 29.525903701782227, "t": 1793806885.1739745} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13580.255112737234, "train_tokens": 6097.0, "train_token_mean_nll": 2.2273667562304795, "grad_norm": 32.73154830932617, "t": 1793806899.7576284} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13277.746270467966, "train_tokens": 6097.0, "train_token_mean_nll": 2.1777507414249575, "grad_norm": 16.67542839050293, "t": 1793806900.8971477} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13268.112707403518, "train_tokens": 6097.0, "train_token_mean_nll": 2.176170691717815, "grad_norm": 20.12318229675293, "t": 1793806900.9823613} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 14451.46727192251, "train_tokens": 6097.0, "train_token_mean_nll": 2.37025869639536, "grad_norm": 45.670440673828125, "t": 1793806900.983211} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 14371.813969898934, "train_tokens": 6097.0, "train_token_mean_nll": 2.357194352943896, "grad_norm": 45.65346908569336, "t": 1793806900.98394} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 13926.491926578112, "train_tokens": 6097.0, "train_token_mean_nll": 2.2841548182020848, "grad_norm": 40.10542297363281, "t": 1793806900.9846344} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 13236.185357397413, "train_tokens": 6602.0, "train_token_mean_nll": 2.0048750920020315, "grad_norm": 20.72406768798828, "t": 1793806918.545974} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 13013.10430810258, "train_tokens": 6602.0, "train_token_mean_nll": 1.9710851723875462, "grad_norm": 15.478771209716797, "t": 1793806918.5468214} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 12952.49655641986, "train_tokens": 6602.0, "train_token_mean_nll": 1.9619049615904058, "grad_norm": 14.910623550415039, "t": 1793806918.865456} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 14375.543604104683, "train_tokens": 6602.0, "train_token_mean_nll": 2.177452833096741, "grad_norm": 34.624576568603516, "t": 1793806918.868463} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 14259.215292806693, "train_tokens": 6602.0, "train_token_mean_nll": 2.159832670828036, "grad_norm": 33.9682731628418, "t": 1793806918.8699138} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 13645.09619822449, "train_tokens": 6602.0, "train_token_mean_nll": 2.0668125110912587, "grad_norm": 27.013469696044922, "t": 1793806918.8729172} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13823.034207487566, "train_tokens": 6404.0, "train_token_mean_nll": 2.1585000323996826, "grad_norm": 19.577598571777344, "t": 1793806930.5047617} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13696.152499115224, "train_tokens": 6404.0, "train_token_mean_nll": 2.138687148518929, "grad_norm": 18.492868423461914, "t": 1793806930.5887098} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13563.28662414201, "train_tokens": 6404.0, "train_token_mean_nll": 2.1179398226330437, "grad_norm": 14.890275001525879, "t": 1793806930.5894861} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14840.724842586258, "train_tokens": 6404.0, "train_token_mean_nll": 2.3174148723588783, "grad_norm": 54.05302810668945, "t": 1793806930.5901427} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14714.44052014436, "train_tokens": 6404.0, "train_token_mean_nll": 2.2976952717277266, "grad_norm": 54.43256759643555, "t": 1793806930.590785} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14103.21794776627, "train_tokens": 6404.0, "train_token_mean_nll": 2.2022513972152202, "grad_norm": 30.259265899658203, "t": 1793806931.0878103} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10847.669104697601, "train_tokens": 5225.0, "train_token_mean_nll": 2.0761089195593496, "grad_norm": 23.989898681640625, "t": 1793806937.0296242} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10795.497054147803, "train_tokens": 5225.0, "train_token_mean_nll": 2.0661238381144122, "grad_norm": 17.562929153442383, "t": 1793806937.964223} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10705.763415693404, "train_tokens": 5225.0, "train_token_mean_nll": 2.0489499360178764, "grad_norm": 14.842544555664062, "t": 1793806938.0895112} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11875.908706777205, "train_tokens": 5225.0, "train_token_mean_nll": 2.2729011878999437, "grad_norm": 42.765296936035156, "t": 1793806938.0903} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11736.548690408665, "train_tokens": 5225.0, "train_token_mean_nll": 2.2462294144322805, "grad_norm": 42.29763412475586, "t": 1793806938.091045} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11142.1092292565, "train_tokens": 5225.0, "train_token_mean_nll": 2.1324610965084214, "grad_norm": 29.453683853149414, "t": 1793806938.112605} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14695.295840789118, "train_tokens": 7976.0, "train_token_mean_nll": 1.8424392979926176, "grad_norm": 17.150331497192383, "t": 1793806953.2660854} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14606.416106723194, "train_tokens": 7976.0, "train_token_mean_nll": 1.83129590104353, "grad_norm": 15.931938171386719, "t": 1793806954.4646697} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14492.830325416824, "train_tokens": 7976.0, "train_token_mean_nll": 1.8170549555437343, "grad_norm": 13.477216720581055, "t": 1793806954.46626} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 15919.205798916166, "train_tokens": 7976.0, "train_token_mean_nll": 1.9958883900346247, "grad_norm": 34.0655632019043, "t": 1793806954.4711978} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 15707.116493724314, "train_tokens": 7976.0, "train_token_mean_nll": 1.9692974540777726, "grad_norm": 31.981956481933594, "t": 1793806954.4720469} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 14956.44908272813, "train_tokens": 7976.0, "train_token_mean_nll": 1.8751816803821626, "grad_norm": 21.661304473876953, "t": 1793806954.4729135} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10364.194707402803, "train_tokens": 5826.0, "train_token_mean_nll": 1.7789554938899421, "grad_norm": 17.12930679321289, "t": 1793806965.9456027} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10303.997184970507, "train_tokens": 5826.0, "train_token_mean_nll": 1.76862292910582, "grad_norm": 15.919819831848145, "t": 1793806967.1548018} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10237.639234138718, "train_tokens": 5826.0, "train_token_mean_nll": 1.7572329615754751, "grad_norm": 14.663389205932617, "t": 1793806967.1562252} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 11381.250552982616, "train_tokens": 5826.0, "train_token_mean_nll": 1.9535273863684546, "grad_norm": 40.144073486328125, "t": 1793806967.1572418} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 11146.839263576589, "train_tokens": 5826.0, "train_token_mean_nll": 1.9132920122857173, "grad_norm": 35.10628890991211, "t": 1793806967.1579926} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 10500.843499431587, "train_tokens": 5826.0, "train_token_mean_nll": 1.8024104873723974, "grad_norm": 20.295942306518555, "t": 1793806967.1587152} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13183.991867304323, "train_tokens": 6074.0, "train_token_mean_nll": 2.170561716711281, "grad_norm": 17.98400115966797, "t": 1793806982.3171413} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13114.59991995226, "train_tokens": 6074.0, "train_token_mean_nll": 2.159137293373767, "grad_norm": 16.593881607055664, "t": 1793806983.5559995} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13011.45053314069, "train_tokens": 6074.0, "train_token_mean_nll": 2.1421551750313945, "grad_norm": 15.233773231506348, "t": 1793806983.556927} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 14259.83827587634, "train_tokens": 6074.0, "train_token_mean_nll": 2.3476849318202735, "grad_norm": 38.54907989501953, "t": 1793806983.5576677} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13974.554198818427, "train_tokens": 6074.0, "train_token_mean_nll": 2.3007168585476503, "grad_norm": 34.685691833496094, "t": 1793806983.5584135} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13262.53251635432, "train_tokens": 6074.0, "train_token_mean_nll": 2.1834923471113465, "grad_norm": 19.349992752075195, "t": 1793806983.5591455} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10806.740294832764, "train_tokens": 5144.0, "train_token_mean_nll": 2.100843758715545, "grad_norm": 19.475004196166992, "t": 1793806993.9953783} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10703.953384687964, "train_tokens": 5144.0, "train_token_mean_nll": 2.0808618554992155, "grad_norm": 16.857419967651367, "t": 1793806993.99609} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10640.070008498069, "train_tokens": 5144.0, "train_token_mean_nll": 2.0684428476862498, "grad_norm": 16.884830474853516, "t": 1793806993.9967127} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 11808.218041844744, "train_tokens": 5144.0, "train_token_mean_nll": 2.2955322787412022, "grad_norm": 38.80863952636719, "t": 1793806993.9972906} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 11521.139891392553, "train_tokens": 5144.0, "train_token_mean_nll": 2.2397239291198585, "grad_norm": 33.50014877319336, "t": 1793806993.9978828} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 10892.12968019478, "train_tokens": 5144.0, "train_token_mean_nll": 2.1174435614686584, "grad_norm": 20.230663299560547, "t": 1793806993.998667} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10681.13025925465, "train_tokens": 4753.0, "train_token_mean_nll": 2.247239692668767, "grad_norm": 20.843219757080078, "t": 1793807011.000959} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10561.472730850564, "train_tokens": 4753.0, "train_token_mean_nll": 2.222064534157493, "grad_norm": 17.568204879760742, "t": 1793807011.1297162} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10496.53366854815, "train_tokens": 4753.0, "train_token_mean_nll": 2.2084017817269412, "grad_norm": 16.567981719970703, "t": 1793807011.1303687} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 11850.029060094901, "train_tokens": 4753.0, "train_token_mean_nll": 2.4931683273921523, "grad_norm": 47.52523422241211, "t": 1793807011.1309757} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 11475.902121548723, "train_tokens": 4753.0, "train_token_mean_nll": 2.4144544753942188, "grad_norm": 43.75772476196289, "t": 1793807011.1315608} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 10731.134988472939, "train_tokens": 4753.0, "train_token_mean_nll": 2.2577603594514914, "grad_norm": 20.51249122619629, "t": 1793807011.3765917} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 14108.830880859321, "train_tokens": 6492.0, "train_token_mean_nll": 2.1732641529358165, "grad_norm": 14.498827934265137, "t": 1793807027.2914538} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13942.072663065755, "train_tokens": 6492.0, "train_token_mean_nll": 2.14757742807544, "grad_norm": 12.386487007141113, "t": 1793807027.2952645} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13883.884194455175, "train_tokens": 6492.0, "train_token_mean_nll": 2.138614324469374, "grad_norm": 11.534483909606934, "t": 1793807027.2965171} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 15443.859060571836, "train_tokens": 6492.0, "train_token_mean_nll": 2.3789062015668265, "grad_norm": 44.12393569946289, "t": 1793807028.854774} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 15005.91005092743, "train_tokens": 6492.0, "train_token_mean_nll": 2.3114464034084152, "grad_norm": 37.6226921081543, "t": 1793807029.0480356} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 14188.39060694955, "train_tokens": 6492.0, "train_token_mean_nll": 2.185519193923221, "grad_norm": 15.11783504486084, "t": 1793807029.0489244} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14402.971291461548, "train_tokens": 7021.0, "train_token_mean_nll": 2.0514130880873878, "grad_norm": 18.052053451538086, "t": 1793807043.6609478} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14274.167139014713, "train_tokens": 7021.0, "train_token_mean_nll": 2.033067531550308, "grad_norm": 15.796545028686523, "t": 1793807043.8301861} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14221.866632447565, "train_tokens": 7021.0, "train_token_mean_nll": 2.0256183780725774, "grad_norm": 14.779635429382324, "t": 1793807044.3865325} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 15684.095206111284, "train_tokens": 7021.0, "train_token_mean_nll": 2.2338833793065493, "grad_norm": 37.569095611572266, "t": 1793807044.3873696} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 15178.751421285851, "train_tokens": 7021.0, "train_token_mean_nll": 2.1619073381691853, "grad_norm": 32.6380729675293, "t": 1793807044.3881013} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 14419.60882378775, "train_tokens": 7021.0, "train_token_mean_nll": 2.053782769375837, "grad_norm": 17.336544036865234, "t": 1793807044.38882} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13725.07269409944, "train_tokens": 6222.0, "train_token_mean_nll": 2.205894036338708, "grad_norm": 16.167739868164062, "t": 1793807052.8105054} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13647.023632788434, "train_tokens": 6222.0, "train_token_mean_nll": 2.1933499891977553, "grad_norm": 14.377480506896973, "t": 1793807052.8953211} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13628.406687317784, "train_tokens": 6222.0, "train_token_mean_nll": 2.190357873242974, "grad_norm": 14.75197696685791, "t": 1793807052.8960404} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 14807.657753197302, "train_tokens": 6222.0, "train_token_mean_nll": 2.379887134875812, "grad_norm": 59.94126892089844, "t": 1793807053.8170931} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 14351.200037162635, "train_tokens": 6222.0, "train_token_mean_nll": 2.3065252390168167, "grad_norm": 47.07252502441406, "t": 1793807053.8178146} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 13749.65663399415, "train_tokens": 6222.0, "train_token_mean_nll": 2.2098451677907667, "grad_norm": 15.917436599731445, "t": 1793807054.0845635} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11951.377888598114, "train_tokens": 5713.0, "train_token_mean_nll": 2.091961821914601, "grad_norm": 18.96132469177246, "t": 1793807062.4505775} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11841.29973580905, "train_tokens": 5713.0, "train_token_mean_nll": 2.0726938098738055, "grad_norm": 16.99378776550293, "t": 1793807062.4540067} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11791.065719682469, "train_tokens": 5713.0, "train_token_mean_nll": 2.0639008786421265, "grad_norm": 15.41885757446289, "t": 1793807062.4546754} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 13274.694277544528, "train_tokens": 5713.0, "train_token_mean_nll": 2.3235943072894325, "grad_norm": 40.54396057128906, "t": 1793807063.5744817} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 12703.320290374366, "train_tokens": 5713.0, "train_token_mean_nll": 2.2235813566207536, "grad_norm": 34.33525848388672, "t": 1793807063.5753837} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 11991.064191757217, "train_tokens": 5713.0, "train_token_mean_nll": 2.098908487967306, "grad_norm": 19.169414520263672, "t": 1793807063.5919273} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12888.228742820891, "train_tokens": 6187.0, "train_token_mean_nll": 2.0831143919219155, "grad_norm": 15.685012817382812, "t": 1793807078.3311572} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12805.04846230615, "train_tokens": 6187.0, "train_token_mean_nll": 2.069670027849709, "grad_norm": 14.624584197998047, "t": 1793807078.3320348} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12787.988333540789, "train_tokens": 6187.0, "train_token_mean_nll": 2.0669126125005315, "grad_norm": 13.436037063598633, "t": 1793807078.3326952} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 14097.89656875761, "train_tokens": 6187.0, "train_token_mean_nll": 2.2786320621880733, "grad_norm": 43.680763244628906, "t": 1793807078.3333585} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 13539.186288826028, "train_tokens": 6187.0, "train_token_mean_nll": 2.18832815400453, "grad_norm": 29.624189376831055, "t": 1793807078.3340187} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 12918.438813878827, "train_tokens": 6187.0, "train_token_mean_nll": 2.087997222220596, "grad_norm": 15.488966941833496, "t": 1793807078.3346324} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15213.437719961865, "train_tokens": 6765.0, "train_token_mean_nll": 2.2488451914208225, "grad_norm": 14.401437759399414, "t": 1793807084.7815} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15113.972029283255, "train_tokens": 6765.0, "train_token_mean_nll": 2.2341422068415753, "grad_norm": 13.372977256774902, "t": 1793807085.4405317} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15080.984977331616, "train_tokens": 6765.0, "train_token_mean_nll": 2.229266072037194, "grad_norm": 12.338144302368164, "t": 1793807085.4424894} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 16657.64988686487, "train_tokens": 6765.0, "train_token_mean_nll": 2.4623281429216366, "grad_norm": 32.93149185180664, "t": 1793807085.4432216} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 15999.56441716446, "train_tokens": 6765.0, "train_token_mean_nll": 2.3650501725298536, "grad_norm": 26.77382469177246, "t": 1793807085.5954924} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 15273.434363064178, "train_tokens": 6765.0, "train_token_mean_nll": 2.257713874806235, "grad_norm": 14.811939239501953, "t": 1793807085.5973163} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12155.798190876225, "train_tokens": 5786.0, "train_token_mean_nll": 2.100898408378193, "grad_norm": 18.53158187866211, "t": 1793807091.415256} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12099.467739654676, "train_tokens": 5786.0, "train_token_mean_nll": 2.091162761779239, "grad_norm": 17.41683006286621, "t": 1793807091.4300182} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12074.47016700547, "train_tokens": 5786.0, "train_token_mean_nll": 2.086842407017883, "grad_norm": 16.126148223876953, "t": 1793807092.5000925} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 13366.95599189328, "train_tokens": 5786.0, "train_token_mean_nll": 2.3102239875377255, "grad_norm": 37.27796936035156, "t": 1793807092.5012746} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12735.843593898844, "train_tokens": 5786.0, "train_token_mean_nll": 2.201148218786527, "grad_norm": 30.17605972290039, "t": 1793807092.5019357} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12176.150864735253, "train_tokens": 5786.0, "train_token_mean_nll": 2.1044159807700056, "grad_norm": 19.220016479492188, "t": 1793807092.5064795} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10726.076091373006, "train_tokens": 4783.0, "train_token_mean_nll": 2.242541520253608, "grad_norm": 16.973051071166992, "t": 1793807142.9352531} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10665.039485977431, "train_tokens": 4783.0, "train_token_mean_nll": 2.229780365038142, "grad_norm": 16.330873489379883, "t": 1793807143.9077206} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10654.611535157215, "train_tokens": 4783.0, "train_token_mean_nll": 2.227600153702115, "grad_norm": 14.236762046813965, "t": 1793807143.9106557} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 11927.938691791178, "train_tokens": 4783.0, "train_token_mean_nll": 2.4938195048695753, "grad_norm": 40.90174102783203, "t": 1793807143.9116418} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 11278.324081838091, "train_tokens": 4783.0, "train_token_mean_nll": 2.3580021078482316, "grad_norm": 29.522212982177734, "t": 1793807143.913005} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 10757.502385613505, "train_tokens": 4783.0, "train_token_mean_nll": 2.249111935106315, "grad_norm": 17.305389404296875, "t": 1793807143.914309} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15473.27451386297, "train_tokens": 7466.0, "train_token_mean_nll": 2.0724985954812443, "grad_norm": 13.814358711242676, "t": 1793807150.8592618} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15416.629347988975, "train_tokens": 7466.0, "train_token_mean_nll": 2.0649115119192305, "grad_norm": 12.939779281616211, "t": 1793807151.60338} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15385.689074758648, "train_tokens": 7466.0, "train_token_mean_nll": 2.0607673553119, "grad_norm": 12.108113288879395, "t": 1793807151.604909} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 16618.92750087411, "train_tokens": 7466.0, "train_token_mean_nll": 2.2259479642210165, "grad_norm": 27.9526424407959, "t": 1793807151.6057467} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15938.1729739212, "train_tokens": 7466.0, "train_token_mean_nll": 2.134767341805679, "grad_norm": 19.59671401977539, "t": 1793807152.550406} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15496.609335428571, "train_tokens": 7466.0, "train_token_mean_nll": 2.075624073858635, "grad_norm": 14.511701583862305, "t": 1793807152.5514307} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10862.301249063035, "train_tokens": 6100.0, "train_token_mean_nll": 1.7807051227972188, "grad_norm": 15.094161987304688, "t": 1793807159.0509946} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10784.608733764695, "train_tokens": 6100.0, "train_token_mean_nll": 1.7679686448794583, "grad_norm": 13.90379524230957, "t": 1793807159.0523498} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10768.664069609204, "train_tokens": 6100.0, "train_token_mean_nll": 1.7653547655097055, "grad_norm": 13.148458480834961, "t": 1793807159.664236} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 12008.411183115133, "train_tokens": 6100.0, "train_token_mean_nll": 1.968591997231989, "grad_norm": 52.25935745239258, "t": 1793807159.665782} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 11358.120186160377, "train_tokens": 6100.0, "train_token_mean_nll": 1.861986915763996, "grad_norm": 21.971466064453125, "t": 1793807159.6674967} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 10908.278381663342, "train_tokens": 6100.0, "train_token_mean_nll": 1.7882423576497282, "grad_norm": 15.582797050476074, "t": 1793807159.6683464} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12403.65662628372, "train_tokens": 6108.0, "train_token_mean_nll": 2.0307230887825343, "grad_norm": 13.236311912536621, "t": 1793807167.2210283} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12334.458984294602, "train_tokens": 6108.0, "train_token_mean_nll": 2.0193940707751477, "grad_norm": 12.585439682006836, "t": 1793807167.2218888} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12286.450024584507, "train_tokens": 6108.0, "train_token_mean_nll": 2.011534057725034, "grad_norm": 11.786494255065918, "t": 1793807167.2225893} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 13653.250074582607, "train_tokens": 6108.0, "train_token_mean_nll": 2.2353061680718085, "grad_norm": 35.24686813354492, "t": 1793807167.6847994} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12902.252481383817, "train_tokens": 6108.0, "train_token_mean_nll": 2.1123530585107755, "grad_norm": 21.328876495361328, "t": 1793807167.6855948} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12433.58177035556, "train_tokens": 6108.0, "train_token_mean_nll": 2.0356224247471446, "grad_norm": 13.612707138061523, "t": 1793807167.6863103} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11294.307668420244, "train_tokens": 5073.0, "train_token_mean_nll": 2.2263567254918675, "grad_norm": 16.974567413330078, "t": 1793807182.5165174} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11233.402735717924, "train_tokens": 5073.0, "train_token_mean_nll": 2.214351022219185, "grad_norm": 15.873043060302734, "t": 1793807182.5183673} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11218.070206392013, "train_tokens": 5073.0, "train_token_mean_nll": 2.2113286430892987, "grad_norm": 14.458547592163086, "t": 1793807182.519055} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 12474.516706233126, "train_tokens": 5073.0, "train_token_mean_nll": 2.459001913312266, "grad_norm": 36.80165100097656, "t": 1793807182.5196443} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11796.553787786908, "train_tokens": 5073.0, "train_token_mean_nll": 2.3253604943400172, "grad_norm": 25.88098907470703, "t": 1793807182.5202405} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11311.274773497167, "train_tokens": 5073.0, "train_token_mean_nll": 2.2297013154932324, "grad_norm": 17.713775634765625, "t": 1793807182.874925} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13513.923268480776, "train_tokens": 6392.0, "train_token_mean_nll": 2.114193252265453, "grad_norm": 17.391315460205078, "t": 1793807195.89869} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13457.625676076437, "train_tokens": 6392.0, "train_token_mean_nll": 2.105385744067027, "grad_norm": 16.207664489746094, "t": 1793807195.8994703} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13412.551182121693, "train_tokens": 6392.0, "train_token_mean_nll": 2.09833403975621, "grad_norm": 14.889500617980957, "t": 1793807195.9012141} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 14862.965221948092, "train_tokens": 6392.0, "train_token_mean_nll": 2.3252448720194137, "grad_norm": 36.680294036865234, "t": 1793807195.926418} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 14005.124746641337, "train_tokens": 6392.0, "train_token_mean_nll": 2.1910395410890704, "grad_norm": 22.847286224365234, "t": 1793807195.9302907} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 13542.070979773998, "train_tokens": 6392.0, "train_token_mean_nll": 2.1185968366354815, "grad_norm": 17.334835052490234, "t": 1793807195.930995} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14646.840180091964, "train_tokens": 7271.0, "train_token_mean_nll": 2.014418949263095, "grad_norm": 16.955463409423828, "t": 1793807205.340429} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14594.706048482854, "train_tokens": 7271.0, "train_token_mean_nll": 2.0072488032571663, "grad_norm": 16.438003540039062, "t": 1793807205.7744792} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14573.299226828129, "train_tokens": 7271.0, "train_token_mean_nll": 2.004304666047054, "grad_norm": 15.015161514282227, "t": 1793807205.7785177} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 16013.604462400015, "train_tokens": 7271.0, "train_token_mean_nll": 2.202393682079496, "grad_norm": 34.052940368652344, "t": 1793807205.7793536} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 15169.665042584706, "train_tokens": 7271.0, "train_token_mean_nll": 2.086324445411182, "grad_norm": 24.445341110229492, "t": 1793807205.780668} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 14651.35517154159, "train_tokens": 7271.0, "train_token_mean_nll": 2.015039908065134, "grad_norm": 17.270490646362305, "t": 1793807205.781796} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11176.536965832287, "train_tokens": 5476.0, "train_token_mean_nll": 2.0410038286764585, "grad_norm": 15.46433162689209, "t": 1793807213.277006} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11133.114354119969, "train_tokens": 5476.0, "train_token_mean_nll": 2.0330742063769116, "grad_norm": 14.543343544006348, "t": 1793807213.3927188} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11116.599661703318, "train_tokens": 5476.0, "train_token_mean_nll": 2.030058375037129, "grad_norm": 13.59369945526123, "t": 1793807213.3947117} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 12233.155264183288, "train_tokens": 5476.0, "train_token_mean_nll": 2.2339582293979707, "grad_norm": 31.012235641479492, "t": 1793807213.3953915} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11564.813929192098, "train_tokens": 5476.0, "train_token_mean_nll": 2.1119090447757665, "grad_norm": 21.535371780395508, "t": 1793807213.3968632} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11191.522643884382, "train_tokens": 5476.0, "train_token_mean_nll": 2.0437404389854605, "grad_norm": 16.153217315673828, "t": 1793807213.3980162} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16851.4304870572, "train_tokens": 7466.0, "train_token_mean_nll": 2.25708953751101, "grad_norm": 13.341506958007812, "t": 1793807220.1743355} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16813.36582694909, "train_tokens": 7466.0, "train_token_mean_nll": 2.251991136746463, "grad_norm": 11.841224670410156, "t": 1793807221.2976797} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16809.55531064523, "train_tokens": 7466.0, "train_token_mean_nll": 2.2514807541716086, "grad_norm": 11.318297386169434, "t": 1793807221.2985883} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 18175.197815488515, "train_tokens": 7466.0, "train_token_mean_nll": 2.4343956356132486, "grad_norm": 51.94609069824219, "t": 1793807221.3001337} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 17286.40073209116, "train_tokens": 7466.0, "train_token_mean_nll": 2.315349682841034, "grad_norm": 21.456388473510742, "t": 1793807221.3009436} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 16866.019709192045, "train_tokens": 7466.0, "train_token_mean_nll": 2.25904362566194, "grad_norm": 13.837346076965332, "t": 1793807221.301747} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11659.1700762859, "train_tokens": 5656.0, "train_token_mean_nll": 2.0613808479996285, "grad_norm": 14.554632186889648, "t": 1793807231.1923351} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11621.979436219208, "train_tokens": 5656.0, "train_token_mean_nll": 2.0548054165875542, "grad_norm": 13.44259262084961, "t": 1793807231.1943202} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11589.1320879003, "train_tokens": 5656.0, "train_token_mean_nll": 2.048997893900336, "grad_norm": 12.966280937194824, "t": 1793807231.1961668} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 12830.256288302038, "train_tokens": 5656.0, "train_token_mean_nll": 2.2684328656828217, "grad_norm": 35.13819122314453, "t": 1793807231.197643} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11989.537803857449, "train_tokens": 5656.0, "train_token_mean_nll": 2.119790983708884, "grad_norm": 19.449567794799805, "t": 1793807231.1986375} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11655.26100863334, "train_tokens": 5656.0, "train_token_mean_nll": 2.0606897115688367, "grad_norm": 15.423412322998047, "t": 1793807231.2004678} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9923.523370532424, "train_tokens": 5681.0, "train_token_mean_nll": 1.7467916512114812, "grad_norm": 16.340787887573242, "t": 1793807238.189032} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9863.108545446881, "train_tokens": 5681.0, "train_token_mean_nll": 1.7361571106225808, "grad_norm": 14.302412033081055, "t": 1793807238.1938517} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9851.731905285336, "train_tokens": 5681.0, "train_token_mean_nll": 1.734154533583055, "grad_norm": 14.114188194274902, "t": 1793807239.5639937} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 11165.96021599389, "train_tokens": 5681.0, "train_token_mean_nll": 1.9654920288670814, "grad_norm": 34.59947967529297, "t": 1793807239.564797} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 10307.306050806588, "train_tokens": 5681.0, "train_token_mean_nll": 1.8143471309288133, "grad_norm": 21.50619125366211, "t": 1793807239.5655088} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 9920.486383431633, "train_tokens": 5681.0, "train_token_mean_nll": 1.7462570645012556, "grad_norm": 17.562158584594727, "t": 1793807239.5662096} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11708.545796620783, "train_tokens": 6193.0, "train_token_mean_nll": 1.8906096878121723, "grad_norm": 15.370129585266113, "t": 1793807246.254719} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11659.791334322828, "train_tokens": 6193.0, "train_token_mean_nll": 1.882737176541713, "grad_norm": 13.31694221496582, "t": 1793807246.255438} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11630.978972558047, "train_tokens": 6193.0, "train_token_mean_nll": 1.8780847686998299, "grad_norm": 12.950379371643066, "t": 1793807246.3322747} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 12906.162799974629, "train_tokens": 6193.0, "train_token_mean_nll": 2.0839920555424882, "grad_norm": 35.40779495239258, "t": 1793807246.3607836} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 12047.943462257192, "train_tokens": 6193.0, "train_token_mean_nll": 1.94541312163042, "grad_norm": 20.95992088317871, "t": 1793807246.3614786} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 11705.112133517772, "train_tokens": 6193.0, "train_token_mean_nll": 1.8900552451990589, "grad_norm": 15.58911418914795, "t": 1793807246.3621027} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10278.108889411626, "train_tokens": 4524.0, "train_token_mean_nll": 2.271907358402216, "grad_norm": 16.94392967224121, "t": 1793807253.3249772} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10227.1066939702, "train_tokens": 4524.0, "train_token_mean_nll": 2.260633663565473, "grad_norm": 15.119022369384766, "t": 1793807253.3259177} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10214.091410497273, "train_tokens": 4524.0, "train_token_mean_nll": 2.2577567220374166, "grad_norm": 14.350902557373047, "t": 1793807253.3267343} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 11312.27930186568, "train_tokens": 4524.0, "train_token_mean_nll": 2.5005038244619096, "grad_norm": 37.80747985839844, "t": 1793807253.6253927} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10557.51966512499, "train_tokens": 4524.0, "train_token_mean_nll": 2.333669245164675, "grad_norm": 22.196849822998047, "t": 1793807253.6262589} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10268.35049868228, "train_tokens": 4524.0, "train_token_mean_nll": 2.2697503312737135, "grad_norm": 17.271696090698242, "t": 1793807253.6269858} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11987.034162489408, "train_tokens": 5628.0, "train_token_mean_nll": 2.1298923529654243, "grad_norm": 20.308155059814453, "t": 1793807260.1545644} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11945.574593909369, "train_tokens": 5628.0, "train_token_mean_nll": 2.1225256918815507, "grad_norm": 18.203134536743164, "t": 1793807260.1554823} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11937.740298523151, "train_tokens": 5628.0, "train_token_mean_nll": 2.121133670668648, "grad_norm": 15.223184585571289, "t": 1793807261.1621516} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 13106.661567205636, "train_tokens": 5628.0, "train_token_mean_nll": 2.3288311242369644, "grad_norm": 40.775306701660156, "t": 1793807261.1651504} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 12226.39864468674, "train_tokens": 5628.0, "train_token_mean_nll": 2.172423355488049, "grad_norm": 21.11092758178711, "t": 1793807261.165787} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 11986.546933379108, "train_tokens": 5628.0, "train_token_mean_nll": 2.1298057806288395, "grad_norm": 18.03183937072754, "t": 1793807261.2893882} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13051.219598203414, "train_tokens": 6703.0, "train_token_mean_nll": 1.947071400597257, "grad_norm": 12.633360862731934, "t": 1793807269.1044576} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13018.053212899204, "train_tokens": 6703.0, "train_token_mean_nll": 1.9421234093539017, "grad_norm": 11.461623191833496, "t": 1793807269.1053855} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13010.304633510475, "train_tokens": 6703.0, "train_token_mean_nll": 1.9409674225735456, "grad_norm": 11.391105651855469, "t": 1793807269.1062374} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 14287.909756901377, "train_tokens": 6703.0, "train_token_mean_nll": 2.1315694102493477, "grad_norm": 35.919803619384766, "t": 1793807269.1070538} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13320.298720790366, "train_tokens": 6703.0, "train_token_mean_nll": 1.9872144891526728, "grad_norm": 15.085948944091797, "t": 1793807269.5573106} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13047.809562042843, "train_tokens": 6703.0, "train_token_mean_nll": 1.9465626677670957, "grad_norm": 13.176280975341797, "t": 1793807269.5582352} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11525.75543262406, "train_tokens": 5733.0, "train_token_mean_nll": 2.010423065170776, "grad_norm": 14.885258674621582, "t": 1793807275.243452} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11518.997116183555, "train_tokens": 5733.0, "train_token_mean_nll": 2.009244220509952, "grad_norm": 13.417550086975098, "t": 1793807275.3653831} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11496.361896778335, "train_tokens": 5733.0, "train_token_mean_nll": 2.0052959875768943, "grad_norm": 12.86583423614502, "t": 1793807276.2447782} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 12498.494114597226, "train_tokens": 5733.0, "train_token_mean_nll": 2.1800966535142554, "grad_norm": 39.31755828857422, "t": 1793807276.3455489} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11730.112771229771, "train_tokens": 5733.0, "train_token_mean_nll": 2.0460688594505094, "grad_norm": 17.82050895690918, "t": 1793807276.3463168} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11522.34311294888, "train_tokens": 5733.0, "train_token_mean_nll": 2.0098278585293703, "grad_norm": 15.277654647827148, "t": 1793807276.3469832} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14732.720515840147, "train_tokens": 6763.0, "train_token_mean_nll": 2.1784297672394124, "grad_norm": 12.289765357971191, "t": 1793807283.6404986} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14713.512183447165, "train_tokens": 6763.0, "train_token_mean_nll": 2.1755895583982205, "grad_norm": 11.005742073059082, "t": 1793807283.641307} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14686.218235055247, "train_tokens": 6763.0, "train_token_mean_nll": 2.171553783092599, "grad_norm": 10.472980499267578, "t": 1793807283.6462653} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 15981.723145945023, "train_tokens": 6763.0, "train_token_mean_nll": 2.363111510564102, "grad_norm": 29.51869010925293, "t": 1793807283.6485302} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 15042.552161142876, "train_tokens": 6763.0, "train_token_mean_nll": 2.2242425197608866, "grad_norm": 15.391060829162598, "t": 1793807283.6500485} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 14715.928740717363, "train_tokens": 6763.0, "train_token_mean_nll": 2.1759468787102416, "grad_norm": 12.578240394592285, "t": 1793807283.6525922} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10471.476814507296, "train_tokens": 5394.0, "train_token_mean_nll": 1.9413193946064693, "grad_norm": 18.36554718017578, "t": 1793807309.6511145} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10426.334948317639, "train_tokens": 5394.0, "train_token_mean_nll": 1.93295049097472, "grad_norm": 16.627870559692383, "t": 1793807310.7729025} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10416.002235072576, "train_tokens": 5394.0, "train_token_mean_nll": 1.9310348971213527, "grad_norm": 15.40526294708252, "t": 1793807310.7962258} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 11426.0211745832, "train_tokens": 5394.0, "train_token_mean_nll": 2.118283495473341, "grad_norm": 38.127952575683594, "t": 1793807310.8002307} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10672.68086386222, "train_tokens": 5394.0, "train_token_mean_nll": 1.9786208498076048, "grad_norm": 20.33489418029785, "t": 1793807310.8027318} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10439.610273374645, "train_tokens": 5394.0, "train_token_mean_nll": 1.9354116190905903, "grad_norm": 18.652708053588867, "t": 1793807310.8036418} {"stage": "train_step", "arm": "sel_adamw_lr5e-05_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8544.389469500911, "train_tokens": 4573.0, "train_token_mean_nll": 1.8684429191998493, "grad_norm": 17.593746185302734, "t": 1793807316.6440628} {"stage": "train_step", "arm": "sel_adamw_lr0.0001_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8525.045670497455, "train_tokens": 4573.0, "train_token_mean_nll": 1.86421291723102, "grad_norm": 15.726753234863281, "t": 1793807316.661013} {"stage": "train_step", "arm": "sel_adamw_lr0.0002_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8523.921878455618, "train_tokens": 4573.0, "train_token_mean_nll": 1.8639671721967237, "grad_norm": 15.235638618469238, "t": 1793807317.6674721} {"stage": "train_step", "arm": "sel_dimuon_lr0.0003_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 9560.027326802394, "train_tokens": 4573.0, "train_token_mean_nll": 2.0905373555220628, "grad_norm": 54.18312072753906, "t": 1793807317.6696866} {"stage": "train_step", "arm": "sel_dimuon_lr0.001_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8713.159033155996, "train_tokens": 4573.0, "train_token_mean_nll": 1.905348574930242, "grad_norm": 20.22059440612793, "t": 1793807317.6704376} {"stage": "train_step", "arm": "sel_dimuon_lr0.003_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8522.63285625221, "train_tokens": 4573.0, "train_token_mean_nll": 1.8636852954848482, "grad_norm": 17.87735366821289, "t": 1793807317.6711183} {"stage": "train_done", "seconds": 494.3076186180115, "steps": 40, "arms": 6, "t": 1793807317.6711478} {"stage": "eval", "arm": "sel_adamw_lr5e-05_s0", "split": "val", "step": 40, "nll_sum": 195324.3961461356, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.0706937086139385, "example_mean": 1.9349720943426238, "per_example": [[157.90014200712085, 104], [783.0602164036245, 423], [280.98192750820454, 219], [1394.1344314457674, 467], [61.898471113612686, 53], [284.98587178799426, 151], [4.549732394421881, 20], [28.63493766432532, 27], [32.73763089979229, 32], [476.6656057405071, 247], [332.06954534545, 223], [687.5053020778596, 280], [1003.2788458392024, 365], [74.79289744261041, 54], [397.5130640793268, 159], [377.6852388933403, 265], [672.1759952688735, 330], [223.23179973321385, 110], [303.1708945791761, 120], [88.20844997759559, 114], [215.23535895551322, 132], [80.43483333737186, 67], [104.56931520647277, 57], [134.80814223980997, 100], [568.0330585694646, 345], [2.1769640590555355, 14], [1265.1850656961578, 788], [1157.8422241015596, 469], [240.14795360406606, 65], [265.7267811154452, 158], [832.4134425181473, 356], [66.47560073934801, 26], [329.61221337725874, 109], [225.17252442562494, 105], [266.20929724056623, 233], [182.448293637819, 69], [132.9309951812029, 61], [105.15586810105378, 86], [275.63338323954304, 105], [223.31588776158424, 88], [1497.1812349184765, 519], [495.1010286444507, 157], [68.51345157416745, 78], [157.8046097191036, 102], [423.4049297356614, 209], [1161.0284661041278, 484], [236.30918341734287, 233], [191.63933874299983, 118], [93.40170497310442, 91], [30.930068399702577, 34], [330.4649422428047, 177], [66.95863596456184, 39], [67.3891617805948, 50], [104.94473685580306, 84], [183.59218402951956, 152], [288.3750498600384, 115], [463.70959283296725, 302], [398.5539683512725, 242], [585.3748516555788, 268], [55.61845555369928, 19], [297.8582037482738, 131], [533.6071210600494, 248], [260.64933423808816, 261], [615.8768883601042, 328], [99.2904896727432, 56], [273.6148444641876, 104], [72.05773595266146, 62], [379.42705979728635, 179], [1546.284556259634, 389], [97.25102942769263, 132], [90.33121191353712, 24], [254.99499809097006, 122], [66.11116799829324, 39], [81.06203717547032, 59], [3.7346215547549946, 18], [223.292569860183, 124], [442.5233021019376, 269], [144.7309275010084, 69], [23.319347586533695, 23], [419.100656105933, 202], [662.6242603461433, 255], [134.49773864349118, 52], [235.4514093377802, 138], [165.21711792281712, 99], [1.0848675041033857, 19], [740.3482729731331, 313], [557.7623518932323, 270], [60.02675342402654, 34], [607.0372274817564, 256], [98.53768466605834, 64], [54.26237441779085, 28], [293.68237266411234, 135], [479.1806252870847, 217], [178.5686823110591, 73], [179.3783591221727, 62], [269.3281528452907, 520], [542.261242165172, 193], [401.0771958925816, 110], [1004.5204808410854, 319], [31.508535581706383, 56], [355.45433551608585, 276], [221.17744564217355, 121], [157.91856292562807, 71], [139.84492987003023, 81], [76.68563102690678, 38], [203.24621679813526, 100], [199.76561391112773, 97], [107.94103434069984, 69], [961.9784764788055, 328], [51.884356591900996, 44], [342.1019377112152, 128], [99.71792296777971, 66], [804.5458155696106, 306], [133.66566581258667, 78], [615.1953697583813, 242], [446.0058452656631, 201], [75.56276615634488, 52], [54.55790304072252, 40], [800.5624135669641, 246], [271.4703770992137, 125], [8.68518826140189, 89], [937.9645225339118, 446], [131.52149805318368, 106], [450.20640424883095, 200], [556.8743592903375, 266], [574.4935113210449, 288], [158.94896382571096, 106], [237.87246975677044, 86], [666.2101271372376, 341], [618.5061047314066, 258], [75.32765708200895, 52], [849.6123527646414, 448], [368.66194669566175, 168], [21.778631517916438, 47], [34.054556167793635, 43], [1233.644442969482, 476], [97.24334463855485, 104], [150.7385004009484, 106], [219.59623847163914, 137], [1053.3769942416839, 491], [14.983840659471753, 20], [115.43805185677593, 66], [84.88964023099834, 54], [159.09606360970065, 92], [86.61291440299829, 42], [744.9763958180429, 425], [714.1997584694836, 231], [117.33831801009364, 96], [999.4383520512492, 417], [225.50443621986778, 96], [1406.6583113114611, 582], [292.6387353673308, 146], [95.72494657789503, 98], [1464.529173289222, 485], [78.14096170453558, 45], [599.7618786394669, 190], [46.84293190712196, 116], [4.062301743181706, 6], [161.31364648748604, 166], [337.3554702373076, 141], [431.88542114036954, 171], [991.4896147851323, 491], [10.372635469113447, 29], [139.78521715047827, 40], [708.3591137402836, 308], [279.9324613747167, 90], [216.26148769765405, 93], [200.70157831201868, 124], [177.14221776847262, 106], [350.0275818969985, 330], [42.61005528235228, 43], [229.85555321217907, 200], [103.16643336375819, 69], [275.6305633482507, 477], [60.05945851941124, 42], [308.65701022969006, 80], [206.69276642245677, 148], [559.7656449959868, 327], [517.4063095098245, 231], [1507.2748588040413, 422], [6.298911598851191, 10], [320.0671026434593, 299], [489.8720827665675, 215], [250.74103648787968, 130], [64.33103976664643, 128], [334.66239078033686, 222], [269.91532767910303, 374], [1127.8912566334475, 489], [154.12937587600754, 88], [237.05052444923422, 85], [1016.878508073587, 422], [85.14707080196968, 51], [316.9043636488027, 253], [758.5451058838371, 368], [326.36602683079036, 245], [204.13814024167868, 130], [189.46876493336458, 77], [1018.1115492244717, 408], [665.0985905617563, 268], [823.2241555014625, 258], [477.65408781166843, 212], [230.17461864486904, 103], [116.1229037216176, 92], [144.641526966745, 94], [161.56838105984207, 86], [150.0779491538633, 66], [321.3630431477641, 135], [249.68015561330685, 156], [473.9040825647389, 150], [128.62694009580719, 85], [470.29995998876984, 210], [98.93226146842062, 59], [592.7437181781861, 208], [821.3464432310284, 375], [21.579756473585803, 17], [1095.785542614547, 457], [199.53985414891213, 88], [765.2159886224254, 319], [75.0373465615994, 27], [21.815989604700007, 39], [138.6164115812553, 73], [11.11719186495975, 36], [204.11811859643058, 119], [117.10026037007265, 68], [609.2610950089056, 321], [82.73060438965331, 71], [464.56750599368024, 192], [1268.6422404030418, 498], [84.36676111989982, 75], [656.0683350901754, 266], [426.7213352132894, 168], [84.15909410201311, 59], [41.5755487764327, 25], [576.9131477066985, 205], [1415.8249619951966, 478], [704.7124912824629, 377], [415.09411028208706, 181], [180.84055725295184, 47], [384.20132360341813, 195], [90.7494256600803, 54], [225.85498410854143, 120], [113.03288251861886, 169], [150.7097016519001, 495], [809.9023600600558, 361], [87.67363741178451, 41], [1239.2069987861414, 465], [81.12872104430426, 50], [105.52922192051255, 65], [215.14728492642143, 110], [49.78364428555051, 62], [668.7605920081332, 306], [56.84364561574421, 44], [172.27061354354737, 52], [447.24196383987146, 194], [405.2367989498607, 197], [299.7131141067657, 105], [302.2445813975828, 148], [1161.5040868791766, 418], [335.45200906112404, 203], [913.4660935955908, 388], [402.69061412020164, 220], [11.370383574059815, 25], [63.56975080692064, 22], [835.6257730789926, 645], [927.6666173281337, 375], [143.27621049542995, 76], [513.5533123213681, 198], [214.43395675712782, 221], [637.0974971537798, 272], [1639.4426486010052, 488], [10.778036664563842, 7], [7.331433340645162, 15], [163.00565785870276, 64], [424.46531572320583, 348], [604.5844770209806, 182], [178.53399928362433, 79], [82.39175660330113, 91], [1120.695079421811, 479], [209.60764279667637, 96], [328.439243773154, 140], [183.06820079517638, 65], [1133.6814414497348, 504], [43.15973122195646, 50], [1059.0718241385766, 464], [103.54518107085278, 33], [304.8723833281256, 128], [242.70951436533142, 111], [93.53688644005524, 159], [250.8168019824734, 123], [39.691112568187236, 40], [950.6320512400416, 470], [253.12064940349228, 143], [437.7826528930582, 120], [123.60542909627497, 93], [966.3109897098184, 372], [317.67552556356895, 155], [69.30277917559715, 66], [546.4247029006619, 282], [41.19605967374082, 24], [22.463535018956463, 34], [124.22175472048912, 103], [92.23366354676182, 35], [668.8060393507767, 271], [52.28583773472383, 15], [927.2811656411379, 365], [762.0609917956317, 355], [159.21539141367248, 53], [143.5860162698118, 70], [2393.2442100628996, 1200], [509.2054215937533, 274], [594.5652884767333, 187], [307.1887926141044, 169], [708.0533028038408, 459], [278.85244289591355, 158], [495.70579298952816, 156], [213.65057898985515, 102], [107.95388749846825, 56], [1000.0241369185005, 464], [672.1401652498753, 275], [550.524926248152, 146], [276.3876654493761, 154], [158.30437666395483, 108], [913.3134371247652, 356], [1090.9272512271418, 423], [100.59390607126988, 80], [423.9906381461708, 342], [346.1023770058673, 178], [1453.9453510446037, 697], [348.7870179686797, 136], [1067.7257027141168, 462], [88.92131972637435, 46], [271.49240771649056, 151], [8.328231458817754, 27], [223.49249270513246, 85], [156.08035072079656, 91], [1194.5159634321753, 441], [143.23949180410364, 135], [1204.9238466515671, 457], [219.47095845687727, 94], [100.19561223683559, 62], [476.07956257613114, 195], [237.18291048489846, 108], [23.62303247325508, 46], [341.1574747763807, 127], [1032.5957900962385, 412], [52.86560244404245, 38], [259.88328421889673, 192], [127.44091936350378, 89], [263.8317069555487, 119], [262.87375096923984, 138], [586.5327916975966, 248], [513.4142592460557, 247], [161.89209930091056, 172], [327.52810379082484, 187], [517.2830244578654, 222], [227.60510769477878, 119], [505.2047235299542, 222], [848.460240629196, 388], [1339.3956086282997, 483], [662.3333257114209, 227], [156.60721472284058, 75], [190.42501831391655, 119], [297.9198813345338, 187], [818.0371016015415, 293], [642.0674881716741, 287], [1083.7145269302637, 593], [300.09836554303274, 107], [124.31625842681024, 56], [241.46097630063923, 97], [251.0653684744466, 124], [122.5718586597975, 101], [280.1523277326196, 91], [424.6986295648967, 155], [987.4587381695164, 388], [209.25453542081232, 78], [655.11403950963, 274], [1443.6699138229778, 508], [793.2167792349937, 303], [828.1964784095726, 543], [4.775473932655586, 18], [324.09154312257306, 172], [422.9887537405575, 189], [314.6005734577384, 168], [239.49155993635395, 154], [370.5200877471034, 182], [439.60066674925474, 205], [36.48138115274196, 18], [259.18258288150537, 204], [78.20545180580666, 57], [1117.1972563384916, 467], [272.416486726881, 123], [792.4885588122852, 308], [245.87546738648052, 426], [1199.726355805702, 496], [177.14260523035773, 60], [628.8927091753867, 204], [671.491299995876, 298], [125.18826645275476, 181], [957.3897090066239, 300], [381.95532912221097, 127], [77.89849092523218, 31], [357.0543464355069, 132], [747.0543555737386, 325], [794.6662811203933, 418], [644.6813235630543, 270], [67.33562392036947, 54], [126.80656626017299, 64], [313.00421225622995, 140], [251.52173013640277, 105], [177.03696210720864, 112], [50.87741668362651, 32], [78.6605198108864, 78], [722.730149595358, 324], [31.52605600638526, 22], [140.8710235279359, 64], [762.9377509916812, 354], [704.3158564342375, 284], [820.6907631335816, 381], [82.7409829143071, 59], [78.8493346904288, 57], [419.6920770115976, 172], [75.79904277371679, 63], [9.065782376506831, 47], [94.52974316498694, 47], [13.751845114052685, 47], [333.7109652758804, 117], [391.00391533756465, 159], [306.1018563335392, 142], [191.69980325106917, 160], [192.512697246455, 123], [720.3622676286177, 318], [585.2022578149008, 312], [572.0545208945332, 240], [560.5222593313811, 235], [18.18918048070691, 69], [1003.4580975418066, 446], [316.9828236380854, 163], [811.9113565584926, 494], [552.0736441767294, 236], [26.329820270281743, 31], [671.0217109221749, 345], [714.4730185725057, 326], [10.009993250132538, 15], [152.32389505878382, 74], [262.39751515805256, 131], [308.48239601835667, 160], [511.33509615647927, 285], [81.74240515571, 57], [307.17170675350644, 158], [126.02492434045416, 70], [71.0383810360654, 74], [180.95221967939142, 88], [499.92336936754873, 198], [489.3296880875423, 238], [407.02809651389543, 194], [117.94244290656366, 74], [2.6416439093291046, 10], [117.5794902464595, 68], [291.75052993328427, 96], [913.1348284851474, 399], [497.9174416535352, 236], [387.44690910403733, 147], [403.22752693507573, 174], [9.076484231282848, 40], [740.2777153589268, 351], [791.3820371405309, 356], [268.82432180324395, 107], [893.2241580342525, 449], [436.89529382201, 176], [1441.1067991182917, 650], [90.637250009313, 56], [138.8109508530713, 84], [343.277283007581, 141], [20.535375690037654, 21], [462.7372667122947, 1062], [1074.998089036002, 405], [718.5178806250769, 279], [119.52590271313238, 75], [60.67902118297934, 31], [1146.0199151734123, 453], [136.8149303728169, 108], [636.0463068753011, 426], [196.16652195968254, 132], [297.65512481873157, 149], [74.3681267078573, 43], [291.289471815835, 147], [894.2339042474778, 383], [241.2729711320644, 123], [768.816408121238, 310], [360.46844993183913, 169], [288.8653223906731, 151], [48.93808835569507, 44], [175.94606495228072, 66], [444.0515010174422, 157], [5.820926475411397, 28], [106.35539884422542, 64], [835.6069081464229, 471], [80.04127308495845, 60], [321.29483750579675, 292], [118.31744875723052, 71]], "final_state": "tinker://3e998640432b43e01b7fb42771192b91/weights/select-sel_adamw_lr5e-05_s0-final", "t": 1793807344.8759263} {"stage": "eval", "arm": "sel_adamw_lr0.0001_s0", "split": "val", "step": 40, "nll_sum": 194884.4326239723, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.0660295206510506, "example_mean": 1.927350718276359, "per_example": [[157.32507604977422, 104], [782.1375936720615, 423], [280.8857917424989, 219], [1390.5531767102048, 467], [62.4846431272822, 53], [285.9525226443693, 151], [4.294124433923571, 20], [27.979815375761632, 27], [32.583050641900456, 32], [473.97704713741666, 247], [330.6772535033697, 223], [684.1219452759442, 280], [1003.0287137440127, 365], [74.87264222076101, 54], [399.7917539137668, 159], [371.4590885381788, 265], [669.9844019087295, 330], [221.78241275758091, 110], [298.37896191776906, 120], [87.92945150167543, 114], [211.41316654684124, 132], [80.25259230932215, 67], [106.66586247095665, 57], [134.50343159669865, 100], [566.4843091859865, 345], [2.4653286991115237, 14], [1261.9097883337263, 788], [1158.5639460038224, 469], [238.52082230857877, 65], [263.49741013130597, 158], [831.8767551499532, 356], [66.93558189794385, 26], [328.6017244454956, 109], [224.59754544747466, 105], [264.07451327056197, 233], [180.48966794204557, 69], [133.1907680483282, 61], [103.29948883417319, 86], [273.67648176481975, 105], [220.55646061791617, 88], [1495.290283998501, 519], [492.6755439309509, 157], [66.57638385544305, 78], [155.9069154159306, 102], [425.28862928302647, 209], [1158.5338087529967, 484], [238.91321023628188, 233], [193.31573773825767, 118], [92.06733864422128, 91], [30.29982120626505, 34], [328.8090116620456, 177], [66.8760409886579, 39], [67.11608795620032, 50], [104.94068167489377, 84], [181.61970008573508, 152], [284.5786637050519, 115], [463.3595865951132, 302], [398.15130634715365, 242], [585.0327797757109, 268], [53.269646295080975, 19], [297.1611698253819, 131], [532.9425729609388, 248], [262.78248144342615, 261], [616.0961723557612, 328], [98.81578616802972, 56], [273.1017727719345, 104], [71.64501866142427, 62], [377.81765664949876, 179], [1542.7839180994565, 389], [94.62268740046738, 132], [90.01735302128509, 24], [256.55956770160935, 122], [65.25540488539082, 39], [82.10564633643207, 59], [3.6221850563497355, 18], [222.55471845893862, 124], [437.8341357461928, 269], [146.12122096662642, 69], [23.456464862276334, 23], [418.50150963471845, 202], [660.4112596900859, 255], [132.93210405463196, 52], [233.81786918904982, 138], [165.343530695935, 99], [1.0895469895038445, 19], [733.7151650407673, 313], [560.6941828192898, 270], [59.90587674785456, 34], [605.4646450376066, 256], [97.09929832126636, 64], [54.455220257343626, 28], [294.17311553292484, 135], [478.57704671187594, 217], [175.8409274238054, 73], [175.05718211955264, 62], [267.32780540505547, 520], [539.6934541173355, 193], [398.4812434769997, 110], [1002.1819507066207, 319], [32.028888329952224, 56], [354.98437104658865, 276], [222.1083008446485, 121], [158.72433830964962, 71], [139.38055473296902, 81], [76.051582917637, 38], [204.37268081617322, 100], [199.4503828165714, 97], [108.54425444842445, 69], [963.5316980443704, 328], [48.94108809646673, 44], [343.3990179223115, 128], [98.39644505804233, 66], [802.5700053659914, 306], [134.47768515923872, 78], [616.611380052721, 242], [450.0418552851621, 201], [74.24931329167612, 52], [54.18809218369279, 40], [799.0316371003557, 246], [269.14537097671155, 125], [7.582284924730288, 89], [937.4669943374442, 446], [131.50070590559903, 106], [447.3360119978097, 200], [555.2392344575636, 266], [572.3281928089415, 288], [157.30808993981555, 106], [238.17543351478935, 86], [659.6078675821454, 341], [613.3580748541419, 258], [74.96394079411016, 52], [843.7674973763396, 448], [368.54601004538927, 168], [21.579279679720912, 47], [33.26560453826096, 43], [1234.0159986580757, 476], [98.87171375199569, 104], [149.1633930314365, 106], [215.5772662343552, 137], [1054.6333962970957, 491], [13.31457658549698, 20], [114.4358551037551, 66], [85.30538722663096, 54], [159.74897207732283, 92], [87.04439756959891, 42], [743.6848138202873, 425], [710.7017679605701, 231], [114.8562696360309, 96], [1000.0401622096188, 417], [224.59727889341048, 96], [1398.163602522281, 582], [292.3855010475072, 146], [95.28245907108703, 98], [1466.4697864697043, 485], [78.56852306333167, 45], [599.3573927425646, 190], [45.684036242259, 116], [1.7914665473690548, 6], [161.68252532230474, 166], [338.1364872029767, 141], [429.66944462986953, 171], [985.0707795020189, 491], [9.694336939695404, 29], [138.1237514415593, 40], [706.6290515010239, 308], [276.33775201530716, 90], [211.58652416862697, 93], [200.96597707846558, 124], [176.6537685766143, 106], [346.89396897127654, 330], [42.97794395378776, 43], [229.0244287497576, 200], [101.87837116565925, 69], [278.4979089241268, 477], [60.75572972427102, 42], [303.2019108790487, 80], [208.00612089276365, 148], [561.8285993198796, 327], [516.4380997929848, 231], [1503.2975650230069, 422], [5.263350631377989, 10], [319.9292773561788, 299], [487.4184571031185, 215], [248.98077690305115, 130], [63.61437971604073, 128], [338.07815349935015, 222], [269.3712465155404, 374], [1127.5851408655699, 489], [155.35311872512762, 88], [234.13759510599948, 85], [1014.4870248321693, 422], [85.19779653688397, 51], [317.8476383694392, 253], [760.0806529373103, 368], [325.04634101303463, 245], [201.6446699600915, 130], [188.69537422194298, 77], [1017.1387658880917, 408], [660.7809034646762, 268], [824.3269870569907, 258], [476.54627307822943, 212], [227.5373219788421, 103], [111.4876450536103, 92], [141.1088789917094, 94], [160.10502810678463, 86], [148.80433436724365, 66], [319.687304582049, 135], [249.21266223771727, 156], [475.60443704571844, 150], [128.98315968546422, 85], [470.23362478418085, 210], [98.21596938519542, 59], [587.9703696658667, 208], [817.861751054905, 375], [21.35667049616211, 17], [1091.64311948963, 457], [195.59442088415744, 88], [761.3666678832368, 319], [73.83343908012102, 27], [22.862351147207846, 39], [136.35277806945942, 73], [11.450267227059157, 36], [204.8635882153958, 119], [118.31934871316253, 68], [605.6359560185729, 321], [88.34917767673141, 71], [461.3400161322138, 192], [1268.8250346817376, 498], [84.30992365096836, 75], [654.6541445061803, 266], [424.42133485913655, 168], [83.67394120704057, 59], [41.63982338426422, 25], [577.785319373228, 205], [1413.5755765692197, 478], [705.9461587410984, 377], [417.43315722505145, 181], [180.37378962310186, 47], [383.28910091530906, 195], [90.60695599660812, 54], [225.83305687948996, 120], [112.33961716119643, 169], [145.4165745206633, 495], [808.5069746294571, 361], [87.2825544305988, 41], [1239.5719122150529, 465], [80.5798031376803, 50], [104.35791948628696, 65], [212.04538208391295, 110], [49.21964695619772, 62], [667.3369046573384, 306], [56.37213238392815, 44], [173.42938064735688, 52], [445.1000671234174, 194], [402.48578708416176, 197], [298.83606911364996, 105], [299.1214165451779, 148], [1161.573182310472, 418], [331.0026724889908, 203], [912.8535412633203, 388], [403.17973500122366, 220], [10.339823052008796, 25], [63.729482744910456, 22], [831.6992691580308, 645], [924.3053499168157, 375], [140.24383466802362, 76], [509.7501008468312, 198], [212.79858225903718, 221], [637.2206524786448, 272], [1632.2429309937183, 488], [10.700167059614614, 7], [6.957986492268901, 15], [162.4195774980194, 64], [419.7786805204214, 348], [607.1890957726309, 182], [177.57092725987604, 79], [82.80475773021121, 91], [1122.6621572988984, 479], [208.301927321716, 96], [329.18767060402274, 140], [182.9988538718526, 65], [1128.921291694346, 504], [43.408462317032445, 50], [1056.7665920960362, 464], [102.55125190725539, 33], [304.9518826136691, 128], [240.81498108544088, 111], [94.35575975365555, 159], [249.37671716158547, 123], [39.71158980889231, 40], [949.2094831410468, 470], [249.9055788216774, 143], [435.4166173482547, 120], [120.83172245031801, 93], [964.4437045073269, 372], [317.8275530402859, 155], [70.07405080603343, 66], [543.5690602451027, 282], [40.384126479679026, 24], [23.677500546929878, 34], [123.48773046974384, 103], [95.25323197383318, 35], [663.4028374957916, 271], [51.645759801974464, 15], [927.3327450533944, 365], [762.533214570785, 355], [158.94374939693944, 53], [142.5893673717287, 70], [2389.9829618154126, 1200], [509.77244734081387, 274], [592.9600803023384, 187], [304.0608828495331, 169], [708.0054230886371, 459], [280.2751398186509, 158], [489.9614061752727, 156], [213.33035133528688, 102], [109.28718421552867, 56], [996.1998945382102, 464], [669.7183503139136, 275], [548.8245848668255, 146], [276.17920345115044, 154], [157.33774522109798, 108], [914.5747075651007, 356], [1086.6972202359811, 423], [99.95443624003838, 80], [419.8605100673266, 342], [342.0923525753383, 178], [1451.0772176254773, 697], [348.68804940193127, 136], [1066.2068725369404, 462], [86.80141875949403, 46], [270.1760079539217, 151], [8.069126389083976, 27], [224.19813308102914, 85], [157.76764158697438, 91], [1190.696575660098, 441], [136.7908570336075, 135], [1201.6269105880742, 457], [217.49467358906713, 94], [100.26877966488382, 62], [477.1278282612384, 195], [236.25077607381127, 108], [24.1127669536329, 46], [341.09059499406294, 127], [1028.3654610398326, 412], [53.71040613191872, 38], [259.8110448884536, 192], [125.76074354076854, 89], [262.9842462955676, 119], [262.45837310553884, 138], [589.470375436993, 248], [514.8601310299691, 247], [164.3831347132682, 172], [327.7021813170426, 187], [518.3485893893344, 222], [228.95254023491634, 119], [504.2401538964714, 222], [846.6840452288288, 388], [1333.1541579402538, 483], [663.0424270243575, 227], [154.9373550952855, 75], [190.85448739466597, 119], [294.12476294679436, 187], [818.833547505167, 293], [635.5003394563876, 287], [1084.5646960368792, 593], [298.0493534086979, 107], [124.86564453694746, 56], [240.5826512081096, 97], [249.45968183181958, 124], [121.40063310710661, 101], [280.08527124635657, 91], [424.9099487177082, 155], [988.5753100819898, 388], [207.91602716772786, 78], [656.7413692629666, 274], [1440.0553775748517, 508], [792.3677058231203, 303], [828.5202050927815, 543], [4.722475885350605, 18], [322.607461615441, 172], [420.7468730234102, 189], [314.239071028318, 168], [236.01129583195018, 154], [367.9044705744575, 182], [442.51884958972846, 205], [34.320488165961706, 18], [257.40991876542694, 204], [79.56955506968552, 57], [1115.0728537468103, 467], [272.53176229865494, 123], [790.8882104951224, 308], [244.84475884145013, 426], [1201.6409937377252, 496], [175.1116007641176, 60], [622.6897078032098, 204], [673.1148772713485, 298], [125.26498985413332, 181], [955.3556894747212, 300], [382.5995237413356, 127], [79.9634283154196, 31], [354.1778091221163, 132], [744.7876068861233, 325], [794.0741604152556, 418], [643.7166076263745, 270], [66.56363815854684, 54], [125.38411353723586, 64], [314.8284842165767, 140], [250.1626529983041, 105], [174.82915995069243, 112], [50.37471301519963, 32], [77.8619133594284, 78], [724.7931175591816, 324], [31.62167051144843, 22], [139.28065089319898, 64], [765.6349713568138, 354], [702.2190563031032, 284], [815.5190790203396, 381], [81.67523059195491, 59], [77.61975339220635, 57], [419.05445704886756, 172], [75.04462273435365, 63], [10.012439721692317, 47], [93.85636641570773, 47], [13.870794460152695, 47], [333.06060120172197, 117], [387.3523760061912, 159], [307.3289496361608, 142], [193.05450070873303, 160], [190.99636004802187, 123], [720.7081679415546, 318], [588.2026782217536, 312], [575.518577947377, 240], [562.0703838523159, 235], [16.71318646996403, 69], [1000.923654872982, 446], [317.2655234876115, 163], [810.4950913213081, 494], [552.8234178170678, 236], [27.7451452637888, 31], [673.5876486426484, 345], [709.0675108675164, 326], [7.80773488830846, 15], [152.40929859840162, 74], [262.59052129362635, 131], [305.6004625567989, 160], [511.6060910673493, 285], [78.91678123610927, 57], [307.37042738659966, 158], [125.39008914277292, 70], [70.45413813348932, 74], [178.6272428078064, 88], [515.9504329964675, 198], [486.82093549488945, 238], [407.3699847408095, 194], [117.70002515733705, 74], [1.6112697697822114, 10], [119.41181328642733, 68], [292.2101511457813, 96], [909.9157390961972, 399], [496.612443456155, 236], [386.54780177416797, 147], [404.23815380125507, 174], [9.293705719524496, 40], [739.0921730423856, 351], [791.8771537956611, 356], [269.7521021129626, 107], [891.4151222746323, 449], [435.99732596419653, 176], [1439.128858473181, 650], [88.69250570235613, 56], [139.82993461769684, 84], [344.49383203027446, 141], [20.069577654736236, 21], [464.4070351653342, 1062], [1079.248101529393, 405], [716.4070296127599, 279], [118.2824996962836, 75], [61.42653344981545, 31], [1145.1705810406193, 453], [137.62456835138528, 108], [627.3367971026846, 426], [197.10115073932775, 132], [298.29589351075833, 149], [73.42393921242365, 43], [291.38825806961495, 147], [892.7130842177119, 383], [240.13296763085964, 123], [770.1578644701472, 310], [361.94830604758454, 169], [288.3329299217685, 151], [48.88333743572639, 44], [176.43361447495136, 66], [445.3040561947455, 157], [5.137673250179432, 28], [106.91521862101536, 64], [838.2286182954099, 471], [79.06195052244539, 60], [321.62320535995605, 292], [117.52081293975743, 71]], "final_state": "tinker://03adbc7870ed91f79da6f4176f6bc747/weights/select-sel_adamw_lr0.0001_s0-final", "t": 1793807373.9584343} {"stage": "eval", "arm": "sel_adamw_lr0.0002_s0", "split": "val", "step": 40, "nll_sum": 194639.8876812118, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.063437024862308, "example_mean": 1.922229335475306, "per_example": [[156.75956579969034, 104], [783.2595573214094, 423], [282.197599702622, 219], [1390.9376897796164, 467], [62.66089793696028, 53], [289.46453711555296, 151], [4.244451788345032, 20], [27.67087105682208, 27], [32.30207879404634, 32], [471.3403663242352, 247], [329.95617375872735, 223], [684.4243317751389, 280], [1000.7290412542134, 365], [73.08853254755559, 54], [398.57713021538007, 159], [372.6204868055315, 265], [668.1611468767123, 330], [220.69387606670716, 110], [299.8778304159282, 120], [87.45434858497538, 114], [210.92668454765226, 132], [80.20323488278314, 67], [106.87699012879784, 57], [135.01073979939247, 100], [565.460004097994, 345], [2.4326004904241927, 14], [1260.2448629484315, 788], [1155.3647718739385, 469], [237.18971073695866, 65], [264.5119300443075, 158], [837.2792809424318, 356], [65.65634723794756, 26], [329.5882423905923, 109], [225.85336453793389, 105], [265.2503486435089, 233], [178.07050656837328, 69], [132.68133523391407, 61], [102.8522096462575, 86], [272.7268598902465, 105], [221.5973640625125, 88], [1499.057172538196, 519], [494.04797831632095, 157], [64.86048156933794, 78], [157.06384834994878, 102], [426.4304978341838, 209], [1156.1189602651139, 484], [237.56102506042953, 233], [194.11732287649465, 118], [91.29335562790425, 91], [30.063913905743902, 34], [325.86835095054175, 177], [68.366027034338, 39], [66.04740285855246, 50], [102.70709864706896, 84], [183.36086367929965, 152], [283.68883463578186, 115], [465.4468873366195, 302], [396.82622630948936, 242], [582.9255916120096, 268], [53.3151757553278, 19], [297.6340458830946, 131], [532.1971048693722, 248], [263.6885919049314, 261], [617.8071802497288, 328], [97.13429063233525, 56], [270.1940224958744, 104], [70.84829885923682, 62], [377.27433150194156, 179], [1543.0120506062394, 389], [93.91073825660897, 132], [89.9005777322136, 24], [256.8887430397954, 122], [65.90069207395027, 39], [82.41677306945212, 59], [3.7047330810364656, 18], [221.08819034157204, 124], [435.8959585396374, 269], [144.84286578811407, 69], [24.003015897572368, 23], [419.0709049154243, 202], [661.7242025116648, 255], [133.28014264675585, 52], [232.68128023419558, 138], [163.6019408797638, 99], [0.8746953777288127, 19], [734.1828148963541, 313], [563.9636413662365, 270], [60.9163197025664, 34], [606.0130688626191, 256], [97.88102745350807, 64], [55.54309032784295, 28], [294.7293511502626, 135], [478.79470698970727, 217], [177.6071807396138, 73], [176.4035787068583, 62], [264.83263096234157, 520], [536.3275909863969, 193], [395.15180797663197, 110], [1003.5986324333207, 319], [28.9703135949012, 56], [352.06228194178857, 276], [221.26298449552723, 121], [158.11470251259698, 71], [139.47126165261352, 81], [76.92989418861862, 38], [205.97911487157012, 100], [199.36035164743953, 97], [108.64154595101354, 69], [966.5667777162489, 328], [46.89699685120104, 44], [344.97356788014895, 128], [99.22306095403042, 66], [801.4022242115307, 306], [135.18465905892026, 78], [616.7163245530796, 242], [449.7752821580011, 201], [74.23411063054846, 52], [54.41892665663363, 40], [798.2341924172251, 246], [270.8394413785463, 125], [7.7151389089849545, 89], [939.1825338048056, 446], [129.8706681995318, 106], [445.868213359945, 200], [552.6892776923903, 266], [571.2207108900047, 288], [157.37829389805302, 106], [238.99157703617038, 86], [658.4803531230673, 341], [608.9074182905933, 258], [74.1560928084873, 52], [840.6344916256385, 448], [373.89250615158016, 168], [21.33045151733313, 47], [32.58765154333014, 43], [1234.6366180987607, 476], [99.59571583296383, 104], [146.97722792462173, 106], [215.36634286757908, 137], [1047.3442781632684, 491], [11.253746826367205, 20], [113.86980764786131, 66], [84.1750263237318, 54], [159.43473303766768, 92], [85.4836062624131, 42], [739.5210040269408, 425], [710.1835299256545, 231], [114.46467673669304, 96], [997.3983668241963, 417], [224.7274991942395, 96], [1397.5007114019, 582], [292.08279793210204, 146], [93.83419196800605, 98], [1470.2898248479905, 485], [77.57963896543242, 45], [601.3432533670348, 190], [42.83491256056425, 116], [0.5277008768407541, 6], [161.8102286176122, 166], [340.6995759811707, 141], [430.2623128080322, 171], [986.5021135506122, 491], [8.977584768656925, 29], [135.68217637866655, 40], [707.5642649798965, 308], [276.87820035752156, 90], [211.18479340499198, 93], [200.84590958951867, 124], [175.10686968007303, 106], [344.5532263225591, 330], [43.34763212149437, 43], [227.72159763150103, 200], [101.15726631895723, 69], [277.786528876214, 477], [61.99007374932421, 42], [302.18955475038274, 80], [206.74445043500327, 148], [562.3158531272702, 327], [513.3087546771494, 231], [1504.1957641408271, 422], [3.941347112049698, 10], [313.99983671517657, 299], [489.4591366827144, 215], [245.92748575123642, 130], [64.56884672956767, 128], [337.96402806292645, 222], [269.01830951042166, 374], [1127.77506363278, 489], [155.66274713805888, 88], [232.54797258910185, 85], [1013.0519154437252, 422], [85.29790690617324, 51], [317.71577022398105, 253], [757.1502583467936, 368], [325.50496361414207, 245], [198.5622589032996, 130], [188.244532557218, 77], [1017.3129543351415, 408], [661.5564412356689, 268], [824.1425177559695, 258], [474.6823218216214, 212], [229.06794275755874, 103], [107.11695385985661, 92], [137.80248230031975, 94], [159.9514839558724, 86], [147.33794629334284, 66], [322.1797285530729, 135], [247.87380684111486, 156], [474.5569015764486, 150], [127.71055310675547, 85], [468.90568619027545, 210], [96.99091049345407, 59], [589.6325355029803, 208], [814.1463592614482, 375], [21.64389336972772, 17], [1085.563405111765, 457], [193.14174074671678, 88], [758.7785001492462, 319], [71.09481178797068, 27], [20.08901160068399, 39], [134.06746469218115, 73], [8.786236110681784, 36], [205.24331099980736, 119], [111.62992052909067, 68], [605.3777622140569, 321], [88.93945447368242, 71], [460.4789660044962, 192], [1270.4880899580294, 498], [83.24611336266116, 75], [650.495977905075, 266], [427.5234617771048, 168], [83.19163620687232, 59], [42.86895699955494, 25], [577.7557700366788, 205], [1411.689321224112, 478], [703.8178139772679, 377], [418.21478561797994, 181], [181.72260822312637, 47], [384.6445588830402, 195], [89.10128795017226, 54], [227.8988504904337, 120], [112.45841824527974, 169], [142.27252057260557, 495], [804.6909037330952, 361], [86.53099635676881, 41], [1239.6484072055655, 465], [80.87843191654792, 50], [103.60767723630943, 65], [210.4786789474765, 110], [48.81998411655968, 62], [666.9517850786415, 306], [54.954889616799846, 44], [174.97995634035487, 52], [446.5312615860912, 194], [398.7238825344939, 197], [299.1322930240972, 105], [296.9220735947174, 148], [1157.0319997839242, 418], [329.95918880031513, 203], [913.926334313036, 388], [404.1447198121041, 220], [9.77554048874481, 25], [63.79415599231106, 22], [832.4456409612862, 645], [923.0013358588731, 375], [139.34494005376428, 76], [511.493287208943, 198], [213.61098881785256, 221], [633.9259286628226, 272], [1634.8670532510032, 488], [10.567661821600268, 7], [7.956025381944528, 15], [163.32562174044506, 64], [415.9855662127135, 348], [608.2029040653906, 182], [176.7913410400763, 79], [81.06851743492393, 91], [1123.8038758370249, 479], [207.30356163383112, 96], [329.0319174053275, 140], [180.9984995171858, 65], [1130.5491912166053, 504], [42.36090042416254, 50], [1054.7781214036859, 464], [102.00988824750948, 33], [302.05317777801247, 128], [241.61310241768797, 111], [94.25595655996858, 159], [246.81859752018227, 123], [39.210995409302996, 40], [948.9462627593948, 470], [251.17568495216256, 143], [437.71652783798163, 120], [119.89008530213619, 93], [966.8713784421484, 372], [314.8301996921973, 155], [69.82483649769028, 66], [543.3683734325277, 282], [39.958884045618106, 24], [24.046783976660663, 34], [122.75336347248958, 103], [96.59381366949765, 35], [660.715152562705, 271], [51.3386259948029, 15], [927.743073940725, 365], [760.5953456593852, 355], [160.933165723025, 53], [140.78875790196525, 70], [2397.706398058086, 1200], [506.51707425298537, 274], [591.3185972521715, 187], [302.981535234665, 169], [707.2144489610473, 459], [279.4492471042288, 158], [489.9122392927802, 156], [210.06095825527518, 102], [110.41540780263222, 56], [995.2675486477856, 464], [669.684662823086, 275], [545.6921434929336, 146], [275.890622244764, 154], [155.7123975399909, 108], [916.358862894881, 356], [1081.2204757221316, 423], [99.70436367842922, 80], [419.9207925372708, 342], [339.103937258109, 178], [1449.343730938781, 697], [348.74066327273795, 136], [1071.5827592280484, 462], [85.2914247005292, 46], [269.244076203242, 151], [6.997562455461775, 27], [221.6559178691332, 85], [156.56602851260322, 91], [1189.5785783074584, 441], [132.6731015429018, 135], [1198.8005990209258, 457], [215.7584644371782, 94], [99.7968511911995, 62], [476.6093238459516, 195], [235.82221399845548, 108], [23.97444434823774, 46], [339.96520173037516, 127], [1025.2120709128067, 412], [52.62773848093275, 38], [258.5187624520622, 192], [123.58131701328057, 89], [261.2237968178524, 119], [259.70371506446145, 138], [591.1512054113509, 248], [512.9098131020482, 247], [165.43027059708857, 172], [327.60272110965025, 187], [515.1046758025636, 222], [229.98429982551352, 119], [503.51663505976103, 222], [845.3304370596661, 388], [1337.3522797542419, 483], [662.5727809795153, 227], [153.87972143821207, 75], [186.61416323291814, 119], [292.1155647625492, 187], [815.219675641084, 293], [632.983541836435, 287], [1085.3070219055844, 593], [298.86647273945164, 107], [123.84118156190016, 56], [242.31480194333926, 97], [248.38036884846588, 124], [120.92117984882793, 101], [282.83102239845357, 91], [426.1136127038644, 155], [987.7076752314933, 388], [206.91751194896324, 78], [654.93512020872, 274], [1443.055772627522, 508], [793.6912155528612, 303], [828.0169194677919, 543], [4.3047000322230815, 18], [322.1511424478722, 172], [420.0716847362837, 189], [309.8051045150005, 168], [235.21594711505077, 154], [366.95483598588635, 182], [441.5096409512071, 205], [32.9016183900676, 18], [257.626571318011, 204], [80.11396776346373, 57], [1113.7906266438513, 467], [273.6931764557012, 123], [787.0714581117873, 308], [242.87637474825078, 426], [1203.1977575111468, 496], [174.0252417607262, 60], [620.7912192605054, 204], [674.5357167919192, 298], [126.81137531454169, 181], [959.1465776230616, 300], [381.6646443144891, 127], [81.75844012138259, 31], [352.9273594709048, 132], [742.8924893514031, 325], [792.6915701587886, 418], [639.4284178755988, 270], [65.73968592554684, 54], [125.59889921559079, 64], [314.83592014546684, 140], [248.78082395270758, 105], [176.44430847470903, 112], [49.682121828012896, 32], [76.76479009035393, 78], [724.4510799935179, 324], [31.819086583935132, 22], [139.1834642630938, 64], [766.8804731494101, 354], [700.6867785485374, 284], [815.0137426472929, 381], [82.21874219535857, 59], [76.87660146176495, 57], [422.5920184912379, 172], [75.10897915178248, 63], [9.550558474251375, 47], [94.06896212196807, 47], [14.960172277687661, 47], [329.66341341582756, 117], [385.6075878157128, 159], [308.9739758937826, 142], [193.83713456225814, 160], [192.49723754009392, 123], [719.3795470526147, 318], [585.6763111105183, 312], [575.4427507030487, 240], [560.0345029433433, 235], [17.835151287695226, 69], [1000.5254542213243, 446], [318.6451544197371, 163], [811.010705775921, 494], [557.7765692317917, 236], [28.735995394907604, 31], [673.7786103411609, 345], [705.7867601770668, 326], [6.887978446370653, 15], [148.81642638641097, 74], [262.7688936410541, 131], [304.2690742155828, 160], [512.0425886825428, 285], [80.19409737135356, 57], [308.62333245558693, 158], [124.06698934885253, 70], [70.12535944461706, 74], [176.6082943300862, 88], [494.54696851576, 198], [485.92380444102855, 238], [405.1328510415433, 194], [116.65690743392759, 74], [1.4131520592904963, 10], [118.71074210845472, 68], [293.28599620410023, 96], [912.1231525740031, 399], [492.38279976391823, 236], [385.73177321060575, 147], [407.2819127586117, 174], [9.321993009270955, 40], [736.785269344241, 351], [794.6275589692559, 356], [268.83278923131775, 107], [893.9963485285998, 449], [436.716074596784, 176], [1437.4035254013033, 650], [86.91643197730582, 56], [139.2882594618968, 84], [344.7464761500096, 141], [21.76755674725149, 21], [468.3225376519508, 1062], [1082.3010658845851, 405], [716.9294137924517, 279], [117.19094247259545, 75], [61.356146045926835, 31], [1143.6078856027616, 453], [137.64772162548888, 108], [626.6064480387649, 426], [197.95867314006136, 132], [299.92539619787567, 149], [73.40493392738608, 43], [290.65396543593124, 147], [889.1736255908982, 383], [238.82548020840022, 123], [769.7318554754465, 310], [360.7828414558253, 169], [288.1828994511816, 151], [49.20261682844466, 44], [176.0558193217571, 66], [444.4455486009492, 157], [5.3089922439503425, 28], [106.57091562658024, 64], [841.0349384008978, 471], [78.61169009066725, 60], [322.3191265281421, 292], [118.41967709039, 71]], "final_state": "tinker://bbaff5449c41db38914ac3f4523738b2/weights/select-sel_adamw_lr0.0002_s0-final", "t": 1793807398.4381287} {"stage": "eval", "arm": "sel_dimuon_lr0.0003_s0", "split": "val", "step": 40, "nll_sum": 212299.01784955614, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.2506468688995436, "example_mean": 2.2017716945822596, "per_example": [[169.1541207674902, 104], [836.4612406406309, 423], [316.6730613527934, 219], [1444.2282294590696, 467], [80.15243131386546, 53], [295.4512067929754, 151], [19.317391388442502, 20], [38.93326166925226, 27], [50.160074889997304, 32], [514.8502428484971, 247], [358.1455304651695, 223], [735.4583536676457, 280], [1073.6375283253083, 365], [87.15334122763443, 54], [410.3471326787651, 159], [431.0886121051019, 265], [760.6784887465312, 330], [240.3274670030073, 110], [326.74973874057815, 120], [109.34371369058863, 114], [243.19464961547055, 132], [101.82189625209844, 67], [130.87680823489643, 57], [178.79904636105834, 100], [599.661690686961, 345], [1.7583010888765784, 14], [1336.245192651264, 788], [1196.9704853069493, 469], [272.20904343348866, 65], [307.79611929060866, 158], [885.1295881998542, 356], [74.62569092963133, 26], [351.1508597150405, 109], [250.50558975662761, 105], [300.8939796055347, 233], [228.3366363977807, 69], [163.85523987753777, 61], [127.62225819942955, 86], [293.6508774674421, 105], [237.8593763602562, 88], [1527.7169170338025, 519], [544.4184601264728, 157], [91.5090562193368, 78], [194.48908167010813, 102], [466.5481115798807, 209], [1242.7834884518693, 484], [236.5160316900649, 233], [188.57139894126885, 118], [156.09503078776373, 91], [46.406307856387, 34], [355.35112684791284, 177], [85.46601525082178, 39], [83.34948805990086, 50], [122.81515622753341, 84], [228.67324247410988, 152], [337.46502759183886, 115], [514.6095805534947, 302], [449.890830532643, 242], [635.627222613821, 268], [61.44482027363597, 19], [328.13302841995255, 131], [574.6407295934987, 248], [279.6457022656143, 261], [669.7757641523272, 328], [103.31109135336828, 56], [308.2641934070143, 104], [87.71772140620214, 62], [407.1725242191744, 179], [1602.4691027149302, 389], [125.1138165016996, 132], [101.25229614882278, 24], [275.0665796259706, 122], [90.14740929210416, 39], [126.47913047625298, 59], [8.897543498968616, 18], [246.70503491975524, 124], [491.02523335419664, 269], [164.08013159361235, 69], [52.63131956378629, 23], [474.5755323130427, 202], [685.8928511258473, 255], [152.9595535868275, 52], [268.3214867803558, 138], [181.05445332404702, 99], [3.5799242691198288, 19], [781.2920548718544, 313], [608.5535395843472, 270], [74.28516380945644, 34], [638.841103770968, 256], [122.14794955271827, 64], [55.29915492916882, 28], [334.6304397479687, 135], [506.1069005625411, 217], [209.5431542104343, 73], [201.3659459362916, 62], [328.18750115423893, 520], [561.1332046196028, 193], [428.67897850825534, 110], [1071.3801249488054, 319], [39.76232071221057, 56], [404.43596229655714, 276], [263.2639813787373, 121], [168.09207717690134, 71], [158.0585909564752, 81], [92.97497932385659, 38], [219.95722080239784, 100], [228.60267597871552, 97], [121.9091984762872, 69], [1005.5329818040768, 328], [79.64149634231808, 44], [366.679657627687, 128], [118.81925950143784, 66], [847.3571223088177, 306], [168.53277828812128, 78], [667.288945777937, 242], [486.1866958965129, 201], [114.551167356125, 52], [78.83785182990835, 40], [835.9325463714811, 246], [292.5833507333084, 125], [29.56717187662332, 89], [1002.9451008012761, 446], [161.222907148363, 106], [486.1038867716793, 200], [616.0605452917895, 266], [623.3655766062344, 288], [168.43943347405002, 106], [269.06916101536535, 86], [698.6898298721885, 341], [638.7785095756376, 258], [93.24552788432311, 52], [883.5193661185249, 448], [404.76428641161533, 168], [47.772698280315126, 47], [53.85056457146311, 43], [1284.8050815596125, 476], [150.5562342036933, 104], [185.30163835321332, 106], [238.24348610021434, 137], [1092.8465685971946, 491], [24.574342063807308, 20], [138.22405535263943, 66], [140.64372459444212, 54], [174.3175594723225, 92], [115.36591913692564, 42], [804.6092063181004, 425], [762.7846243412721, 231], [140.2554960892553, 96], [1050.8343947512922, 417], [236.37981793224571, 96], [1467.637025513075, 582], [335.49233879981284, 146], [125.72907018274873, 98], [1522.3627668281977, 485], [97.02294346943563, 45], [680.2851967153006, 190], [76.068830086513, 116], [12.415688305973703, 6], [170.55728543512066, 166], [348.0105509668331, 141], [456.6477145045251, 171], [1030.0658185639998, 491], [12.222453535976683, 29], [163.46414884699516, 40], [748.2029649713113, 308], [311.73736837721617, 90], [248.280006523221, 93], [228.7964733231961, 124], [207.37526026916203, 106], [378.1743189038649, 330], [53.49346381270425, 43], [252.23010217047346, 200], [120.89670036679672, 69], [326.5260537145497, 477], [80.51396234850148, 42], [345.666462911321, 80], [242.12661578192615, 148], [599.8561645916718, 327], [543.0222428153809, 231], [1548.5019584956037, 422], [14.881368855875621, 10], [426.2863223982324, 299], [537.6135297097981, 215], [292.34839672922726, 130], [91.26772525865522, 128], [402.9455799600114, 222], [295.3588048468448, 374], [1142.9364934597993, 489], [178.51152919865854, 88], [261.00467826299655, 85], [1065.1650176585413, 422], [96.42426253265137, 51], [350.7279100836663, 253], [812.7892701853389, 368], [380.91916085310834, 245], [225.3652828959746, 130], [230.26584957234286, 77], [1048.0874632814252, 408], [703.2787900482158, 268], [902.7763517376882, 258], [509.35473575947333, 212], [269.2321038849516, 103], [135.11660151659373, 92], [177.71688060222914, 94], [187.8368149739954, 86], [169.15332032913875, 66], [350.452290013382, 135], [260.96418914414085, 156], [522.2010456287971, 150], [159.2695010025712, 85], [529.5228397443666, 210], [129.41023396947207, 59], [644.0617864020844, 208], [865.6264613421063, 375], [24.71593562900108, 17], [1138.4926164967387, 457], [221.98053784017634, 88], [798.4180733811163, 319], [101.96744645934541, 27], [27.566366764188842, 39], [164.97473465053622, 73], [33.74187898596256, 36], [214.33486155175888, 119], [152.25771520713715, 68], [665.1949638893695, 321], [102.9124562010752, 71], [508.25385275998906, 192], [1331.2011517094147, 498], [116.56094640960146, 75], [716.1269638769588, 266], [457.5741062716288, 168], [121.07618305353009, 59], [49.49265143269395, 25], [620.0718043327299, 205], [1463.1179364368747, 478], [741.3347627740932, 377], [449.61909215123, 181], [204.12782913962747, 47], [439.5987245936467, 195], [126.91100012819061, 54], [267.6822594215687, 120], [133.20347055634738, 169], [147.1717147091913, 495], [844.3053098911696, 361], [105.6822421942502, 41], [1275.6937001709457, 465], [93.80041880557201, 50], [127.08519347756658, 65], [239.46350020501995, 110], [68.8163579562306, 62], [701.0074291283208, 306], [70.40484673709511, 44], [196.3954823904246, 52], [488.5017209953328, 194], [427.40697756456393, 197], [319.9175649383942, 105], [351.99757979730043, 148], [1236.4156547986377, 418], [366.03934806468146, 203], [962.0072727800425, 388], [444.2430053101907, 220], [27.61741237427509, 25], [72.99541999967425, 22], [950.9008386342807, 645], [953.7536100658214, 375], [171.9893800723596, 76], [559.0691074956584, 198], [275.5450697277747, 221], [656.0509601402582, 272], [1696.0394064031416, 488], [23.521569222146127, 7], [23.82067727414369, 15], [192.7366476196985, 64], [461.44067780783143, 348], [638.6318766694944, 182], [186.85346774520758, 79], [91.73543530046402, 91], [1181.3462660159505, 479], [235.01150013773713, 96], [351.69174152271535, 140], [199.56613354716671, 65], [1195.4301609645813, 504], [54.47633393392698, 50], [1106.912922886624, 464], [154.0450124213964, 33], [333.9229430245422, 128], [271.3091780596842, 111], [115.97699756404859, 159], [283.5465621148751, 123], [68.50733466275597, 40], [981.504672192319, 470], [287.6089313265984, 143], [472.1268273988255, 120], [146.7778645519138, 93], [1015.6891027145812, 372], [339.9127848678678, 155], [73.80413310681433, 66], [591.5415872331558, 282], [51.00492037588617, 24], [44.829914131500345, 34], [135.9110626110496, 103], [113.74596616828899, 35], [735.1314626419378, 271], [58.14357751948211, 15], [963.6092279898434, 365], [797.0488278208313, 355], [172.5491538757915, 53], [161.7097008092885, 70], [2477.5095984469945, 1200], [602.4855186877262, 274], [629.5279182157594, 187], [345.6713213333401, 169], [766.192690047724, 459], [301.6084330512947, 158], [532.5167840588183, 156], [243.5045605486505, 102], [119.01002146552969, 56], [1052.4651543988555, 464], [733.1147200618642, 275], [590.6310317381958, 146], [326.0855206798203, 154], [189.0961189656823, 108], [979.8166192724661, 356], [1175.0683109206366, 423], [134.35835127571954, 80], [460.3421660820809, 342], [383.9257097007935, 178], [1515.7011883254168, 697], [382.24711174209847, 136], [1127.9802043087413, 462], [108.22869959191644, 46], [299.53167528890924, 151], [29.431685217567292, 27], [254.7849063619384, 85], [197.39057680771532, 91], [1243.0812060411124, 441], [195.48472059227663, 135], [1257.3603597679921, 457], [227.4529284136927, 94], [106.32413093558807, 62], [521.6644752990305, 195], [242.03051383846196, 108], [43.964312941010576, 46], [367.29163216984944, 127], [1089.6946337532736, 412], [69.99898450750698, 38], [311.48501641710925, 192], [164.44328323497027, 89], [326.959230771738, 119], [295.18590094316824, 138], [622.2241424760687, 248], [543.8149027768472, 247], [179.09910620607062, 172], [381.1566290117694, 187], [545.5394050035075, 222], [259.848055290793, 119], [564.7488740816557, 222], [904.6859987698131, 388], [1393.2046936555425, 483], [688.9897455573305, 227], [206.343322957375, 75], [230.34113139315332, 119], [348.57473109635794, 187], [904.6826379233485, 293], [709.2148326898096, 287], [1185.1131697457593, 593], [324.59528439515134, 107], [147.42000530887822, 56], [261.014214028021, 97], [294.69651654412337, 124], [158.21570865204671, 101], [279.25240326334847, 91], [445.3167287731344, 155], [1027.5590652703036, 388], [241.92128509817667, 78], [698.5153998081314, 274], [1483.6838854478115, 508], [827.5221438956859, 303], [889.2657632275084, 543], [16.20086900505862, 18], [378.08797203271524, 172], [472.1427404950439, 189], [354.07040578869055, 168], [280.8147071408082, 154], [410.16898995059864, 182], [479.5317535856602, 205], [46.66306433262935, 18], [283.6787316903735, 204], [105.09662865900452, 57], [1173.2584135235847, 467], [322.41742454079804, 123], [829.6220512231577, 308], [269.87821570645474, 426], [1244.564433774209, 496], [220.1961559789795, 60], [688.6487523281278, 204], [722.4454567299772, 298], [152.42717136917804, 181], [1002.2577897283322, 300], [408.58187390025796, 127], [75.54414192837419, 31], [382.60439334714647, 132], [801.0672487245515, 325], [845.7151585990105, 418], [692.2919527345625, 270], [77.87155207903561, 54], [158.17272295193925, 64], [371.54115274772766, 140], [275.9334018751083, 105], [209.14864572985334, 112], [78.18152246223667, 32], [96.06379894135625, 78], [785.872721238009, 324], [43.69383343014465, 22], [171.65642368404565, 64], [801.8993079407187, 354], [738.238215884277, 284], [876.3705300672618, 381], [106.99446027742852, 59], [95.91775436785178, 57], [474.81780538433986, 172], [91.1635731973629, 63], [8.55487980558604, 47], [99.97667482694669, 47], [15.329673728560579, 47], [379.25325232755654, 117], [438.7246451263152, 159], [318.4784686216026, 142], [235.86629397915476, 160], [226.36691373535075, 123], [774.9349429033805, 318], [655.0672613885195, 312], [600.514727761788, 240], [594.4629694835921, 235], [26.92154256286335, 69], [1067.6993850577126, 446], [350.1967157331876, 163], [850.5536488939681, 494], [590.7038122891279, 236], [36.66422508609543, 31], [816.7839205740111, 345], [770.1013191254933, 326], [17.36400893923428, 15], [189.05638682459175, 74], [297.43566964946376, 131], [328.5361910130796, 160], [538.0520404088825, 285], [110.06833043129518, 57], [321.6397760020168, 158], [155.23479398521113, 70], [111.7871318846428, 74], [220.59728986755073, 88], [565.797070957602, 198], [529.3104707589646, 238], [455.8653379134083, 194], [135.2963670530474, 74], [11.954186714705202, 10], [155.98397771015743, 68], [326.946129154996, 96], [954.2714107822158, 399], [576.3998400011483, 236], [432.8104319267437, 147], [431.05984680159634, 174], [20.420658630000275, 40], [766.5912233178115, 351], [858.0069413121787, 356], [286.91491739176104, 107], [943.3085025593234, 449], [459.987538999924, 176], [1506.728419914084, 650], [126.19872849988099, 56], [160.89243557539976, 84], [365.92028158070616, 141], [39.3909831926357, 21], [487.8589936167823, 1062], [1154.5406647880054, 405], [761.3576449189945, 279], [150.35579830503093, 75], [66.69182920780463, 31], [1217.6693641554052, 453], [190.62035488014885, 108], [664.5270484461785, 426], [221.2557827008327, 132], [332.7991955798402, 149], [91.6783070808574, 43], [314.6854894732919, 147], [963.5056265843841, 383], [267.0495915667625, 123], [802.9336805415351, 310], [383.9851911875371, 169], [318.913342188418, 151], [65.79870986764286, 44], [217.36451691228126, 66], [463.3324199490828, 157], [13.474674608421992, 28], [141.7377472433311, 64], [878.6810729339086, 471], [97.94887188416669, 60], [362.8815325240994, 292], [135.93579465691698, 71]], "final_state": "tinker://df15cdc0afbf74e50388cdfd5d48723d/weights/select-sel_dimuon_lr0.0003_s0-final", "t": 1793807425.5962727} {"stage": "eval", "arm": "sel_dimuon_lr0.001_s0", "split": "val", "step": 40, "nll_sum": 198715.1598467283, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.1066402324519578, "example_mean": 1.9816628419992373, "per_example": [[161.76335875324912, 104], [794.3221024123409, 423], [286.729625738046, 219], [1408.8531691553071, 467], [63.01471846654704, 53], [287.70840120781577, 151], [5.443515780949383, 20], [29.323562798583225, 27], [33.673355752162024, 32], [481.7519262770709, 247], [340.36806297871124, 223], [705.9285633281534, 280], [1017.7343156014215, 365], [78.05485131358546, 54], [400.9438488226733, 159], [386.3756845293083, 265], [687.8275925362674, 330], [222.68586918220262, 110], [313.6373619762047, 120], [88.98346299149307, 114], [220.37044138338433, 132], [80.1742005445376, 67], [105.05411334901237, 57], [137.3158742503001, 100], [561.4812312522805, 345], [1.917639024509299, 14], [1287.8997492931944, 788], [1164.3713359400278, 469], [246.13749191118268, 65], [262.9639186062909, 158], [834.5437113034841, 356], [65.7401761723446, 26], [332.6118720331415, 109], [223.06988028327214, 105], [274.7627010945421, 233], [198.00676911580308, 69], [136.85207806991957, 61], [108.40442589390295, 86], [279.79614209796546, 105], [228.1891734022637, 88], [1505.8520521793394, 519], [504.85342868289104, 157], [72.26085994235086, 78], [162.52583505003167, 102], [434.1158194327827, 209], [1177.4018967811423, 484], [227.17078747292635, 233], [194.2895987168772, 118], [100.9434386129924, 91], [32.840176134772946, 34], [334.67823725984044, 177], [69.26681180106152, 39], [69.87887349487471, 50], [104.69308627745522, 84], [183.84349218696275, 152], [296.90842406224215, 115], [476.84577850784444, 302], [410.100212377738, 242], [599.5391067495734, 268], [55.63718168507205, 19], [305.12162648579397, 131], [551.1431513059613, 248], [268.0693229441649, 261], [630.7747657396817, 328], [98.57819516340714, 56], [282.0512884547279, 104], [75.81805566380717, 62], [384.58886490344526, 179], [1558.668264698934, 389], [98.3679757230559, 132], [92.67866901378125, 24], [263.08535321894976, 122], [67.36976532124845, 39], [84.17290516753462, 59], [7.138081601042359, 18], [225.2657060854699, 124], [455.81613763377163, 269], [151.15956247340728, 69], [25.794440710607887, 23], [430.2395947693958, 202], [669.0232983296298, 255], [138.18472132458805, 52], [246.097111484577, 138], [167.89406161822262, 99], [0.6357425714231795, 19], [736.3315413528044, 313], [563.386796662, 270], [62.85774274775167, 34], [613.0516489020952, 256], [100.6977708559225, 64], [52.21553549147154, 28], [299.57873263664044, 135], [483.61397317172623, 217], [192.98314416591893, 73], [186.54014549643398, 62], [275.9904428329137, 520], [553.1256104949839, 193], [407.48533863352486, 110], [1025.0753647990055, 319], [33.79800081713438, 56], [361.46761106936924, 276], [228.96971451535774, 121], [156.84759749378992, 71], [141.20553644295398, 81], [84.2023776604301, 38], [203.0621590568835, 100], [202.45211040640288, 97], [105.28928367141509, 69], [970.3290219154937, 328], [57.810884700378665, 44], [353.5003701547371, 128], [102.91235029568725, 66], [813.7198378052556, 306], [137.3785623104127, 78], [630.1877697998984, 242], [456.0283080124643, 201], [84.2528206551749, 52], [58.431841799084395, 40], [808.992880244506, 246], [275.520488095084, 125], [12.053122174163946, 89], [945.5872204853212, 446], [138.73766415139107, 106], [455.7809174512222, 200], [567.6805937141326, 266], [581.0087074822802, 288], [159.7672409374245, 106], [246.4952626104341, 86], [669.5988064423946, 341], [624.6720612122854, 258], [77.11570651153784, 52], [859.629809686402, 448], [372.5684680321201, 168], [27.537067178775033, 47], [34.6657202827173, 43], [1251.6893615484241, 476], [103.38880157027552, 104], [148.56965978891458, 106], [224.7267449470528, 137], [1068.0470049977864, 491], [13.842815080743094, 20], [119.77886116061609, 66], [94.36656336571332, 54], [167.61248369612258, 92], [90.01785281391676, 42], [754.074744718964, 425], [725.1242587668812, 231], [117.98226988613419, 96], [1016.0117618753543, 417], [226.85387359288688, 96], [1423.2183426988593, 582], [301.91400749420836, 146], [104.66441729367125, 98], [1484.1947508701098, 485], [82.59947130803721, 45], [606.6891677140936, 190], [52.11699363126894, 116], [2.8298029044779014, 6], [162.7258526919004, 166], [340.5609207916418, 141], [436.3499997451431, 171], [996.9649038710559, 491], [9.287045138069061, 29], [148.90898024756052, 40], [722.265616877721, 308], [285.31760886427844, 90], [227.81185144511073, 93], [212.9390073349864, 124], [182.95562021764044, 106], [354.22135776855976, 330], [45.97528292118841, 43], [234.0954800014838, 200], [104.41011072458787, 69], [286.6770611095402, 477], [62.134605045429794, 42], [317.69719941541393, 80], [213.18973344075425, 148], [572.7872131001163, 327], [523.801020418287, 231], [1515.7185275289748, 422], [8.598678633001782, 10], [337.4359083449808, 299], [503.8212767891805, 215], [258.5935045994938, 130], [68.26014409652271, 128], [346.6535703326206, 222], [264.45507078176024, 374], [1129.4555170156777, 489], [158.33540368231752, 88], [236.1226860452398, 85], [1029.7209692671527, 422], [87.3300178401841, 51], [319.28390093587063, 253], [774.8325140876022, 368], [339.4902350703413, 245], [206.33940887014433, 130], [199.2190197724808, 77], [1024.576356737581, 408], [677.6965589272261, 268], [836.039853621273, 258], [490.8316405265532, 212], [241.09022280379304, 103], [118.95346867964372, 92], [154.77782063870472, 94], [165.92852891714756, 86], [155.76305639464374, 66], [327.1785302673011, 135], [252.245307280813, 156], [479.9334587310691, 150], [132.6171799328015, 85], [485.80704168961165, 210], [104.23297419455093, 59], [606.0469465863997, 208], [834.8433449008734, 375], [21.270858504459966, 17], [1103.640270546202, 457], [204.92891949424848, 88], [771.96009912464, 319], [81.33334910670601, 27], [24.149859631465915, 39], [143.64546627818982, 73], [14.451443632495511, 36], [213.25002674721122, 119], [115.21135261928885, 68], [612.8816803270452, 321], [82.74074173711278, 71], [472.0507280057054, 192], [1288.119863792374, 498], [93.36953246803387, 75], [669.0389940572782, 266], [432.814111299052, 168], [90.71533281530651, 59], [42.427065752388216, 25], [583.9915174134057, 205], [1423.5024879921589, 478], [715.4161411539967, 377], [421.00679543951924, 181], [182.86458217119616, 47], [395.00330382559605, 195], [98.44720111018887, 54], [233.57247896371155, 120], [116.52556788127322, 169], [143.57154733215566, 495], [830.0829348321381, 361], [87.78320017084025, 41], [1243.279365898949, 465], [82.14634554138638, 50], [111.22242937247711, 65], [222.31075149982053, 110], [53.07210145171484, 62], [678.3898944482653, 306], [61.12575092602174, 44], [181.08708566706594, 52], [456.2169520158777, 194], [412.59323752194086, 197], [296.56158139902914, 105], [308.35910973903856, 148], [1186.0278788575665, 418], [338.9748493425525, 203], [929.1607515758933, 388], [413.7151670953026, 220], [11.634424736286746, 25], [62.11200641811547, 22], [865.9840039973459, 645], [929.5176945201962, 375], [145.19880340207192, 76], [529.4793057424081, 198], [217.38844716823496, 221], [639.9358696523991, 272], [1648.3033970797655, 488], [12.400357620661453, 7], [11.203676739351067, 15], [167.81112716663938, 64], [434.04169554956525, 348], [615.8965353200897, 182], [178.1044033458138, 79], [82.74220976892116, 91], [1136.6607209256267, 479], [216.1049959369359, 96], [331.0612665379847, 140], [187.65079966571614, 65], [1145.1808103260641, 504], [45.233372180017795, 50], [1064.1380450316196, 464], [117.62444832199128, 33], [311.2530591264358, 128], [252.63075519435824, 111], [94.38527604621959, 159], [254.57072998087506, 123], [41.312140234857, 40], [958.1677977755835, 470], [269.9935318505959, 143], [444.2748138168806, 120], [125.97001538732775, 93], [978.8036717802455, 372], [323.9911419394191, 155], [70.34254266281584, 66], [552.9373911912776, 282], [41.90103197633283, 24], [25.837054358926252, 34], [126.35262239366239, 103], [99.93449683836116, 35], [686.8394412935561, 271], [52.03377190823994, 15], [933.4660390056607, 365], [769.7726653978877, 355], [161.93961971276167, 53], [148.8210416443644, 70], [2412.0640003315266, 1200], [528.8150606962281, 274], [598.3324746435967, 187], [322.7304455928669, 169], [718.637902134016, 459], [283.4816166925832, 158], [497.9725845039293, 156], [211.05275948496984, 102], [110.45127587763136, 56], [1015.3429426027374, 464], [680.7811580330576, 275], [559.0191933666998, 146], [285.765264779837, 154], [164.94522407541353, 108], [934.8083031403914, 356], [1112.1931527937431, 423], [101.95774410534068, 80], [433.8469159318689, 342], [348.7816925388713, 178], [1475.5801655434216, 697], [349.68207774104076, 136], [1068.405453464094, 462], [89.0940063009366, 46], [276.59250428023915, 151], [11.22326955043809, 27], [230.2831660360025, 85], [161.03883619268788, 91], [1203.0098166109433, 441], [159.46807194720805, 135], [1220.573396161184, 457], [218.48270277923393, 94], [100.13915827506571, 62], [481.0654162351419, 195], [236.21116565167813, 108], [30.222498780683964, 46], [349.02653213380245, 127], [1048.7924258734583, 412], [52.88833960444572, 38], [267.1427509630944, 192], [136.96540564524776, 89], [277.46630649079816, 119], [269.989923885528, 138], [599.3252582470227, 248], [519.4218761213688, 247], [158.2521528338582, 172], [331.61429996085633, 187], [529.3706626332073, 222], [237.79340193822145, 119], [518.5270869649823, 222], [858.4377076189485, 388], [1350.2974434477637, 483], [660.9046366621515, 227], [165.57747399300365, 75], [199.26234320463777, 119], [311.9219342925139, 187], [845.1437146897579, 293], [657.5437882611038, 287], [1097.0934061756836, 593], [307.7453299257902, 107], [128.4768743469026, 56], [247.6229747105388, 97], [262.27047849954124, 124], [128.2227106190178, 101], [279.0162609873778, 91], [429.1260830329261, 155], [1000.5917270341829, 388], [217.43586214259142, 78], [661.2441773723417, 274], [1453.1484054967632, 508], [800.113456811722, 303], [844.005589338007, 543], [5.938589051464078, 18], [339.3471006140667, 172], [431.2356366142624, 189], [320.6489214046717, 168], [247.39690311072582, 154], [375.46732024347773, 182], [453.233588798204, 205], [36.48781086672807, 18], [260.9632637962492, 204], [79.77824372285974, 57], [1124.0644896134977, 467], [284.4094173517151, 123], [801.9966833586802, 308], [247.2049855562018, 426], [1210.478529666193, 496], [184.56124843540465, 60], [636.1043515433838, 204], [689.8353561190883, 298], [131.09338477850724, 181], [965.9169643679238, 300], [389.2617157736955, 127], [74.4949775005224, 31], [361.99938702070995, 132], [756.1818321913406, 325], [806.5251578545974, 418], [660.2025820371907, 270], [68.43339358960566, 54], [128.88971404250424, 64], [322.9447805332529, 140], [253.48866383984114, 105], [180.9909661504089, 112], [57.16433142405549, 32], [80.51060547445377, 78], [735.4270491358063, 324], [33.75496842071857, 22], [151.6828760261069, 64], [784.4806674705178, 354], [714.7669806697222, 284], [837.0165125163, 381], [90.07616272106316, 59], [81.00534691759276, 57], [427.4398822512153, 172], [78.256400846205, 63], [6.989143555963892, 47], [96.66100772214054, 47], [17.731560833793537, 47], [343.1083221579877, 117], [404.8466637675276, 159], [311.6945212923815, 142], [196.83539365994602, 160], [199.04647109155576, 123], [740.5888956877488, 318], [594.294670539439, 312], [576.6883902957411, 240], [578.0541419645281, 235], [20.533497768428333, 69], [1006.784896310475, 446], [320.9637148588653, 163], [817.8184137410012, 494], [562.2537629918643, 236], [25.37588594603585, 31], [680.8870210740715, 345], [726.6274242770287, 326], [10.052913570063538, 15], [166.74923075036168, 74], [269.7945858126035, 131], [311.3283234575017, 160], [517.6094171588602, 285], [85.17331278759775, 57], [308.66722948920915, 158], [128.5259682964861, 70], [79.0155359231685, 74], [189.63679013126057, 88], [511.53471610581437, 198], [493.16956198904336, 238], [418.328491656808, 194], [121.74705426695346, 74], [3.577120167999965, 10], [123.27241598226811, 68], [303.94825137638895, 96], [916.694829737269, 399], [511.2324944855635, 236], [400.9463560084664, 147], [415.2919997633401, 174], [8.356489018931825, 40], [751.575230943801, 351], [807.0080944531342, 356], [272.7402639640492, 107], [901.44559158008, 449], [438.32631293322265, 176], [1461.394082161563, 650], [103.04698701684174, 56], [143.73981185638286, 84], [349.27921088866196, 141], [21.895763213415194, 21], [461.26029906313175, 1062], [1093.0008935377496, 405], [733.0544509623692, 279], [123.26884478887769, 75], [61.46441261283928, 31], [1160.2512768398706, 453], [147.7468998905947, 108], [633.6895322380577, 426], [201.0883732715372, 132], [305.0356362813602, 149], [78.60318117867973, 43], [296.0705263413479, 147], [913.1434629093253, 383], [259.4788877097849, 123], [771.9105714619798, 310], [364.41251231851834, 169], [291.04631245117525, 151], [53.577800453058444, 44], [193.82129513285986, 66], [446.7542116426047, 157], [4.6600972648884635, 28], [110.05640725113278, 64], [842.7686244962315, 471], [82.54911165722297, 60], [334.15132471578727, 292], [117.49008089442191, 71]], "final_state": "tinker://07a741b9c4df208a09f7f0ba7592d096/weights/select-sel_dimuon_lr0.001_s0-final", "t": 1793807451.7725666} {"stage": "eval", "arm": "sel_dimuon_lr0.003_s0", "split": "val", "step": 40, "nll_sum": 195023.0376017507, "n_tokens": 94328.0, "n_examples": 500, "token_mean": 2.067498914444817, "example_mean": 1.9289748489949794, "per_example": [[157.04193325342385, 104], [786.0775834985288, 423], [283.1358505340577, 219], [1390.0813065560724, 467], [61.91088364413736, 53], [286.2891293933135, 151], [3.856744773178434, 20], [27.873194299267652, 27], [32.015976715072156, 32], [474.08990280340504, 247], [334.08767009561416, 223], [686.1227957178025, 280], [1000.9223998069101, 365], [74.0797950349779, 54], [397.76744642245285, 159], [378.3771794357526, 265], [671.2165597463754, 330], [221.66017947773707, 110], [302.27093951056486, 120], [87.33610358141823, 114], [214.75999774582306, 132], [79.65242837877258, 67], [105.56095659420976, 57], [134.9882487015857, 100], [567.2631435115172, 345], [2.6813598844767057, 14], [1262.6137191296405, 788], [1158.6224214494705, 469], [238.9649413644155, 65], [264.7875461331332, 158], [830.2347687336733, 356], [67.03037204562543, 26], [330.4011957243856, 109], [225.4999811216885, 105], [267.07287872438246, 233], [179.07926436762455, 69], [133.0282057590357, 61], [105.00095532185969, 86], [273.67840941817485, 105], [222.24051071380197, 88], [1495.0623150137399, 519], [496.1482069837648, 157], [67.08397715627507, 78], [158.32130816249628, 102], [423.3067794950948, 209], [1159.10821404329, 484], [238.86608427023748, 233], [192.48497055512235, 118], [92.05706933832312, 91], [31.301901313020608, 34], [332.7101346310592, 177], [66.52565516882169, 39], [67.27249554359423, 50], [105.6954011767848, 84], [182.71793715000967, 152], [287.1016504898944, 115], [464.38551864374585, 302], [395.6164735476268, 242], [584.1860283001506, 268], [54.760721466123414, 19], [297.99660460151426, 131], [531.1582113394616, 248], [262.29077418873476, 261], [611.9939716705485, 328], [98.38153144958778, 56], [271.4037058261074, 104], [70.63323176687845, 62], [380.3533574751468, 179], [1543.846506590734, 389], [96.24006379635375, 132], [88.19434087505715, 24], [255.89037311552238, 122], [66.20075782931417, 39], [81.82211902139898, 59], [3.2268126328571043, 18], [222.15278577056597, 124], [439.7569461341027, 269], [143.0245366126328, 69], [24.56500587672417, 23], [420.1172542360455, 202], [663.0130182031298, 255], [137.2174790093577, 52], [234.4953647989587, 138], [164.59614914133363, 99], [1.2466453905103663, 19], [738.0814706172605, 313], [561.1687957695608, 270], [60.67589902302643, 34], [607.8585509431905, 256], [98.07437099134768, 64], [55.11545820821152, 28], [293.67511073993956, 135], [480.81448258151977, 217], [178.01586884325297, 73], [178.09238522527448, 62], [266.2313053757503, 520], [538.3755127048607, 193], [399.651296304928, 110], [1003.0657620513684, 319], [29.542749658578032, 56], [355.3097206023647, 276], [221.86514253296264, 121], [159.3047465715872, 71], [140.16958567784422, 81], [75.22081101033109, 38], [203.8173224452812, 100], [199.32083280817824, 97], [108.47690121435699, 69], [962.9856347503492, 328], [49.521244417806884, 44], [343.91338856765924, 128], [98.88875617973508, 66], [803.4144893823006, 306], [136.26701058815388, 78], [616.0272920350444, 242], [447.61625838048326, 201], [75.48419937461222, 52], [54.29950035302318, 40], [797.4802963401198, 246], [269.527274074273, 125], [8.02502659158381, 89], [937.9099850733874, 446], [131.51045619221918, 106], [449.2887691555734, 200], [555.5965746569618, 266], [573.4778617623524, 288], [157.8976030973954, 106], [239.41820867549814, 86], [663.784402689851, 341], [612.0681844251485, 258], [75.21946330659011, 52], [847.1365712745173, 448], [368.82748371220805, 168], [22.90461036096076, 47], [33.597745609641606, 43], [1237.9593924323617, 476], [97.00304291554858, 104], [146.82528358433774, 106], [217.04119672888552, 137], [1051.359718239215, 491], [14.101304540014098, 20], [113.95482876975257, 66], [84.64343093465868, 54], [159.34718239901122, 92], [84.5012049190791, 42], [749.2767048471524, 425], [710.2008335470159, 231], [115.60066352624926, 96], [997.1508562663, 417], [224.81063891435042, 96], [1402.6926114060916, 582], [291.75001134308695, 146], [94.94949246683063, 98], [1463.3848495635793, 485], [79.28048717396814, 45], [597.6424889534683, 190], [43.58317485549799, 116], [3.1343303051689873, 6], [162.58835158199508, 166], [338.89419386875215, 141], [429.4468669038524, 171], [988.0352986337084, 491], [9.73086050557231, 29], [139.0974686670154, 40], [708.9689465097099, 308], [277.9495007951426, 90], [214.7832081196575, 93], [199.36859077631925, 124], [174.81883805867255, 106], [347.29685145564235, 330], [43.500767693791204, 43], [228.84579755515983, 200], [103.51627875929717, 69], [277.19480665420724, 477], [59.08482422891075, 42], [305.2643518888708, 80], [206.20272899240445, 148], [559.0294349835531, 327], [521.246137635906, 231], [1505.8820349395655, 422], [5.557173796734787, 10], [320.8970265002275, 299], [489.0819367559634, 215], [250.90182197144532, 130], [65.95903801287386, 128], [336.24048786874323, 222], [270.43076830103655, 374], [1126.0704583315182, 489], [154.86606957323283, 88], [235.0814698904053, 85], [1016.1092493040187, 422], [85.68431219481317, 51], [320.2050897243912, 253], [757.8717086666074, 368], [327.0567228267455, 245], [201.65332665606957, 130], [189.30689952953935, 77], [1019.4392855248279, 408], [659.6947305731153, 268], [823.8844388532052, 258], [476.89837732331307, 212], [231.87314508154486, 103], [110.70808306401932, 92], [141.65491304445823, 94], [161.40157078331777, 86], [147.94021682103084, 66], [319.2375397726064, 135], [250.59321601717238, 156], [471.703655882392, 150], [128.2157028204283, 85], [469.1408116483726, 210], [98.29135347722058, 59], [587.7161717665836, 208], [818.1219441131716, 375], [20.353741522540076, 17], [1094.2731644645974, 457], [199.56340044793433, 88], [765.7792545631328, 319], [73.0298420670515, 27], [20.515171653265725, 39], [136.82786253952918, 73], [9.370303718707419, 36], [203.3898875580453, 119], [112.22852327068085, 68], [603.056577267401, 321], [83.72325716391515, 71], [461.8674003456226, 192], [1264.5588801389677, 498], [84.67389183879823, 75], [652.9088415467941, 266], [427.4459887221092, 168], [82.62814320594026, 59], [43.39538584038473, 25], [579.5185173806021, 205], [1413.6539682585153, 478], [707.0663632092328, 377], [416.0269735317843, 181], [182.09189113287266, 47], [381.3729159837858, 195], [89.54513931664587, 54], [225.4844614646945, 120], [112.2394636757981, 169], [151.0111386475619, 495], [807.5668841535226, 361], [85.97057350488285, 41], [1239.4662618718748, 465], [79.99157514813851, 50], [106.54903675499395, 65], [214.52064677030148, 110], [49.027249339322225, 62], [667.7819911700935, 306], [56.302168275513395, 44], [173.72072510420446, 52], [445.3851478515335, 194], [404.1248573054413, 197], [298.95629325898653, 105], [299.4481155380636, 148], [1160.3253325611454, 418], [332.03404030270303, 203], [913.1418826947174, 388], [403.8342024411577, 220], [10.968219592284186, 25], [65.13021597559964, 22], [833.7858202725433, 645], [929.2430299636981, 375], [138.16433427073298, 76], [512.4063964823872, 198], [214.38160552445152, 221], [633.0787160752443, 272], [1636.9137864285294, 488], [11.107692799232609, 7], [7.734875627002339, 15], [163.23376057872338, 64], [419.1449466251411, 348], [602.8211758756424, 182], [177.6441353232981, 79], [80.26406164511252, 91], [1121.56784507957, 479], [210.96960132271488, 96], [328.95825465992857, 140], [181.43181543220362, 65], [1131.3293085866007, 504], [43.435662478977065, 50], [1060.3648912828808, 464], [101.70073371036415, 33], [302.29003632958575, 128], [242.2904850870682, 111], [92.70054793989425, 159], [248.9083045813968, 123], [39.08663601526132, 40], [955.9517107015381, 470], [256.0290625242269, 143], [434.1995306376166, 120], [122.8563389402184, 93], [964.7270413566475, 372], [317.01873481369694, 155], [69.32458406512069, 66], [544.7054921326344, 282], [39.58678931315529, 24], [23.105685378310227, 34], [121.74316575509147, 103], [95.91702285320798, 35], [665.3194981595298, 271], [51.19258937787163, 15], [929.211399535172, 365], [760.2764707759188, 355], [159.35215655641332, 53], [143.92934298192267, 70], [2401.0220008600827, 1200], [507.8850508950545, 274], [593.8525331543751, 187], [304.3597529077633, 169], [708.9968257145956, 459], [279.2341183009048, 158], [488.88633827958074, 156], [214.22829882564565, 102], [107.66882733803322, 56], [996.3090531365178, 464], [671.5405858543809, 275], [545.4838602754862, 146], [275.24986658737635, 154], [158.3115779592008, 108], [915.0212025967166, 356], [1091.6176658272263, 423], [99.47346264705084, 80], [421.2385443427038, 342], [344.0109230313101, 178], [1454.4437436765766, 697], [348.54810626554354, 136], [1069.3661969221644, 462], [88.06750811338588, 46], [269.6987870146131, 151], [7.066050326218829, 27], [222.271796775354, 85], [155.759211710003, 91], [1193.2273700434725, 441], [143.44415875778577, 135], [1207.164700365327, 457], [217.92099168924506, 94], [98.63388721716547, 62], [476.6253034977981, 195], [236.9651989585849, 108], [23.66849299619753, 46], [337.87651418739915, 127], [1029.171524751906, 412], [53.11517896644364, 38], [256.49473679935545, 192], [127.07368545931604, 89], [261.0590487447189, 119], [261.2539762348597, 138], [587.3012761728687, 248], [512.5342954918024, 247], [162.93083042769558, 172], [326.8003283210037, 187], [515.822525914482, 222], [228.4789930695224, 119], [505.7816269579271, 222], [846.6612386246943, 388], [1341.6453218731622, 483], [662.7851418169121, 227], [157.0409503006431, 75], [187.81474925091652, 119], [296.6469158884156, 187], [819.3969391027404, 293], [638.5510235575584, 287], [1081.2115229228766, 593], [300.3589388932778, 107], [123.91937207160481, 56], [240.37508477613073, 97], [250.87686468815082, 124], [120.77481580004269, 101], [280.49344526563584, 91], [424.2455265210374, 155], [986.3107313336877, 388], [209.94533802929254, 78], [656.424489144174, 274], [1443.5986116004324, 508], [792.6534081419504, 303], [828.2356726428116, 543], [3.735005047607956, 18], [324.5620482401646, 172], [423.21123657970367, 189], [313.97561165449224, 168], [237.57434459659726, 154], [369.2161605379438, 182], [439.99428655557404, 205], [35.50605380926754, 18], [262.25334955259586, 204], [78.58229318581652, 57], [1117.807811104558, 467], [273.55555417034975, 123], [793.242146009612, 308], [242.9818238294033, 426], [1200.2490488008095, 496], [175.47694484427234, 60], [626.8893294705776, 204], [669.3820164028543, 298], [125.00538872001425, 181], [954.7742258697858, 300], [382.1962871271571, 127], [79.12671841061126, 31], [352.62686649508305, 132], [745.5468060600451, 325], [795.2882961598916, 418], [644.6690010521525, 270], [68.39618109678395, 54], [124.01618081854394, 64], [313.36302527515056, 140], [252.363581911427, 105], [173.7502417211872, 112], [49.71182711602523, 32], [78.16562084602265, 78], [726.092307471521, 324], [32.815246321656105, 22], [140.80832434742842, 64], [761.5782538093863, 354], [707.179123147293, 284], [822.2608498467307, 381], [82.2159364051331, 59], [78.03120691548975, 57], [419.4979591421761, 172], [76.72458001382074, 63], [10.412339616373174, 47], [94.52213348736268, 47], [13.932186211479802, 47], [332.32707815919093, 117], [390.8774503791883, 159], [308.0343365874023, 142], [191.85196008143976, 160], [189.51405434309163, 123], [719.805306355716, 318], [585.0186141776715, 312], [572.430052876045, 240], [556.5887932897676, 235], [17.001047613441415, 69], [1001.021062644526, 446], [317.74413334396377, 163], [814.8224842718314, 494], [555.3563835043001, 236], [26.550652929935495, 31], [669.7071353282809, 345], [710.4267837633306, 326], [7.230583952787583, 15], [150.94029876618697, 74], [263.4180733949761, 131], [305.70060859223304, 160], [512.2099593467574, 285], [79.39672605862688, 57], [308.5624191426032, 158], [124.21369044586754, 70], [70.01696744430956, 74], [180.92083390809057, 88], [498.1037195136905, 198], [490.96767618176636, 238], [404.928278598014, 194], [117.54984026391924, 74], [2.107540810078717, 10], [118.59149325081671, 68], [292.2858093852701, 96], [911.4214732804171, 399], [499.2812498293508, 236], [389.1225092142254, 147], [402.4859519701566, 174], [8.431052654713767, 40], [740.380643567898, 351], [793.4794109829194, 356], [268.9113654687699, 107], [894.4814362864454, 449], [435.85813466318905, 176], [1442.2322270044874, 650], [90.36677862737406, 56], [137.46036244878724, 84], [345.1279236600931, 141], [20.70876686129077, 21], [461.803012091598, 1062], [1076.357221135564, 405], [715.010848717664, 279], [119.7204098623879, 75], [61.131604065063584, 31], [1144.8424667781637, 453], [136.55589390573732, 108], [627.5070959765485, 426], [196.24755886581033, 132], [299.76825867296793, 149], [73.62968457989746, 43], [290.35699356357327, 147], [890.1395009364087, 383], [242.221893130667, 123], [769.3596630008487, 310], [358.70520898860923, 169], [288.4647041075186, 151], [48.27634293022675, 44], [175.52246903141258, 66], [443.66720054369944, 157], [5.40466724680482, 28], [105.94649047513303, 64], [835.0460636694606, 471], [78.9928229393463, 60], [319.87804697624597, 292], [116.72487580541201, 71]], "final_state": "tinker://c1d1931de8c1fc62d30b56642bd6b4bf/weights/select-sel_dimuon_lr0.003_s0-final", "t": 1793807477.9954503} {"stage": "eval_done", "seconds": 160.32491517066956, "total_seconds": 737.437087059021, "t": 1793807477.9960814}