{"stage": "eval_set", "split": "test", "n": 500, "sha256": "77a0f36db82bf06978bcea4d7d139c42367885e890c59d5081516e05bfc7a85a", "t": 1793807491.1281042} {"stage": "get_info", "arm": "baseline_adamw_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807495.1743798} {"stage": "init_saved", "group": "s0", "path": "tinker://f11c48d0f72f37d4ff9c6cde3cf5e327/weights/confirm-init-s0", "by": "baseline_adamw_s0", "t": 1793807500.8067744} {"stage": "initial_output", "arm": "baseline_adamw_s0", "init": "s0", "init_path": "tinker://f11c48d0f72f37d4ff9c6cde3cf5e327/weights/confirm-init-s0", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807502.3120492} {"stage": "step0_saved", "arm": "baseline_adamw_s0", "path": "tinker://f11c48d0f72f37d4ff9c6cde3cf5e327/weights/confirm-baseline_adamw_s0-step0", "before_first_update": true, "t": 1793807506.251714} {"stage": "get_info", "arm": "treatment_dimuon_s0", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807508.9328723} {"stage": "get_info", "arm": "treatment_dimuon_s0", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807513.0904653} {"stage": "initial_output", "arm": "treatment_dimuon_s0", "init": "s0", "init_path": "tinker://f11c48d0f72f37d4ff9c6cde3cf5e327/weights/confirm-init-s0", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807514.291326} {"stage": "step0_saved", "arm": "treatment_dimuon_s0", "path": "tinker://5114900d3184a1f9e9047b5305999c3f/weights/confirm-treatment_dimuon_s0-step0", "before_first_update": true, "t": 1793807519.6843896} {"stage": "get_info", "arm": "baseline_adamw_s1", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807715.9412515} {"stage": "init_saved", "group": "s1", "path": "tinker://3237e16ec54b87586f4118a972d03f52/weights/confirm-init-s1", "by": "baseline_adamw_s1", "t": 1793807720.3055637} {"stage": "initial_output", "arm": "baseline_adamw_s1", "init": "s1", "init_path": "tinker://3237e16ec54b87586f4118a972d03f52/weights/confirm-init-s1", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807721.693859} {"stage": "step0_saved", "arm": "baseline_adamw_s1", "path": "tinker://3237e16ec54b87586f4118a972d03f52/weights/confirm-baseline_adamw_s1-step0", "before_first_update": true, "t": 1793807725.575416} {"stage": "get_info", "arm": "treatment_dimuon_s1", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807728.1463645} {"stage": "get_info", "arm": "treatment_dimuon_s1", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807732.4113746} {"stage": "initial_output", "arm": "treatment_dimuon_s1", "init": "s1", "init_path": "tinker://3237e16ec54b87586f4118a972d03f52/weights/confirm-init-s1", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807733.6006818} {"stage": "step0_saved", "arm": "treatment_dimuon_s1", "path": "tinker://08e25db82a092035669aa384182fbeb0/weights/confirm-treatment_dimuon_s1-step0", "before_first_update": true, "t": 1793807737.7806604} {"stage": "get_info", "arm": "baseline_adamw_s2", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807740.4266436} {"stage": "init_saved", "group": "s2", "path": "tinker://8eaad4366b3e3f1193bc20115d07490d/weights/confirm-init-s2", "by": "baseline_adamw_s2", "t": 1793807744.3411934} {"stage": "initial_output", "arm": "baseline_adamw_s2", "init": "s2", "init_path": "tinker://8eaad4366b3e3f1193bc20115d07490d/weights/confirm-init-s2", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807745.535681} {"stage": "step0_saved", "arm": "baseline_adamw_s2", "path": "tinker://8eaad4366b3e3f1193bc20115d07490d/weights/confirm-baseline_adamw_s2-step0", "before_first_update": true, "t": 1793807749.4412212} {"stage": "get_info", "arm": "treatment_dimuon_s2", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807752.046658} {"stage": "get_info", "arm": "treatment_dimuon_s2", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793807756.2980297} {"stage": "initial_output", "arm": "treatment_dimuon_s2", "init": "s2", "init_path": "tinker://8eaad4366b3e3f1193bc20115d07490d/weights/confirm-init-s2", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793807757.5229127} {"stage": "step0_saved", "arm": "treatment_dimuon_s2", "path": "tinker://c8db5bb847cd27aaacea58a0dd7561a8/weights/confirm-treatment_dimuon_s2-step0", "before_first_update": true, "t": 1793807761.3435047} {"stage": "setup_done", "seconds": 274.54359698295593, "t": 1793807761.3451395} {"stage": "train_step", "arm": "baseline_adamw_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": 37.608055114746094, "t": 1793807768.539028} {"stage": "train_step", "arm": "treatment_dimuon_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": 37.609336853027344, "t": 1793807769.1515718} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 1, "batch_sha256": "1ac9ae98a20e133f44093eaa077da51aafd0c393c59501ce0bf5699ab3a1daa6", "params_type": "AdamParams", "train_nll_sum": 15597.49257108001, "train_tokens": 7215.0, "train_token_mean_nll": 2.1618146321663216, "grad_norm": 29.42059898376465, "t": 1793807769.704997} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 1, "batch_sha256": "1ac9ae98a20e133f44093eaa077da51aafd0c393c59501ce0bf5699ab3a1daa6", "params_type": "DimuonParams", "train_nll_sum": 15597.49257108001, "train_tokens": 7215.0, "train_token_mean_nll": 2.1618146321663216, "grad_norm": 29.423738479614258, "t": 1793807769.7058065} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 1, "batch_sha256": "cf85e7dd2077a3808f9d8eb003dcac558db2a9c27c6c364c6c7e818eba440acd", "params_type": "AdamParams", "train_nll_sum": 14288.20404328693, "train_tokens": 6537.0, "train_token_mean_nll": 2.1857433139493545, "grad_norm": 34.98456573486328, "t": 1793807769.706629} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 1, "batch_sha256": "cf85e7dd2077a3808f9d8eb003dcac558db2a9c27c6c364c6c7e818eba440acd", "params_type": "DimuonParams", "train_nll_sum": 14288.20404328693, "train_tokens": 6537.0, "train_token_mean_nll": 2.1857433139493545, "grad_norm": 34.98648452758789, "t": 1793807769.7073853} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13525.71215649397, "train_tokens": 6073.0, "train_token_mean_nll": 2.227187906552605, "grad_norm": 24.235151290893555, "t": 1793807776.4338403} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14160.180366090572, "train_tokens": 6073.0, "train_token_mean_nll": 2.3316615126116536, "grad_norm": 47.722049713134766, "t": 1793807777.570357} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 2, "batch_sha256": "50d9810e7139e0ec50571174bb67f2686423197bf607f62b4173c92b192bca56", "params_type": "AdamParams", "train_nll_sum": 17147.231115863193, "train_tokens": 7364.0, "train_token_mean_nll": 2.328521335668549, "grad_norm": 22.783037185668945, "t": 1793807777.5947874} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 2, "batch_sha256": "50d9810e7139e0ec50571174bb67f2686423197bf607f62b4173c92b192bca56", "params_type": "DimuonParams", "train_nll_sum": 17877.37323375871, "train_tokens": 7364.0, "train_token_mean_nll": 2.427671541792329, "grad_norm": 33.294429779052734, "t": 1793807777.595644} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 2, "batch_sha256": "4296296b3ce362f8d77ee2d8a3f8e1f567518fdec3382a588b7a0e74d379e4d2", "params_type": "AdamParams", "train_nll_sum": 12189.409659338595, "train_tokens": 5965.0, "train_token_mean_nll": 2.0434886268798986, "grad_norm": 36.76326370239258, "t": 1793807777.5966227} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 2, "batch_sha256": "4296296b3ce362f8d77ee2d8a3f8e1f567518fdec3382a588b7a0e74d379e4d2", "params_type": "DimuonParams", "train_nll_sum": 12722.788495389937, "train_tokens": 5965.0, "train_token_mean_nll": 2.1329067050108863, "grad_norm": 52.657283782958984, "t": 1793807777.5975754} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12365.795715993296, "train_tokens": 5852.0, "train_token_mean_nll": 2.1130888099783487, "grad_norm": 26.842697143554688, "t": 1793807783.852818} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13307.010963071534, "train_tokens": 5852.0, "train_token_mean_nll": 2.273925318364924, "grad_norm": 53.29970932006836, "t": 1793807784.8737829} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 3, "batch_sha256": "2db342ac8653a81d68a42b9b183fb3b9aed939bb57d0d1bdecac65d6b1181cac", "params_type": "AdamParams", "train_nll_sum": 12755.303031367004, "train_tokens": 5761.0, "train_token_mean_nll": 2.214077943302726, "grad_norm": 17.413562774658203, "t": 1793807784.8746321} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 3, "batch_sha256": "2db342ac8653a81d68a42b9b183fb3b9aed939bb57d0d1bdecac65d6b1181cac", "params_type": "DimuonParams", "train_nll_sum": 13730.033904726588, "train_tokens": 5761.0, "train_token_mean_nll": 2.383272679174898, "grad_norm": 30.465068817138672, "t": 1793807784.9500751} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 3, "batch_sha256": "a6c4910fee3391dd40cdcf358d57ba6873eb4e332b80d45b1df01230ae171087", "params_type": "AdamParams", "train_nll_sum": 12109.845140456904, "train_tokens": 6328.0, "train_token_mean_nll": 1.9136923420443908, "grad_norm": 20.154399871826172, "t": 1793807784.9509132} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 3, "batch_sha256": "a6c4910fee3391dd40cdcf358d57ba6873eb4e332b80d45b1df01230ae171087", "params_type": "DimuonParams", "train_nll_sum": 12959.060802072516, "train_tokens": 6328.0, "train_token_mean_nll": 2.047892035725745, "grad_norm": 33.321327209472656, "t": 1793807784.951671} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16047.399671182084, "train_tokens": 7125.0, "train_token_mean_nll": 2.252266620516784, "grad_norm": 15.21214771270752, "t": 1793807791.6843865} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17062.758317540003, "train_tokens": 7125.0, "train_token_mean_nll": 2.394773097198597, "grad_norm": 29.346864700317383, "t": 1793807791.6851695} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 4, "batch_sha256": "f721be7f9ab8f69c54fad3c79e81a13aede41a5591f61329128dba053380d7b9", "params_type": "AdamParams", "train_nll_sum": 10986.925268987674, "train_tokens": 5212.0, "train_token_mean_nll": 2.108005615692186, "grad_norm": 17.605539321899414, "t": 1793807791.6859398} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 4, "batch_sha256": "f721be7f9ab8f69c54fad3c79e81a13aede41a5591f61329128dba053380d7b9", "params_type": "DimuonParams", "train_nll_sum": 11688.17350229705, "train_tokens": 5212.0, "train_token_mean_nll": 2.242550556849012, "grad_norm": 33.585540771484375, "t": 1793807791.686669} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 4, "batch_sha256": "1647d08d8e432294bb570c4a95cf7480267f9c0c779cf74346b683326fad6fc4", "params_type": "AdamParams", "train_nll_sum": 12364.753052571505, "train_tokens": 5785.0, "train_token_mean_nll": 2.137381685837771, "grad_norm": 18.103822708129883, "t": 1793807791.6881177} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 4, "batch_sha256": "1647d08d8e432294bb570c4a95cf7480267f9c0c779cf74346b683326fad6fc4", "params_type": "DimuonParams", "train_nll_sum": 13259.251736970615, "train_tokens": 5785.0, "train_token_mean_nll": 2.2920054860796224, "grad_norm": 37.82242965698242, "t": 1793807791.6889827} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15765.918990541653, "train_tokens": 6823.0, "train_token_mean_nll": 2.310701889277686, "grad_norm": 15.927567481994629, "t": 1793807797.9046032} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16649.432601887922, "train_tokens": 6823.0, "train_token_mean_nll": 2.440192378995738, "grad_norm": 30.156465530395508, "t": 1793807798.8972394} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 5, "batch_sha256": "664b97e5939bce1b4a840d90b4f260b25fc57a67fe8a41c35788a775b82681c3", "params_type": "AdamParams", "train_nll_sum": 14220.32768872282, "train_tokens": 6654.0, "train_token_mean_nll": 2.137109661665588, "grad_norm": 13.942651748657227, "t": 1793807799.0811493} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 5, "batch_sha256": "664b97e5939bce1b4a840d90b4f260b25fc57a67fe8a41c35788a775b82681c3", "params_type": "DimuonParams", "train_nll_sum": 15001.298061928135, "train_tokens": 6654.0, "train_token_mean_nll": 2.2544782179032365, "grad_norm": 25.550609588623047, "t": 1793807799.0819435} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 5, "batch_sha256": "bea5e8f11e3528d2034c41e890df9f874b18344ab6dc3886bac4e9645e222c63", "params_type": "AdamParams", "train_nll_sum": 12001.280240258648, "train_tokens": 6010.0, "train_token_mean_nll": 1.9968852313242342, "grad_norm": 17.891544342041016, "t": 1793807799.0826619} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 5, "batch_sha256": "bea5e8f11e3528d2034c41e890df9f874b18344ab6dc3886bac4e9645e222c63", "params_type": "DimuonParams", "train_nll_sum": 12807.706101133197, "train_tokens": 6010.0, "train_token_mean_nll": 2.131065907010515, "grad_norm": 31.303071975708008, "t": 1793807799.0839097} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13265.20035825982, "train_tokens": 6097.0, "train_token_mean_nll": 2.175693022512682, "grad_norm": 20.884681701660156, "t": 1793807804.8758597} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 13925.643016685848, "train_tokens": 6097.0, "train_token_mean_nll": 2.2840155841702225, "grad_norm": 40.790687561035156, "t": 1793807805.9573286} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 6, "batch_sha256": "3518b819b1d63dff7d6bb94000852131c68cb7d52b02f898313b56add0be2493", "params_type": "AdamParams", "train_nll_sum": 13376.961628499595, "train_tokens": 6410.0, "train_token_mean_nll": 2.086889489625522, "grad_norm": 15.014702796936035, "t": 1793807805.9654772} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 6, "batch_sha256": "3518b819b1d63dff7d6bb94000852131c68cb7d52b02f898313b56add0be2493", "params_type": "DimuonParams", "train_nll_sum": 14208.640616344077, "train_tokens": 6410.0, "train_token_mean_nll": 2.2166366016137404, "grad_norm": 30.805639266967773, "t": 1793807805.966199} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 6, "batch_sha256": "0c3ad9f926b09e5f4914db7a0518ac86cb66fdfca48ee01344c08119d3fe618b", "params_type": "AdamParams", "train_nll_sum": 10908.677685743405, "train_tokens": 5732.0, "train_token_mean_nll": 1.9031189263334622, "grad_norm": 16.914161682128906, "t": 1793807805.9668796} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 6, "batch_sha256": "0c3ad9f926b09e5f4914db7a0518ac86cb66fdfca48ee01344c08119d3fe618b", "params_type": "DimuonParams", "train_nll_sum": 11578.443395004297, "train_tokens": 5732.0, "train_token_mean_nll": 2.0199657004543434, "grad_norm": 34.780147552490234, "t": 1793807805.9675307} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 12940.841338033608, "train_tokens": 6602.0, "train_token_mean_nll": 1.960139554382552, "grad_norm": 15.098225593566895, "t": 1793807812.4201639} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 13641.296684438728, "train_tokens": 6602.0, "train_token_mean_nll": 2.0662370015811464, "grad_norm": 27.620450973510742, "t": 1793807813.948903} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 7, "batch_sha256": "35dbaf237d42fbc446db7b993bd8883bc7af7c74b6ceae19ec46571aff5808dc", "params_type": "AdamParams", "train_nll_sum": 14675.212268196428, "train_tokens": 6319.0, "train_token_mean_nll": 2.3223947251458186, "grad_norm": 13.528425216674805, "t": 1793807813.9497302} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 7, "batch_sha256": "35dbaf237d42fbc446db7b993bd8883bc7af7c74b6ceae19ec46571aff5808dc", "params_type": "DimuonParams", "train_nll_sum": 15446.155546374159, "train_tokens": 6319.0, "train_token_mean_nll": 2.444398725490451, "grad_norm": 27.036792755126953, "t": 1793807813.9505136} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 7, "batch_sha256": "208b68c215448bd900070c92b94743060495eff9af76b7a908c9d612edc71cdb", "params_type": "AdamParams", "train_nll_sum": 14339.639778490064, "train_tokens": 6270.0, "train_token_mean_nll": 2.2870238881164378, "grad_norm": 16.80855941772461, "t": 1793807813.9512281} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 7, "batch_sha256": "208b68c215448bd900070c92b94743060495eff9af76b7a908c9d612edc71cdb", "params_type": "DimuonParams", "train_nll_sum": 14845.784036070403, "train_tokens": 6270.0, "train_token_mean_nll": 2.3677486500909732, "grad_norm": 29.980518341064453, "t": 1793807813.9518983} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13571.321706744158, "train_tokens": 6404.0, "train_token_mean_nll": 2.11919452010371, "grad_norm": 15.018590927124023, "t": 1793807821.0833306} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14101.604563668847, "train_tokens": 6404.0, "train_token_mean_nll": 2.201999463408627, "grad_norm": 30.56712532043457, "t": 1793807821.0848274} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 8, "batch_sha256": "09e5894dc0399de6706a0e11975888debedfe108acedecb4cc135deecf689875", "params_type": "AdamParams", "train_nll_sum": 13515.600610345024, "train_tokens": 5930.0, "train_token_mean_nll": 2.2791906594173734, "grad_norm": 15.34875774383545, "t": 1793807821.0855212} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 8, "batch_sha256": "09e5894dc0399de6706a0e11975888debedfe108acedecb4cc135deecf689875", "params_type": "DimuonParams", "train_nll_sum": 14077.604812404239, "train_tokens": 5930.0, "train_token_mean_nll": 2.373963712041187, "grad_norm": 33.443153381347656, "t": 1793807821.0862536} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 8, "batch_sha256": "5bd1bfcb3aed30a8c5da6e8f49183bacee46f6b61b0181bb2eae5a0db0aa7625", "params_type": "AdamParams", "train_nll_sum": 16308.208505770617, "train_tokens": 7756.0, "train_token_mean_nll": 2.102657104921431, "grad_norm": 11.602840423583984, "t": 1793807821.8748763} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 8, "batch_sha256": "5bd1bfcb3aed30a8c5da6e8f49183bacee46f6b61b0181bb2eae5a0db0aa7625", "params_type": "DimuonParams", "train_nll_sum": 16991.20387322223, "train_tokens": 7756.0, "train_token_mean_nll": 2.1907173637470643, "grad_norm": 22.98558807373047, "t": 1793807821.8758395} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10710.578740148587, "train_tokens": 5225.0, "train_token_mean_nll": 2.0498715292150407, "grad_norm": 15.062013626098633, "t": 1793807827.8198771} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11146.337526299834, "train_tokens": 5225.0, "train_token_mean_nll": 2.133270339961691, "grad_norm": 30.057170867919922, "t": 1793807828.8937979} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 9, "batch_sha256": "c01c0297794b714d3c768f53d99206463d0ee1c7cd358f38989413163be584b4", "params_type": "AdamParams", "train_nll_sum": 12294.607831544323, "train_tokens": 6087.0, "train_token_mean_nll": 2.019814002225123, "grad_norm": 14.420003890991211, "t": 1793807828.8950331} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 9, "batch_sha256": "c01c0297794b714d3c768f53d99206463d0ee1c7cd358f38989413163be584b4", "params_type": "DimuonParams", "train_nll_sum": 12764.64967946407, "train_tokens": 6087.0, "train_token_mean_nll": 2.0970346113790157, "grad_norm": 25.45828628540039, "t": 1793807828.8958747} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 9, "batch_sha256": "ea39bae2e59a90515aec49ba63d547b342512eb78440cd14db1f6f21beac4eb6", "params_type": "AdamParams", "train_nll_sum": 14220.096889301782, "train_tokens": 6743.0, "train_token_mean_nll": 2.1088679948541866, "grad_norm": 12.768843650817871, "t": 1793807828.8982244} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 9, "batch_sha256": "ea39bae2e59a90515aec49ba63d547b342512eb78440cd14db1f6f21beac4eb6", "params_type": "DimuonParams", "train_nll_sum": 14787.567942975898, "train_tokens": 6743.0, "train_token_mean_nll": 2.1930250545715406, "grad_norm": 24.43447494506836, "t": 1793807828.9008164} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14491.076521311528, "train_tokens": 7976.0, "train_token_mean_nll": 1.8168350703750662, "grad_norm": 13.503714561462402, "t": 1793807835.282304} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 14959.279129354, "train_tokens": 7976.0, "train_token_mean_nll": 1.8755365006712637, "grad_norm": 21.976778030395508, "t": 1793807836.461427} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 10, "batch_sha256": "d4b822a4a3f019be6db05b832270b68fcb610684c5421970715c23882b885b63", "params_type": "AdamParams", "train_nll_sum": 12243.921058846481, "train_tokens": 6005.0, "train_token_mean_nll": 2.038954381156783, "grad_norm": 14.513922691345215, "t": 1793807836.463122} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 10, "batch_sha256": "d4b822a4a3f019be6db05b832270b68fcb610684c5421970715c23882b885b63", "params_type": "DimuonParams", "train_nll_sum": 12627.423670415363, "train_tokens": 6005.0, "train_token_mean_nll": 2.102818263183241, "grad_norm": 25.538206100463867, "t": 1793807836.4854977} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 10, "batch_sha256": "d86636715c462840fcf022632729d33f1ddb20fb80e87702da7ed1fe5d526723", "params_type": "AdamParams", "train_nll_sum": 12394.687132397023, "train_tokens": 6039.0, "train_token_mean_nll": 2.0524403266098727, "grad_norm": 15.224900245666504, "t": 1793807836.4875727} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 10, "batch_sha256": "d86636715c462840fcf022632729d33f1ddb20fb80e87702da7ed1fe5d526723", "params_type": "DimuonParams", "train_nll_sum": 12828.526852292536, "train_tokens": 6039.0, "train_token_mean_nll": 2.124279988788299, "grad_norm": 23.21336555480957, "t": 1793807836.4886284} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10238.407342868095, "train_tokens": 5826.0, "train_token_mean_nll": 1.7573648031012865, "grad_norm": 14.750724792480469, "t": 1793807842.4190035} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 10498.797069369622, "train_tokens": 5826.0, "train_token_mean_nll": 1.8020592292086548, "grad_norm": 20.454017639160156, "t": 1793807843.5434523} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 11, "batch_sha256": "fdafeb58ece6d6612065223f0d70874c13bab7412fec68406df5061b1e269afd", "params_type": "AdamParams", "train_nll_sum": 13408.49453757446, "train_tokens": 6275.0, "train_token_mean_nll": 2.1368118784979218, "grad_norm": 12.713764190673828, "t": 1793807843.5608485} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 11, "batch_sha256": "fdafeb58ece6d6612065223f0d70874c13bab7412fec68406df5061b1e269afd", "params_type": "DimuonParams", "train_nll_sum": 13811.640929883166, "train_tokens": 6275.0, "train_token_mean_nll": 2.2010583155192296, "grad_norm": 25.078590393066406, "t": 1793807843.5625997} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 11, "batch_sha256": "d47fc04c014ee56646778ed8fee8639fe096625feac016599668fd13125cc75b", "params_type": "AdamParams", "train_nll_sum": 12199.335550727705, "train_tokens": 5544.0, "train_token_mean_nll": 2.2004573504198603, "grad_norm": 16.6391544342041, "t": 1793807843.563594} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 11, "batch_sha256": "d47fc04c014ee56646778ed8fee8639fe096625feac016599668fd13125cc75b", "params_type": "DimuonParams", "train_nll_sum": 12577.16149053913, "train_tokens": 5544.0, "train_token_mean_nll": 2.2686077724637683, "grad_norm": 23.669832229614258, "t": 1793807843.5644538} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13009.996518349339, "train_tokens": 6074.0, "train_token_mean_nll": 2.1419157916281426, "grad_norm": 15.390886306762695, "t": 1793807849.5537546} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13260.626121497187, "train_tokens": 6074.0, "train_token_mean_nll": 2.1831784855938734, "grad_norm": 19.620798110961914, "t": 1793807850.6382372} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 12, "batch_sha256": "0cd0deb0bce10bc07bff8a5c4a7d37e4799794ee2bc407de243dcbd6a0212b4e", "params_type": "AdamParams", "train_nll_sum": 13482.630586898687, "train_tokens": 6439.0, "train_token_mean_nll": 2.093901318046077, "grad_norm": 14.138471603393555, "t": 1793807850.741916} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 12, "batch_sha256": "0cd0deb0bce10bc07bff8a5c4a7d37e4799794ee2bc407de243dcbd6a0212b4e", "params_type": "DimuonParams", "train_nll_sum": 13757.578656041282, "train_tokens": 6439.0, "train_token_mean_nll": 2.1366017481039417, "grad_norm": 16.992029190063477, "t": 1793807850.742896} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 12, "batch_sha256": "ddbcb9d52ea63bd8f116a9702b9cb6fcd512ffaa97cbc81dcc8e8904b4548fc1", "params_type": "AdamParams", "train_nll_sum": 10618.954378139828, "train_tokens": 5308.0, "train_token_mean_nll": 2.000556589702304, "grad_norm": 14.309048652648926, "t": 1793807850.743646} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 12, "batch_sha256": "ddbcb9d52ea63bd8f116a9702b9cb6fcd512ffaa97cbc81dcc8e8904b4548fc1", "params_type": "DimuonParams", "train_nll_sum": 10965.640874882847, "train_tokens": 5308.0, "train_token_mean_nll": 2.0658705491489915, "grad_norm": 20.326522827148438, "t": 1793807850.7443848} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10643.399213208526, "train_tokens": 5144.0, "train_token_mean_nll": 2.0690900492240525, "grad_norm": 17.018598556518555, "t": 1793807857.468823} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 10894.226060111638, "train_tokens": 5144.0, "train_token_mean_nll": 2.1178511003327447, "grad_norm": 20.199499130249023, "t": 1793807857.4974124} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 13, "batch_sha256": "4423e1e3a317c841cb928c4929bb731d0920644e6c3f753b2a9e023ac9ab38b7", "params_type": "AdamParams", "train_nll_sum": 8164.939701854697, "train_tokens": 5083.0, "train_token_mean_nll": 1.6063229789208533, "grad_norm": 19.163068771362305, "t": 1793807857.4984553} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 13, "batch_sha256": "4423e1e3a317c841cb928c4929bb731d0920644e6c3f753b2a9e023ac9ab38b7", "params_type": "DimuonParams", "train_nll_sum": 8358.592193304888, "train_tokens": 5083.0, "train_token_mean_nll": 1.644421049243535, "grad_norm": 21.824119567871094, "t": 1793807857.4994082} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 13, "batch_sha256": "4d47bc552e47814dea16e7defd1726fb0d4fb8d532e51ac2b9dad13a727befab", "params_type": "AdamParams", "train_nll_sum": 11937.022699947453, "train_tokens": 5894.0, "train_token_mean_nll": 2.0252837970728628, "grad_norm": 14.851977348327637, "t": 1793807857.5010493} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 13, "batch_sha256": "4d47bc552e47814dea16e7defd1726fb0d4fb8d532e51ac2b9dad13a727befab", "params_type": "DimuonParams", "train_nll_sum": 12193.129256051747, "train_tokens": 5894.0, "train_token_mean_nll": 2.0687358764933403, "grad_norm": 20.75523567199707, "t": 1793807857.5018733} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10498.065445463752, "train_tokens": 4753.0, "train_token_mean_nll": 2.2087240575349782, "grad_norm": 16.46755599975586, "t": 1793807864.981399} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 10732.665379502138, "train_tokens": 4753.0, "train_token_mean_nll": 2.2580823436781268, "grad_norm": 20.311359405517578, "t": 1793807864.9824326} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 14, "batch_sha256": "aa7752ed07735b56cf0c4c339590b15cb1bfd240f46c0444b72245147624dd3a", "params_type": "AdamParams", "train_nll_sum": 9714.946551645067, "train_tokens": 4931.0, "train_token_mean_nll": 1.970177763464828, "grad_norm": 17.497949600219727, "t": 1793807864.9851387} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 14, "batch_sha256": "aa7752ed07735b56cf0c4c339590b15cb1bfd240f46c0444b72245147624dd3a", "params_type": "DimuonParams", "train_nll_sum": 9926.89195289062, "train_tokens": 4931.0, "train_token_mean_nll": 2.0131599985582276, "grad_norm": 20.929052352905273, "t": 1793807864.9859266} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 14, "batch_sha256": "b2bbfb7b0c1c3b67b120d25bb4dade56026cfe54b3675a187bdd0b6d449cc152", "params_type": "AdamParams", "train_nll_sum": 14885.085758180088, "train_tokens": 7087.0, "train_token_mean_nll": 2.1003366386595297, "grad_norm": 15.630956649780273, "t": 1793807864.9869785} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 14, "batch_sha256": "b2bbfb7b0c1c3b67b120d25bb4dade56026cfe54b3675a187bdd0b6d449cc152", "params_type": "DimuonParams", "train_nll_sum": 15125.94422392848, "train_tokens": 7087.0, "train_token_mean_nll": 2.1343225940353436, "grad_norm": 17.612146377563477, "t": 1793807864.9879968} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13890.210437621983, "train_tokens": 6492.0, "train_token_mean_nll": 2.139588791993528, "grad_norm": 11.455778121948242, "t": 1793807870.8065128} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 14187.348188256232, "train_tokens": 6492.0, "train_token_mean_nll": 2.1853586241922724, "grad_norm": 15.118622779846191, "t": 1793807871.8520179} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 15, "batch_sha256": "3a2e7dd389accb68efa700655bd64767cde1ba73660f5de804de1d3caf6e8c26", "params_type": "AdamParams", "train_nll_sum": 9333.599345864757, "train_tokens": 4025.0, "train_token_mean_nll": 2.318906669780064, "grad_norm": 19.00314712524414, "t": 1793807871.8658369} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 15, "batch_sha256": "3a2e7dd389accb68efa700655bd64767cde1ba73660f5de804de1d3caf6e8c26", "params_type": "DimuonParams", "train_nll_sum": 9448.300464778149, "train_tokens": 4025.0, "train_token_mean_nll": 2.3474038421809067, "grad_norm": 21.011756896972656, "t": 1793807871.873511} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 15, "batch_sha256": "7c8d69ae74171bd47517682cf751adff52070c502e3fb972333422746e92bf13", "params_type": "AdamParams", "train_nll_sum": 12594.050283251165, "train_tokens": 6778.0, "train_token_mean_nll": 1.8580776458027686, "grad_norm": 13.879204750061035, "t": 1793807871.8745108} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 15, "batch_sha256": "7c8d69ae74171bd47517682cf751adff52070c502e3fb972333422746e92bf13", "params_type": "DimuonParams", "train_nll_sum": 12757.391597704516, "train_tokens": 6778.0, "train_token_mean_nll": 1.8821763938779161, "grad_norm": 17.071456909179688, "t": 1793807871.875403} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14224.43199041116, "train_tokens": 7021.0, "train_token_mean_nll": 2.025983761630987, "grad_norm": 15.123994827270508, "t": 1793807877.796111} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 14420.448614746809, "train_tokens": 7021.0, "train_token_mean_nll": 2.053902380678936, "grad_norm": 17.293556213378906, "t": 1793807878.8261862} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 16, "batch_sha256": "7f2e4a214ff2c0c95a557bc04375287e34bf3802d513b23d68f86f098c69fed3", "params_type": "AdamParams", "train_nll_sum": 11864.475786497984, "train_tokens": 5540.0, "train_token_mean_nll": 2.141602127526712, "grad_norm": 13.97468376159668, "t": 1793807878.8507931} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 16, "batch_sha256": "7f2e4a214ff2c0c95a557bc04375287e34bf3802d513b23d68f86f098c69fed3", "params_type": "DimuonParams", "train_nll_sum": 12009.788248488601, "train_tokens": 5540.0, "train_token_mean_nll": 2.1678318138066066, "grad_norm": 16.93016815185547, "t": 1793807878.8516808} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 16, "batch_sha256": "6fb7db5c5b1c64fc5265dd2a612ddab163046f5079d43ee4b57ab775be873efc", "params_type": "AdamParams", "train_nll_sum": 11245.920534532217, "train_tokens": 5632.0, "train_token_mean_nll": 1.9967898676371123, "grad_norm": 14.27025032043457, "t": 1793807878.8525941} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 16, "batch_sha256": "6fb7db5c5b1c64fc5265dd2a612ddab163046f5079d43ee4b57ab775be873efc", "params_type": "DimuonParams", "train_nll_sum": 11411.31189627447, "train_tokens": 5632.0, "train_token_mean_nll": 2.0261562315828248, "grad_norm": 17.478317260742188, "t": 1793807878.853372} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13634.794897136084, "train_tokens": 6222.0, "train_token_mean_nll": 2.1913845864892454, "grad_norm": 14.837108612060547, "t": 1793807886.1195214} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 13747.326090414015, "train_tokens": 6222.0, "train_token_mean_nll": 2.209470602766637, "grad_norm": 16.096031188964844, "t": 1793807886.1207912} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 17, "batch_sha256": "26861da4cd0ccc024108c0d89731e307706c8e6dd91c071b2ac2ef5d47fcc390", "params_type": "AdamParams", "train_nll_sum": 15719.468321020227, "train_tokens": 7278.0, "train_token_mean_nll": 2.159860994918965, "grad_norm": 15.446585655212402, "t": 1793807886.121557} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 17, "batch_sha256": "26861da4cd0ccc024108c0d89731e307706c8e6dd91c071b2ac2ef5d47fcc390", "params_type": "DimuonParams", "train_nll_sum": 15952.551758478738, "train_tokens": 7278.0, "train_token_mean_nll": 2.1918867488978755, "grad_norm": 14.623943328857422, "t": 1793807886.1222963} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 17, "batch_sha256": "94ede2a87189f21723e09b068412dea94fd5727bb0c19c1a9a04afef6bea6c5c", "params_type": "AdamParams", "train_nll_sum": 12555.096673305175, "train_tokens": 6431.0, "train_token_mean_nll": 1.952277511009979, "grad_norm": 18.124101638793945, "t": 1793807886.2248447} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 17, "batch_sha256": "94ede2a87189f21723e09b068412dea94fd5727bb0c19c1a9a04afef6bea6c5c", "params_type": "DimuonParams", "train_nll_sum": 12780.721042927438, "train_tokens": 6431.0, "train_token_mean_nll": 1.9873613812669007, "grad_norm": 20.4919376373291, "t": 1793807886.2256691} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11785.96996216116, "train_tokens": 5713.0, "train_token_mean_nll": 2.0630089203852897, "grad_norm": 15.264391899108887, "t": 1793807891.9040468} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 11990.581219932339, "train_tokens": 5713.0, "train_token_mean_nll": 2.0988239488766567, "grad_norm": 19.169382095336914, "t": 1793807891.916371} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 18, "batch_sha256": "a107ac6f23ac22babc3d7f6b1141ce15f5213599cb252f9000d39ffbfe03bb5a", "params_type": "AdamParams", "train_nll_sum": 11378.39938618804, "train_tokens": 5378.0, "train_token_mean_nll": 2.115730640793611, "grad_norm": 16.6918888092041, "t": 1793807891.9172225} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 18, "batch_sha256": "a107ac6f23ac22babc3d7f6b1141ce15f5213599cb252f9000d39ffbfe03bb5a", "params_type": "DimuonParams", "train_nll_sum": 11530.62606644798, "train_tokens": 5378.0, "train_token_mean_nll": 2.1440360852450686, "grad_norm": 18.716251373291016, "t": 1793807891.9183319} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 18, "batch_sha256": "40bb127b4698166381926adbca87a57c25c0ba6d372723ceab0d4be586f022f3", "params_type": "AdamParams", "train_nll_sum": 12584.19635272132, "train_tokens": 6227.0, "train_token_mean_nll": 2.020908359197257, "grad_norm": 12.367196083068848, "t": 1793807892.9054718} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 18, "batch_sha256": "40bb127b4698166381926adbca87a57c25c0ba6d372723ceab0d4be586f022f3", "params_type": "DimuonParams", "train_nll_sum": 12715.090597981505, "train_tokens": 6227.0, "train_token_mean_nll": 2.041928793637627, "grad_norm": 14.748300552368164, "t": 1793807892.9071972} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12784.921389452635, "train_tokens": 6187.0, "train_token_mean_nll": 2.0664169047119176, "grad_norm": 13.373936653137207, "t": 1793807899.5767841} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 12918.176611225066, "train_tokens": 6187.0, "train_token_mean_nll": 2.0879548426095145, "grad_norm": 15.649476051330566, "t": 1793807899.5780463} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 19, "batch_sha256": "c76d31a2c124cb095fdb5fbabb4c535f52c0f96574554f03ae070386e37047ac", "params_type": "AdamParams", "train_nll_sum": 10986.064478601613, "train_tokens": 5041.0, "train_token_mean_nll": 2.179342288950925, "grad_norm": 16.328699111938477, "t": 1793807899.578724} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 19, "batch_sha256": "c76d31a2c124cb095fdb5fbabb4c535f52c0f96574554f03ae070386e37047ac", "params_type": "DimuonParams", "train_nll_sum": 11162.657900516733, "train_tokens": 5041.0, "train_token_mean_nll": 2.2143737156351384, "grad_norm": 19.889087677001953, "t": 1793807899.5793161} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 19, "batch_sha256": "dffa2501a13c2c9fe6911d2218f77792b9892b0472e1b3af56c4bb29f55228ae", "params_type": "AdamParams", "train_nll_sum": 13818.053347612535, "train_tokens": 6188.0, "train_token_mean_nll": 2.2330402953478563, "grad_norm": 14.270597457885742, "t": 1793807899.579987} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 19, "batch_sha256": "dffa2501a13c2c9fe6911d2218f77792b9892b0472e1b3af56c4bb29f55228ae", "params_type": "DimuonParams", "train_nll_sum": 13993.660553407923, "train_tokens": 6188.0, "train_token_mean_nll": 2.261418964674842, "grad_norm": 17.561229705810547, "t": 1793807899.5806587} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15082.325597972445, "train_tokens": 6765.0, "train_token_mean_nll": 2.22946424212453, "grad_norm": 12.17990493774414, "t": 1793807905.5092125} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 15268.790545788392, "train_tokens": 6765.0, "train_token_mean_nll": 2.257027427315357, "grad_norm": 14.832173347473145, "t": 1793807906.5767024} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 20, "batch_sha256": "9faf371ccb1bf94db32b7b9b2cc23fd53bdedf7dbc9a9bc6538e7da8deb64c18", "params_type": "AdamParams", "train_nll_sum": 14073.356663207229, "train_tokens": 6592.0, "train_token_mean_nll": 2.1349145423554656, "grad_norm": 12.232830047607422, "t": 1793807906.5789502} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 20, "batch_sha256": "9faf371ccb1bf94db32b7b9b2cc23fd53bdedf7dbc9a9bc6538e7da8deb64c18", "params_type": "DimuonParams", "train_nll_sum": 14210.743221265631, "train_tokens": 6592.0, "train_token_mean_nll": 2.1557559498279173, "grad_norm": 14.023427963256836, "t": 1793807906.5796945} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 20, "batch_sha256": "549ac0dbf8e211188ac19f5d08cf14f600894fb80e0f6d6fe3316549d7459aa7", "params_type": "AdamParams", "train_nll_sum": 11072.044929523134, "train_tokens": 5851.0, "train_token_mean_nll": 1.8923337770506126, "grad_norm": 15.518397331237793, "t": 1793807906.5803244} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 20, "batch_sha256": "549ac0dbf8e211188ac19f5d08cf14f600894fb80e0f6d6fe3316549d7459aa7", "params_type": "DimuonParams", "train_nll_sum": 11219.62067196163, "train_tokens": 5851.0, "train_token_mean_nll": 1.917556088183495, "grad_norm": 19.509065628051758, "t": 1793807906.5849326} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12080.587888034857, "train_tokens": 5786.0, "train_token_mean_nll": 2.087899738685596, "grad_norm": 15.967435836791992, "t": 1793807913.7135427} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12177.669703043492, "train_tokens": 5786.0, "train_token_mean_nll": 2.1046784830700815, "grad_norm": 19.264179229736328, "t": 1793807913.7143962} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 21, "batch_sha256": "2c846678f04d4fb796bea82f40b1c860287b8a9b121e6e1a8a1204124c0b8d43", "params_type": "AdamParams", "train_nll_sum": 12593.530431203437, "train_tokens": 5935.0, "train_token_mean_nll": 2.1219090869761477, "grad_norm": 15.957416534423828, "t": 1793807913.719315} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 21, "batch_sha256": "2c846678f04d4fb796bea82f40b1c860287b8a9b121e6e1a8a1204124c0b8d43", "params_type": "DimuonParams", "train_nll_sum": 12729.409189502192, "train_tokens": 5935.0, "train_token_mean_nll": 2.144803570261532, "grad_norm": 19.2011775970459, "t": 1793807913.7209413} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 21, "batch_sha256": "3e1541a82d312b97698cf3b601d7c9605881f4bbaffeaff8a980c9d8690e713d", "params_type": "AdamParams", "train_nll_sum": 14375.959278566263, "train_tokens": 6780.0, "train_token_mean_nll": 2.120347976189714, "grad_norm": 12.898948669433594, "t": 1793807913.7219188} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 21, "batch_sha256": "3e1541a82d312b97698cf3b601d7c9605881f4bbaffeaff8a980c9d8690e713d", "params_type": "DimuonParams", "train_nll_sum": 14622.179398272128, "train_tokens": 6780.0, "train_token_mean_nll": 2.1566636280637357, "grad_norm": 16.834945678710938, "t": 1793807914.486905} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10652.915288663298, "train_tokens": 4783.0, "train_token_mean_nll": 2.227245512996717, "grad_norm": 14.042709350585938, "t": 1793807920.9520013} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 10764.574744392841, "train_tokens": 4783.0, "train_token_mean_nll": 2.2505905800528625, "grad_norm": 17.341310501098633, "t": 1793807922.2106209} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 22, "batch_sha256": "4ca082b2732b5b72116083a4ecf1a7909fb87b24b99f7ce5f2434aace8550e20", "params_type": "AdamParams", "train_nll_sum": 13987.5836907083, "train_tokens": 6488.0, "train_token_mean_nll": 2.15591610522631, "grad_norm": 12.118069648742676, "t": 1793807922.21152} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 22, "batch_sha256": "4ca082b2732b5b72116083a4ecf1a7909fb87b24b99f7ce5f2434aace8550e20", "params_type": "DimuonParams", "train_nll_sum": 14166.724153044133, "train_tokens": 6488.0, "train_token_mean_nll": 2.183527150592499, "grad_norm": 14.339595794677734, "t": 1793807922.2188137} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 22, "batch_sha256": "631e9fc53beefaa4bb4a57ff58ee2a4cbc3c9e9bfd52cdd07de2cead5be6b596", "params_type": "AdamParams", "train_nll_sum": 13498.789486333837, "train_tokens": 6759.0, "train_token_mean_nll": 1.9971577875919273, "grad_norm": 13.276604652404785, "t": 1793807922.2321699} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 22, "batch_sha256": "631e9fc53beefaa4bb4a57ff58ee2a4cbc3c9e9bfd52cdd07de2cead5be6b596", "params_type": "DimuonParams", "train_nll_sum": 13674.804393361175, "train_tokens": 6759.0, "train_token_mean_nll": 2.0231993480339066, "grad_norm": 16.01648712158203, "t": 1793807922.2331169} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15391.334849417446, "train_tokens": 7466.0, "train_token_mean_nll": 2.061523553364244, "grad_norm": 11.95634651184082, "t": 1793807929.8488574} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15493.868817718258, "train_tokens": 7466.0, "train_token_mean_nll": 2.075257007462933, "grad_norm": 14.633231163024902, "t": 1793807929.8502436} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 23, "batch_sha256": "f7eb5328998ed2d1f45d2cb6f01cfca2decf6c21fb815fe1048d0dd9516edf04", "params_type": "AdamParams", "train_nll_sum": 15038.71501396463, "train_tokens": 7322.0, "train_token_mean_nll": 2.053908087129832, "grad_norm": 9.918360710144043, "t": 1793807929.8510854} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 23, "batch_sha256": "f7eb5328998ed2d1f45d2cb6f01cfca2decf6c21fb815fe1048d0dd9516edf04", "params_type": "DimuonParams", "train_nll_sum": 15192.97132896792, "train_tokens": 7322.0, "train_token_mean_nll": 2.074975598056258, "grad_norm": 12.630289077758789, "t": 1793807929.8521173} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 23, "batch_sha256": "f5f3aac8480c147807a2b076a4e782a916bb46fdb705b61af6532fb96bf0cfca", "params_type": "AdamParams", "train_nll_sum": 16087.677048831865, "train_tokens": 7542.0, "train_token_mean_nll": 2.1330783676520637, "grad_norm": 10.924492835998535, "t": 1793807930.2056425} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 23, "batch_sha256": "f5f3aac8480c147807a2b076a4e782a916bb46fdb705b61af6532fb96bf0cfca", "params_type": "DimuonParams", "train_nll_sum": 16225.53530268381, "train_tokens": 7542.0, "train_token_mean_nll": 2.151357107224053, "grad_norm": 13.768621444702148, "t": 1793807930.2064369} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10763.066328066045, "train_tokens": 6100.0, "train_token_mean_nll": 1.7644371029616466, "grad_norm": 12.83590030670166, "t": 1793807936.5232954} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 10910.744782898013, "train_tokens": 6100.0, "train_token_mean_nll": 1.7886466857209857, "grad_norm": 15.633607864379883, "t": 1793807937.7906227} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 24, "batch_sha256": "38216f071a1c7edc7cea56b21d21520825c740154de3fae90b75b42009176166", "params_type": "AdamParams", "train_nll_sum": 11981.752335475221, "train_tokens": 6063.0, "train_token_mean_nll": 1.9762085329828833, "grad_norm": 12.100253105163574, "t": 1793807937.8139765} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 24, "batch_sha256": "38216f071a1c7edc7cea56b21d21520825c740154de3fae90b75b42009176166", "params_type": "DimuonParams", "train_nll_sum": 12149.521485556186, "train_tokens": 6063.0, "train_token_mean_nll": 2.0038795127092506, "grad_norm": 15.086061477661133, "t": 1793807937.8153927} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 24, "batch_sha256": "a2b88d8394109399d9625c8387ddaa171ebb319892add1606f7e7c49c9fc4f0f", "params_type": "AdamParams", "train_nll_sum": 14945.623506376458, "train_tokens": 7510.0, "train_token_mean_nll": 1.9900963390647748, "grad_norm": 12.164435386657715, "t": 1793807937.8162587} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 24, "batch_sha256": "a2b88d8394109399d9625c8387ddaa171ebb319892add1606f7e7c49c9fc4f0f", "params_type": "DimuonParams", "train_nll_sum": 15034.312977742577, "train_tokens": 7510.0, "train_token_mean_nll": 2.0019058558911556, "grad_norm": 14.203142166137695, "t": 1793807937.8170748} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12292.595664616563, "train_tokens": 6108.0, "train_token_mean_nll": 2.0125402201402363, "grad_norm": 11.565865516662598, "t": 1793807943.439948} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12437.16252379369, "train_tokens": 6108.0, "train_token_mean_nll": 2.036208664668253, "grad_norm": 13.731551170349121, "t": 1793807944.5398638} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 25, "batch_sha256": "7046ac44d17c0a8332b66b37ae61e5681ed0ad53bea9e4457d5c4167491dd011", "params_type": "AdamParams", "train_nll_sum": 14015.452550587746, "train_tokens": 6578.0, "train_token_mean_nll": 2.130655602096039, "grad_norm": 11.357137680053711, "t": 1793807944.6565614} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 25, "batch_sha256": "7046ac44d17c0a8332b66b37ae61e5681ed0ad53bea9e4457d5c4167491dd011", "params_type": "DimuonParams", "train_nll_sum": 14077.94236362494, "train_tokens": 6578.0, "train_token_mean_nll": 2.1401554216517087, "grad_norm": 13.417967796325684, "t": 1793807944.657528} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 25, "batch_sha256": "55604a4a2bd9dbbeb79d77300a1061608aaabfeafd7df0789d390d8e39c4ff10", "params_type": "AdamParams", "train_nll_sum": 9918.348214287067, "train_tokens": 4699.0, "train_token_mean_nll": 2.110735946858282, "grad_norm": 15.07942008972168, "t": 1793807944.6582363} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 25, "batch_sha256": "55604a4a2bd9dbbeb79d77300a1061608aaabfeafd7df0789d390d8e39c4ff10", "params_type": "DimuonParams", "train_nll_sum": 9980.269893105571, "train_tokens": 4699.0, "train_token_mean_nll": 2.1239135758896723, "grad_norm": 18.82094955444336, "t": 1793807944.6596043} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11212.492702573301, "train_tokens": 5073.0, "train_token_mean_nll": 2.2102291942781984, "grad_norm": 14.351615905761719, "t": 1793807951.5517654} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11306.020934104701, "train_tokens": 5073.0, "train_token_mean_nll": 2.2286656680671597, "grad_norm": 17.760251998901367, "t": 1793807951.5802274} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 26, "batch_sha256": "2245785e935cba39c24aa1945d2e95f3231fb700f493538307472a79b7774874", "params_type": "AdamParams", "train_nll_sum": 12569.124049347394, "train_tokens": 5799.0, "train_token_mean_nll": 2.167464054034729, "grad_norm": 16.414579391479492, "t": 1793807951.5813806} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 26, "batch_sha256": "2245785e935cba39c24aa1945d2e95f3231fb700f493538307472a79b7774874", "params_type": "DimuonParams", "train_nll_sum": 12646.697004961652, "train_tokens": 5799.0, "train_token_mean_nll": 2.1808410079257894, "grad_norm": 19.139644622802734, "t": 1793807951.5825334} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 26, "batch_sha256": "df1d0fc3e81e5794ccb9c607fc5436d83da8d7ff594139ec2cfeb6e3dc14ea64", "params_type": "AdamParams", "train_nll_sum": 11515.258035816372, "train_tokens": 5480.0, "train_token_mean_nll": 2.101324459090579, "grad_norm": 12.282224655151367, "t": 1793807951.5840816} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 26, "batch_sha256": "df1d0fc3e81e5794ccb9c607fc5436d83da8d7ff594139ec2cfeb6e3dc14ea64", "params_type": "DimuonParams", "train_nll_sum": 11597.976862354843, "train_tokens": 5480.0, "train_token_mean_nll": 2.116419135466212, "grad_norm": 15.611076354980469, "t": 1793807951.5851996} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13408.945204017931, "train_tokens": 6392.0, "train_token_mean_nll": 2.097769900503431, "grad_norm": 15.231206893920898, "t": 1793807957.325404} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 13541.57747904658, "train_tokens": 6392.0, "train_token_mean_nll": 2.1185196306393275, "grad_norm": 17.599498748779297, "t": 1793807958.4123762} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 27, "batch_sha256": "bfac5dff1b18924a2809d7a0f8fe674f7c6a8281dd4f7aeccbc060906b45bc53", "params_type": "AdamParams", "train_nll_sum": 9133.76581247778, "train_tokens": 4557.0, "train_token_mean_nll": 2.0043374615926663, "grad_norm": 13.606008529663086, "t": 1793807958.4142716} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 27, "batch_sha256": "bfac5dff1b18924a2809d7a0f8fe674f7c6a8281dd4f7aeccbc060906b45bc53", "params_type": "DimuonParams", "train_nll_sum": 9197.166142841852, "train_tokens": 4557.0, "train_token_mean_nll": 2.0182501959275516, "grad_norm": 16.74062156677246, "t": 1793807958.4148986} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 27, "batch_sha256": "2b0f0cfb33d9de4252034260ca69016a867c5e1b46ee3703d30a9f71566282d2", "params_type": "AdamParams", "train_nll_sum": 9527.344523123917, "train_tokens": 5429.0, "train_token_mean_nll": 1.7548986043698502, "grad_norm": 12.005993843078613, "t": 1793807958.4156091} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 27, "batch_sha256": "2b0f0cfb33d9de4252034260ca69016a867c5e1b46ee3703d30a9f71566282d2", "params_type": "DimuonParams", "train_nll_sum": 9607.229694861422, "train_tokens": 5429.0, "train_token_mean_nll": 1.7696131322271913, "grad_norm": 14.81560230255127, "t": 1793807958.416294} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14568.611977383174, "train_tokens": 7271.0, "train_token_mean_nll": 2.003660016144021, "grad_norm": 14.747552871704102, "t": 1793807964.381151} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 14644.730863707326, "train_tokens": 7271.0, "train_token_mean_nll": 2.0141288493614806, "grad_norm": 17.085187911987305, "t": 1793807965.5143352} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 28, "batch_sha256": "76f812b9ed722f204b923417d1a3c5ff5887084676ef9257cf57b5509b78cdf7", "params_type": "AdamParams", "train_nll_sum": 11840.028754180688, "train_tokens": 6179.0, "train_token_mean_nll": 1.9161723182037043, "grad_norm": 12.35190486907959, "t": 1793807965.5152805} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 28, "batch_sha256": "76f812b9ed722f204b923417d1a3c5ff5887084676ef9257cf57b5509b78cdf7", "params_type": "DimuonParams", "train_nll_sum": 11928.23400996501, "train_tokens": 6179.0, "train_token_mean_nll": 1.9304473231857922, "grad_norm": 14.651286125183105, "t": 1793807965.524778} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 28, "batch_sha256": "1a0ca50431d8528bd18fe295215d92723f8b5c5d7abb88369f062dd14e1de718", "params_type": "AdamParams", "train_nll_sum": 9300.797560500254, "train_tokens": 4864.0, "train_token_mean_nll": 1.9121705510896903, "grad_norm": 11.531170845031738, "t": 1793807965.5255718} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 28, "batch_sha256": "1a0ca50431d8528bd18fe295215d92723f8b5c5d7abb88369f062dd14e1de718", "params_type": "DimuonParams", "train_nll_sum": 9354.064401655447, "train_tokens": 4864.0, "train_token_mean_nll": 1.9231217931035047, "grad_norm": 13.992648124694824, "t": 1793807965.5262616} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11118.287358976637, "train_tokens": 5476.0, "train_token_mean_nll": 2.0303665739548276, "grad_norm": 13.31817626953125, "t": 1793807972.6985326} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11197.590862960582, "train_tokens": 5476.0, "train_token_mean_nll": 2.044848587100179, "grad_norm": 16.165651321411133, "t": 1793807973.1989727} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 29, "batch_sha256": "c10cf607c8e0353ac912ff03cae32c4f040dcd3b42f351a402de35fa9abfcb3a", "params_type": "AdamParams", "train_nll_sum": 12899.827648172464, "train_tokens": 6609.0, "train_token_mean_nll": 1.9518577164733641, "grad_norm": 11.083402633666992, "t": 1793807973.199965} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 29, "batch_sha256": "c10cf607c8e0353ac912ff03cae32c4f040dcd3b42f351a402de35fa9abfcb3a", "params_type": "DimuonParams", "train_nll_sum": 13021.148589332002, "train_tokens": 6609.0, "train_token_mean_nll": 1.9702146450797402, "grad_norm": 13.110578536987305, "t": 1793807973.2008686} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 29, "batch_sha256": "c13f8bfd3555f9604975b00db1c266c4d482aafa0fac79056a28aba33bfe32fd", "params_type": "AdamParams", "train_nll_sum": 13189.444688278814, "train_tokens": 6135.0, "train_token_mean_nll": 2.1498687348457723, "grad_norm": 11.711735725402832, "t": 1793807973.2016437} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 29, "batch_sha256": "c13f8bfd3555f9604975b00db1c266c4d482aafa0fac79056a28aba33bfe32fd", "params_type": "DimuonParams", "train_nll_sum": 13252.723387097745, "train_tokens": 6135.0, "train_token_mean_nll": 2.1601831111813765, "grad_norm": 14.1800537109375, "t": 1793807973.2023911} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16813.716123700746, "train_tokens": 7466.0, "train_token_mean_nll": 2.2520380556791784, "grad_norm": 11.170796394348145, "t": 1793807980.492607} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 16870.895172912118, "train_tokens": 7466.0, "train_token_mean_nll": 2.2596966478585747, "grad_norm": 13.89580249786377, "t": 1793807981.1392226} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 30, "batch_sha256": "ef8017d8d6971a6056552434051494aebbd3c97ebf74ea29dbc7b354ac632938", "params_type": "AdamParams", "train_nll_sum": 17473.81689915218, "train_tokens": 7852.0, "train_token_mean_nll": 2.225396956081531, "grad_norm": 11.442909240722656, "t": 1793807981.4302847} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 30, "batch_sha256": "ef8017d8d6971a6056552434051494aebbd3c97ebf74ea29dbc7b354ac632938", "params_type": "DimuonParams", "train_nll_sum": 17541.012226301773, "train_tokens": 7852.0, "train_token_mean_nll": 2.2339546900537153, "grad_norm": 14.144923210144043, "t": 1793807981.431428} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 30, "batch_sha256": "8c7d731af9ce8704942b2d759bc515a94ba2819930db2aa3b59ace586a674110", "params_type": "AdamParams", "train_nll_sum": 15459.012735707307, "train_tokens": 7486.0, "train_token_mean_nll": 2.065056470171962, "grad_norm": 12.357539176940918, "t": 1793807981.4323034} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 30, "batch_sha256": "8c7d731af9ce8704942b2d759bc515a94ba2819930db2aa3b59ace586a674110", "params_type": "DimuonParams", "train_nll_sum": 15524.061867117265, "train_tokens": 7486.0, "train_token_mean_nll": 2.0737459079771927, "grad_norm": 15.659969329833984, "t": 1793807981.7277563} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11586.645979105544, "train_tokens": 5656.0, "train_token_mean_nll": 2.048558341426016, "grad_norm": 12.977124214172363, "t": 1793807988.8056889} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11653.735403108654, "train_tokens": 5656.0, "train_token_mean_nll": 2.060419979333213, "grad_norm": 15.450094223022461, "t": 1793807989.8281336} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 31, "batch_sha256": "3d9f778073a0e6dc418cd06c96c0f36f6670df17b89a552e5a0e25c1145ad1d2", "params_type": "AdamParams", "train_nll_sum": 16354.290629786177, "train_tokens": 7619.0, "train_token_mean_nll": 2.1465140608723163, "grad_norm": 11.24875259399414, "t": 1793807989.9996047} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 31, "batch_sha256": "3d9f778073a0e6dc418cd06c96c0f36f6670df17b89a552e5a0e25c1145ad1d2", "params_type": "DimuonParams", "train_nll_sum": 16426.88543108772, "train_tokens": 7619.0, "train_token_mean_nll": 2.156042188093939, "grad_norm": 13.48734188079834, "t": 1793807990.00052} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 31, "batch_sha256": "87b2917df5b1b280054655f2cb0edb78b831b980d9c016af6e1cf59a3063f923", "params_type": "AdamParams", "train_nll_sum": 14193.491043754027, "train_tokens": 6531.0, "train_token_mean_nll": 2.1732492793988714, "grad_norm": 13.853772163391113, "t": 1793807990.0012631} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 31, "batch_sha256": "87b2917df5b1b280054655f2cb0edb78b831b980d9c016af6e1cf59a3063f923", "params_type": "DimuonParams", "train_nll_sum": 14252.099197692149, "train_tokens": 6531.0, "train_token_mean_nll": 2.1822231201488513, "grad_norm": 17.099279403686523, "t": 1793807990.0019617} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9860.279495302695, "train_tokens": 5681.0, "train_token_mean_nll": 1.735659126087431, "grad_norm": 14.138022422790527, "t": 1793807995.894433} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 9921.649367526388, "train_tokens": 5681.0, "train_token_mean_nll": 1.7464617791808463, "grad_norm": 17.683454513549805, "t": 1793807996.831601} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 32, "batch_sha256": "b31754ba08f728234a5e32c0e6b1070918f41aa49b7f459c2b140a6930b9e116", "params_type": "AdamParams", "train_nll_sum": 14386.366479365939, "train_tokens": 6289.0, "train_token_mean_nll": 2.287544359892819, "grad_norm": 15.519747734069824, "t": 1793807996.8323689} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 32, "batch_sha256": "b31754ba08f728234a5e32c0e6b1070918f41aa49b7f459c2b140a6930b9e116", "params_type": "DimuonParams", "train_nll_sum": 14448.54269453121, "train_tokens": 6289.0, "train_token_mean_nll": 2.297430862542727, "grad_norm": 17.923786163330078, "t": 1793807996.8330452} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 32, "batch_sha256": "b771daa9d49e7abf074c3787597e45a5758d526bc848a25d3feee34493f877cd", "params_type": "AdamParams", "train_nll_sum": 11508.380378011543, "train_tokens": 5626.0, "train_token_mean_nll": 2.0455706324229546, "grad_norm": 13.162169456481934, "t": 1793807996.9794555} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 32, "batch_sha256": "b771daa9d49e7abf074c3787597e45a5758d526bc848a25d3feee34493f877cd", "params_type": "DimuonParams", "train_nll_sum": 11558.70895145192, "train_tokens": 5626.0, "train_token_mean_nll": 2.054516344019182, "grad_norm": 16.044740676879883, "t": 1793807996.9804497} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11626.619742165976, "train_tokens": 6193.0, "train_token_mean_nll": 1.87738087230195, "grad_norm": 13.5198392868042, "t": 1793808003.531257} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 11699.72014970879, "train_tokens": 6193.0, "train_token_mean_nll": 1.889184587390407, "grad_norm": 15.654040336608887, "t": 1793808003.5329046} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 33, "batch_sha256": "aac7d009a518f7eca3cda3c5e2fb180dda59369611b1346d8f27463da28f78cb", "params_type": "AdamParams", "train_nll_sum": 10800.65713121894, "train_tokens": 5605.0, "train_token_mean_nll": 1.9269682660515506, "grad_norm": 12.425692558288574, "t": 1793808003.5336232} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 33, "batch_sha256": "aac7d009a518f7eca3cda3c5e2fb180dda59369611b1346d8f27463da28f78cb", "params_type": "DimuonParams", "train_nll_sum": 10824.357264564289, "train_tokens": 5605.0, "train_token_mean_nll": 1.9311966573709705, "grad_norm": 15.406224250793457, "t": 1793808003.5342994} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 33, "batch_sha256": "b4fcbad313dbdd8afee98ab00795d0c6c4562935d75f765a9048e881dde5ca8b", "params_type": "AdamParams", "train_nll_sum": 11958.48029963702, "train_tokens": 5595.0, "train_token_mean_nll": 2.1373512599887436, "grad_norm": 12.40589714050293, "t": 1793808003.5350678} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 33, "batch_sha256": "b4fcbad313dbdd8afee98ab00795d0c6c4562935d75f765a9048e881dde5ca8b", "params_type": "DimuonParams", "train_nll_sum": 12004.986045792273, "train_tokens": 5595.0, "train_token_mean_nll": 2.145663278961979, "grad_norm": 14.867135047912598, "t": 1793808003.5357697} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10224.17294278571, "train_tokens": 4524.0, "train_token_mean_nll": 2.2599851774504223, "grad_norm": 14.2941312789917, "t": 1793808011.3036957} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10275.396665894144, "train_tokens": 4524.0, "train_token_mean_nll": 2.2713078394991477, "grad_norm": 17.319231033325195, "t": 1793808011.3044448} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 34, "batch_sha256": "a1c29dd355cb78ae299df82f938b4cda40af76d69a5ea7d39207ef77237b424c", "params_type": "AdamParams", "train_nll_sum": 14382.513218452425, "train_tokens": 7042.0, "train_token_mean_nll": 2.042390403074755, "grad_norm": 14.194859504699707, "t": 1793808011.3052082} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 34, "batch_sha256": "a1c29dd355cb78ae299df82f938b4cda40af76d69a5ea7d39207ef77237b424c", "params_type": "DimuonParams", "train_nll_sum": 14436.00314689441, "train_tokens": 7042.0, "train_token_mean_nll": 2.0499862463638756, "grad_norm": 16.276342391967773, "t": 1793808011.3090367} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 34, "batch_sha256": "109d2849aafe2f34b4d81285a3168965d17e254f7dab377e9eccfd6d23726f68", "params_type": "AdamParams", "train_nll_sum": 11362.36493618213, "train_tokens": 6634.0, "train_token_mean_nll": 1.7127472017157266, "grad_norm": 10.527226448059082, "t": 1793808011.3098783} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 34, "batch_sha256": "109d2849aafe2f34b4d81285a3168965d17e254f7dab377e9eccfd6d23726f68", "params_type": "DimuonParams", "train_nll_sum": 11378.450911634662, "train_tokens": 6634.0, "train_token_mean_nll": 1.715171979444477, "grad_norm": 12.780980110168457, "t": 1793808011.3105905} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11929.737841711309, "train_tokens": 5628.0, "train_token_mean_nll": 2.119711770026885, "grad_norm": 15.070450782775879, "t": 1793808016.9346125} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 11981.587662057223, "train_tokens": 5628.0, "train_token_mean_nll": 2.1289246023555832, "grad_norm": 18.399288177490234, "t": 1793808016.9441295} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 35, "batch_sha256": "1103c34bea7d7fa593ff2edd3a50d6bb5ba9fbb7bc465274b611f3f0446bf440", "params_type": "AdamParams", "train_nll_sum": 9972.445815647543, "train_tokens": 5136.0, "train_token_mean_nll": 1.9416755871587896, "grad_norm": 17.728713989257812, "t": 1793808016.9450774} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 35, "batch_sha256": "1103c34bea7d7fa593ff2edd3a50d6bb5ba9fbb7bc465274b611f3f0446bf440", "params_type": "DimuonParams", "train_nll_sum": 10004.956697810516, "train_tokens": 5136.0, "train_token_mean_nll": 1.9480055875799291, "grad_norm": 22.123098373413086, "t": 1793808016.9457698} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 35, "batch_sha256": "dfb7cdfd3b999a11489a28e0e5586b4876ff73cb030560d462017ceb7c77eb41", "params_type": "AdamParams", "train_nll_sum": 12218.765415144657, "train_tokens": 5939.0, "train_token_mean_nll": 2.05737757453185, "grad_norm": 11.656039237976074, "t": 1793808017.0816424} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 35, "batch_sha256": "dfb7cdfd3b999a11489a28e0e5586b4876ff73cb030560d462017ceb7c77eb41", "params_type": "DimuonParams", "train_nll_sum": 12269.85024552856, "train_tokens": 5939.0, "train_token_mean_nll": 2.0659791624058865, "grad_norm": 14.16628360748291, "t": 1793808017.462505} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13014.780155180566, "train_tokens": 6703.0, "train_token_mean_nll": 1.9416351119171364, "grad_norm": 11.317943572998047, "t": 1793808023.6882734} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13053.099475031395, "train_tokens": 6703.0, "train_token_mean_nll": 1.9473518536523042, "grad_norm": 12.95235538482666, "t": 1793808023.6893234} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 36, "batch_sha256": "b10df2ca4fe56463dab4451a52beff79f71e206db4b282fc209c24a9ba25b8d1", "params_type": "AdamParams", "train_nll_sum": 11994.559770762125, "train_tokens": 6087.0, "train_token_mean_nll": 1.9705207443341755, "grad_norm": 12.008646011352539, "t": 1793808023.690112} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 36, "batch_sha256": "b10df2ca4fe56463dab4451a52beff79f71e206db4b282fc209c24a9ba25b8d1", "params_type": "DimuonParams", "train_nll_sum": 12034.862283185774, "train_tokens": 6087.0, "train_token_mean_nll": 1.9771418240817766, "grad_norm": 14.458035469055176, "t": 1793808023.7548804} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 36, "batch_sha256": "d34730f7c5881f96897302573746eb674f7301deefded373dba6d324770f634d", "params_type": "AdamParams", "train_nll_sum": 14135.132915321748, "train_tokens": 7181.0, "train_token_mean_nll": 1.9684073130931274, "grad_norm": 10.881412506103516, "t": 1793808023.7557719} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 36, "batch_sha256": "d34730f7c5881f96897302573746eb674f7301deefded373dba6d324770f634d", "params_type": "DimuonParams", "train_nll_sum": 14212.146767359232, "train_tokens": 7181.0, "train_token_mean_nll": 1.979131982642979, "grad_norm": 13.093036651611328, "t": 1793808024.2742712} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11499.004737679432, "train_tokens": 5733.0, "train_token_mean_nll": 2.005756975000773, "grad_norm": 12.70694351196289, "t": 1793808030.4619412} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11525.052359448246, "train_tokens": 5733.0, "train_token_mean_nll": 2.010300428998473, "grad_norm": 15.22634220123291, "t": 1793808030.4647317} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 37, "batch_sha256": "2e39851f7ccb072a299b237a2bfffa27b1070a549d935080531865880ab7b693", "params_type": "AdamParams", "train_nll_sum": 14501.446446019574, "train_tokens": 6860.0, "train_token_mean_nll": 2.113913476096148, "grad_norm": 11.01588249206543, "t": 1793808030.465656} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 37, "batch_sha256": "2e39851f7ccb072a299b237a2bfffa27b1070a549d935080531865880ab7b693", "params_type": "DimuonParams", "train_nll_sum": 14517.98341585636, "train_tokens": 6860.0, "train_token_mean_nll": 2.116324113098595, "grad_norm": 13.177689552307129, "t": 1793808030.4665203} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 37, "batch_sha256": "6d6986ad469c9bcacaac9f043e8a80069a72e4d33b2997e8116028154a2890f7", "params_type": "AdamParams", "train_nll_sum": 12008.345856261134, "train_tokens": 5621.0, "train_token_mean_nll": 2.1363362135316017, "grad_norm": 16.72659683227539, "t": 1793808030.4671779} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 37, "batch_sha256": "6d6986ad469c9bcacaac9f043e8a80069a72e4d33b2997e8116028154a2890f7", "params_type": "DimuonParams", "train_nll_sum": 12080.993811740915, "train_tokens": 5621.0, "train_token_mean_nll": 2.1492605962890794, "grad_norm": 20.521575927734375, "t": 1793808030.8415341} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14690.00720824952, "train_tokens": 6763.0, "train_token_mean_nll": 2.1721140334540174, "grad_norm": 10.439863204956055, "t": 1793808037.2921402} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 14717.83378495469, "train_tokens": 6763.0, "train_token_mean_nll": 2.176228564979253, "grad_norm": 12.54360294342041, "t": 1793808037.294334} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 38, "batch_sha256": "8d8c9e2a13bbea71ea15b8f30a12f447d3c13ec8239354a931a2f1373cea4e5a", "params_type": "AdamParams", "train_nll_sum": 8322.462180709097, "train_tokens": 3948.0, "train_token_mean_nll": 2.1080198026112202, "grad_norm": 15.566967964172363, "t": 1793808037.2952263} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 38, "batch_sha256": "8d8c9e2a13bbea71ea15b8f30a12f447d3c13ec8239354a931a2f1373cea4e5a", "params_type": "DimuonParams", "train_nll_sum": 8352.275912695683, "train_tokens": 3948.0, "train_token_mean_nll": 2.115571406457873, "grad_norm": 19.694820404052734, "t": 1793808038.3285851} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 38, "batch_sha256": "98be2d605f07f587af79327ea4389f4e6e118a3ea7fce3bbabdd703e1611ecf4", "params_type": "AdamParams", "train_nll_sum": 12267.547884368427, "train_tokens": 5742.0, "train_token_mean_nll": 2.1364590533556997, "grad_norm": 13.005484580993652, "t": 1793808038.3293939} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 38, "batch_sha256": "98be2d605f07f587af79327ea4389f4e6e118a3ea7fce3bbabdd703e1611ecf4", "params_type": "DimuonParams", "train_nll_sum": 12301.57843594281, "train_tokens": 5742.0, "train_token_mean_nll": 2.1423856558590755, "grad_norm": 16.0761775970459, "t": 1793808038.3301492} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10415.155087448207, "train_tokens": 5394.0, "train_token_mean_nll": 1.9308778434275504, "grad_norm": 15.293580055236816, "t": 1793808044.0073535} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10449.103161870768, "train_tokens": 5394.0, "train_token_mean_nll": 1.9371715168466384, "grad_norm": 19.000808715820312, "t": 1793808044.4550169} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 39, "batch_sha256": "281962a115600e1f0685f37ed364e6e78cc0fb24a91ef45a6536a383c9b27189", "params_type": "AdamParams", "train_nll_sum": 13591.545884211322, "train_tokens": 6636.0, "train_token_mean_nll": 2.0481533882174987, "grad_norm": 13.710845947265625, "t": 1793808044.4560642} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 39, "batch_sha256": "281962a115600e1f0685f37ed364e6e78cc0fb24a91ef45a6536a383c9b27189", "params_type": "DimuonParams", "train_nll_sum": 13641.54912816516, "train_tokens": 6636.0, "train_token_mean_nll": 2.05568853649264, "grad_norm": 16.478681564331055, "t": 1793808044.456981} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 39, "batch_sha256": "288465aed676b97b80e3937c1d0b03f3c25022dafdc8684fb9cf38822c1dea86", "params_type": "AdamParams", "train_nll_sum": 13440.782087491776, "train_tokens": 6388.0, "train_token_mean_nll": 2.1040673274094828, "grad_norm": 16.20481300354004, "t": 1793808044.4740047} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 39, "batch_sha256": "288465aed676b97b80e3937c1d0b03f3c25022dafdc8684fb9cf38822c1dea86", "params_type": "DimuonParams", "train_nll_sum": 13474.984141828485, "train_tokens": 6388.0, "train_token_mean_nll": 2.109421437355743, "grad_norm": 20.80690574645996, "t": 1793808045.045666} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8523.275916869941, "train_tokens": 4573.0, "train_token_mean_nll": 1.863825916656449, "grad_norm": 15.35016918182373, "t": 1793808051.120164} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8529.12722133085, "train_tokens": 4573.0, "train_token_mean_nll": 1.8651054496678, "grad_norm": 18.022611618041992, "t": 1793808051.1208856} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 40, "batch_sha256": "3e12b2e3c711a8f33a8deba24d3336e42c39a6b62a4f61280bff34f09b984214", "params_type": "AdamParams", "train_nll_sum": 10540.688980460156, "train_tokens": 5120.0, "train_token_mean_nll": 2.0587283164961243, "grad_norm": 11.102394104003906, "t": 1793808051.1217346} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 40, "batch_sha256": "3e12b2e3c711a8f33a8deba24d3336e42c39a6b62a4f61280bff34f09b984214", "params_type": "DimuonParams", "train_nll_sum": 10589.981695313332, "train_tokens": 5120.0, "train_token_mean_nll": 2.068355799865885, "grad_norm": 13.645885467529297, "t": 1793808051.1225116} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 40, "batch_sha256": "df734de2fd38e35f6b377032490db76976ef0544f0d025aa45eea4cce51c196b", "params_type": "AdamParams", "train_nll_sum": 13929.268407354062, "train_tokens": 7110.0, "train_token_mean_nll": 1.9591094806405152, "grad_norm": 13.345056533813477, "t": 1793808051.766285} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 40, "batch_sha256": "df734de2fd38e35f6b377032490db76976ef0544f0d025aa45eea4cce51c196b", "params_type": "DimuonParams", "train_nll_sum": 13967.133884576659, "train_tokens": 7110.0, "train_token_mean_nll": 1.9644351455100786, "grad_norm": 15.930176734924316, "t": 1793808051.7672465} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 41, "batch_sha256": "339671525396af887b30be0ae36f8174726683630fe0194cdbbeb3fb395eefe1", "params_type": "AdamParams", "train_nll_sum": 11909.38749443115, "train_tokens": 5807.0, "train_token_mean_nll": 2.0508674865560788, "grad_norm": 11.773676872253418, "t": 1793808057.28998} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 41, "batch_sha256": "339671525396af887b30be0ae36f8174726683630fe0194cdbbeb3fb395eefe1", "params_type": "DimuonParams", "train_nll_sum": 11930.478855844243, "train_tokens": 5807.0, "train_token_mean_nll": 2.054499544660624, "grad_norm": 13.972307205200195, "t": 1793808057.6856618} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 41, "batch_sha256": "5eda7f4a3fc1631bb4066bd841dfed0989c3cf5c72d43f901bd07da76cbb3fdf", "params_type": "AdamParams", "train_nll_sum": 12349.536812157214, "train_tokens": 5911.0, "train_token_mean_nll": 2.089246626993269, "grad_norm": 12.247430801391602, "t": 1793808057.6865668} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 41, "batch_sha256": "5eda7f4a3fc1631bb4066bd841dfed0989c3cf5c72d43f901bd07da76cbb3fdf", "params_type": "DimuonParams", "train_nll_sum": 12382.765889920012, "train_tokens": 5911.0, "train_token_mean_nll": 2.0948681931855884, "grad_norm": 14.509553909301758, "t": 1793808057.6873686} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 41, "batch_sha256": "bf3e18e6a21e99d2c95b7b9ed8157d4c551bbf6b58910e3b41d9de2cc16ab439", "params_type": "AdamParams", "train_nll_sum": 13723.158185104156, "train_tokens": 7472.0, "train_token_mean_nll": 1.8366111061434898, "grad_norm": 10.964775085449219, "t": 1793808057.6884062} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 41, "batch_sha256": "bf3e18e6a21e99d2c95b7b9ed8157d4c551bbf6b58910e3b41d9de2cc16ab439", "params_type": "DimuonParams", "train_nll_sum": 13756.576379983373, "train_tokens": 7472.0, "train_token_mean_nll": 1.8410835626316078, "grad_norm": 13.061842918395996, "t": 1793808058.2803361} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 42, "batch_sha256": "8464fe6ea784ffc8ff5c8e028c8dc4fb41e2349adbe88c3a36b6768ec0eb9a4d", "params_type": "AdamParams", "train_nll_sum": 13758.145699483333, "train_tokens": 6410.0, "train_token_mean_nll": 2.1463565833827354, "grad_norm": 11.836418151855469, "t": 1793808064.0668812} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 42, "batch_sha256": "8464fe6ea784ffc8ff5c8e028c8dc4fb41e2349adbe88c3a36b6768ec0eb9a4d", "params_type": "DimuonParams", "train_nll_sum": 13771.346602897818, "train_tokens": 6410.0, "train_token_mean_nll": 2.1484160066923272, "grad_norm": 14.24169921875, "t": 1793808064.100757} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 42, "batch_sha256": "e88ea0308e5ece07f8ab20875cd7f894ae223dc5da3e34c56eaa9744944efde7", "params_type": "AdamParams", "train_nll_sum": 9058.644363425135, "train_tokens": 4482.0, "train_token_mean_nll": 2.021116546948937, "grad_norm": 13.948769569396973, "t": 1793808064.1015656} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 42, "batch_sha256": "e88ea0308e5ece07f8ab20875cd7f894ae223dc5da3e34c56eaa9744944efde7", "params_type": "DimuonParams", "train_nll_sum": 9083.983210670835, "train_tokens": 4482.0, "train_token_mean_nll": 2.026770015767701, "grad_norm": 16.93419647216797, "t": 1793808064.1023102} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 42, "batch_sha256": "1e5e82e19a70831651e61cc8108b557d5812578d7abcd0e2e36d261aa8beb0cb", "params_type": "AdamParams", "train_nll_sum": 13318.60327351587, "train_tokens": 6160.0, "train_token_mean_nll": 2.1621109210253033, "grad_norm": 11.604281425476074, "t": 1793808065.154137} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 42, "batch_sha256": "1e5e82e19a70831651e61cc8108b557d5812578d7abcd0e2e36d261aa8beb0cb", "params_type": "DimuonParams", "train_nll_sum": 13344.671827040162, "train_tokens": 6160.0, "train_token_mean_nll": 2.1663428290649613, "grad_norm": 13.941291809082031, "t": 1793808065.1549869} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 43, "batch_sha256": "ea6aa48fe7e75e4ffc0aaac0df296392ebde870f06b23509ea8aad0d5baea62a", "params_type": "AdamParams", "train_nll_sum": 12192.919865421034, "train_tokens": 5708.0, "train_token_mean_nll": 2.1361106982167195, "grad_norm": 13.777538299560547, "t": 1793808070.900307} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 43, "batch_sha256": "ea6aa48fe7e75e4ffc0aaac0df296392ebde870f06b23509ea8aad0d5baea62a", "params_type": "DimuonParams", "train_nll_sum": 12211.76585424197, "train_tokens": 5708.0, "train_token_mean_nll": 2.139412378108264, "grad_norm": 17.463912963867188, "t": 1793808070.9010577} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 43, "batch_sha256": "b8012ae367c707efab98f1400374dacd2c60c00b50d150d6f2e79ab55d5242f2", "params_type": "AdamParams", "train_nll_sum": 10539.4035209389, "train_tokens": 5690.0, "train_token_mean_nll": 1.8522677541193147, "grad_norm": 11.82060718536377, "t": 1793808070.9017055} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 43, "batch_sha256": "b8012ae367c707efab98f1400374dacd2c60c00b50d150d6f2e79ab55d5242f2", "params_type": "DimuonParams", "train_nll_sum": 10569.265675214214, "train_tokens": 5690.0, "train_token_mean_nll": 1.85751593589002, "grad_norm": 14.09438705444336, "t": 1793808070.9023278} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 43, "batch_sha256": "e50aaa379b9d9a19abc98ff935f9d56dbea2fab19de5e2ec7cc3332f1c35b07b", "params_type": "AdamParams", "train_nll_sum": 10786.545515448946, "train_tokens": 5433.0, "train_token_mean_nll": 1.9853755780322007, "grad_norm": 14.151480674743652, "t": 1793808070.9030428} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 43, "batch_sha256": "e50aaa379b9d9a19abc98ff935f9d56dbea2fab19de5e2ec7cc3332f1c35b07b", "params_type": "DimuonParams", "train_nll_sum": 10822.901526010817, "train_tokens": 5433.0, "train_token_mean_nll": 1.9920672788534544, "grad_norm": 16.281875610351562, "t": 1793808071.4651403} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 44, "batch_sha256": "571260dd784d9d1571e7faa5b3a02012a61c5d570a192b122f92d4c35c6f463d", "params_type": "AdamParams", "train_nll_sum": 9863.469447358893, "train_tokens": 4980.0, "train_token_mean_nll": 1.980616354891344, "grad_norm": 13.794587135314941, "t": 1793808078.112199} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 44, "batch_sha256": "571260dd784d9d1571e7faa5b3a02012a61c5d570a192b122f92d4c35c6f463d", "params_type": "DimuonParams", "train_nll_sum": 9893.872515857027, "train_tokens": 4980.0, "train_token_mean_nll": 1.9867213887263107, "grad_norm": 16.554658889770508, "t": 1793808078.1165617} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 44, "batch_sha256": "b99e5da46e23dc920ec070d8e23fb3b0db2141823f1bad6e91556272faac4ddc", "params_type": "AdamParams", "train_nll_sum": 10563.420660409183, "train_tokens": 5455.0, "train_token_mean_nll": 1.936465748929273, "grad_norm": 13.158161163330078, "t": 1793808078.264924} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 44, "batch_sha256": "b99e5da46e23dc920ec070d8e23fb3b0db2141823f1bad6e91556272faac4ddc", "params_type": "DimuonParams", "train_nll_sum": 10588.416746694773, "train_tokens": 5455.0, "train_token_mean_nll": 1.941047982895467, "grad_norm": 16.201322555541992, "t": 1793808078.2658074} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 44, "batch_sha256": "3d712158c7db25f034d9cd1a3800eb81bb33057aa2f90fff19885e876daa0166", "params_type": "AdamParams", "train_nll_sum": 13112.621308544403, "train_tokens": 6252.0, "train_token_mean_nll": 2.0973482579245686, "grad_norm": 12.369545936584473, "t": 1793808078.2717538} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 44, "batch_sha256": "3d712158c7db25f034d9cd1a3800eb81bb33057aa2f90fff19885e876daa0166", "params_type": "DimuonParams", "train_nll_sum": 13122.880497590615, "train_tokens": 6252.0, "train_token_mean_nll": 2.0989892030695163, "grad_norm": 14.786314964294434, "t": 1793808078.2725697} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 45, "batch_sha256": "ac4fde0ee46427dddeaf1f726c2f25c16747febd84fa91d5756a91c8523f4f56", "params_type": "AdamParams", "train_nll_sum": 10446.178835460794, "train_tokens": 6240.0, "train_token_mean_nll": 1.674067121067435, "grad_norm": 12.77053451538086, "t": 1793808083.8641953} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 45, "batch_sha256": "ac4fde0ee46427dddeaf1f726c2f25c16747febd84fa91d5756a91c8523f4f56", "params_type": "DimuonParams", "train_nll_sum": 10480.450726132072, "train_tokens": 6240.0, "train_token_mean_nll": 1.6795594112391141, "grad_norm": 14.868786811828613, "t": 1793808084.1961303} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 45, "batch_sha256": "e3343e3ed07bd11bd9e81ee5587508abb48dee6c3c460d850887b02a74ece5ff", "params_type": "AdamParams", "train_nll_sum": 12630.437487565869, "train_tokens": 6377.0, "train_token_mean_nll": 1.9806237239400766, "grad_norm": 11.821600914001465, "t": 1793808084.196971} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 45, "batch_sha256": "e3343e3ed07bd11bd9e81ee5587508abb48dee6c3c460d850887b02a74ece5ff", "params_type": "DimuonParams", "train_nll_sum": 12660.229923471881, "train_tokens": 6377.0, "train_token_mean_nll": 1.985295581538636, "grad_norm": 14.275245666503906, "t": 1793808084.1977272} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 45, "batch_sha256": "eb2c9989bedddbeb687480b8c55fa29d8da49869f7eb6430191d1e390a19d58a", "params_type": "AdamParams", "train_nll_sum": 10257.424501099133, "train_tokens": 5771.0, "train_token_mean_nll": 1.777408508247987, "grad_norm": 14.301102638244629, "t": 1793808084.2015982} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 45, "batch_sha256": "eb2c9989bedddbeb687480b8c55fa29d8da49869f7eb6430191d1e390a19d58a", "params_type": "DimuonParams", "train_nll_sum": 10284.64534003066, "train_tokens": 5771.0, "train_token_mean_nll": 1.782125340500894, "grad_norm": 16.88384437561035, "t": 1793808084.8959594} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 46, "batch_sha256": "452717908a729bafc21f3fe73beb9fd4b2df1164c3f4b5d5759ef625bb44b9b5", "params_type": "AdamParams", "train_nll_sum": 10409.210734105289, "train_tokens": 5492.0, "train_token_mean_nll": 1.8953406289339565, "grad_norm": 14.00539779663086, "t": 1793808091.1306376} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 46, "batch_sha256": "452717908a729bafc21f3fe73beb9fd4b2df1164c3f4b5d5759ef625bb44b9b5", "params_type": "DimuonParams", "train_nll_sum": 10431.81854995379, "train_tokens": 5492.0, "train_token_mean_nll": 1.899457128542205, "grad_norm": 16.822668075561523, "t": 1793808092.2290688} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 46, "batch_sha256": "87f50bbfd4aff7020c69c0cb63483225b677ce7d449ebf370aa8ad3c1025f49b", "params_type": "AdamParams", "train_nll_sum": 14811.703071339569, "train_tokens": 7802.0, "train_token_mean_nll": 1.8984495092719262, "grad_norm": 12.272891998291016, "t": 1793808092.230802} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 46, "batch_sha256": "87f50bbfd4aff7020c69c0cb63483225b677ce7d449ebf370aa8ad3c1025f49b", "params_type": "DimuonParams", "train_nll_sum": 14807.791291731286, "train_tokens": 7802.0, "train_token_mean_nll": 1.8979481276251329, "grad_norm": 14.702573776245117, "t": 1793808092.2317076} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 46, "batch_sha256": "b1162906812423743284d2196d5fa85d7e57a187bde09251a80e96ef2da6de3d", "params_type": "AdamParams", "train_nll_sum": 12581.454603131519, "train_tokens": 6333.0, "train_token_mean_nll": 1.9866500241799334, "grad_norm": 11.929417610168457, "t": 1793808092.2329834} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 46, "batch_sha256": "b1162906812423743284d2196d5fa85d7e57a187bde09251a80e96ef2da6de3d", "params_type": "DimuonParams", "train_nll_sum": 12605.85806268814, "train_tokens": 6333.0, "train_token_mean_nll": 1.99050340481417, "grad_norm": 14.316572189331055, "t": 1793808092.2338033} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 47, "batch_sha256": "a3fc858866347e7cf23eca30ffd19e339946335315a654875063f4b511f67a0b", "params_type": "AdamParams", "train_nll_sum": 13757.731657631994, "train_tokens": 6595.0, "train_token_mean_nll": 2.0860851641595137, "grad_norm": 14.892011642456055, "t": 1793808098.2073202} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 47, "batch_sha256": "a3fc858866347e7cf23eca30ffd19e339946335315a654875063f4b511f67a0b", "params_type": "DimuonParams", "train_nll_sum": 13793.614919553322, "train_tokens": 6595.0, "train_token_mean_nll": 2.0915261439807917, "grad_norm": 18.660871505737305, "t": 1793808099.331338} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 47, "batch_sha256": "afa410be048591736b1a4b51c5c5f9a4c6ef7eb207347682582f031b1c97abaf", "params_type": "AdamParams", "train_nll_sum": 9556.208965593942, "train_tokens": 4572.0, "train_token_mean_nll": 2.090159441293513, "grad_norm": 13.006397247314453, "t": 1793808099.3320503} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 47, "batch_sha256": "afa410be048591736b1a4b51c5c5f9a4c6ef7eb207347682582f031b1c97abaf", "params_type": "DimuonParams", "train_nll_sum": 9568.172988731756, "train_tokens": 4572.0, "train_token_mean_nll": 2.09277624425454, "grad_norm": 15.857527732849121, "t": 1793808099.332682} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 47, "batch_sha256": "e06f267d76b04fc06bc99679c9b6d50afe7b5227773bd805b7e5eab66fc14f8f", "params_type": "AdamParams", "train_nll_sum": 14331.966161919107, "train_tokens": 7065.0, "train_token_mean_nll": 2.0285868594365333, "grad_norm": 12.46955394744873, "t": 1793808099.3334334} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 47, "batch_sha256": "e06f267d76b04fc06bc99679c9b6d50afe7b5227773bd805b7e5eab66fc14f8f", "params_type": "DimuonParams", "train_nll_sum": 14361.780599315061, "train_tokens": 7065.0, "train_token_mean_nll": 2.0328068788839437, "grad_norm": 16.198490142822266, "t": 1793808099.3341653} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 48, "batch_sha256": "d770c94db4de84e375b45953ef68fcffaed96e8f25c1e73a0b0fa9c27ebe5fcf", "params_type": "AdamParams", "train_nll_sum": 13662.91883042764, "train_tokens": 5920.0, "train_token_mean_nll": 2.307925478112777, "grad_norm": 14.50514030456543, "t": 1793808113.8127844} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 48, "batch_sha256": "d770c94db4de84e375b45953ef68fcffaed96e8f25c1e73a0b0fa9c27ebe5fcf", "params_type": "DimuonParams", "train_nll_sum": 13682.961621118791, "train_tokens": 5920.0, "train_token_mean_nll": 2.3113110846484446, "grad_norm": 16.890399932861328, "t": 1793808113.9209278} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 48, "batch_sha256": "fcc19d505abbb050c58bbb2f4c03e8d3bfdd3b92b2fdf643a9b5cd40115f464d", "params_type": "AdamParams", "train_nll_sum": 14548.880667363412, "train_tokens": 7694.0, "train_token_mean_nll": 1.8909384802915794, "grad_norm": 11.250749588012695, "t": 1793808113.9327025} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 48, "batch_sha256": "fcc19d505abbb050c58bbb2f4c03e8d3bfdd3b92b2fdf643a9b5cd40115f464d", "params_type": "DimuonParams", "train_nll_sum": 14591.754518247968, "train_tokens": 7694.0, "train_token_mean_nll": 1.8965108549841394, "grad_norm": 14.028447151184082, "t": 1793808115.011931} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 48, "batch_sha256": "461f9c6da9be76e6059bbe46dd6605dd176e53cac71afb9f057998bc5ea30896", "params_type": "AdamParams", "train_nll_sum": 11295.252371328515, "train_tokens": 5997.0, "train_token_mean_nll": 1.8834838037899808, "grad_norm": 13.172298431396484, "t": 1793808115.0142395} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 48, "batch_sha256": "461f9c6da9be76e6059bbe46dd6605dd176e53cac71afb9f057998bc5ea30896", "params_type": "DimuonParams", "train_nll_sum": 11332.853965596703, "train_tokens": 5997.0, "train_token_mean_nll": 1.8897538712017181, "grad_norm": 15.603525161743164, "t": 1793808115.0155354} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 49, "batch_sha256": "ba7db5470f88d4979a5a6a2584c26bd2bbfc960b243ed9ec8dac64d9448dd5a7", "params_type": "AdamParams", "train_nll_sum": 17345.123136549737, "train_tokens": 7880.0, "train_token_mean_nll": 2.2011577584453983, "grad_norm": 11.542787551879883, "t": 1793808121.5050364} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 49, "batch_sha256": "ba7db5470f88d4979a5a6a2584c26bd2bbfc960b243ed9ec8dac64d9448dd5a7", "params_type": "DimuonParams", "train_nll_sum": 17362.03927009611, "train_tokens": 7880.0, "train_token_mean_nll": 2.2033044759005214, "grad_norm": 13.923696517944336, "t": 1793808121.5062337} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 49, "batch_sha256": "4cd6fdd0fe5096a1ab25701e21a4cde624e35dacf45c6928611d4b098fd5dcb2", "params_type": "AdamParams", "train_nll_sum": 9112.670801445784, "train_tokens": 4908.0, "train_token_mean_nll": 1.8566973923076169, "grad_norm": 15.678593635559082, "t": 1793808121.5070796} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 49, "batch_sha256": "4cd6fdd0fe5096a1ab25701e21a4cde624e35dacf45c6928611d4b098fd5dcb2", "params_type": "DimuonParams", "train_nll_sum": 9130.309771270237, "train_tokens": 4908.0, "train_token_mean_nll": 1.8602913144397384, "grad_norm": 19.379968643188477, "t": 1793808122.1849346} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 49, "batch_sha256": "915697b4316d1780b4a2064e301fc13b18e45b64a6a1401e68be8f391c4e7ef6", "params_type": "AdamParams", "train_nll_sum": 12114.093466705885, "train_tokens": 6193.0, "train_token_mean_nll": 1.9560945368490044, "grad_norm": 11.906630516052246, "t": 1793808122.1868415} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 49, "batch_sha256": "915697b4316d1780b4a2064e301fc13b18e45b64a6a1401e68be8f391c4e7ef6", "params_type": "DimuonParams", "train_nll_sum": 12125.270120254845, "train_tokens": 6193.0, "train_token_mean_nll": 1.9578992604965033, "grad_norm": 14.383871078491211, "t": 1793808122.1883996} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 50, "batch_sha256": "0b8cc65a4c9000f996b2d259b4f87d9dd0c79a134a9d8b0c5212a6cc61c9ba85", "params_type": "AdamParams", "train_nll_sum": 8156.3176122852, "train_tokens": 4184.0, "train_token_mean_nll": 1.9494066950968452, "grad_norm": 15.960683822631836, "t": 1793808128.592643} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 50, "batch_sha256": "0b8cc65a4c9000f996b2d259b4f87d9dd0c79a134a9d8b0c5212a6cc61c9ba85", "params_type": "DimuonParams", "train_nll_sum": 8168.47381912443, "train_tokens": 4184.0, "train_token_mean_nll": 1.9523120982610969, "grad_norm": 18.442623138427734, "t": 1793808128.5935447} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 50, "batch_sha256": "5ca0310f6f999a5dd13bd1a7bb96761abd2255780ed60a287b4a962ade52406c", "params_type": "AdamParams", "train_nll_sum": 10503.5556943336, "train_tokens": 5054.0, "train_token_mean_nll": 2.0782658674977443, "grad_norm": 14.059233665466309, "t": 1793808128.6064115} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 50, "batch_sha256": "5ca0310f6f999a5dd13bd1a7bb96761abd2255780ed60a287b4a962ade52406c", "params_type": "DimuonParams", "train_nll_sum": 10522.21146611158, "train_tokens": 5054.0, "train_token_mean_nll": 2.0819571559381833, "grad_norm": 17.03910255432129, "t": 1793808129.653437} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 50, "batch_sha256": "e11d80bb297f4199e95694db678dfb639c1432c297d816c18f0aeedb6456f506", "params_type": "AdamParams", "train_nll_sum": 14894.114701031958, "train_tokens": 7991.0, "train_token_mean_nll": 1.8638611814581352, "grad_norm": 12.609333992004395, "t": 1793808129.6546755} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 50, "batch_sha256": "e11d80bb297f4199e95694db678dfb639c1432c297d816c18f0aeedb6456f506", "params_type": "DimuonParams", "train_nll_sum": 14910.148323057654, "train_tokens": 7991.0, "train_token_mean_nll": 1.8658676414788704, "grad_norm": 15.342862129211426, "t": 1793808129.6557517} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 51, "batch_sha256": "d4c4746d6ffe262c69a670d91d33dbc8a24fedd42d48fa944f56bb96142af76f", "params_type": "AdamParams", "train_nll_sum": 9975.610158273463, "train_tokens": 5102.0, "train_token_mean_nll": 1.955235232903462, "grad_norm": 13.731261253356934, "t": 1793808135.744338} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 51, "batch_sha256": "d4c4746d6ffe262c69a670d91d33dbc8a24fedd42d48fa944f56bb96142af76f", "params_type": "DimuonParams", "train_nll_sum": 9980.457256297055, "train_tokens": 5102.0, "train_token_mean_nll": 1.9561852717163966, "grad_norm": 16.66936492919922, "t": 1793808135.8599792} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 51, "batch_sha256": "2683793f1ca94cc8c4169bac8ef2be2e08181316cfe6dd2ddaae3d027c1c9db8", "params_type": "AdamParams", "train_nll_sum": 10765.977876080562, "train_tokens": 5794.0, "train_token_mean_nll": 1.8581252806490443, "grad_norm": 12.820779800415039, "t": 1793808135.8616426} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 51, "batch_sha256": "2683793f1ca94cc8c4169bac8ef2be2e08181316cfe6dd2ddaae3d027c1c9db8", "params_type": "DimuonParams", "train_nll_sum": 10792.016803279766, "train_tokens": 5794.0, "train_token_mean_nll": 1.8626193999447302, "grad_norm": 15.83881950378418, "t": 1793808135.9950645} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 51, "batch_sha256": "ea8c2c5a9360a342a54d181df5f21dace18284302fcb2fa6a33babfe160b7795", "params_type": "AdamParams", "train_nll_sum": 10564.164519080034, "train_tokens": 4973.0, "train_token_mean_nll": 2.1243041462055166, "grad_norm": 13.311602592468262, "t": 1793808136.8314662} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 51, "batch_sha256": "ea8c2c5a9360a342a54d181df5f21dace18284302fcb2fa6a33babfe160b7795", "params_type": "DimuonParams", "train_nll_sum": 10584.657215113923, "train_tokens": 4973.0, "train_token_mean_nll": 2.1284249376862903, "grad_norm": 15.900814056396484, "t": 1793808136.8330133} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 52, "batch_sha256": "58c87ab3984c900e7be6da1094f414c97c752c083788408db43a960bf12a8bfa", "params_type": "AdamParams", "train_nll_sum": 12025.175491470902, "train_tokens": 6744.0, "train_token_mean_nll": 1.783092451285721, "grad_norm": 12.440006256103516, "t": 1793808142.9591112} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 52, "batch_sha256": "58c87ab3984c900e7be6da1094f414c97c752c083788408db43a960bf12a8bfa", "params_type": "DimuonParams", "train_nll_sum": 12041.798282275857, "train_tokens": 6744.0, "train_token_mean_nll": 1.785557277917535, "grad_norm": 14.829336166381836, "t": 1793808142.9601746} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 52, "batch_sha256": "cd73d35dd56402db8eb3d076682a3ccbbf957272cccf43dd4da79957d2b25c1d", "params_type": "AdamParams", "train_nll_sum": 13485.190281227518, "train_tokens": 6427.0, "train_token_mean_nll": 2.0982091615415466, "grad_norm": 12.525762557983398, "t": 1793808142.9613578} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 52, "batch_sha256": "cd73d35dd56402db8eb3d076682a3ccbbf957272cccf43dd4da79957d2b25c1d", "params_type": "DimuonParams", "train_nll_sum": 13507.359986334235, "train_tokens": 6427.0, "train_token_mean_nll": 2.101658625538235, "grad_norm": 15.409331321716309, "t": 1793808144.0120018} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 52, "batch_sha256": "23dbf584484307d81a5d8d133c1c409876e9e4f25b0afd4bac8b0467ee1d6556", "params_type": "AdamParams", "train_nll_sum": 14829.972195124392, "train_tokens": 6489.0, "train_token_mean_nll": 2.2854017868892575, "grad_norm": 14.443300247192383, "t": 1793808144.0128946} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 52, "batch_sha256": "23dbf584484307d81a5d8d133c1c409876e9e4f25b0afd4bac8b0467ee1d6556", "params_type": "DimuonParams", "train_nll_sum": 14871.111864373033, "train_tokens": 6489.0, "train_token_mean_nll": 2.291741695850367, "grad_norm": 17.745203018188477, "t": 1793808144.0136876} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 53, "batch_sha256": "924a94410de7c2aa94f211e78a9f0be874dd4b81f0a9535ade17060ecab392f9", "params_type": "AdamParams", "train_nll_sum": 11418.053906289584, "train_tokens": 5768.0, "train_token_mean_nll": 1.9795516481084576, "grad_norm": 11.861115455627441, "t": 1793808151.6130261} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 53, "batch_sha256": "924a94410de7c2aa94f211e78a9f0be874dd4b81f0a9535ade17060ecab392f9", "params_type": "DimuonParams", "train_nll_sum": 11446.837823941918, "train_tokens": 5768.0, "train_token_mean_nll": 1.9845419250939524, "grad_norm": 14.439009666442871, "t": 1793808151.737468} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 53, "batch_sha256": "75a56968870425969dc1d832050236bf78207fa76a300186bf2e28bcd63c0c93", "params_type": "AdamParams", "train_nll_sum": 12874.263081648249, "train_tokens": 6335.0, "train_token_mean_nll": 2.0322435803706784, "grad_norm": 12.723533630371094, "t": 1793808151.765678} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 53, "batch_sha256": "75a56968870425969dc1d832050236bf78207fa76a300186bf2e28bcd63c0c93", "params_type": "DimuonParams", "train_nll_sum": 12882.46308832088, "train_tokens": 6335.0, "train_token_mean_nll": 2.033537977635498, "grad_norm": 15.397186279296875, "t": 1793808151.8421547} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 53, "batch_sha256": "9818b4e8f3a801166e376d843b3207233d1abac2b5b5f3e72867a5568808c747", "params_type": "AdamParams", "train_nll_sum": 12240.798020928798, "train_tokens": 5923.0, "train_token_mean_nll": 2.0666550769759917, "grad_norm": 12.13247013092041, "t": 1793808152.6894443} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 53, "batch_sha256": "9818b4e8f3a801166e376d843b3207233d1abac2b5b5f3e72867a5568808c747", "params_type": "DimuonParams", "train_nll_sum": 12262.344439797824, "train_tokens": 5923.0, "train_token_mean_nll": 2.070292831301338, "grad_norm": 14.905084609985352, "t": 1793808152.690816} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 54, "batch_sha256": "33d38653b89d346b1528e2e66ddd8373e2f5329c336659e48c5562a9ee6facc1", "params_type": "AdamParams", "train_nll_sum": 13279.196920599337, "train_tokens": 5996.0, "train_token_mean_nll": 2.2146759373914837, "grad_norm": 14.248461723327637, "t": 1793808158.4069083} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 54, "batch_sha256": "33d38653b89d346b1528e2e66ddd8373e2f5329c336659e48c5562a9ee6facc1", "params_type": "DimuonParams", "train_nll_sum": 13297.57795683655, "train_tokens": 5996.0, "train_token_mean_nll": 2.2177414871308456, "grad_norm": 17.570632934570312, "t": 1793808158.407859} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 54, "batch_sha256": "eb245a85346dfeff19f368dbd71c324f4b28ef2d7739d9255275694fecaa32da", "params_type": "AdamParams", "train_nll_sum": 15315.606531795374, "train_tokens": 8072.0, "train_token_mean_nll": 1.897374446456315, "grad_norm": 10.818218231201172, "t": 1793808158.4094017} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 54, "batch_sha256": "eb245a85346dfeff19f368dbd71c324f4b28ef2d7739d9255275694fecaa32da", "params_type": "DimuonParams", "train_nll_sum": 15323.52210102133, "train_tokens": 8072.0, "train_token_mean_nll": 1.8983550670244462, "grad_norm": 12.947431564331055, "t": 1793808159.3860166} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 54, "batch_sha256": "8566a5fb9dfe9f83495a563bc35295f97bfbcbbddd9ab91d4a377ca6e71999e4", "params_type": "AdamParams", "train_nll_sum": 11566.75344461428, "train_tokens": 5626.0, "train_token_mean_nll": 2.0559462219364164, "grad_norm": 10.561108589172363, "t": 1793808159.386917} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 54, "batch_sha256": "8566a5fb9dfe9f83495a563bc35295f97bfbcbbddd9ab91d4a377ca6e71999e4", "params_type": "DimuonParams", "train_nll_sum": 11576.238595147412, "train_tokens": 5626.0, "train_token_mean_nll": 2.0576321711957717, "grad_norm": 12.606510162353516, "t": 1793808159.387672} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 55, "batch_sha256": "67365c869861e69978c9789d9732de30126f8627ace03a5d82813a2ea5e55f3d", "params_type": "AdamParams", "train_nll_sum": 15155.14024963406, "train_tokens": 7249.0, "train_token_mean_nll": 2.090652538230661, "grad_norm": 12.739724159240723, "t": 1793808165.684107} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 55, "batch_sha256": "67365c869861e69978c9789d9732de30126f8627ace03a5d82813a2ea5e55f3d", "params_type": "DimuonParams", "train_nll_sum": 15150.856304697074, "train_tokens": 7249.0, "train_token_mean_nll": 2.090061567760667, "grad_norm": 15.83326530456543, "t": 1793808165.7017984} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 55, "batch_sha256": "ce038285eb1ab0a136a1a8f446080222d7297e6ab6f1e68c3a075d8959a4e5c9", "params_type": "AdamParams", "train_nll_sum": 8208.448830820533, "train_tokens": 4556.0, "train_token_mean_nll": 1.801678847853497, "grad_norm": 14.30212688446045, "t": 1793808165.70258} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 55, "batch_sha256": "ce038285eb1ab0a136a1a8f446080222d7297e6ab6f1e68c3a075d8959a4e5c9", "params_type": "DimuonParams", "train_nll_sum": 8205.721008920453, "train_tokens": 4556.0, "train_token_mean_nll": 1.8010801160931635, "grad_norm": 17.301166534423828, "t": 1793808166.685239} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 55, "batch_sha256": "f4337c0aee81e9893abcd9cfa7e3d3e9223b9c3b9d53bd30a70028bffe01de11", "params_type": "AdamParams", "train_nll_sum": 14651.303623220645, "train_tokens": 7693.0, "train_token_mean_nll": 1.9044980661927264, "grad_norm": 10.205975532531738, "t": 1793808166.702971} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 55, "batch_sha256": "f4337c0aee81e9893abcd9cfa7e3d3e9223b9c3b9d53bd30a70028bffe01de11", "params_type": "DimuonParams", "train_nll_sum": 14672.582190368503, "train_tokens": 7693.0, "train_token_mean_nll": 1.9072640309851168, "grad_norm": 12.060009002685547, "t": 1793808166.8782916} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 56, "batch_sha256": "442323b97a1f746694139f935b1b8bd281e064f0b7ebb7df225272e3d9879506", "params_type": "AdamParams", "train_nll_sum": 12172.733197408077, "train_tokens": 6083.0, "train_token_mean_nll": 2.0011068876225675, "grad_norm": 12.626282691955566, "t": 1793808172.6946692} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 56, "batch_sha256": "442323b97a1f746694139f935b1b8bd281e064f0b7ebb7df225272e3d9879506", "params_type": "DimuonParams", "train_nll_sum": 12188.854772163651, "train_tokens": 6083.0, "train_token_mean_nll": 2.003757154720311, "grad_norm": 15.298714637756348, "t": 1793808172.7127423} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 56, "batch_sha256": "ffb0f262c27feed79d48b2ed1f1560ff9faa82d4f9f156445ae81f72a332b74b", "params_type": "AdamParams", "train_nll_sum": 15203.244444672024, "train_tokens": 6843.0, "train_token_mean_nll": 2.2217221167137255, "grad_norm": 10.829383850097656, "t": 1793808172.7146702} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 56, "batch_sha256": "ffb0f262c27feed79d48b2ed1f1560ff9faa82d4f9f156445ae81f72a332b74b", "params_type": "DimuonParams", "train_nll_sum": 15206.432012359517, "train_tokens": 6843.0, "train_token_mean_nll": 2.2221879310769426, "grad_norm": 12.906144142150879, "t": 1793808172.7171643} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 56, "batch_sha256": "dd292ab1238253bc9dc821f9cff79c83b3593dc6901e9a40d0a19ef0b95f893b", "params_type": "AdamParams", "train_nll_sum": 8969.143730451524, "train_tokens": 4644.0, "train_token_mean_nll": 1.9313401659025675, "grad_norm": 12.318361282348633, "t": 1793808173.2486227} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 56, "batch_sha256": "dd292ab1238253bc9dc821f9cff79c83b3593dc6901e9a40d0a19ef0b95f893b", "params_type": "DimuonParams", "train_nll_sum": 8988.058847141821, "train_tokens": 4644.0, "train_token_mean_nll": 1.935413188445698, "grad_norm": 14.836250305175781, "t": 1793808173.2502646} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 57, "batch_sha256": "df2b34ab38fbf88495c3529fa6ccc58bc5211f21d877e81ee67683e5c3163edd", "params_type": "AdamParams", "train_nll_sum": 11860.489688683609, "train_tokens": 5255.0, "train_token_mean_nll": 2.2569913774849875, "grad_norm": 14.001595497131348, "t": 1793808181.1712754} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 57, "batch_sha256": "df2b34ab38fbf88495c3529fa6ccc58bc5211f21d877e81ee67683e5c3163edd", "params_type": "DimuonParams", "train_nll_sum": 11871.898647898744, "train_tokens": 5255.0, "train_token_mean_nll": 2.2591624448903413, "grad_norm": 16.57477378845215, "t": 1793808181.1928558} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 57, "batch_sha256": "b2b59aadbff1a3b4d85e09548769bcdde8cf7762770f022ff2bb6c0c29772fb0", "params_type": "AdamParams", "train_nll_sum": 8100.574618271185, "train_tokens": 4835.0, "train_token_mean_nll": 1.6754032302525719, "grad_norm": 12.647289276123047, "t": 1793808181.1936662} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 57, "batch_sha256": "b2b59aadbff1a3b4d85e09548769bcdde8cf7762770f022ff2bb6c0c29772fb0", "params_type": "DimuonParams", "train_nll_sum": 8110.605036611243, "train_tokens": 4835.0, "train_token_mean_nll": 1.677477773859616, "grad_norm": 15.481450080871582, "t": 1793808182.2557368} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 57, "batch_sha256": "f8923317aa79fc644209ed7ac8c30b3bff57a25ab7de7a57b40cae49aefde094", "params_type": "AdamParams", "train_nll_sum": 11630.74943844924, "train_tokens": 5855.0, "train_token_mean_nll": 1.9864644642953442, "grad_norm": 13.969709396362305, "t": 1793808182.256469} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 57, "batch_sha256": "f8923317aa79fc644209ed7ac8c30b3bff57a25ab7de7a57b40cae49aefde094", "params_type": "DimuonParams", "train_nll_sum": 11629.24034289205, "train_tokens": 5855.0, "train_token_mean_nll": 1.9862067195374977, "grad_norm": 16.64280891418457, "t": 1793808182.438606} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 58, "batch_sha256": "42bfa915dd9a0e0797259ee04a6cc756bffc38eb6a29282303da52c398a07dd5", "params_type": "AdamParams", "train_nll_sum": 15076.453679592974, "train_tokens": 7436.0, "train_token_mean_nll": 2.02749511559884, "grad_norm": 12.719351768493652, "t": 1793808189.1550188} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 58, "batch_sha256": "42bfa915dd9a0e0797259ee04a6cc756bffc38eb6a29282303da52c398a07dd5", "params_type": "DimuonParams", "train_nll_sum": 15086.246057022587, "train_tokens": 7436.0, "train_token_mean_nll": 2.02881200336506, "grad_norm": 14.021732330322266, "t": 1793808189.1602888} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 58, "batch_sha256": "92de68b1084b74488964372b5b5088c844114fc351e796590e8ca43d59d1fd67", "params_type": "AdamParams", "train_nll_sum": 13083.602336959317, "train_tokens": 6307.0, "train_token_mean_nll": 2.0744573231265764, "grad_norm": 13.90694808959961, "t": 1793808189.1623642} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 58, "batch_sha256": "92de68b1084b74488964372b5b5088c844114fc351e796590e8ca43d59d1fd67", "params_type": "DimuonParams", "train_nll_sum": 13104.076977940433, "train_tokens": 6307.0, "train_token_mean_nll": 2.0777036590994817, "grad_norm": 17.054975509643555, "t": 1793808190.212378} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 58, "batch_sha256": "ac84e4b3520df2bef792c1b7507445d208bb9b181fe63180c0328380dc2a7937", "params_type": "AdamParams", "train_nll_sum": 15550.038596764563, "train_tokens": 7010.0, "train_token_mean_nll": 2.2182651350591387, "grad_norm": 13.581707954406738, "t": 1793808190.2132752} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 58, "batch_sha256": "ac84e4b3520df2bef792c1b7507445d208bb9b181fe63180c0328380dc2a7937", "params_type": "DimuonParams", "train_nll_sum": 15582.841027479893, "train_tokens": 7010.0, "train_token_mean_nll": 2.222944511766033, "grad_norm": 16.20697021484375, "t": 1793808190.3268585} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 59, "batch_sha256": "7e36e4533a60548c38d7ab09aeb459cca41b02e616e75af696e703c98834022c", "params_type": "AdamParams", "train_nll_sum": 14659.420408080367, "train_tokens": 6825.0, "train_token_mean_nll": 2.1479004260923613, "grad_norm": 13.445318222045898, "t": 1793808198.334283} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 59, "batch_sha256": "7e36e4533a60548c38d7ab09aeb459cca41b02e616e75af696e703c98834022c", "params_type": "DimuonParams", "train_nll_sum": 14659.977816939056, "train_tokens": 6825.0, "train_token_mean_nll": 2.1479820977200084, "grad_norm": 15.764039039611816, "t": 1793808198.3351276} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 59, "batch_sha256": "45d4b19855f88f217bef9b805c9958abd41e9b6fb63cbad886fba64feaf4145d", "params_type": "AdamParams", "train_nll_sum": 12023.577215969453, "train_tokens": 5787.0, "train_token_mean_nll": 2.0776874401191385, "grad_norm": 14.860023498535156, "t": 1793808198.3527668} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 59, "batch_sha256": "45d4b19855f88f217bef9b805c9958abd41e9b6fb63cbad886fba64feaf4145d", "params_type": "DimuonParams", "train_nll_sum": 12051.912970809964, "train_tokens": 5787.0, "train_token_mean_nll": 2.0825838898928573, "grad_norm": 17.83222770690918, "t": 1793808199.3106754} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 59, "batch_sha256": "06559cc7797dd6c3569c8b9f5fd27ad01268ca5bd53ffa29346f6c2d24bceb6c", "params_type": "AdamParams", "train_nll_sum": 10645.694934228191, "train_tokens": 5189.0, "train_token_mean_nll": 2.051588925463132, "grad_norm": 11.607961654663086, "t": 1793808199.3113856} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 59, "batch_sha256": "06559cc7797dd6c3569c8b9f5fd27ad01268ca5bd53ffa29346f6c2d24bceb6c", "params_type": "DimuonParams", "train_nll_sum": 10643.855168175083, "train_tokens": 5189.0, "train_token_mean_nll": 2.0512343742869694, "grad_norm": 13.837386131286621, "t": 1793808199.3120296} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 60, "batch_sha256": "35a1a0ce33cfc9cc60babf4114304737eeb335fee4c71a93b2e298f9f6b895b6", "params_type": "AdamParams", "train_nll_sum": 10695.6574841375, "train_tokens": 5293.0, "train_token_mean_nll": 2.0207174540218213, "grad_norm": 13.078775405883789, "t": 1793808205.6884518} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 60, "batch_sha256": "35a1a0ce33cfc9cc60babf4114304737eeb335fee4c71a93b2e298f9f6b895b6", "params_type": "DimuonParams", "train_nll_sum": 10708.285436695187, "train_tokens": 5293.0, "train_token_mean_nll": 2.0231032376148095, "grad_norm": 15.96023178100586, "t": 1793808206.755885} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 60, "batch_sha256": "7cc763ed0221157d2f1854d4a7356392b7a66b15efff6a64d39b9acc7af94074", "params_type": "AdamParams", "train_nll_sum": 14768.415201122196, "train_tokens": 7450.0, "train_token_mean_nll": 1.9823376108888853, "grad_norm": 11.949891090393066, "t": 1793808206.844474} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 60, "batch_sha256": "7cc763ed0221157d2f1854d4a7356392b7a66b15efff6a64d39b9acc7af94074", "params_type": "DimuonParams", "train_nll_sum": 14779.07489006899, "train_tokens": 7450.0, "train_token_mean_nll": 1.9837684416199988, "grad_norm": 13.788446426391602, "t": 1793808206.8454962} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 60, "batch_sha256": "b54b8ecf5e37fa0bffaf3e7c6edc4c0a820d77b480cca14a09fd248755573706", "params_type": "AdamParams", "train_nll_sum": 12305.78138525917, "train_tokens": 5734.0, "train_token_mean_nll": 2.146107670955558, "grad_norm": 16.364614486694336, "t": 1793808206.8462143} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 60, "batch_sha256": "b54b8ecf5e37fa0bffaf3e7c6edc4c0a820d77b480cca14a09fd248755573706", "params_type": "DimuonParams", "train_nll_sum": 12319.498500764214, "train_tokens": 5734.0, "train_token_mean_nll": 2.1484999129341147, "grad_norm": 19.664241790771484, "t": 1793808206.846922} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 61, "batch_sha256": "172033af6f0097382622e7e8b5769a342ff17e8ba56a3b8a79c8277c864b2f46", "params_type": "AdamParams", "train_nll_sum": 14553.681427401003, "train_tokens": 7139.0, "train_token_mean_nll": 2.038616252612551, "grad_norm": 10.874828338623047, "t": 1793808214.3086662} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 61, "batch_sha256": "172033af6f0097382622e7e8b5769a342ff17e8ba56a3b8a79c8277c864b2f46", "params_type": "DimuonParams", "train_nll_sum": 14578.96360787841, "train_tokens": 7139.0, "train_token_mean_nll": 2.04215767024491, "grad_norm": 13.202643394470215, "t": 1793808214.3310373} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 61, "batch_sha256": "a0e1d24923037faeebccb273654744ec7e0dc60d92c4a0447ab8418aff0a058d", "params_type": "AdamParams", "train_nll_sum": 13722.005447247484, "train_tokens": 6700.0, "train_token_mean_nll": 2.04806051451455, "grad_norm": 12.023846626281738, "t": 1793808214.3318396} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 61, "batch_sha256": "a0e1d24923037faeebccb273654744ec7e0dc60d92c4a0447ab8418aff0a058d", "params_type": "DimuonParams", "train_nll_sum": 13736.52932118246, "train_tokens": 6700.0, "train_token_mean_nll": 2.0502282568929044, "grad_norm": 14.291915893554688, "t": 1793808214.8448808} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 61, "batch_sha256": "da09fe44b16a2c0f53f238e3b9becd3a9d9ef37b9a42f84f0b668554a5aec62d", "params_type": "AdamParams", "train_nll_sum": 11849.596132512548, "train_tokens": 5879.0, "train_token_mean_nll": 2.0155802232543882, "grad_norm": 14.153862953186035, "t": 1793808214.845786} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 61, "batch_sha256": "da09fe44b16a2c0f53f238e3b9becd3a9d9ef37b9a42f84f0b668554a5aec62d", "params_type": "DimuonParams", "train_nll_sum": 11840.18031441456, "train_tokens": 5879.0, "train_token_mean_nll": 2.013978621264596, "grad_norm": 17.16948127746582, "t": 1793808214.8465436} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 62, "batch_sha256": "12931d50e4a9167b83c280c25fdd98d71ca670a34ea52e1ad1e1de32d7d261a6", "params_type": "AdamParams", "train_nll_sum": 12331.087168079233, "train_tokens": 5817.0, "train_token_mean_nll": 2.1198361987414875, "grad_norm": 13.024725914001465, "t": 1793808222.1700256} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 62, "batch_sha256": "12931d50e4a9167b83c280c25fdd98d71ca670a34ea52e1ad1e1de32d7d261a6", "params_type": "DimuonParams", "train_nll_sum": 12334.855734270994, "train_tokens": 5817.0, "train_token_mean_nll": 2.1204840526510216, "grad_norm": 15.656781196594238, "t": 1793808222.1708832} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 62, "batch_sha256": "83ded23e73f43d4314cc8df2748a83456d05af3e595399224d2b550511070784", "params_type": "AdamParams", "train_nll_sum": 14963.716285161892, "train_tokens": 7142.0, "train_token_mean_nll": 2.0951717005267283, "grad_norm": 12.213579177856445, "t": 1793808222.4499924} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 62, "batch_sha256": "83ded23e73f43d4314cc8df2748a83456d05af3e595399224d2b550511070784", "params_type": "DimuonParams", "train_nll_sum": 14979.547868106332, "train_tokens": 7142.0, "train_token_mean_nll": 2.0973883881414634, "grad_norm": 14.494688034057617, "t": 1793808222.4511304} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 62, "batch_sha256": "dafb298a769a3f378640e034ccec846502cec774aba766dd8007b267a2896c9d", "params_type": "AdamParams", "train_nll_sum": 13206.59853738167, "train_tokens": 6801.0, "train_token_mean_nll": 1.9418612758979075, "grad_norm": 10.513688087463379, "t": 1793808222.4520206} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 62, "batch_sha256": "dafb298a769a3f378640e034ccec846502cec774aba766dd8007b267a2896c9d", "params_type": "DimuonParams", "train_nll_sum": 13218.029425647841, "train_tokens": 6801.0, "train_token_mean_nll": 1.9435420417067844, "grad_norm": 12.563185691833496, "t": 1793808222.462513} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 63, "batch_sha256": "a19a60a3c3a8810232eff4f115941cc10853ff4490ad2c3db9f5ef287172c717", "params_type": "AdamParams", "train_nll_sum": 13768.775193543554, "train_tokens": 6921.0, "train_token_mean_nll": 1.989419909484692, "grad_norm": 12.945450782775879, "t": 1793808230.3418837} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 63, "batch_sha256": "a19a60a3c3a8810232eff4f115941cc10853ff4490ad2c3db9f5ef287172c717", "params_type": "DimuonParams", "train_nll_sum": 13781.97492520258, "train_tokens": 6921.0, "train_token_mean_nll": 1.9913271095510157, "grad_norm": 15.366912841796875, "t": 1793808230.3452673} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 63, "batch_sha256": "b8aa6ce5f8551b870fa30e4879a2cfaf59a74ede21260be63beee05657372b70", "params_type": "AdamParams", "train_nll_sum": 10594.472355724083, "train_tokens": 5712.0, "train_token_mean_nll": 1.8547745720805469, "grad_norm": 12.962177276611328, "t": 1793808230.3468459} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 63, "batch_sha256": "b8aa6ce5f8551b870fa30e4879a2cfaf59a74ede21260be63beee05657372b70", "params_type": "DimuonParams", "train_nll_sum": 10602.692332054357, "train_tokens": 5712.0, "train_token_mean_nll": 1.8562136435669394, "grad_norm": 15.74029541015625, "t": 1793808230.6892364} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 63, "batch_sha256": "f42e10d4ff925c13e7c4b55778f62ef66e9a763e692d6994f56d5d0970beedcb", "params_type": "AdamParams", "train_nll_sum": 13193.072827819233, "train_tokens": 6575.0, "train_token_mean_nll": 2.0065510004287805, "grad_norm": 10.406201362609863, "t": 1793808230.690235} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 63, "batch_sha256": "f42e10d4ff925c13e7c4b55778f62ef66e9a763e692d6994f56d5d0970beedcb", "params_type": "DimuonParams", "train_nll_sum": 13202.395764776964, "train_tokens": 6575.0, "train_token_mean_nll": 2.0079689376086636, "grad_norm": 12.777302742004395, "t": 1793808230.6911528} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 64, "batch_sha256": "59e2dd2f0afe0126082063c81b854e14e1b61ce36b978ae27369abc57be787cd", "params_type": "AdamParams", "train_nll_sum": 10893.068365594663, "train_tokens": 5307.0, "train_token_mean_nll": 2.0525849567730665, "grad_norm": 12.663962364196777, "t": 1793808237.044443} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 64, "batch_sha256": "59e2dd2f0afe0126082063c81b854e14e1b61ce36b978ae27369abc57be787cd", "params_type": "DimuonParams", "train_nll_sum": 10902.969895153708, "train_tokens": 5307.0, "train_token_mean_nll": 2.0544507057007175, "grad_norm": 15.239995956420898, "t": 1793808237.0458717} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 64, "batch_sha256": "f8d1408a42b9b4d9b25b437bc46100b2b053f9aa14df05ab80728963ae46ed85", "params_type": "AdamParams", "train_nll_sum": 14112.66538148189, "train_tokens": 6388.0, "train_token_mean_nll": 2.209246302674059, "grad_norm": 12.825221061706543, "t": 1793808237.1525025} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 64, "batch_sha256": "f8d1408a42b9b4d9b25b437bc46100b2b053f9aa14df05ab80728963ae46ed85", "params_type": "DimuonParams", "train_nll_sum": 14092.7322305912, "train_tokens": 6388.0, "train_token_mean_nll": 2.206125897086913, "grad_norm": 14.84398078918457, "t": 1793808237.1548038} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 64, "batch_sha256": "9e1afbfae446904171689b9a35240e0167ca216f927db0cb22396520559596d8", "params_type": "AdamParams", "train_nll_sum": 10997.199785358644, "train_tokens": 5309.0, "train_token_mean_nll": 2.071425840150432, "grad_norm": 15.84472370147705, "t": 1793808237.156364} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 64, "batch_sha256": "9e1afbfae446904171689b9a35240e0167ca216f927db0cb22396520559596d8", "params_type": "DimuonParams", "train_nll_sum": 11006.7706311562, "train_tokens": 5309.0, "train_token_mean_nll": 2.0732285988239214, "grad_norm": 18.049577713012695, "t": 1793808237.1591852} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 65, "batch_sha256": "dad50f8ee2029dc3bb8a70600cf062eb3042adb487dfea8efe9d59363a279184", "params_type": "AdamParams", "train_nll_sum": 12195.3922665942, "train_tokens": 6452.0, "train_token_mean_nll": 1.890172390978642, "grad_norm": 10.248604774475098, "t": 1793808243.2464182} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 65, "batch_sha256": "dad50f8ee2029dc3bb8a70600cf062eb3042adb487dfea8efe9d59363a279184", "params_type": "DimuonParams", "train_nll_sum": 12200.688384497447, "train_tokens": 6452.0, "train_token_mean_nll": 1.890993240002704, "grad_norm": 12.068266868591309, "t": 1793808244.1348383} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 65, "batch_sha256": "e37db63e946c144b131bd257e19827e1280756dbd5915df16a02d780a4ddb3cd", "params_type": "AdamParams", "train_nll_sum": 11851.567603693145, "train_tokens": 6328.0, "train_token_mean_nll": 1.8728773077896879, "grad_norm": 13.265167236328125, "t": 1793808244.254276} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 65, "batch_sha256": "e37db63e946c144b131bd257e19827e1280756dbd5915df16a02d780a4ddb3cd", "params_type": "DimuonParams", "train_nll_sum": 11846.525121070938, "train_tokens": 6328.0, "train_token_mean_nll": 1.872080455289339, "grad_norm": 15.7520170211792, "t": 1793808244.3698888} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 65, "batch_sha256": "042cfef915388be326507be5c13cdb917607e8c0c2831bef000d728303d28e41", "params_type": "AdamParams", "train_nll_sum": 14240.758579089426, "train_tokens": 7109.0, "train_token_mean_nll": 2.0032013755928295, "grad_norm": 10.814623832702637, "t": 1793808244.3721914} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 65, "batch_sha256": "042cfef915388be326507be5c13cdb917607e8c0c2831bef000d728303d28e41", "params_type": "DimuonParams", "train_nll_sum": 14256.390418163182, "train_tokens": 7109.0, "train_token_mean_nll": 2.005400255755125, "grad_norm": 12.983278274536133, "t": 1793808244.3729546} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 66, "batch_sha256": "0a28d3341341628e2845ec34ab5df350d048b251d0d1eed68132b24229c995f1", "params_type": "AdamParams", "train_nll_sum": 13348.375668869769, "train_tokens": 7161.0, "train_token_mean_nll": 1.8640379372810736, "grad_norm": 12.13188648223877, "t": 1793808250.329491} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 66, "batch_sha256": "0a28d3341341628e2845ec34ab5df350d048b251d0d1eed68132b24229c995f1", "params_type": "DimuonParams", "train_nll_sum": 13342.80127674655, "train_tokens": 7161.0, "train_token_mean_nll": 1.8632594996154936, "grad_norm": 14.248248100280762, "t": 1793808251.370395} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 66, "batch_sha256": "83fdf895e532b1c4ade42b802dcaa52bfcaa2f8e37b011732901ea5e8a8c1737", "params_type": "AdamParams", "train_nll_sum": 12734.587935707425, "train_tokens": 6001.0, "train_token_mean_nll": 2.1220776430107358, "grad_norm": 12.771584510803223, "t": 1793808251.3730853} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 66, "batch_sha256": "83fdf895e532b1c4ade42b802dcaa52bfcaa2f8e37b011732901ea5e8a8c1737", "params_type": "DimuonParams", "train_nll_sum": 12741.62233025362, "train_tokens": 6001.0, "train_token_mean_nll": 2.123249846734481, "grad_norm": 15.247501373291016, "t": 1793808251.3762178} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 66, "batch_sha256": "a747a066d9a81bdf974a033cbd0bcf5bd46aa72c2cf32e3eba2761df9c9c90d6", "params_type": "AdamParams", "train_nll_sum": 9209.107348075935, "train_tokens": 5206.0, "train_token_mean_nll": 1.7689410964417855, "grad_norm": 11.288220405578613, "t": 1793808251.376949} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 66, "batch_sha256": "a747a066d9a81bdf974a033cbd0bcf5bd46aa72c2cf32e3eba2761df9c9c90d6", "params_type": "DimuonParams", "train_nll_sum": 9222.924323878242, "train_tokens": 5206.0, "train_token_mean_nll": 1.771595144809497, "grad_norm": 13.488191604614258, "t": 1793808251.3776124} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 67, "batch_sha256": "ff1501c3c883e795527b8a5d101dcdadb78e546b6ecdc81e40d7628b98ca00e6", "params_type": "AdamParams", "train_nll_sum": 14122.250850081575, "train_tokens": 6707.0, "train_token_mean_nll": 2.105598755044219, "grad_norm": 10.797585487365723, "t": 1793808257.044612} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 67, "batch_sha256": "ff1501c3c883e795527b8a5d101dcdadb78e546b6ecdc81e40d7628b98ca00e6", "params_type": "DimuonParams", "train_nll_sum": 14126.766853274601, "train_tokens": 6707.0, "train_token_mean_nll": 2.106272081895721, "grad_norm": 12.906126022338867, "t": 1793808258.0705676} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 67, "batch_sha256": "8b299423205210277a1d3a8e9cc52a13da7f143845fef0362432010466a32229", "params_type": "AdamParams", "train_nll_sum": 13837.1607204014, "train_tokens": 6242.0, "train_token_mean_nll": 2.2167831977573536, "grad_norm": 11.662714004516602, "t": 1793808258.071658} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 67, "batch_sha256": "8b299423205210277a1d3a8e9cc52a13da7f143845fef0362432010466a32229", "params_type": "DimuonParams", "train_nll_sum": 13848.215149578187, "train_tokens": 6242.0, "train_token_mean_nll": 2.2185541732743013, "grad_norm": 13.799670219421387, "t": 1793808258.1739113} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 67, "batch_sha256": "298e4ad35888877d437721f52193d3e0263c1df1772dc57d231b8cfaba99d5d1", "params_type": "AdamParams", "train_nll_sum": 11647.62673833422, "train_tokens": 5220.0, "train_token_mean_nll": 2.2313461184548316, "grad_norm": 13.834627151489258, "t": 1793808258.174666} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 67, "batch_sha256": "298e4ad35888877d437721f52193d3e0263c1df1772dc57d231b8cfaba99d5d1", "params_type": "DimuonParams", "train_nll_sum": 11652.432253068195, "train_tokens": 5220.0, "train_token_mean_nll": 2.232266715147164, "grad_norm": 16.463823318481445, "t": 1793808258.1753576} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 68, "batch_sha256": "76f4ab79119ee76dcf92087a903f4c150ee53331bdc723e27ed00628b8b0e926", "params_type": "AdamParams", "train_nll_sum": 10191.144859419528, "train_tokens": 5066.0, "train_token_mean_nll": 2.0116748636832864, "grad_norm": 13.66269588470459, "t": 1793808264.914528} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 68, "batch_sha256": "76f4ab79119ee76dcf92087a903f4c150ee53331bdc723e27ed00628b8b0e926", "params_type": "DimuonParams", "train_nll_sum": 10183.746486103104, "train_tokens": 5066.0, "train_token_mean_nll": 2.0102144662659107, "grad_norm": 16.572856903076172, "t": 1793808264.9152663} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 68, "batch_sha256": "dacc04c37e4c29d43c6fc57331ec00e4bc46bf797750fc0afb90065756afb5d3", "params_type": "AdamParams", "train_nll_sum": 10162.119749166694, "train_tokens": 5375.0, "train_token_mean_nll": 1.8906269300775245, "grad_norm": 12.59128189086914, "t": 1793808265.0047143} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 68, "batch_sha256": "dacc04c37e4c29d43c6fc57331ec00e4bc46bf797750fc0afb90065756afb5d3", "params_type": "DimuonParams", "train_nll_sum": 10160.350808305091, "train_tokens": 5375.0, "train_token_mean_nll": 1.8902978248009472, "grad_norm": 15.054816246032715, "t": 1793808265.0054784} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 68, "batch_sha256": "92eb41d46a75fd48fbc6e93d741aba0181d033edd25cdde5b1fd5c948c0f809f", "params_type": "AdamParams", "train_nll_sum": 11553.639242311909, "train_tokens": 5483.0, "train_token_mean_nll": 2.107174766060899, "grad_norm": 14.023231506347656, "t": 1793808265.006131} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 68, "batch_sha256": "92eb41d46a75fd48fbc6e93d741aba0181d033edd25cdde5b1fd5c948c0f809f", "params_type": "DimuonParams", "train_nll_sum": 11556.185502322938, "train_tokens": 5483.0, "train_token_mean_nll": 2.107639157819248, "grad_norm": 16.442930221557617, "t": 1793808265.0067794} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 69, "batch_sha256": "6958d5a5adc6c3355cbf8c47a33b021708a7f5dbf682bc9cdbae0dd722e5b9ac", "params_type": "AdamParams", "train_nll_sum": 10760.294900027762, "train_tokens": 5101.0, "train_token_mean_nll": 2.1094481278235175, "grad_norm": 14.49050235748291, "t": 1793808272.2348645} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 69, "batch_sha256": "6958d5a5adc6c3355cbf8c47a33b021708a7f5dbf682bc9cdbae0dd722e5b9ac", "params_type": "DimuonParams", "train_nll_sum": 10763.810934733416, "train_tokens": 5101.0, "train_token_mean_nll": 2.1101374112396423, "grad_norm": 17.3825626373291, "t": 1793808272.7398791} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 69, "batch_sha256": "0ae5b47d5455f49f235c7a93469e2f9e1b7fba91b0ed58ce01c331c27d8dab4b", "params_type": "AdamParams", "train_nll_sum": 13841.581051082943, "train_tokens": 6656.0, "train_token_mean_nll": 2.079564460799721, "grad_norm": 11.36973762512207, "t": 1793808272.7406402} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 69, "batch_sha256": "0ae5b47d5455f49f235c7a93469e2f9e1b7fba91b0ed58ce01c331c27d8dab4b", "params_type": "DimuonParams", "train_nll_sum": 13850.337256210069, "train_tokens": 6656.0, "train_token_mean_nll": 2.0808799964257916, "grad_norm": 13.414081573486328, "t": 1793808272.7422216} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 69, "batch_sha256": "6e947572117dcddff783c84a986bcedefc66656da9fbaeff38fbde8d2b218f29", "params_type": "AdamParams", "train_nll_sum": 15019.772487096798, "train_tokens": 8128.0, "train_token_mean_nll": 1.8479050796132872, "grad_norm": 11.12021255493164, "t": 1793808272.7431934} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 69, "batch_sha256": "6e947572117dcddff783c84a986bcedefc66656da9fbaeff38fbde8d2b218f29", "params_type": "DimuonParams", "train_nll_sum": 15031.01182167943, "train_tokens": 8128.0, "train_token_mean_nll": 1.849287871761741, "grad_norm": 13.107497215270996, "t": 1793808272.7440631} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 70, "batch_sha256": "eba75e9aaa57ca7c9892a829562930ea4ec0211d6d12fae3ed1cab7f9b3cb67b", "params_type": "AdamParams", "train_nll_sum": 12711.77012422578, "train_tokens": 6820.0, "train_token_mean_nll": 1.8638959126430763, "grad_norm": 12.833695411682129, "t": 1793808278.8090363} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 70, "batch_sha256": "eba75e9aaa57ca7c9892a829562930ea4ec0211d6d12fae3ed1cab7f9b3cb67b", "params_type": "DimuonParams", "train_nll_sum": 12707.505913690162, "train_tokens": 6820.0, "train_token_mean_nll": 1.863270661831402, "grad_norm": 14.305652618408203, "t": 1793808279.6536872} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 70, "batch_sha256": "cd2688e8efa1666bdb45ed99f1f6fe6408b19d6f0c10d999728fa9d233485cfe", "params_type": "AdamParams", "train_nll_sum": 13135.37799136798, "train_tokens": 5501.0, "train_token_mean_nll": 2.387816395449551, "grad_norm": 15.130826950073242, "t": 1793808279.9293382} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 70, "batch_sha256": "cd2688e8efa1666bdb45ed99f1f6fe6408b19d6f0c10d999728fa9d233485cfe", "params_type": "DimuonParams", "train_nll_sum": 13117.105751015779, "train_tokens": 5501.0, "train_token_mean_nll": 2.3844947738621665, "grad_norm": 17.135242462158203, "t": 1793808279.9301279} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 70, "batch_sha256": "d3fbec652b1795837b526caeefbf6785f5440c8f4a361b88ca28e7f4d2b0fed9", "params_type": "AdamParams", "train_nll_sum": 10225.393696021269, "train_tokens": 4661.0, "train_token_mean_nll": 2.1938197159453483, "grad_norm": 29.76433563232422, "t": 1793808279.9307601} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 70, "batch_sha256": "d3fbec652b1795837b526caeefbf6785f5440c8f4a361b88ca28e7f4d2b0fed9", "params_type": "DimuonParams", "train_nll_sum": 10230.741941186812, "train_tokens": 4661.0, "train_token_mean_nll": 2.194967161807941, "grad_norm": 43.92847442626953, "t": 1793808279.9313908} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 71, "batch_sha256": "e451ed7e9994d8d90d343c1a3535b67ee9fd607a3f804186647cd89be28e16b6", "params_type": "AdamParams", "train_nll_sum": 11904.693833478199, "train_tokens": 5812.0, "train_token_mean_nll": 2.048295566668651, "grad_norm": 13.553559303283691, "t": 1793808287.627263} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 71, "batch_sha256": "e451ed7e9994d8d90d343c1a3535b67ee9fd607a3f804186647cd89be28e16b6", "params_type": "DimuonParams", "train_nll_sum": 11896.00603720692, "train_tokens": 5812.0, "train_token_mean_nll": 2.0468007634561114, "grad_norm": 16.3823184967041, "t": 1793808287.627986} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 71, "batch_sha256": "d8d3096e1cebfc2a1fe49db798e7edf3e3209730ac74b037832f441c68786a23", "params_type": "AdamParams", "train_nll_sum": 11574.244054028528, "train_tokens": 6201.0, "train_token_mean_nll": 1.8665125066970696, "grad_norm": 10.247197151184082, "t": 1793808287.6289403} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 71, "batch_sha256": "d8d3096e1cebfc2a1fe49db798e7edf3e3209730ac74b037832f441c68786a23", "params_type": "DimuonParams", "train_nll_sum": 11585.143151237222, "train_tokens": 6201.0, "train_token_mean_nll": 1.8682701421121144, "grad_norm": 12.066222190856934, "t": 1793808287.6302955} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 71, "batch_sha256": "8c74b87a6fe70775b4273b685480b5d7634f15d2e7dc8a2ada6ed0d1dc5aa4aa", "params_type": "AdamParams", "train_nll_sum": 15841.469320335409, "train_tokens": 7584.0, "train_token_mean_nll": 2.0888013344324117, "grad_norm": 10.33151912689209, "t": 1793808287.9259577} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 71, "batch_sha256": "8c74b87a6fe70775b4273b685480b5d7634f15d2e7dc8a2ada6ed0d1dc5aa4aa", "params_type": "DimuonParams", "train_nll_sum": 15844.774920195854, "train_tokens": 7584.0, "train_token_mean_nll": 2.089237199392913, "grad_norm": 12.176223754882812, "t": 1793808287.9268074} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 72, "batch_sha256": "e2e32646fe9b89f98880192f2e54646fe848abadd686769abdc626a348b7efbd", "params_type": "AdamParams", "train_nll_sum": 10496.58561719284, "train_tokens": 5108.0, "train_token_mean_nll": 2.054930622003297, "grad_norm": 12.62655258178711, "t": 1793808294.7851744} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 72, "batch_sha256": "e2e32646fe9b89f98880192f2e54646fe848abadd686769abdc626a348b7efbd", "params_type": "DimuonParams", "train_nll_sum": 10492.219664917768, "train_tokens": 5108.0, "train_token_mean_nll": 2.0540758936800643, "grad_norm": 15.142318725585938, "t": 1793808294.7865634} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 72, "batch_sha256": "ba48ecef7852c8b833fa3db54d89937b633b454824a690e39f88caaae117a011", "params_type": "AdamParams", "train_nll_sum": 11279.422327756507, "train_tokens": 5553.0, "train_token_mean_nll": 2.031230384973259, "grad_norm": 12.465333938598633, "t": 1793808294.7874646} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 72, "batch_sha256": "ba48ecef7852c8b833fa3db54d89937b633b454824a690e39f88caaae117a011", "params_type": "DimuonParams", "train_nll_sum": 11278.945776789045, "train_tokens": 5553.0, "train_token_mean_nll": 2.0311445663225367, "grad_norm": 14.954215049743652, "t": 1793808294.788213} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 72, "batch_sha256": "e2f234d1c013f3c77d26182505ca017e566908681f4cd3739b0907ec512982b3", "params_type": "AdamParams", "train_nll_sum": 13654.27379231037, "train_tokens": 6639.0, "train_token_mean_nll": 2.056676275389422, "grad_norm": 10.583734512329102, "t": 1793808294.7888918} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 72, "batch_sha256": "e2f234d1c013f3c77d26182505ca017e566908681f4cd3739b0907ec512982b3", "params_type": "DimuonParams", "train_nll_sum": 13649.71219832234, "train_tokens": 6639.0, "train_token_mean_nll": 2.055989184865543, "grad_norm": 12.703766822814941, "t": 1793808294.9551303} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 73, "batch_sha256": "47408e1be8f671ac5602ced2a90c0e9a9d29b54060104a1163c39d115b854452", "params_type": "AdamParams", "train_nll_sum": 13655.310295343621, "train_tokens": 6351.0, "train_token_mean_nll": 2.1501039671459017, "grad_norm": 14.598289489746094, "t": 1793808300.466618} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 73, "batch_sha256": "47408e1be8f671ac5602ced2a90c0e9a9d29b54060104a1163c39d115b854452", "params_type": "DimuonParams", "train_nll_sum": 13650.196110361836, "train_tokens": 6351.0, "train_token_mean_nll": 2.1492987104962737, "grad_norm": 17.285926818847656, "t": 1793808301.5205886} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 73, "batch_sha256": "5abeb8b89ff745a51e5cf91c6434b8f0e47b38effd01a63ee51ae753300b07bb", "params_type": "AdamParams", "train_nll_sum": 12236.009262862997, "train_tokens": 5780.0, "train_token_mean_nll": 2.1169566198724907, "grad_norm": 13.488899230957031, "t": 1793808301.5214047} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 73, "batch_sha256": "5abeb8b89ff745a51e5cf91c6434b8f0e47b38effd01a63ee51ae753300b07bb", "params_type": "DimuonParams", "train_nll_sum": 12250.298977708095, "train_tokens": 5780.0, "train_token_mean_nll": 2.119428888876833, "grad_norm": 16.31972885131836, "t": 1793808301.5221343} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 73, "batch_sha256": "f80d0fbb6d238b129631ff15be3c6fb1cb1ee87c526059d30ed3704b018f2e88", "params_type": "AdamParams", "train_nll_sum": 8273.766279602942, "train_tokens": 3876.0, "train_token_mean_nll": 2.1346146232205734, "grad_norm": 13.693997383117676, "t": 1793808301.5227928} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 73, "batch_sha256": "f80d0fbb6d238b129631ff15be3c6fb1cb1ee87c526059d30ed3704b018f2e88", "params_type": "DimuonParams", "train_nll_sum": 8275.470337753606, "train_tokens": 3876.0, "train_token_mean_nll": 2.135054266706297, "grad_norm": 16.533035278320312, "t": 1793808301.538729} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 74, "batch_sha256": "8a85c32a692f01f63a963e75fa2ef264210000057ed7a191834127b292a253e4", "params_type": "AdamParams", "train_nll_sum": 15460.010649672258, "train_tokens": 7393.0, "train_token_mean_nll": 2.0911687609457945, "grad_norm": 13.37060832977295, "t": 1793808307.9511902} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 74, "batch_sha256": "8a85c32a692f01f63a963e75fa2ef264210000057ed7a191834127b292a253e4", "params_type": "DimuonParams", "train_nll_sum": 15454.835242801264, "train_tokens": 7393.0, "train_token_mean_nll": 2.0904687194374767, "grad_norm": 15.294918060302734, "t": 1793808308.9442708} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 74, "batch_sha256": "fcff70d4fa91234e8ca01a7602c55163ef21b57067d665f385b4989053c067dd", "params_type": "AdamParams", "train_nll_sum": 9166.103028068801, "train_tokens": 5283.0, "train_token_mean_nll": 1.7350185553792923, "grad_norm": 14.021646499633789, "t": 1793808309.1336923} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 74, "batch_sha256": "fcff70d4fa91234e8ca01a7602c55163ef21b57067d665f385b4989053c067dd", "params_type": "DimuonParams", "train_nll_sum": 9179.912643332953, "train_tokens": 5283.0, "train_token_mean_nll": 1.7376325276041933, "grad_norm": 16.704355239868164, "t": 1793808309.1383336} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 74, "batch_sha256": "9b48e9065c50173c8f5db494ea5f118133953e4b365c9090c28fc8fd8e2c01cb", "params_type": "AdamParams", "train_nll_sum": 12761.593907662846, "train_tokens": 6348.0, "train_token_mean_nll": 2.0103330037276064, "grad_norm": 11.576353073120117, "t": 1793808309.158579} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 74, "batch_sha256": "9b48e9065c50173c8f5db494ea5f118133953e4b365c9090c28fc8fd8e2c01cb", "params_type": "DimuonParams", "train_nll_sum": 12763.208472303453, "train_tokens": 6348.0, "train_token_mean_nll": 2.010587345983531, "grad_norm": 13.894095420837402, "t": 1793808309.1593995} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 75, "batch_sha256": "98e2ab98d53e633310b0d7fb4e76345dd953e4024952c818fc9b30f42320ef00", "params_type": "AdamParams", "train_nll_sum": 14637.542222274613, "train_tokens": 7446.0, "train_token_mean_nll": 1.9658262452692201, "grad_norm": 11.183231353759766, "t": 1793808317.0204163} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 75, "batch_sha256": "98e2ab98d53e633310b0d7fb4e76345dd953e4024952c818fc9b30f42320ef00", "params_type": "DimuonParams", "train_nll_sum": 14620.915560524287, "train_tokens": 7446.0, "train_token_mean_nll": 1.963593279683627, "grad_norm": 13.258218765258789, "t": 1793808317.413497} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 75, "batch_sha256": "41e1195a76137d8c02df92b2718e5717d296b443a267a02b6bd7488c0959ada0", "params_type": "AdamParams", "train_nll_sum": 13126.808516498091, "train_tokens": 6953.0, "train_token_mean_nll": 1.8879344910827112, "grad_norm": 11.692608833312988, "t": 1793808317.4377606} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 75, "batch_sha256": "41e1195a76137d8c02df92b2718e5717d296b443a267a02b6bd7488c0959ada0", "params_type": "DimuonParams", "train_nll_sum": 13121.62312118218, "train_tokens": 6953.0, "train_token_mean_nll": 1.8871887129558722, "grad_norm": 13.903372764587402, "t": 1793808317.4388888} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 75, "batch_sha256": "8adc07ca50fe888c7ffe991ad44563043f98da34e867d1c80a77b41ec6d1d087", "params_type": "AdamParams", "train_nll_sum": 10947.533090257117, "train_tokens": 5698.0, "train_token_mean_nll": 1.9212939786341026, "grad_norm": 12.785300254821777, "t": 1793808317.4399855} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 75, "batch_sha256": "8adc07ca50fe888c7ffe991ad44563043f98da34e867d1c80a77b41ec6d1d087", "params_type": "DimuonParams", "train_nll_sum": 10957.295884632214, "train_tokens": 5698.0, "train_token_mean_nll": 1.9230073507603045, "grad_norm": 15.424124717712402, "t": 1793808317.4409547} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 76, "batch_sha256": "7396544ede609941d10f15b1cd0c1ea82042ed5677d913f78e48ea17c6ae646e", "params_type": "AdamParams", "train_nll_sum": 11059.596428409095, "train_tokens": 6245.0, "train_token_mean_nll": 1.7709521902976935, "grad_norm": 12.445777893066406, "t": 1793808324.7514884} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 76, "batch_sha256": "7396544ede609941d10f15b1cd0c1ea82042ed5677d913f78e48ea17c6ae646e", "params_type": "DimuonParams", "train_nll_sum": 11074.019559015998, "train_tokens": 6245.0, "train_token_mean_nll": 1.7732617388336267, "grad_norm": 14.842350006103516, "t": 1793808325.6393921} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 76, "batch_sha256": "4607619119d4f632dae68711d1dc71c77702952862369bbd78cc502ccb86952b", "params_type": "AdamParams", "train_nll_sum": 9838.884774170147, "train_tokens": 5546.0, "train_token_mean_nll": 1.7740506264280826, "grad_norm": 11.703930854797363, "t": 1793808325.640145} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 76, "batch_sha256": "4607619119d4f632dae68711d1dc71c77702952862369bbd78cc502ccb86952b", "params_type": "DimuonParams", "train_nll_sum": 9849.99331231798, "train_tokens": 5546.0, "train_token_mean_nll": 1.7760536084237253, "grad_norm": 13.919916152954102, "t": 1793808325.6407642} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 76, "batch_sha256": "d0c6fe96542f673a53705a4cc7e217076386418518d73df1f244412d75400172", "params_type": "AdamParams", "train_nll_sum": 13571.733029705832, "train_tokens": 6870.0, "train_token_mean_nll": 1.9755069912235563, "grad_norm": 11.715271949768066, "t": 1793808325.641626} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 76, "batch_sha256": "d0c6fe96542f673a53705a4cc7e217076386418518d73df1f244412d75400172", "params_type": "DimuonParams", "train_nll_sum": 13562.562070855689, "train_tokens": 6870.0, "train_token_mean_nll": 1.9741720627155297, "grad_norm": 14.227892875671387, "t": 1793808325.6424081} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 77, "batch_sha256": "8ddf313dfbe5747f96dfdf062ae88da84e0819226fca3f720cc0a4c4fa108aba", "params_type": "AdamParams", "train_nll_sum": 10263.507297819602, "train_tokens": 4859.0, "train_token_mean_nll": 2.1122674002509987, "grad_norm": 13.350395202636719, "t": 1793808332.44773} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 77, "batch_sha256": "8ddf313dfbe5747f96dfdf062ae88da84e0819226fca3f720cc0a4c4fa108aba", "params_type": "DimuonParams", "train_nll_sum": 10254.515030733095, "train_tokens": 4859.0, "train_token_mean_nll": 2.1104167587431766, "grad_norm": 15.695840835571289, "t": 1793808332.448432} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 77, "batch_sha256": "f2991e5a78368522628e691160810b631299b8410f64779ceae5b5815cbcbe5a", "params_type": "AdamParams", "train_nll_sum": 14724.55029810485, "train_tokens": 6800.0, "train_token_mean_nll": 2.1653750438389485, "grad_norm": 12.483027458190918, "t": 1793808332.5185719} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 77, "batch_sha256": "f2991e5a78368522628e691160810b631299b8410f64779ceae5b5815cbcbe5a", "params_type": "DimuonParams", "train_nll_sum": 14708.268585899837, "train_tokens": 6800.0, "train_token_mean_nll": 2.162980674397035, "grad_norm": 15.22408390045166, "t": 1793808332.5193985} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 77, "batch_sha256": "45393a98e3c8cd54c599fa2e676ff4bd16866ef95ad197bbdf4a6267a197cafd", "params_type": "AdamParams", "train_nll_sum": 11875.119710809757, "train_tokens": 5545.0, "train_token_mean_nll": 2.141590570028811, "grad_norm": 12.054120063781738, "t": 1793808332.5201604} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 77, "batch_sha256": "45393a98e3c8cd54c599fa2e676ff4bd16866ef95ad197bbdf4a6267a197cafd", "params_type": "DimuonParams", "train_nll_sum": 11869.434413960405, "train_tokens": 5545.0, "train_token_mean_nll": 2.140565268523067, "grad_norm": 14.740877151489258, "t": 1793808332.5385375} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 78, "batch_sha256": "da9e20abd2abe29a1fa8e83594b6617ae95171781a478da3da480ea0447f929d", "params_type": "AdamParams", "train_nll_sum": 12790.883161800444, "train_tokens": 6786.0, "train_token_mean_nll": 1.8848928915120018, "grad_norm": 11.211113929748535, "t": 1793808340.4531236} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 78, "batch_sha256": "da9e20abd2abe29a1fa8e83594b6617ae95171781a478da3da480ea0447f929d", "params_type": "DimuonParams", "train_nll_sum": 12794.397797999216, "train_tokens": 6786.0, "train_token_mean_nll": 1.8854108160918386, "grad_norm": 13.375370979309082, "t": 1793808340.5801227} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 78, "batch_sha256": "310c767f0ee543d4c825c4793e0b27e89818bf0bfe0d68adba86b9beebed9517", "params_type": "AdamParams", "train_nll_sum": 13410.815578445588, "train_tokens": 6655.0, "train_token_mean_nll": 2.015148847249525, "grad_norm": 11.155810356140137, "t": 1793808340.9486144} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 78, "batch_sha256": "310c767f0ee543d4c825c4793e0b27e89818bf0bfe0d68adba86b9beebed9517", "params_type": "DimuonParams", "train_nll_sum": 13396.254616660288, "train_tokens": 6655.0, "train_token_mean_nll": 2.012960874028593, "grad_norm": 13.166726112365723, "t": 1793808340.949461} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 78, "batch_sha256": "70edcf9da1500d5af7812ad7d6dfbb04a1739e209a70e6c12ee4f8c187f72f28", "params_type": "AdamParams", "train_nll_sum": 11736.77139630801, "train_tokens": 6620.0, "train_token_mean_nll": 1.7729261927957718, "grad_norm": 11.963502883911133, "t": 1793808340.950316} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 78, "batch_sha256": "70edcf9da1500d5af7812ad7d6dfbb04a1739e209a70e6c12ee4f8c187f72f28", "params_type": "DimuonParams", "train_nll_sum": 11723.948240944843, "train_tokens": 6620.0, "train_token_mean_nll": 1.7709891602635714, "grad_norm": 14.555924415588379, "t": 1793808340.9511204} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 79, "batch_sha256": "834142a0e097109fe53a00e94c1ee4446c7a700fe4e81fc38bad7865c0a44b36", "params_type": "AdamParams", "train_nll_sum": 13142.230257535657, "train_tokens": 6504.0, "train_token_mean_nll": 2.020638108477192, "grad_norm": 13.139837265014648, "t": 1793808347.9533858} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 79, "batch_sha256": "834142a0e097109fe53a00e94c1ee4446c7a700fe4e81fc38bad7865c0a44b36", "params_type": "DimuonParams", "train_nll_sum": 13140.521914165824, "train_tokens": 6504.0, "train_token_mean_nll": 2.020375448057476, "grad_norm": 15.406059265136719, "t": 1793808347.954165} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 79, "batch_sha256": "a7398358fae1394c6b5ecf33395a38d23eb065096a0713de8094f034ccf3d1f8", "params_type": "AdamParams", "train_nll_sum": 13462.328436868265, "train_tokens": 6616.0, "train_token_mean_nll": 2.0348138507962914, "grad_norm": 12.061371803283691, "t": 1793808347.9549708} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 79, "batch_sha256": "a7398358fae1394c6b5ecf33395a38d23eb065096a0713de8094f034ccf3d1f8", "params_type": "DimuonParams", "train_nll_sum": 13461.394437978406, "train_tokens": 6616.0, "train_token_mean_nll": 2.0346726780499407, "grad_norm": 14.134526252746582, "t": 1793808347.955709} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 79, "batch_sha256": "b3b98a72ceed0a956ef8225c0a6e28047b1fd0ebb6390015c5aa828ca480d509", "params_type": "AdamParams", "train_nll_sum": 11564.100625229345, "train_tokens": 5483.0, "train_token_mean_nll": 2.1090827330347155, "grad_norm": 14.216008186340332, "t": 1793808347.9564192} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 79, "batch_sha256": "b3b98a72ceed0a956ef8225c0a6e28047b1fd0ebb6390015c5aa828ca480d509", "params_type": "DimuonParams", "train_nll_sum": 11561.028856271463, "train_tokens": 5483.0, "train_token_mean_nll": 2.108522497952118, "grad_norm": 17.551786422729492, "t": 1793808348.440108} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 80, "batch_sha256": "031a15d3f6ba066158ebd6d6d3a78f565b92545c72330c797964ebb0d9042068", "params_type": "AdamParams", "train_nll_sum": 15948.3034387077, "train_tokens": 7894.0, "train_token_mean_nll": 2.0203069975560806, "grad_norm": 11.203434944152832, "t": 1793808355.7641993} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 80, "batch_sha256": "031a15d3f6ba066158ebd6d6d3a78f565b92545c72330c797964ebb0d9042068", "params_type": "DimuonParams", "train_nll_sum": 15937.851201062636, "train_tokens": 7894.0, "train_token_mean_nll": 2.0189829238741623, "grad_norm": 13.349772453308105, "t": 1793808355.7673352} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 80, "batch_sha256": "52ca14dfe9ee5ea69d0ec2f5bec34d9578f4e7c7e151b214cab0e9bdbd1d06b6", "params_type": "AdamParams", "train_nll_sum": 10523.630819495107, "train_tokens": 5108.0, "train_token_mean_nll": 2.060225297473592, "grad_norm": 14.222708702087402, "t": 1793808355.7684197} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 80, "batch_sha256": "52ca14dfe9ee5ea69d0ec2f5bec34d9578f4e7c7e151b214cab0e9bdbd1d06b6", "params_type": "DimuonParams", "train_nll_sum": 10513.598825376346, "train_tokens": 5108.0, "train_token_mean_nll": 2.05826132055136, "grad_norm": 17.085012435913086, "t": 1793808355.7691045} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 80, "batch_sha256": "1ab2241740041c9c851abb2dcfc31278ac635a388f3e433827f230123834fa5d", "params_type": "AdamParams", "train_nll_sum": 13376.396156685189, "train_tokens": 6162.0, "train_token_mean_nll": 2.170788081253682, "grad_norm": 13.250619888305664, "t": 1793808355.76988} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 80, "batch_sha256": "1ab2241740041c9c851abb2dcfc31278ac635a388f3e433827f230123834fa5d", "params_type": "DimuonParams", "train_nll_sum": 13369.682301529498, "train_tokens": 6162.0, "train_token_mean_nll": 2.1696985234549655, "grad_norm": 15.788368225097656, "t": 1793808355.77067} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 81, "batch_sha256": "8cadf76329cc80f4828d49e5424389a6c6bdaed2dc58c75c93478317248c3cd3", "params_type": "AdamParams", "train_nll_sum": 10339.11365276003, "train_tokens": 5358.0, "train_token_mean_nll": 1.929659136386717, "grad_norm": 15.863320350646973, "t": 1793808362.6045709} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 81, "batch_sha256": "8cadf76329cc80f4828d49e5424389a6c6bdaed2dc58c75c93478317248c3cd3", "params_type": "DimuonParams", "train_nll_sum": 10360.576005923009, "train_tokens": 5358.0, "train_token_mean_nll": 1.9336648014040703, "grad_norm": 19.633031845092773, "t": 1793808362.6068885} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 81, "batch_sha256": "5471aa7b8f1735d98788c6e78ea82d0a0fc4a09281041534414a5ef03a3e6a57", "params_type": "AdamParams", "train_nll_sum": 9782.133753136357, "train_tokens": 5289.0, "train_token_mean_nll": 1.849524249033155, "grad_norm": 11.886087417602539, "t": 1793808362.6075616} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 81, "batch_sha256": "5471aa7b8f1735d98788c6e78ea82d0a0fc4a09281041534414a5ef03a3e6a57", "params_type": "DimuonParams", "train_nll_sum": 9780.373811860522, "train_tokens": 5289.0, "train_token_mean_nll": 1.8491914940178713, "grad_norm": 14.288344383239746, "t": 1793808362.6081998} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 81, "batch_sha256": "597597ef427e9e289d6b75dc2837ef86813457c68e77f4eb29fd890f07a60e3a", "params_type": "AdamParams", "train_nll_sum": 12015.890389254428, "train_tokens": 5647.0, "train_token_mean_nll": 2.1278360880563887, "grad_norm": 16.873327255249023, "t": 1793808362.6088452} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 81, "batch_sha256": "597597ef427e9e289d6b75dc2837ef86813457c68e77f4eb29fd890f07a60e3a", "params_type": "DimuonParams", "train_nll_sum": 12017.914025962527, "train_tokens": 5647.0, "train_token_mean_nll": 2.1281944441229905, "grad_norm": 18.589263916015625, "t": 1793808362.6094818} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 82, "batch_sha256": "78af3496648e639b5d8c420222527047062017ed14bc61871ae8c1912361aabd", "params_type": "AdamParams", "train_nll_sum": 11178.827701393546, "train_tokens": 5359.0, "train_token_mean_nll": 2.0859913605884577, "grad_norm": 11.679503440856934, "t": 1793808369.822639} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 82, "batch_sha256": "78af3496648e639b5d8c420222527047062017ed14bc61871ae8c1912361aabd", "params_type": "DimuonParams", "train_nll_sum": 11197.631951623553, "train_tokens": 5359.0, "train_token_mean_nll": 2.0895002708758263, "grad_norm": 14.010184288024902, "t": 1793808370.413048} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 82, "batch_sha256": "0c45b4d6a3d5b026ac6d649b5ec9deaa2bb4fa541590981a755448018fb8990a", "params_type": "AdamParams", "train_nll_sum": 13968.194861261163, "train_tokens": 6713.0, "train_token_mean_nll": 2.0807678923374295, "grad_norm": 12.380824089050293, "t": 1793808370.4138238} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 82, "batch_sha256": "0c45b4d6a3d5b026ac6d649b5ec9deaa2bb4fa541590981a755448018fb8990a", "params_type": "DimuonParams", "train_nll_sum": 13970.013282740236, "train_tokens": 6713.0, "train_token_mean_nll": 2.0810387729391087, "grad_norm": 14.538789749145508, "t": 1793808370.4166281} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 82, "batch_sha256": "1859b464479511530f2c8284721c1471f540431c4c9b844cbf9b41892d3fdd05", "params_type": "AdamParams", "train_nll_sum": 14687.166307171288, "train_tokens": 7080.0, "train_token_mean_nll": 2.0744585179620465, "grad_norm": 12.219290733337402, "t": 1793808370.4175158} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 82, "batch_sha256": "1859b464479511530f2c8284721c1471f540431c4c9b844cbf9b41892d3fdd05", "params_type": "DimuonParams", "train_nll_sum": 14708.564905024436, "train_tokens": 7080.0, "train_token_mean_nll": 2.077480918788762, "grad_norm": 14.91925048828125, "t": 1793808370.4196703} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 83, "batch_sha256": "f59b804c13d2b71aa1fced4a9fff0a37748118927fb1d9b3e094d4a7c8fd8792", "params_type": "AdamParams", "train_nll_sum": 14218.145489843999, "train_tokens": 7632.0, "train_token_mean_nll": 1.8629645557971697, "grad_norm": 14.612399101257324, "t": 1793808377.6164918} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 83, "batch_sha256": "f59b804c13d2b71aa1fced4a9fff0a37748118927fb1d9b3e094d4a7c8fd8792", "params_type": "DimuonParams", "train_nll_sum": 14236.891830728111, "train_tokens": 7632.0, "train_token_mean_nll": 1.8654208373595533, "grad_norm": 19.935659408569336, "t": 1793808377.6188176} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 83, "batch_sha256": "ca3aada1721de6d1a8dccef68fc56d5b49af2235002329e4f4bbea6db74a44ad", "params_type": "AdamParams", "train_nll_sum": 10832.244492022623, "train_tokens": 5331.0, "train_token_mean_nll": 2.031934813735251, "grad_norm": 11.8697509765625, "t": 1793808377.8903458} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 83, "batch_sha256": "ca3aada1721de6d1a8dccef68fc56d5b49af2235002329e4f4bbea6db74a44ad", "params_type": "DimuonParams", "train_nll_sum": 10824.758084203293, "train_tokens": 5331.0, "train_token_mean_nll": 2.03053049788094, "grad_norm": 14.588129043579102, "t": 1793808377.8911772} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 83, "batch_sha256": "db6b336ddeff56dac99f9c139490e039d5d89ff4eb68d6bd12654e404847e86a", "params_type": "AdamParams", "train_nll_sum": 9760.04737318845, "train_tokens": 4605.0, "train_token_mean_nll": 2.1194456836457003, "grad_norm": 16.665416717529297, "t": 1793808377.891884} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 83, "batch_sha256": "db6b336ddeff56dac99f9c139490e039d5d89ff4eb68d6bd12654e404847e86a", "params_type": "DimuonParams", "train_nll_sum": 9742.515634474814, "train_tokens": 4605.0, "train_token_mean_nll": 2.1156385742616317, "grad_norm": 18.975500106811523, "t": 1793808377.8925633} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 84, "batch_sha256": "45c26c7290e67a38d919151c1eb779d9e29e11b008ee18cae033577b5ab0a739", "params_type": "AdamParams", "train_nll_sum": 12666.155088185347, "train_tokens": 6150.0, "train_token_mean_nll": 2.059537412713065, "grad_norm": 11.3579740524292, "t": 1793808386.5252948} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 84, "batch_sha256": "45c26c7290e67a38d919151c1eb779d9e29e11b008ee18cae033577b5ab0a739", "params_type": "DimuonParams", "train_nll_sum": 12651.931895877304, "train_tokens": 6150.0, "train_token_mean_nll": 2.057224698516635, "grad_norm": 13.311543464660645, "t": 1793808386.526164} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 84, "batch_sha256": "a242c52aec9e51ffab293fed7314b75e7674c9c10912b684d0b5e740be7b2045", "params_type": "AdamParams", "train_nll_sum": 12920.013455243623, "train_tokens": 7223.0, "train_token_mean_nll": 1.7887323072467982, "grad_norm": 11.699918746948242, "t": 1793808386.5270133} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 84, "batch_sha256": "a242c52aec9e51ffab293fed7314b75e7674c9c10912b684d0b5e740be7b2045", "params_type": "DimuonParams", "train_nll_sum": 12907.288668162662, "train_tokens": 7223.0, "train_token_mean_nll": 1.7869706033729285, "grad_norm": 13.521749496459961, "t": 1793808386.5278654} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 84, "batch_sha256": "b4494969997db67ca0a52af20d94ae0139e897a5ae2c91460bda9d7f750b16a2", "params_type": "AdamParams", "train_nll_sum": 9724.10886534912, "train_tokens": 4689.0, "train_token_mean_nll": 2.0738129378010495, "grad_norm": 13.131866455078125, "t": 1793808386.5286555} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 84, "batch_sha256": "b4494969997db67ca0a52af20d94ae0139e897a5ae2c91460bda9d7f750b16a2", "params_type": "DimuonParams", "train_nll_sum": 9719.14824571788, "train_tokens": 4689.0, "train_token_mean_nll": 2.0727550108163535, "grad_norm": 16.367422103881836, "t": 1793808386.5293593} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 85, "batch_sha256": "ba3a57ddeff9c44ee72c3876e20ea766dfb74638998f18555be0a5f5e586b473", "params_type": "AdamParams", "train_nll_sum": 12432.486467667622, "train_tokens": 6340.0, "train_token_mean_nll": 1.9609600106731266, "grad_norm": 12.490928649902344, "t": 1793808392.430432} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 85, "batch_sha256": "ba3a57ddeff9c44ee72c3876e20ea766dfb74638998f18555be0a5f5e586b473", "params_type": "DimuonParams", "train_nll_sum": 12443.304936596123, "train_tokens": 6340.0, "train_token_mean_nll": 1.9626663937848774, "grad_norm": 15.559322357177734, "t": 1793808393.3994079} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 85, "batch_sha256": "93ce321d8fe4574841eafdb65f91e6f2669bf0dd0324ac9b8087ee26765de9cf", "params_type": "AdamParams", "train_nll_sum": 11940.08540207228, "train_tokens": 5793.0, "train_token_mean_nll": 2.0611229763632455, "grad_norm": 14.235013008117676, "t": 1793808393.4001746} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 85, "batch_sha256": "93ce321d8fe4574841eafdb65f91e6f2669bf0dd0324ac9b8087ee26765de9cf", "params_type": "DimuonParams", "train_nll_sum": 11940.294048002588, "train_tokens": 5793.0, "train_token_mean_nll": 2.0611589932681835, "grad_norm": 17.545839309692383, "t": 1793808393.4008427} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 85, "batch_sha256": "d362d3fdf33d84be2db29a62e6573ea7b609a6a5fdf893e6e454e866a5076073", "params_type": "AdamParams", "train_nll_sum": 12057.243460805605, "train_tokens": 6278.0, "train_token_mean_nll": 1.9205548679206124, "grad_norm": 14.558945655822754, "t": 1793808393.4015055} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 85, "batch_sha256": "d362d3fdf33d84be2db29a62e6573ea7b609a6a5fdf893e6e454e866a5076073", "params_type": "DimuonParams", "train_nll_sum": 12059.875563787566, "train_tokens": 6278.0, "train_token_mean_nll": 1.9209741261209885, "grad_norm": 18.300888061523438, "t": 1793808393.4025917} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 86, "batch_sha256": "44c953142ba0a45c0962597342d79d69a2158cac69472217e000c7467f3fde06", "params_type": "AdamParams", "train_nll_sum": 13244.855796665239, "train_tokens": 6502.0, "train_token_mean_nll": 2.0370433399977297, "grad_norm": 11.439416885375977, "t": 1793808400.488854} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 86, "batch_sha256": "44c953142ba0a45c0962597342d79d69a2158cac69472217e000c7467f3fde06", "params_type": "DimuonParams", "train_nll_sum": 13227.916557865039, "train_tokens": 6502.0, "train_token_mean_nll": 2.034438104870046, "grad_norm": 13.333196640014648, "t": 1793808400.519684} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 86, "batch_sha256": "625dae2156dec386dce338c0e0cc1c91f79a4b376f205d7e757ade86c22dd822", "params_type": "AdamParams", "train_nll_sum": 10683.093705353722, "train_tokens": 5820.0, "train_token_mean_nll": 1.8355831108855192, "grad_norm": 13.202695846557617, "t": 1793808400.5206037} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 86, "batch_sha256": "625dae2156dec386dce338c0e0cc1c91f79a4b376f205d7e757ade86c22dd822", "params_type": "DimuonParams", "train_nll_sum": 10683.68592843358, "train_tokens": 5820.0, "train_token_mean_nll": 1.8356848674284503, "grad_norm": 15.521724700927734, "t": 1793808400.9576442} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 86, "batch_sha256": "d9d47e899a207a224c8e2b39ca4be9bd760615d99e41b29cf5c069a500cd9b91", "params_type": "AdamParams", "train_nll_sum": 11049.025985505941, "train_tokens": 5781.0, "train_token_mean_nll": 1.9112655224884867, "grad_norm": 13.095293998718262, "t": 1793808400.9585614} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 86, "batch_sha256": "d9d47e899a207a224c8e2b39ca4be9bd760615d99e41b29cf5c069a500cd9b91", "params_type": "DimuonParams", "train_nll_sum": 11034.845858007846, "train_tokens": 5781.0, "train_token_mean_nll": 1.9088126376073078, "grad_norm": 15.350415229797363, "t": 1793808400.9593942} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 87, "batch_sha256": "585a24332d63793dc03e6fb9cbefcd3427bb588fd94ec163d2c48bc46a641954", "params_type": "AdamParams", "train_nll_sum": 12951.411846720159, "train_tokens": 6398.0, "train_token_mean_nll": 2.024290691891241, "grad_norm": 11.38148021697998, "t": 1793808406.931329} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 87, "batch_sha256": "585a24332d63793dc03e6fb9cbefcd3427bb588fd94ec163d2c48bc46a641954", "params_type": "DimuonParams", "train_nll_sum": 12962.053873805831, "train_tokens": 6398.0, "train_token_mean_nll": 2.025954028416041, "grad_norm": 13.4202880859375, "t": 1793808408.042722} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 87, "batch_sha256": "11b1fd45279eacc7545f854ee7cddacc08f1c03cd16482d195e0d7660c831e4b", "params_type": "AdamParams", "train_nll_sum": 12854.21210296532, "train_tokens": 6206.0, "train_token_mean_nll": 2.0712555757275735, "grad_norm": 12.15174674987793, "t": 1793808408.0434995} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 87, "batch_sha256": "11b1fd45279eacc7545f854ee7cddacc08f1c03cd16482d195e0d7660c831e4b", "params_type": "DimuonParams", "train_nll_sum": 12854.05854190023, "train_tokens": 6206.0, "train_token_mean_nll": 2.071230831759624, "grad_norm": 15.032690048217773, "t": 1793808408.0442173} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 87, "batch_sha256": "6e03885797c80c45cb97af9fe7bf5bc69403ba9f27f1d693a3460055a7990a4b", "params_type": "AdamParams", "train_nll_sum": 12711.478279865129, "train_tokens": 6187.0, "train_token_mean_nll": 2.0545463520066476, "grad_norm": 11.863450050354004, "t": 1793808408.0448878} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 87, "batch_sha256": "6e03885797c80c45cb97af9fe7bf5bc69403ba9f27f1d693a3460055a7990a4b", "params_type": "DimuonParams", "train_nll_sum": 12716.237543990765, "train_tokens": 6187.0, "train_token_mean_nll": 2.055315588167248, "grad_norm": 14.502931594848633, "t": 1793808408.0455532} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 88, "batch_sha256": "edcf8dc5478f15f631d62bbf0cb019a2703f304d276f04a86a460ed3092363b6", "params_type": "AdamParams", "train_nll_sum": 13178.66881688036, "train_tokens": 6765.0, "train_token_mean_nll": 1.9480663439586636, "grad_norm": 11.032679557800293, "t": 1793808414.3777099} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 88, "batch_sha256": "edcf8dc5478f15f631d62bbf0cb019a2703f304d276f04a86a460ed3092363b6", "params_type": "DimuonParams", "train_nll_sum": 13180.076198341883, "train_tokens": 6765.0, "train_token_mean_nll": 1.9482743826078173, "grad_norm": 13.11916732788086, "t": 1793808415.5964813} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 88, "batch_sha256": "70c14f5ae1d176b4c1830f898d93817dffcdb59221d685e63b450d273ff08a6f", "params_type": "AdamParams", "train_nll_sum": 12868.330596516835, "train_tokens": 6293.0, "train_token_mean_nll": 2.044864229543435, "grad_norm": 13.309551239013672, "t": 1793808415.627328} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 88, "batch_sha256": "70c14f5ae1d176b4c1830f898d93817dffcdb59221d685e63b450d273ff08a6f", "params_type": "DimuonParams", "train_nll_sum": 12872.026023742004, "train_tokens": 6293.0, "train_token_mean_nll": 2.045451457769268, "grad_norm": 16.13889503479004, "t": 1793808415.635078} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 88, "batch_sha256": "5b5556509a5eb61bc33cf059dc51c7f14f00a8de778437c7660e12ab35895404", "params_type": "AdamParams", "train_nll_sum": 13973.399836681549, "train_tokens": 7455.0, "train_token_mean_nll": 1.8743661752758616, "grad_norm": 10.672883033752441, "t": 1793808415.636723} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 88, "batch_sha256": "5b5556509a5eb61bc33cf059dc51c7f14f00a8de778437c7660e12ab35895404", "params_type": "DimuonParams", "train_nll_sum": 13964.404463358194, "train_tokens": 7455.0, "train_token_mean_nll": 1.873159552429, "grad_norm": 12.749420166015625, "t": 1793808415.6378448} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 89, "batch_sha256": "894acb0dbcb70a7d4df665e7efa3e8eef238cdc4650a6cd7b68cdfbf16118a01", "params_type": "AdamParams", "train_nll_sum": 11201.899572597524, "train_tokens": 5346.0, "train_token_mean_nll": 2.095379643209413, "grad_norm": 14.877462387084961, "t": 1793808421.220175} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 89, "batch_sha256": "894acb0dbcb70a7d4df665e7efa3e8eef238cdc4650a6cd7b68cdfbf16118a01", "params_type": "DimuonParams", "train_nll_sum": 11217.524864571378, "train_tokens": 5346.0, "train_token_mean_nll": 2.0983024438031013, "grad_norm": 17.807952880859375, "t": 1793808422.2558544} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 89, "batch_sha256": "1043f2607cfca2d05c771c869e92c203e0c4b5ee95b3689b2b85927b2b559ec0", "params_type": "AdamParams", "train_nll_sum": 12505.182825697995, "train_tokens": 5762.0, "train_token_mean_nll": 2.1702851137969446, "grad_norm": 13.179018020629883, "t": 1793808422.328074} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 89, "batch_sha256": "1043f2607cfca2d05c771c869e92c203e0c4b5ee95b3689b2b85927b2b559ec0", "params_type": "DimuonParams", "train_nll_sum": 12501.752902369297, "train_tokens": 5762.0, "train_token_mean_nll": 2.169689847686445, "grad_norm": 15.852400779724121, "t": 1793808422.3288677} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 89, "batch_sha256": "37ae2eafaa05b2e124c9076f2e9541ed5437ea04c59e1a53ff07401239e5ff64", "params_type": "AdamParams", "train_nll_sum": 12562.309988992145, "train_tokens": 6263.0, "train_token_mean_nll": 2.0057975393568808, "grad_norm": 15.781149864196777, "t": 1793808422.335949} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 89, "batch_sha256": "37ae2eafaa05b2e124c9076f2e9541ed5437ea04c59e1a53ff07401239e5ff64", "params_type": "DimuonParams", "train_nll_sum": 12570.27220815008, "train_tokens": 6263.0, "train_token_mean_nll": 2.0070688500958136, "grad_norm": 19.64773178100586, "t": 1793808422.3366623} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 90, "batch_sha256": "c7255f31ac403d5e223864c6c87d0769ce70b28ec4d28b9387285c9721b60067", "params_type": "AdamParams", "train_nll_sum": 11210.372681560857, "train_tokens": 5236.0, "train_token_mean_nll": 2.1410184647748007, "grad_norm": 12.857081413269043, "t": 1793808428.6165564} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 90, "batch_sha256": "c7255f31ac403d5e223864c6c87d0769ce70b28ec4d28b9387285c9721b60067", "params_type": "DimuonParams", "train_nll_sum": 11216.60841531024, "train_tokens": 5236.0, "train_token_mean_nll": 2.1422093994099005, "grad_norm": 15.143559455871582, "t": 1793808429.8464549} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 90, "batch_sha256": "fe2d278c75dd378d8fd82bd3a42a8dcc6054e951403e6dda5e0fc2ea74150349", "params_type": "AdamParams", "train_nll_sum": 14452.42417898056, "train_tokens": 6695.0, "train_token_mean_nll": 2.1586891977566185, "grad_norm": 12.165826797485352, "t": 1793808429.8490381} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 90, "batch_sha256": "fe2d278c75dd378d8fd82bd3a42a8dcc6054e951403e6dda5e0fc2ea74150349", "params_type": "DimuonParams", "train_nll_sum": 14450.963159249568, "train_tokens": 6695.0, "train_token_mean_nll": 2.15847097225535, "grad_norm": 15.024467468261719, "t": 1793808429.8499837} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 90, "batch_sha256": "8307b4b51f30c34ad6e32a09f5df1ded1d380a6bee16059996fa45095493021e", "params_type": "AdamParams", "train_nll_sum": 13470.94948052044, "train_tokens": 6685.0, "train_token_mean_nll": 2.015100894617867, "grad_norm": 12.783626556396484, "t": 1793808429.8508623} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 90, "batch_sha256": "8307b4b51f30c34ad6e32a09f5df1ded1d380a6bee16059996fa45095493021e", "params_type": "DimuonParams", "train_nll_sum": 13485.864133314404, "train_tokens": 6685.0, "train_token_mean_nll": 2.0173319571150943, "grad_norm": 14.964451789855957, "t": 1793808429.8518198} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 91, "batch_sha256": "4a627b6b95c505341771bbd8491c6e9beac55eb7f896643572e7590dce0b2126", "params_type": "AdamParams", "train_nll_sum": 13092.862989076115, "train_tokens": 7044.0, "train_token_mean_nll": 1.858725580504843, "grad_norm": 11.259328842163086, "t": 1793808435.8746111} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 91, "batch_sha256": "4a627b6b95c505341771bbd8491c6e9beac55eb7f896643572e7590dce0b2126", "params_type": "DimuonParams", "train_nll_sum": 13097.110264332527, "train_tokens": 7044.0, "train_token_mean_nll": 1.8593285440562928, "grad_norm": 13.365264892578125, "t": 1793808436.8826017} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 91, "batch_sha256": "def8b5041675a0a5a79f849ff0be47c3508c3fca8f899cf64f338411a349eb4a", "params_type": "AdamParams", "train_nll_sum": 12083.88977030728, "train_tokens": 5715.0, "train_token_mean_nll": 2.1144164077528047, "grad_norm": 12.620758056640625, "t": 1793808436.8924944} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 91, "batch_sha256": "def8b5041675a0a5a79f849ff0be47c3508c3fca8f899cf64f338411a349eb4a", "params_type": "DimuonParams", "train_nll_sum": 12079.693292416483, "train_tokens": 5715.0, "train_token_mean_nll": 2.113682115908396, "grad_norm": 14.960343360900879, "t": 1793808436.8941734} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 91, "batch_sha256": "7eee93e82cdc9c2f32f811842764b4a46b00beb4f4423a5260037aca086d0af2", "params_type": "AdamParams", "train_nll_sum": 9415.578192213738, "train_tokens": 4538.0, "train_token_mean_nll": 2.0748299233613348, "grad_norm": 15.657475471496582, "t": 1793808436.9047983} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 91, "batch_sha256": "7eee93e82cdc9c2f32f811842764b4a46b00beb4f4423a5260037aca086d0af2", "params_type": "DimuonParams", "train_nll_sum": 9418.42388106473, "train_tokens": 4538.0, "train_token_mean_nll": 2.0754570033196846, "grad_norm": 19.173540115356445, "t": 1793808436.9057033} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 92, "batch_sha256": "fa1afc69b11e95f5e1a7b884b52eef8c51a919327c050b36874acb8f0ac9a8e3", "params_type": "AdamParams", "train_nll_sum": 12017.262972055822, "train_tokens": 5961.0, "train_token_mean_nll": 2.0159810387612516, "grad_norm": 11.237149238586426, "t": 1793808443.7458847} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 92, "batch_sha256": "fa1afc69b11e95f5e1a7b884b52eef8c51a919327c050b36874acb8f0ac9a8e3", "params_type": "DimuonParams", "train_nll_sum": 12031.5660138277, "train_tokens": 5961.0, "train_token_mean_nll": 2.018380475394682, "grad_norm": 13.54302978515625, "t": 1793808443.7515202} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 92, "batch_sha256": "317221ed6d5140e055eff37f8806b761709e7b039e992a770008ed8c1faa2e11", "params_type": "AdamParams", "train_nll_sum": 13360.519217882831, "train_tokens": 6439.0, "train_token_mean_nll": 2.074936980568851, "grad_norm": 13.079484939575195, "t": 1793808443.853058} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 92, "batch_sha256": "317221ed6d5140e055eff37f8806b761709e7b039e992a770008ed8c1faa2e11", "params_type": "DimuonParams", "train_nll_sum": 13362.908277663937, "train_tokens": 6439.0, "train_token_mean_nll": 2.075308010197847, "grad_norm": 15.753771781921387, "t": 1793808443.8545868} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 92, "batch_sha256": "a39132d5f5caafd6652de8719120968afdd460a3eb39ba4d2f9c16ac9f03a138", "params_type": "AdamParams", "train_nll_sum": 10302.310855241709, "train_tokens": 4550.0, "train_token_mean_nll": 2.264244144009167, "grad_norm": 15.879949569702148, "t": 1793808443.8553636} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 92, "batch_sha256": "a39132d5f5caafd6652de8719120968afdd460a3eb39ba4d2f9c16ac9f03a138", "params_type": "DimuonParams", "train_nll_sum": 10307.219670341445, "train_tokens": 4550.0, "train_token_mean_nll": 2.2653230044706474, "grad_norm": 19.259685516357422, "t": 1793808443.8585982} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 93, "batch_sha256": "ad679c87fce8184c7030d1c8436d6af026ab828cbbb5cc93812141e1cfb17e9c", "params_type": "AdamParams", "train_nll_sum": 9324.551347267074, "train_tokens": 4879.0, "train_token_mean_nll": 1.9111603499215155, "grad_norm": 12.397963523864746, "t": 1793808451.0204408} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 93, "batch_sha256": "ad679c87fce8184c7030d1c8436d6af026ab828cbbb5cc93812141e1cfb17e9c", "params_type": "DimuonParams", "train_nll_sum": 9336.457057414242, "train_tokens": 4879.0, "train_token_mean_nll": 1.91360054466371, "grad_norm": 14.653572082519531, "t": 1793808451.0221276} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 93, "batch_sha256": "634a1ca235f93cd5919c6573911f630a5e273177361ab46a8a3f73dd57194069", "params_type": "AdamParams", "train_nll_sum": 10383.50980590869, "train_tokens": 5439.0, "train_token_mean_nll": 1.9090843548278527, "grad_norm": 14.526565551757812, "t": 1793808451.0228896} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 93, "batch_sha256": "634a1ca235f93cd5919c6573911f630a5e273177361ab46a8a3f73dd57194069", "params_type": "DimuonParams", "train_nll_sum": 10381.351585466222, "train_tokens": 5439.0, "train_token_mean_nll": 1.9086875501868399, "grad_norm": 17.21184730529785, "t": 1793808451.0235875} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 93, "batch_sha256": "e4b6c88196f77cd291666fb8196b2cf3b95747069c3fe0c726c7004f0589f7bc", "params_type": "AdamParams", "train_nll_sum": 9423.281810292981, "train_tokens": 5303.0, "train_token_mean_nll": 1.776971866923059, "grad_norm": 13.764739990234375, "t": 1793808451.8293216} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 93, "batch_sha256": "e4b6c88196f77cd291666fb8196b2cf3b95747069c3fe0c726c7004f0589f7bc", "params_type": "DimuonParams", "train_nll_sum": 9433.662965493026, "train_tokens": 5303.0, "train_token_mean_nll": 1.7789294673756413, "grad_norm": 16.444509506225586, "t": 1793808451.8302271} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 94, "batch_sha256": "fe781b9987c5a69aac42ad06a47ea5a161c4ea6d43c9eba76a58a60fa19b965a", "params_type": "AdamParams", "train_nll_sum": 9240.459882854424, "train_tokens": 4760.0, "train_token_mean_nll": 1.9412730846332824, "grad_norm": 17.293210983276367, "t": 1793808457.5843856} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 94, "batch_sha256": "fe781b9987c5a69aac42ad06a47ea5a161c4ea6d43c9eba76a58a60fa19b965a", "params_type": "DimuonParams", "train_nll_sum": 9251.207184180937, "train_tokens": 4760.0, "train_token_mean_nll": 1.9435309210464153, "grad_norm": 27.03343391418457, "t": 1793808457.8776438} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 94, "batch_sha256": "6f503f5ef20c2eaeaa36b74f95c14ffad64cf262438245a149b2e3f7daabde82", "params_type": "AdamParams", "train_nll_sum": 9854.791101623723, "train_tokens": 5676.0, "train_token_mean_nll": 1.736221124317076, "grad_norm": 11.334662437438965, "t": 1793808457.8791955} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 94, "batch_sha256": "6f503f5ef20c2eaeaa36b74f95c14ffad64cf262438245a149b2e3f7daabde82", "params_type": "DimuonParams", "train_nll_sum": 9854.596645708689, "train_tokens": 5676.0, "train_token_mean_nll": 1.7361868649944836, "grad_norm": 13.73377513885498, "t": 1793808457.8805707} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 94, "batch_sha256": "2bd932f50c2c1ce8d5ee44a3a4fd650179cf04387e7748d6115bb0d10e890755", "params_type": "AdamParams", "train_nll_sum": 13155.127593548414, "train_tokens": 6994.0, "train_token_mean_nll": 1.8809161557833018, "grad_norm": 14.140024185180664, "t": 1793808457.8814666} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 94, "batch_sha256": "2bd932f50c2c1ce8d5ee44a3a4fd650179cf04387e7748d6115bb0d10e890755", "params_type": "DimuonParams", "train_nll_sum": 13142.40521281648, "train_tokens": 6994.0, "train_token_mean_nll": 1.8790971136426193, "grad_norm": 16.84038734436035, "t": 1793808458.7500603} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 95, "batch_sha256": "6b39689f46263c458b3ee4671540327b5f07e3b1ed0ac58a6b9e8a6fdab0f28e", "params_type": "AdamParams", "train_nll_sum": 10719.215677430713, "train_tokens": 5251.0, "train_token_mean_nll": 2.0413665354086294, "grad_norm": 14.194106101989746, "t": 1793808465.156251} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 95, "batch_sha256": "6b39689f46263c458b3ee4671540327b5f07e3b1ed0ac58a6b9e8a6fdab0f28e", "params_type": "DimuonParams", "train_nll_sum": 10715.697787676852, "train_tokens": 5251.0, "train_token_mean_nll": 2.0406965887786805, "grad_norm": 16.891401290893555, "t": 1793808465.179415} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 95, "batch_sha256": "37c83d3bb0070f11891d9fc8d0dbb47f65a5c93f90bad12e10fc9e8386c93eee", "params_type": "AdamParams", "train_nll_sum": 13731.806975101446, "train_tokens": 6231.0, "train_token_mean_nll": 2.2037886334619556, "grad_norm": 14.483519554138184, "t": 1793808465.312335} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 95, "batch_sha256": "37c83d3bb0070f11891d9fc8d0dbb47f65a5c93f90bad12e10fc9e8386c93eee", "params_type": "DimuonParams", "train_nll_sum": 13731.944590160503, "train_tokens": 6231.0, "train_token_mean_nll": 2.2038107190114755, "grad_norm": 16.12574005126953, "t": 1793808465.3161829} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 95, "batch_sha256": "92a604a9e5ea5b1fc225d143e3a5885072f746cbce6de6d45d40dc6c48a8a040", "params_type": "AdamParams", "train_nll_sum": 11178.148191390324, "train_tokens": 5441.0, "train_token_mean_nll": 2.0544290004393173, "grad_norm": 13.859067916870117, "t": 1793808465.317592} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 95, "batch_sha256": "92a604a9e5ea5b1fc225d143e3a5885072f746cbce6de6d45d40dc6c48a8a040", "params_type": "DimuonParams", "train_nll_sum": 11188.159853047171, "train_tokens": 5441.0, "train_token_mean_nll": 2.0562690411775724, "grad_norm": 16.9705867767334, "t": 1793808465.3230727} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 96, "batch_sha256": "9dadf9e3f68346862a9ed9d9f039ef74bbdbb79bc6b73818e8c1ad4ded42c9a7", "params_type": "AdamParams", "train_nll_sum": 13915.111526321214, "train_tokens": 6757.0, "train_token_mean_nll": 2.059362368850261, "grad_norm": 11.785521507263184, "t": 1793808471.3360057} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 96, "batch_sha256": "9dadf9e3f68346862a9ed9d9f039ef74bbdbb79bc6b73818e8c1ad4ded42c9a7", "params_type": "DimuonParams", "train_nll_sum": 13906.691991849559, "train_tokens": 6757.0, "train_token_mean_nll": 2.058116322606121, "grad_norm": 13.850006103515625, "t": 1793808472.446186} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 96, "batch_sha256": "dc73b229533a192368027de1f6f6eeaf1a36b79e605f020798d359a0f9173cab", "params_type": "AdamParams", "train_nll_sum": 13350.755681370912, "train_tokens": 6755.0, "train_token_mean_nll": 1.9764257115278923, "grad_norm": 13.446596145629883, "t": 1793808472.4483554} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 96, "batch_sha256": "dc73b229533a192368027de1f6f6eeaf1a36b79e605f020798d359a0f9173cab", "params_type": "DimuonParams", "train_nll_sum": 13365.200828838031, "train_tokens": 6755.0, "train_token_mean_nll": 1.9785641493468589, "grad_norm": 16.426908493041992, "t": 1793808472.450883} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 96, "batch_sha256": "8bc47d09542be0f506b287717e55d98533a00c7450cbceae033f09df62eac5c6", "params_type": "AdamParams", "train_nll_sum": 11874.458786496863, "train_tokens": 5610.0, "train_token_mean_nll": 2.11665932023117, "grad_norm": 12.43871784210205, "t": 1793808472.4517076} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 96, "batch_sha256": "8bc47d09542be0f506b287717e55d98533a00c7450cbceae033f09df62eac5c6", "params_type": "DimuonParams", "train_nll_sum": 11876.481317181482, "train_tokens": 5610.0, "train_token_mean_nll": 2.1170198426348454, "grad_norm": 15.017266273498535, "t": 1793808472.4545438} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 97, "batch_sha256": "4c7efe2fd446504fc38d57f98c6e33340b1c3497447a6453198ec9f9e1daaa36", "params_type": "AdamParams", "train_nll_sum": 13758.670460736432, "train_tokens": 6288.0, "train_token_mean_nll": 2.1880837246718245, "grad_norm": 15.592048645019531, "t": 1793808479.793631} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 97, "batch_sha256": "4c7efe2fd446504fc38d57f98c6e33340b1c3497447a6453198ec9f9e1daaa36", "params_type": "DimuonParams", "train_nll_sum": 13759.297394809164, "train_tokens": 6288.0, "train_token_mean_nll": 2.188183427927666, "grad_norm": 18.52349281311035, "t": 1793808479.8867202} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 97, "batch_sha256": "73f7e6a2160529759394e428b75ed5ab51621b52bb389895d2828a7264b646eb", "params_type": "AdamParams", "train_nll_sum": 11621.116104346136, "train_tokens": 6549.0, "train_token_mean_nll": 1.7744871131998987, "grad_norm": 11.770272254943848, "t": 1793808479.8875918} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 97, "batch_sha256": "73f7e6a2160529759394e428b75ed5ab51621b52bb389895d2828a7264b646eb", "params_type": "DimuonParams", "train_nll_sum": 11636.522885300796, "train_tokens": 6549.0, "train_token_mean_nll": 1.7768396526646504, "grad_norm": 14.482361793518066, "t": 1793808480.2185535} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 97, "batch_sha256": "163a01e6491ae116506694035443c762b404f661d12c0929592130fb004fa61d", "params_type": "AdamParams", "train_nll_sum": 13605.466066506038, "train_tokens": 6547.0, "train_token_mean_nll": 2.0781222035292557, "grad_norm": 16.417964935302734, "t": 1793808480.219372} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 97, "batch_sha256": "163a01e6491ae116506694035443c762b404f661d12c0929592130fb004fa61d", "params_type": "DimuonParams", "train_nll_sum": 13591.074439235625, "train_tokens": 6547.0, "train_token_mean_nll": 2.0759240017161487, "grad_norm": 16.76241111755371, "t": 1793808480.2200978} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 98, "batch_sha256": "81980b68fa31cb512325571f4d74da0f06cfcfe2304e59533da1ee7b64763923", "params_type": "AdamParams", "train_nll_sum": 14000.030611092105, "train_tokens": 6652.0, "train_token_mean_nll": 2.104634788197851, "grad_norm": 12.489612579345703, "t": 1793808486.506228} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 98, "batch_sha256": "81980b68fa31cb512325571f4d74da0f06cfcfe2304e59533da1ee7b64763923", "params_type": "DimuonParams", "train_nll_sum": 13998.96943621156, "train_tokens": 6652.0, "train_token_mean_nll": 2.1044752610059474, "grad_norm": 14.732860565185547, "t": 1793808487.5683272} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 98, "batch_sha256": "97541c0bed6d2b39ceeb33fd1499c7ecf80026d94bc67a13af90e77ad97c0bed", "params_type": "AdamParams", "train_nll_sum": 12444.80625243577, "train_tokens": 6410.0, "train_token_mean_nll": 1.9414674340773432, "grad_norm": 11.359041213989258, "t": 1793808487.7163851} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 98, "batch_sha256": "97541c0bed6d2b39ceeb33fd1499c7ecf80026d94bc67a13af90e77ad97c0bed", "params_type": "DimuonParams", "train_nll_sum": 12449.122075435986, "train_tokens": 6410.0, "train_token_mean_nll": 1.9421407293971897, "grad_norm": 13.577371597290039, "t": 1793808487.721193} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 98, "batch_sha256": "9cd991678f4a6e7e3d097fe7a6029f3017e58b2444ab66ae40cd09c020a72448", "params_type": "AdamParams", "train_nll_sum": 14967.628877658884, "train_tokens": 6436.0, "train_token_mean_nll": 2.3256104533341957, "grad_norm": 15.164359092712402, "t": 1793808487.7240493} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 98, "batch_sha256": "9cd991678f4a6e7e3d097fe7a6029f3017e58b2444ab66ae40cd09c020a72448", "params_type": "DimuonParams", "train_nll_sum": 14968.4172251899, "train_tokens": 6436.0, "train_token_mean_nll": 2.3257329436280143, "grad_norm": 17.556846618652344, "t": 1793808487.7258189} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 99, "batch_sha256": "41f2d7e9951654925375c067b36022c7d00bc54affb20deb2096e538b4c3405f", "params_type": "AdamParams", "train_nll_sum": 14955.843560214988, "train_tokens": 7581.0, "train_token_mean_nll": 1.972806168080067, "grad_norm": 11.769316673278809, "t": 1793808495.412623} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 99, "batch_sha256": "41f2d7e9951654925375c067b36022c7d00bc54affb20deb2096e538b4c3405f", "params_type": "DimuonParams", "train_nll_sum": 14944.674653686136, "train_tokens": 7581.0, "train_token_mean_nll": 1.9713328919253577, "grad_norm": 13.699947357177734, "t": 1793808495.7415628} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 99, "batch_sha256": "a315bbb959c26656549bfcf19c43736f24bd5dd6c69c98b1b7431de5575620c7", "params_type": "AdamParams", "train_nll_sum": 14072.086536727988, "train_tokens": 6627.0, "train_token_mean_nll": 2.123447493093102, "grad_norm": 11.272058486938477, "t": 1793808495.7424726} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 99, "batch_sha256": "a315bbb959c26656549bfcf19c43736f24bd5dd6c69c98b1b7431de5575620c7", "params_type": "DimuonParams", "train_nll_sum": 14089.398917382805, "train_tokens": 6627.0, "train_token_mean_nll": 2.1260598939765813, "grad_norm": 13.624918937683105, "t": 1793808495.7463703} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 99, "batch_sha256": "6e2d5435ca2e7ca820af7cd57a2c6c51d9aea28f6c00384c9f5bddcb725419c4", "params_type": "AdamParams", "train_nll_sum": 12260.164048196775, "train_tokens": 6113.0, "train_token_mean_nll": 2.0055887531812164, "grad_norm": 10.872276306152344, "t": 1793808495.7492497} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 99, "batch_sha256": "6e2d5435ca2e7ca820af7cd57a2c6c51d9aea28f6c00384c9f5bddcb725419c4", "params_type": "DimuonParams", "train_nll_sum": 12250.341864763255, "train_tokens": 6113.0, "train_token_mean_nll": 2.003981983439106, "grad_norm": 13.056107521057129, "t": 1793808495.751838} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 100, "batch_sha256": "48a6e7030d06dee7cfa73048eda791aca35f3999b64ee370cc078e51c2a5bdb2", "params_type": "AdamParams", "train_nll_sum": 13585.684346622727, "train_tokens": 6117.0, "train_token_mean_nll": 2.2209717748279756, "grad_norm": 12.274271965026855, "t": 1793808502.8548079} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 100, "batch_sha256": "48a6e7030d06dee7cfa73048eda791aca35f3999b64ee370cc078e51c2a5bdb2", "params_type": "DimuonParams", "train_nll_sum": 13602.507761351086, "train_tokens": 6117.0, "train_token_mean_nll": 2.223722046975819, "grad_norm": 14.567658424377441, "t": 1793808502.857241} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 100, "batch_sha256": "03d96d89099faac92ea492a2c9d6399389b9ea0a04e7d345d140690918367ed3", "params_type": "AdamParams", "train_nll_sum": 8825.175774038064, "train_tokens": 4547.0, "train_token_mean_nll": 1.9408787715060618, "grad_norm": 13.959826469421387, "t": 1793808502.8600075} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 100, "batch_sha256": "03d96d89099faac92ea492a2c9d6399389b9ea0a04e7d345d140690918367ed3", "params_type": "DimuonParams", "train_nll_sum": 8826.245789923072, "train_tokens": 4547.0, "train_token_mean_nll": 1.941114094990779, "grad_norm": 17.200443267822266, "t": 1793808502.945105} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 100, "batch_sha256": "93b47ab28a3053481df98795dbf0b456db0ff979c1b9ff2449928f6637c4d95a", "params_type": "AdamParams", "train_nll_sum": 14213.872177613568, "train_tokens": 6463.0, "train_token_mean_nll": 2.199268478665259, "grad_norm": 11.959219932556152, "t": 1793808502.9458954} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 100, "batch_sha256": "93b47ab28a3053481df98795dbf0b456db0ff979c1b9ff2449928f6637c4d95a", "params_type": "DimuonParams", "train_nll_sum": 14210.616220523796, "train_tokens": 6463.0, "train_token_mean_nll": 2.198764694495404, "grad_norm": 14.303712844848633, "t": 1793808503.7420416} {"stage": "train_done", "seconds": 742.3969576358795, "steps": 100, "arms": 6, "t": 1793808503.7421346} {"stage": "eval", "arm": "baseline_adamw_s0", "split": "test", "step": 100, "nll_sum": 197912.80585593503, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0330861653887684, "example_mean": 1.91155507915606, "per_example": [[130.69179450774288, 55], [1255.9076798445826, 555], [577.3764216692002, 233], [1054.7429404476488, 416], [503.53286076831364, 287], [124.83850252687978, 60], [705.3791541187675, 468], [134.47844231135286, 71], [81.65124391276277, 65], [614.0416510170937, 271], [47.20338787168407, 35], [21.542080794328967, 31], [179.49897929537065, 107], [390.63181380739627, 112], [10.798775014766761, 11], [241.33261069077548, 86], [130.91432428089638, 105], [449.02189675618456, 407], [191.1910632650347, 132], [725.2794072466118, 231], [289.32687018190734, 268], [391.1457817284522, 155], [88.93596275953496, 102], [131.96782716911184, 74], [239.7558978494544, 83], [362.1797856361077, 135], [947.4278112312536, 390], [870.8931368968833, 284], [26.01756174148909, 44], [339.4013649758399, 137], [1206.510354376025, 447], [0.9844081496040644, 25], [389.86499428919024, 155], [845.1398690754036, 457], [311.36947936947126, 187], [463.41785988077936, 230], [391.3725753227927, 148], [324.5584637601612, 436], [483.39655442774165, 146], [314.8695304140376, 191], [13.57357953778876, 37], [430.54257745345126, 333], [78.9114447679508, 53], [187.77322009835734, 94], [1074.2523523689633, 521], [319.59823187525353, 175], [135.3787169952966, 79], [54.42953094180643, 19], [2.681460506842086, 10], [329.64655665952205, 208], [309.05721590315466, 156], [225.3948554946462, 160], [1158.9090110772727, 420], [763.9777035831939, 285], [85.06297019911426, 31], [411.1949771377897, 167], [55.47958119285124, 44], [737.3542758394315, 245], [9.388700918244922, 45], [236.2361797865169, 102], [129.23753716892725, 114], [63.51221178381729, 20], [165.47666207934208, 86], [152.12079984353613, 63], [72.4032006633779, 72], [100.08265822309022, 66], [141.9407134361652, 101], [100.72350213619575, 48], [65.36016041585117, 25], [64.55050130367681, 26], [65.69348797334419, 64], [223.50094795295036, 72], [381.1634516077314, 342], [323.88263558978406, 123], [365.4553470101873, 314], [114.86588902289895, 68], [72.15965829875302, 58], [209.52027147436706, 106], [204.18135632573512, 81], [322.18924009714874, 181], [285.0385968504643, 312], [639.4787361557194, 302], [1271.2885983990436, 473], [76.28535627661222, 74], [312.955367732721, 169], [196.78524278536406, 86], [1483.4671306918572, 663], [94.96143721214048, 81], [581.2593033162152, 272], [574.8547918530671, 206], [869.4814878387438, 720], [734.5451864549132, 291], [1278.8730666550468, 562], [180.25083506286046, 117], [148.15931616331204, 106], [549.1252969294574, 216], [74.21372924941375, 45], [385.7955412196625, 220], [305.77120017702646, 134], [1183.314051157205, 454], [80.05449792361128, 57], [200.6885778554215, 101], [70.7351086054382, 22], [136.96836034733087, 74], [629.053217010493, 294], [411.7192596771106, 150], [544.0050823576255, 203], [369.5249114780813, 166], [723.2942357919501, 262], [118.31440964949934, 52], [485.14788841414656, 181], [31.654742112028543, 37], [1179.8113176781171, 642], [256.693987915095, 176], [207.28792091908554, 113], [539.0842943458156, 194], [118.35305392633381, 72], [4.540718985793887, 10], [174.87818299904757, 123], [398.6059790799741, 141], [327.83199247161747, 117], [1327.5116256421175, 576], [122.44881479741116, 93], [314.9512206554041, 137], [572.762071895444, 240], [39.81014106041414, 61], [123.99738335800885, 123], [191.82160953857056, 98], [269.9488541302296, 120], [5.8100229256058356, 32], [876.4619482503745, 334], [2.112397394598247, 26], [54.34023065577048, 35], [234.4041756132674, 72], [639.2392484713466, 263], [647.9714774269089, 247], [192.7398751986948, 66], [567.373796220535, 265], [1350.58446981613, 516], [1211.8768803865887, 502], [1395.7437907161548, 492], [299.81508495600633, 141], [1418.161732956777, 476], [153.13268124125716, 170], [373.8690005402882, 123], [380.9235819903647, 397], [138.90373777073728, 57], [802.2612978337779, 411], [604.5732552232976, 227], [61.19348379118219, 42], [59.60577662691435, 32], [188.10085714447405, 89], [632.3964161307754, 271], [77.54924314514801, 59], [200.98711827221086, 107], [190.50427539298835, 150], [382.7676383402013, 237], [196.84422747553708, 92], [321.3743693967964, 153], [636.4138246422708, 268], [566.0630278440931, 253], [905.5162575082179, 428], [523.483135897662, 270], [112.05404805415856, 79], [292.28687308996314, 144], [807.7811358261305, 312], [162.56772147264246, 102], [1021.0614586570398, 554], [78.09924233888523, 71], [796.0631832617662, 306], [2.126835765336409, 6], [197.69136100544665, 273], [511.15895257776265, 256], [439.984107109225, 234], [1354.0449397937537, 653], [448.35483627692383, 220], [482.3943401899887, 221], [83.85183019509077, 67], [231.26607305972584, 107], [74.87579784493028, 60], [1110.647862820458, 517], [92.32177639245992, 66], [408.4136201888864, 185], [32.44186847376909, 47], [217.456571314975, 138], [39.38425148096303, 37], [703.6226878355887, 372], [3.2652014161367333, 11], [162.08633311586004, 69], [1.6077298959367, 11], [307.57099717924666, 122], [543.3854032608924, 239], [400.0571756250188, 215], [370.9643074394007, 131], [363.65616367906705, 136], [808.8883326527512, 241], [297.2821016739649, 145], [349.1241417246147, 226], [1329.7848904253074, 548], [27.06111831174212, 38], [421.1818220444902, 170], [66.4491100796613, 27], [598.5162945417937, 264], [698.8665129535202, 258], [189.42414713905305, 82], [289.2340347429522, 147], [577.9113441091483, 259], [518.8659899993822, 152], [247.74935639467708, 151], [878.0677998095198, 320], [228.91641247452299, 110], [239.34531727811736, 141], [220.82972043457198, 132], [293.2313558038895, 101], [273.0326236467008, 135], [1290.6245796919734, 629], [214.5907770051162, 241], [779.2356739510219, 492], [805.4157081091389, 304], [1137.444606348637, 404], [6.952159430391475, 17], [297.3703236064671, 138], [383.6913819489955, 141], [261.4413590237896, 161], [200.8851936794963, 125], [1197.193791596685, 639], [616.4671250955425, 315], [192.27293550338607, 102], [53.84078109277743, 25], [828.3412462550036, 386], [309.42997755878514, 153], [442.70273594090617, 518], [547.3151447426401, 219], [193.0196731573892, 121], [891.8693457937625, 613], [430.94298955218255, 204], [613.2223246542419, 273], [141.63822368331103, 75], [860.8231927019488, 373], [912.142634801758, 288], [582.1191942125524, 243], [159.15868998558562, 71], [104.24257300298086, 51], [226.66684554063022, 104], [1334.5469674799988, 748], [518.1214905333227, 180], [268.7819884952024, 137], [694.1013959652355, 394], [948.1614264523264, 426], [256.29304440789974, 124], [0.8218334973222454, 16], [149.1769896575015, 49], [248.4507282044765, 216], [21.31673876315881, 68], [8.646279044205357, 12], [647.0328181317, 216], [793.9393073119954, 331], [254.9024323255269, 129], [614.5671878908372, 238], [622.2215839653518, 247], [220.92719876993488, 108], [194.91976955286827, 133], [214.13553925300766, 116], [13.063782830489345, 30], [973.0755102765847, 537], [1231.6277584182471, 557], [1393.647819054966, 519], [549.5461909758069, 390], [272.52631384983306, 154], [320.9568826775803, 374], [31.825872271306253, 30], [380.83845428997483, 187], [324.99154532435625, 190], [96.00220965900826, 38], [403.39859135662164, 167], [149.86682287865733, 127], [640.6991467302983, 290], [1018.5054313879355, 424], [168.83067091508883, 56], [299.6163996963628, 181], [230.42590278731313, 147], [282.5049682540848, 188], [8.535168844497093, 34], [185.33274833251744, 74], [288.8836714083286, 115], [592.9440158007751, 268], [936.2625434669449, 366], [561.199423218683, 251], [1517.5862988028102, 517], [75.40846140125268, 54], [1224.3882019894554, 488], [566.6154382589211, 217], [272.33362191646074, 109], [295.20583737318384, 282], [1290.8416983358413, 503], [885.9543399867216, 320], [53.40632274708378, 18], [111.64778353937527, 72], [350.7650983431554, 168], [82.90486832840224, 41], [509.1970957464139, 239], [50.47131101100649, 42], [539.378525496651, 219], [730.0554932607452, 417], [216.02566780027826, 182], [460.13271479907144, 328], [225.30565867500968, 138], [24.099336685346998, 259], [2.7845489856631502, 13], [318.89674876882555, 157], [238.76777475214385, 209], [101.53914903242867, 92], [65.34796915640823, 99], [717.9559654438506, 336], [170.9869846395386, 86], [75.54038031297364, 41], [1158.5167978552236, 405], [452.7720402630298, 259], [51.69194846976461, 22], [780.2248179998023, 336], [246.817902509119, 65], [241.16968004966338, 73], [208.71251905318468, 108], [337.8366596632086, 166], [227.6095477932231, 237], [15.892776562552626, 35], [629.5517496879404, 483], [156.6385234675788, 110], [38.915739110076174, 48], [297.2404570797453, 371], [1073.2768543676013, 455], [1213.7736936363053, 587], [553.7907708673883, 193], [248.48977527909028, 141], [78.75614759749783, 44], [122.85631751776327, 34], [107.38429401556186, 90], [202.02717567339687, 85], [32.59543365778694, 47], [289.4069570137141, 321], [1187.722671059962, 487], [175.78210010338762, 100], [391.83358010711663, 215], [341.08347935068355, 157], [59.68519995769401, 47], [712.6846707601508, 274], [249.07957776943977, 133], [774.4450378186817, 369], [213.98718976745158, 110], [86.85245059758563, 75], [87.7724836263128, 37], [447.9108949956658, 916], [970.563313375193, 370], [334.9145634013504, 167], [344.98795896597085, 204], [440.5885497528968, 211], [911.1257110795104, 465], [15.618458184977953, 27], [1313.8480682146346, 480], [639.8236219611158, 477], [1609.2374715817095, 580], [208.00034501629557, 147], [43.153713036543024, 59], [199.0896637119049, 60], [48.84494022805711, 42], [35.391002170638444, 58], [57.71657029576636, 25], [23.496458733279724, 36], [78.58293127415982, 24], [1.2871874333445703, 75], [469.2793149531892, 219], [253.5305555555442, 91], [321.9686451300247, 206], [713.5157437263655, 273], [253.68272992592347, 109], [408.98243947744504, 191], [40.45879725718942, 28], [367.95077476959204, 148], [258.67961930081356, 305], [331.3195704579982, 141], [180.03261396499693, 55], [236.13133646199458, 154], [573.0556537613388, 203], [60.62855028948036, 82], [41.79273821452762, 42], [688.4275343365207, 299], [940.3627862336457, 524], [106.1860016640544, 84], [480.3020295604192, 291], [419.33624370624364, 313], [153.68806275081533, 50], [32.874112021798055, 24], [475.82288682912326, 236], [19.157999273920723, 32], [336.44927126999164, 163], [188.55205623517895, 78], [66.72481454540366, 38], [108.69070464532672, 77], [20.776021203863138, 33], [81.49279751772019, 119], [453.80155519779373, 204], [192.39835682247895, 98], [334.24624961295694, 106], [351.05958900964515, 184], [375.14243435697006, 314], [712.592042844914, 366], [231.6840634537466, 152], [205.13628016301345, 143], [268.27691542496905, 157], [120.1280929130453, 133], [232.98973407775316, 103], [572.5907855659761, 263], [457.35071253888214, 179], [166.58605311978158, 88], [76.23077326719056, 52], [254.54655143516493, 132], [51.214954209788175, 47], [338.17343640543413, 157], [221.02042677032023, 143], [482.4137426799243, 228], [756.9487075772031, 300], [303.3516605525938, 123], [250.50858666121894, 132], [146.38044230715047, 98], [950.8439281636593, 497], [311.48648881282907, 151], [45.98075953079706, 30], [452.30311993587065, 194], [217.691229746099, 148], [664.0245910532003, 284], [1.1172626031038817, 17], [144.35846675171672, 293], [481.76294145198335, 247], [672.3923462750818, 242], [374.2995879217124, 160], [336.58507673578515, 191], [387.09628374242584, 177], [524.3267644569792, 251], [161.09786368214736, 81], [555.4369208092407, 160], [28.3053367753173, 30], [376.9727647468344, 167], [478.77581203721365, 264], [935.5834776335244, 347], [802.5624782613991, 352], [1068.567005289768, 446], [1441.918188229591, 506], [128.76704636118188, 160], [421.3205323204086, 263], [15.196476595790045, 78], [80.64952381151579, 22], [316.6481839201556, 142], [51.92618221423231, 38], [1050.161528496419, 426], [1237.6628912676956, 519], [218.90977884060044, 95], [775.2814283445764, 362], [74.89218492169562, 31], [43.74660280003582, 31], [108.70200009204063, 46], [140.6588329375977, 83], [1053.03915684001, 454], [1530.2238252271445, 493], [51.56614994371557, 50], [273.1174228657173, 120], [707.4986738398798, 289], [358.8244833516187, 112], [1011.9230622509613, 439], [507.15477523969594, 223], [235.6299317846142, 205], [91.07789221104986, 81], [232.74869306471555, 102], [59.929011366443774, 22], [184.78554698031257, 88], [284.1079322338737, 110], [122.34175547323366, 70], [472.9922458950098, 231], [8.117521529485202, 35], [70.45867687918417, 42], [348.1533435718866, 169], [583.8665368851798, 300], [291.04209490624, 150], [1570.7763126232032, 745], [164.36292375348307, 88], [49.2497546690787, 38], [363.71836997942523, 195], [1280.6768051568192, 533], [507.62817016602366, 225], [341.2980072950986, 140], [157.67381139667793, 90], [167.2111579073444, 105], [101.15664646746336, 50], [118.4938718974845, 61], [92.53483026010963, 75], [470.58447546167463, 199], [186.30379640079673, 94], [11.028526422784807, 97], [459.02614855794036, 212], [208.99703879862477, 236], [1086.7508686128394, 447]], "final_state": "tinker://f11c48d0f72f37d4ff9c6cde3cf5e327/weights/confirm-baseline_adamw_s0-final", "t": 1793808532.4902823} {"stage": "eval", "arm": "treatment_dimuon_s0", "split": "test", "step": 100, "nll_sum": 197859.48967028427, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0325384676338447, "example_mean": 1.9114180149242066, "per_example": [[132.52601834289908, 55], [1251.47399141383, 555], [577.906861570727, 233], [1056.212419206321, 416], [504.95020823263076, 287], [124.2106176592838, 60], [708.4484334887884, 468], [133.85370778220022, 71], [81.75378594847461, 65], [613.3028864362041, 271], [46.9300384550188, 35], [22.110289867704523, 31], [179.05020462114226, 107], [390.06038220621485, 112], [10.638349081713386, 11], [240.51877362983896, 86], [130.9727781130066, 105], [446.96825997506494, 407], [190.75402572303165, 132], [725.1494439017263, 231], [290.69915457320803, 268], [392.7417110979568, 155], [89.04943300540435, 102], [133.12439122956948, 74], [238.58942567642111, 83], [363.98566344368646, 135], [947.3239171944437, 390], [868.4007233803732, 284], [26.785635071079007, 44], [336.7054585449364, 137], [1199.8346658239584, 447], [0.95167626552103, 25], [389.23815054171473, 155], [846.9213687169758, 457], [310.9707893684281, 187], [465.3486642227472, 230], [392.67786674881427, 148], [325.0234342570161, 436], [479.92828424622985, 146], [312.0012010770147, 191], [13.642661829582266, 37], [429.17891349378897, 333], [79.46577247675634, 53], [189.06537066016608, 94], [1075.252735811653, 521], [320.85187436498745, 175], [134.88677015237772, 79], [52.80923001323933, 19], [3.225698097141958, 10], [330.5706522968776, 208], [310.09529723769356, 156], [225.96825955546728, 160], [1161.1253455663923, 420], [765.2798650005752, 285], [85.09496310103165, 31], [411.87551958392214, 167], [55.58712534198469, 44], [738.0539186455126, 245], [8.94795196981795, 45], [236.3687809001931, 102], [130.12974221823515, 114], [62.479237621330526, 20], [165.93953414823, 86], [152.66847075240184, 63], [72.1791692320437, 72], [99.97887688622905, 66], [141.92128620537278, 101], [102.13634723789164, 48], [66.04591692901977, 25], [64.5609143954307, 26], [66.02985770695341, 64], [223.5823113361521, 72], [380.44861173646495, 342], [325.2309530765797, 123], [363.69849279659434, 314], [115.73845068652736, 68], [70.05794437701684, 58], [207.90020372365734, 106], [203.1668424256577, 81], [321.4650169388419, 181], [284.20177707698895, 312], [640.1518046466567, 302], [1267.8867196720653, 473], [76.7969513344051, 74], [313.06986854106435, 169], [198.7448121350983, 86], [1478.966862633446, 663], [94.81960641289379, 81], [581.4247963585804, 272], [576.9995174081807, 206], [870.7888685769049, 720], [735.8873800500223, 291], [1278.8942594518721, 562], [180.1810193620213, 117], [146.88962572683613, 106], [549.5885415843513, 216], [73.76840795936391, 45], [383.5403915533732, 220], [306.6595862469876, 134], [1179.413914310635, 454], [81.3797193407554, 57], [201.24034313648417, 101], [70.71064220705705, 22], [136.99350283044532, 74], [629.0689124988462, 294], [409.9796256839436, 150], [543.5527664697674, 203], [369.0206156929248, 166], [725.6659986775703, 262], [116.82357771048487, 52], [485.27031588445425, 181], [31.58379967566725, 37], [1176.4981900120229, 642], [257.6463805832991, 176], [210.17389267853648, 113], [538.5895720483222, 194], [118.95703226863588, 72], [4.533863109115373, 10], [175.60075249051533, 123], [397.5052944873373, 141], [328.1883957436012, 117], [1325.0659580405268, 576], [120.18878193960313, 93], [314.97825776942364, 137], [569.1179119407211, 240], [39.00648177805124, 61], [123.76812297554318, 123], [189.42517184371707, 98], [267.5573217675983, 120], [5.425621608032998, 32], [876.3138245107912, 334], [2.034059023480495, 26], [52.55931685174892, 35], [233.81060250984956, 72], [638.7469393031537, 263], [647.896936339781, 247], [190.72231834405954, 66], [567.2398665960827, 265], [1347.4556750387783, 516], [1213.0195204051633, 502], [1393.8784793626446, 492], [300.0948020605015, 141], [1414.8542654101452, 476], [154.06943180789858, 170], [374.6476768408588, 123], [375.2217200068444, 397], [139.71865398719797, 57], [805.3031941826575, 411], [601.757542630628, 227], [61.21893743626879, 42], [59.45981836220062, 32], [189.55234946562996, 89], [631.2605896011476, 271], [77.32655449237427, 59], [201.94742667696391, 107], [189.51715320102107, 150], [380.2596183865604, 237], [197.93155219687833, 92], [321.0393779397509, 153], [636.8621484480282, 268], [566.5387577819674, 253], [906.0672665631846, 428], [523.5773427118296, 270], [112.75604074635686, 79], [292.06680812470904, 144], [808.2405989045835, 312], [163.36988178499814, 102], [1020.3001963222414, 554], [76.62725173663966, 71], [795.302515259581, 306], [1.7448169857252651, 6], [197.64582512765446, 273], [513.4466569142342, 256], [439.1272523793996, 234], [1352.7378909088166, 653], [447.20134153733306, 220], [480.5185772484256, 221], [84.89904416942557, 67], [230.7050574538216, 107], [75.85783551025452, 60], [1110.848534093273, 517], [93.0845550951417, 66], [406.661135190463, 185], [33.39654048315424, 47], [217.5081929009284, 138], [40.20219531397197, 37], [705.2901315312938, 372], [4.048050751436676, 11], [162.06967019417198, 69], [1.6630911647500852, 11], [306.53692134323865, 122], [544.4441952763755, 239], [401.5599205445724, 215], [370.38489571040554, 131], [365.3160277911047, 136], [808.000427318997, 241], [296.0538861074747, 145], [350.65822961901176, 226], [1326.0014473345655, 548], [27.149281333552835, 38], [421.34579274380303, 170], [66.41070241134298, 27], [598.7090654376989, 264], [699.0951791671523, 258], [189.74686959098494, 82], [289.5766621475659, 147], [577.8729821520792, 259], [517.3591497031748, 152], [247.45052476445562, 151], [877.3544005471631, 320], [229.06414457463325, 110], [239.35041228817045, 141], [219.89368178109862, 132], [292.46854758567497, 101], [272.39791298198156, 135], [1293.3749133139954, 629], [213.80874377071768, 241], [773.6840496266077, 492], [804.8819793219336, 304], [1137.3500526384446, 404], [6.762423168242094, 17], [299.46280628204477, 138], [381.1664080649607, 141], [259.6087070847349, 161], [200.2328672607955, 125], [1198.2693576329789, 639], [618.546546368576, 315], [194.0069030169568, 102], [51.21638634914757, 25], [827.1423071411746, 386], [309.530889560172, 153], [443.3503116179668, 518], [548.7296929319091, 219], [194.528442261465, 121], [894.8292724198959, 613], [432.0065871558909, 204], [609.6785550908426, 273], [141.72532687263083, 75], [859.0882891294182, 373], [912.3779448086461, 288], [579.0437138752126, 243], [159.0668933784873, 71], [104.22187473501253, 51], [226.10324146418498, 104], [1339.4092628600229, 748], [516.650301556866, 180], [269.9228761524207, 137], [693.7824849324634, 394], [948.0974697387664, 426], [258.16997619601534, 124], [1.0196189947223502, 16], [148.6684905337802, 49], [251.72174103494854, 216], [20.73745035169486, 68], [8.63237722016492, 12], [642.7025042143414, 216], [795.3877263945687, 331], [256.58504940011665, 129], [611.2172189127061, 238], [624.2487587724881, 247], [222.37964195623908, 108], [193.65594834345393, 133], [214.0660569427057, 116], [10.846308981844231, 30], [974.8407121784235, 537], [1224.9222652572626, 557], [1395.9935119893307, 519], [546.4489539864171, 390], [271.1608718391117, 154], [319.77878349148887, 374], [31.592732873652494, 30], [380.8641637294154, 187], [327.03679738388746, 190], [94.30147259710702, 38], [404.08541991903667, 167], [150.49228640709407, 127], [641.6253094278509, 290], [1016.1412627585908, 424], [168.69658263557812, 56], [300.7721531670268, 181], [231.20957833921784, 147], [282.9343774267236, 188], [8.323995654502141, 34], [183.6442734023285, 74], [289.8808091211931, 115], [595.7816834095278, 268], [936.905862825427, 366], [558.273669595203, 251], [1518.927737869844, 517], [76.21973897973021, 54], [1224.425569050718, 488], [565.870287139523, 217], [271.91077094813045, 109], [294.51882872454553, 282], [1288.2336857716523, 503], [885.1965965203926, 320], [54.50644989160355, 18], [110.45988225898054, 72], [350.7628502686566, 168], [83.03287716162276, 41], [509.12016930929724, 239], [49.45312113890395, 42], [543.2337993614574, 219], [728.0643071175032, 417], [216.78705414891556, 182], [461.5200115174057, 328], [226.74030524082082, 138], [26.215926951636902, 259], [2.4550425806590965, 13], [320.2532563221321, 157], [238.54811068078743, 209], [102.4140239691369, 92], [65.44312453181283, 99], [718.7040937905633, 336], [171.46106916022018, 86], [76.49448382366074, 41], [1155.714436527875, 405], [453.9311061358767, 259], [50.81802723329167, 22], [781.7349267760019, 336], [244.97101094778452, 65], [241.2259531090349, 73], [207.32612866334966, 108], [338.02217736364764, 166], [224.76162030590785, 237], [16.001720982064853, 35], [629.9980703188321, 483], [157.6069645128241, 110], [39.77518741897529, 48], [296.9882690647791, 371], [1073.975338437458, 455], [1211.767872455101, 587], [548.1951282696405, 193], [245.6432162141964, 141], [78.57909509410774, 44], [124.25208273983253, 34], [107.59620806337512, 90], [203.2486809056678, 85], [33.238796801459785, 47], [287.68681537929024, 321], [1194.0051284172914, 487], [175.75265058456898, 100], [392.7021181732068, 215], [342.01463387981494, 157], [60.54239944213622, 47], [710.5394512457568, 274], [250.04852994739645, 133], [778.5024086826766, 369], [213.7679229195645, 110], [87.05923280110983, 75], [87.7506793803177, 37], [435.62920434073294, 916], [968.1391205385326, 370], [334.51556129853725, 167], [344.5583400354899, 204], [437.38773332326673, 211], [905.1292282709765, 465], [16.094661638033017, 27], [1312.7613829011352, 480], [635.7076611817338, 477], [1608.8868353065845, 580], [208.5238618202202, 147], [43.47413750711485, 59], [197.5751577011838, 60], [48.55614831028106, 42], [34.393461625987584, 58], [57.13023183288033, 25], [24.17500756886693, 36], [76.65732692374968, 24], [1.8536180769319728, 75], [465.4659964086768, 219], [255.67736629752469, 91], [322.0270376970002, 206], [710.4873856967088, 273], [254.19515726882673, 109], [409.4431502938039, 191], [40.34121567536022, 28], [367.1564059174633, 148], [259.8619039805641, 305], [330.85474361191245, 141], [178.59672931858267, 55], [235.43162462608962, 154], [574.2599953682392, 203], [60.74368050421754, 82], [42.220185467394, 42], [689.3738394150896, 299], [936.9887790882703, 524], [107.7391494663616, 84], [481.5108074060663, 291], [419.45608105124256, 313], [154.21203448473716, 50], [33.70280018559697, 24], [474.5635346621166, 236], [19.461473431981176, 32], [338.2186625381528, 163], [189.52102211607803, 78], [67.64996246567875, 38], [110.12476304195553, 77], [20.807033610301005, 33], [81.58481666862394, 119], [454.18252749226485, 204], [191.787981135476, 98], [334.1910598059276, 106], [350.70761630138895, 184], [375.24225827241736, 314], [711.8797604007182, 366], [231.64496929657707, 152], [206.14974388141218, 143], [269.88774333384936, 157], [119.442561439678, 133], [232.80508067331027, 103], [572.7031506484655, 263], [458.7844698907884, 179], [164.87070934018993, 88], [77.75535756774286, 52], [254.33364010328978, 132], [51.47952796731806, 47], [340.4775916133881, 157], [220.68122841038075, 143], [481.6965530260168, 228], [758.7711672254445, 300], [303.42532013008895, 123], [250.1449018572439, 132], [146.7743442919907, 98], [953.0822020230935, 497], [311.00461358877874, 151], [46.80949095519463, 30], [452.6199223308695, 194], [218.98888954560812, 148], [663.5677332306004, 284], [1.2369425357719592, 17], [145.378863015437, 293], [482.17267176869063, 247], [671.3133491805565, 242], [374.6768626142011, 160], [338.75097183125035, 191], [387.15286201428773, 177], [524.4965315101781, 251], [162.16601876513957, 81], [554.0130004161065, 160], [29.207408934980776, 30], [375.9864065145666, 167], [478.8051081423787, 264], [933.7266543774895, 347], [803.522387422363, 352], [1069.2825396311891, 446], [1439.0492151794133, 506], [127.25018888787508, 160], [422.81081747260214, 263], [16.14315967116454, 78], [80.12611361422705, 22], [319.5862281417394, 142], [50.91407471889124, 38], [1048.9032130871879, 426], [1238.111771816973, 519], [220.7349685426807, 95], [776.5290361413317, 362], [76.30699928881404, 31], [45.356494929066685, 31], [110.49980179337126, 46], [137.99432551095424, 83], [1055.6779274364071, 454], [1531.7617603735916, 493], [51.08448424287417, 50], [272.9080934357753, 120], [704.6069677682935, 289], [359.38958611892576, 112], [1014.8713844802733, 439], [508.62376746982795, 223], [237.73366680828076, 205], [91.60720827859814, 81], [235.25503137442593, 102], [60.37789873548354, 22], [185.88888308179048, 88], [283.75572240932036, 110], [122.79792618940019, 70], [470.5966754296833, 231], [8.035188732443203, 35], [70.23345355219317, 42], [347.58235317761137, 169], [584.8816693178087, 300], [293.4712504917069, 150], [1568.416081478732, 745], [165.56909901267682, 88], [48.477232719268386, 38], [365.67847652247565, 195], [1283.2604575071887, 533], [508.59366331649653, 225], [341.3579810428746, 140], [158.46301483178968, 90], [166.80403779642256, 105], [101.26820347614375, 50], [117.49396647312642, 61], [93.45596685556666, 75], [472.88297938777396, 199], [185.39589261147194, 94], [11.36571927684804, 97], [455.400494557467, 212], [209.15066328210196, 236], [1083.8561001695489, 447]], "final_state": "tinker://5114900d3184a1f9e9047b5305999c3f/weights/confirm-treatment_dimuon_s0-final", "t": 1793808556.8621802} {"stage": "eval", "arm": "baseline_adamw_s1", "split": "test", "step": 100, "nll_sum": 197750.79997667333, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0314219380012872, "example_mean": 1.91241359540049, "per_example": [[136.8068574020706, 55], [1249.4988615613938, 555], [573.777063275101, 233], [1056.947910558734, 416], [502.568650923753, 287], [122.65927270361465, 60], [711.5075373244754, 468], [131.4728463431245, 71], [81.5135818469721, 65], [617.6630945531747, 271], [45.73247868621047, 35], [23.381873855254753, 31], [181.45490495885315, 107], [388.18169463246, 112], [10.363851478688048, 11], [240.76991448040008, 86], [129.4112402195576, 105], [441.6744085373807, 407], [188.7021261307964, 132], [726.9818589193009, 231], [288.9332649493331, 268], [395.4854727408074, 155], [83.50275512285543, 102], [132.67882256374855, 74], [239.64855652685566, 83], [357.5415853572713, 135], [951.8228594814419, 390], [869.0378144436004, 284], [27.042953296260976, 44], [336.5193883220394, 137], [1206.513374752144, 447], [1.046463022820717, 25], [386.68123324691834, 155], [840.8432485201856, 457], [308.92888753951365, 187], [467.2373759369925, 230], [393.697025207641, 148], [326.0064040093415, 436], [484.83909600671814, 146], [324.565783296629, 191], [15.43936194687467, 37], [427.5812804743914, 333], [81.5407961172416, 53], [185.3809623271809, 94], [1071.7779137311722, 521], [318.7917007189244, 175], [135.04481863045385, 79], [57.13771825442694, 19], [3.192185549611736, 10], [328.3685829009082, 208], [316.0221347731711, 156], [224.63225002853778, 160], [1159.8904676624516, 420], [765.4841512147659, 285], [84.20459868720988, 31], [413.31811312484206, 167], [57.98103852506961, 44], [745.8742747278984, 245], [9.286487197646693, 45], [235.4316628820393, 102], [131.09667653126684, 114], [65.55713776273888, 20], [164.36230849072012, 86], [153.14832996411542, 63], [70.68541960999414, 72], [103.92494582204199, 66], [142.78936962961325, 101], [100.7005344208344, 48], [65.92509671134451, 25], [65.14562697669999, 26], [65.07249463248615, 64], [223.13287906459868, 72], [377.6130176952282, 342], [325.4261825656513, 123], [362.55084430111447, 314], [115.80409755549931, 68], [74.80243526397544, 58], [209.81213863004814, 106], [204.9092637665292, 81], [322.849365356812, 181], [289.06770690381154, 312], [637.9007865173382, 302], [1276.590281714747, 473], [77.11266115361991, 74], [313.64630798268354, 169], [200.09502465331877, 86], [1485.4617673559637, 663], [98.66201012104148, 81], [578.2316070732822, 272], [577.336227073094, 206], [861.2425181902596, 720], [734.5273499088335, 291], [1278.4515483089676, 562], [180.50017571306307, 117], [145.39805670278156, 106], [551.6161971326519, 216], [74.43810054727953, 45], [385.89399840700435, 220], [303.11777209791876, 134], [1182.6153337004112, 454], [82.01250904539575, 57], [200.72997869895585, 101], [69.9818188564418, 22], [138.2063170823899, 74], [627.9990019749687, 294], [413.12155828896084, 150], [548.4446025837065, 203], [368.7733278374817, 166], [722.1095821504464, 262], [117.88056047012128, 52], [483.71939420752665, 181], [33.00437184317434, 37], [1177.9793967819496, 642], [255.70673935121476, 176], [212.32804354786595, 113], [539.2442860780629, 194], [111.59384159788351, 72], [4.399213579757543, 10], [177.59198209259785, 123], [398.74444624684565, 141], [329.2912590324213, 117], [1323.3192990349994, 576], [122.72334237855642, 93], [310.5915635771512, 137], [579.0713929137324, 240], [38.7120355584284, 61], [126.6938376941689, 123], [189.58660538423067, 98], [270.85734629614217, 120], [6.140739408222544, 32], [881.718213400466, 334], [2.1260713799780433, 26], [54.79412254528961, 35], [230.4348680941257, 72], [637.3256543634875, 263], [649.9704312721906, 247], [189.94456601414242, 66], [570.5761498213387, 265], [1347.9434229190533, 516], [1215.2761794151008, 502], [1396.6755347682588, 492], [301.1704424608615, 141], [1426.2224641107232, 476], [155.48837117526438, 170], [375.9340097808099, 123], [366.10583893364037, 397], [136.55003823610514, 57], [796.5150155835488, 411], [612.8302255703165, 227], [61.294522683791456, 42], [60.47047050452554, 32], [185.2966056423886, 89], [632.117031930748, 271], [74.85751326348577, 59], [200.52644515738473, 107], [188.7514176231657, 150], [376.0901048001424, 237], [196.04800928847726, 92], [319.759122251437, 153], [633.3333142739166, 268], [570.6921026808088, 253], [900.5904841223601, 428], [522.4331210226565, 270], [112.20200581348399, 79], [294.3374400958196, 144], [807.597034426095, 312], [163.2228994768684, 102], [1019.7861658873157, 554], [75.89473549372724, 71], [796.3835294231612, 306], [1.7108094058635288, 6], [199.93844301902385, 273], [515.5373601944211, 256], [434.95739722712597, 234], [1349.4456052016096, 653], [446.6573315341684, 220], [478.2718858968997, 221], [84.59210609125648, 67], [229.7005813382484, 107], [78.57960758302022, 60], [1110.0864483995292, 517], [91.30743442535334, 66], [409.95791647653004, 185], [33.765792391472104, 47], [214.95997779799563, 138], [38.319364422564604, 37], [711.3201382580991, 372], [3.2771080220945805, 11], [162.6932966211706, 69], [1.3861212137161374, 11], [305.37619382221465, 122], [541.8546218055742, 239], [397.5080923009656, 215], [369.1207855176481, 131], [362.15111587053116, 136], [816.0021423355429, 241], [293.32089750630666, 145], [350.8165510741783, 226], [1331.7263888517623, 548], [27.863511441662467, 38], [417.2078834993795, 170], [68.34228895322929, 27], [596.2189513356961, 264], [701.8204795749286, 258], [189.0418768096324, 82], [291.8924281339159, 147], [574.8514786068145, 259], [516.1266320472266, 152], [248.57228954843958, 151], [883.8958052456851, 320], [227.08940342274036, 110], [237.89451791906072, 141], [219.42012364320135, 132], [293.5514281301047, 101], [276.8315127307078, 135], [1292.508404818081, 629], [214.9183769351028, 241], [751.7667020571612, 492], [803.9888284789272, 304], [1139.4920125764297, 404], [7.313838960990324, 17], [295.36311054647035, 138], [386.19257372869333, 141], [256.0342316428005, 161], [198.82223363417984, 125], [1194.2931284271974, 639], [612.1252265483668, 315], [190.32161428775817, 102], [46.90387546637504, 25], [820.6600267074182, 386], [307.810774182386, 153], [441.68936651076984, 518], [549.959114677391, 219], [193.61538327590188, 121], [900.5910295112493, 613], [430.34977515503306, 204], [609.5617931365152, 273], [141.74058607581037, 75], [860.9422237253598, 373], [917.319976669723, 288], [566.3235302333223, 243], [164.26629211968873, 71], [105.48739544542468, 51], [230.40889827731917, 104], [1329.1157258008434, 748], [516.8293936807861, 180], [263.6217501421097, 137], [685.1142922417574, 394], [945.3921807739569, 426], [256.43129052189715, 124], [1.6202812620385885, 16], [148.87934339954742, 49], [253.01505528321627, 216], [19.953326261429766, 68], [7.765421667250848, 12], [640.6451871867223, 216], [787.3519845554474, 331], [254.10675374873927, 129], [614.146746771436, 238], [627.719699342663, 247], [220.19566474568273, 108], [196.1164642089525, 133], [205.94936647902284, 116], [15.63728374354821, 30], [983.3827522477015, 537], [1224.517385250244, 557], [1398.6421884629892, 519], [540.351656225931, 390], [268.20141264182007, 154], [319.4485779753845, 374], [33.07589895080383, 30], [382.92840571237593, 187], [324.6183443280131, 190], [99.42756599952867, 38], [405.51046870084883, 167], [148.73101279108175, 127], [641.5401925637307, 290], [1007.3607977307138, 424], [170.2826195538296, 56], [299.5716864521837, 181], [220.03746555572388, 147], [279.409458828235, 188], [8.531885300316276, 34], [189.43548785864732, 74], [288.50912517854204, 115], [591.0976446717268, 268], [934.6124971649851, 366], [558.5612622611634, 251], [1524.8893893940863, 517], [74.31555799547664, 54], [1221.2788735582776, 488], [567.6932483725479, 217], [268.63492407942704, 109], [294.0828847627162, 282], [1280.8128059697847, 503], [880.9188022857774, 320], [54.85191896510173, 18], [107.65890721451603, 72], [351.50956761985526, 168], [85.093991073383, 41], [508.49793570026395, 239], [51.5016967616541, 42], [544.5623152088078, 219], [725.7959219569764, 417], [216.96249234247693, 182], [452.8739265501624, 328], [224.8444248002752, 138], [23.657289306993675, 259], [1.0335283056729168, 13], [317.50261240205145, 157], [240.90208407007094, 209], [103.49252757337035, 92], [63.01027002639694, 99], [718.6136899567205, 336], [171.13314300606817, 86], [74.76536806056879, 41], [1159.2437741042122, 405], [454.08971924281605, 259], [54.16346214603266, 22], [781.0414342317052, 336], [248.71085492878046, 65], [238.2073374420521, 73], [207.42944156883732, 108], [340.17484866998143, 166], [223.6692217850523, 237], [16.822422469329354, 35], [625.9321936920564, 483], [155.69499783895662, 110], [39.04959341860376, 48], [292.29210561843496, 371], [1068.2579273084878, 455], [1220.2930100377462, 587], [546.1666532645972, 193], [245.5421843908, 141], [82.65132088012683, 44], [124.92487306517052, 34], [103.75686416704627, 90], [204.11006850119654, 85], [30.70069136468817, 47], [283.480376843032, 321], [1196.3400809333261, 487], [176.27428524363313, 100], [392.32360932375946, 215], [341.06194468590087, 157], [60.1951524523314, 47], [711.7350849726436, 274], [251.64595576941883, 133], [782.2626263240554, 369], [214.22335347911576, 110], [87.98771500469911, 75], [87.36977653717383, 37], [429.09350412841513, 916], [965.6467246138069, 370], [335.74047121307547, 167], [342.323634282445, 204], [442.26396261457853, 211], [911.4188980671406, 465], [16.162941157926042, 27], [1317.2392655666931, 480], [628.7122583947064, 477], [1614.2037913309832, 580], [210.87194313066118, 147], [44.99578016737041, 59], [198.6294841208046, 60], [52.60757240625071, 42], [34.03823743565499, 58], [59.74192246585153, 25], [24.52547156215951, 36], [82.00974236394086, 24], [1.7192067827672872, 75], [468.04047429236016, 219], [258.13572246765034, 91], [319.8035789757323, 206], [709.5655498900694, 273], [252.89440356666, 109], [414.08019303229275, 191], [40.80047479082066, 28], [365.2023995804666, 148], [258.3063431604304, 305], [328.6344876902689, 141], [178.10640519102185, 55], [238.83580739259082, 154], [574.5028655502853, 203], [62.490704752689446, 82], [42.19390460188379, 42], [687.8285561511143, 299], [941.7133217225492, 524], [105.73445946021002, 84], [477.1018954295091, 291], [418.8513386228209, 313], [153.2773713408776, 50], [35.25468920897316, 24], [476.787756480865, 236], [19.461769256435673, 32], [336.08282784232097, 163], [189.04957031778395, 78], [67.9963573801773, 38], [109.21482805965763, 77], [19.967829905986946, 33], [83.96160898808395, 119], [454.7503237250994, 204], [191.21005751714483, 98], [331.72051956658925, 106], [349.2009673128837, 184], [370.6433104713915, 314], [711.194284217541, 366], [230.89551674087033, 152], [205.05804546284668, 143], [268.5548511113857, 157], [117.1892978210135, 133], [232.8724906794978, 103], [576.640738943754, 263], [457.1272966249551, 179], [163.36805404075858, 88], [77.05262938506871, 52], [240.6374441718144, 132], [50.96612855334752, 47], [336.64366939366204, 157], [218.71511989395094, 143], [480.23477999370334, 228], [758.818211004389, 300], [305.2109845216162, 123], [250.51309695138207, 132], [145.38285571421466, 98], [952.464700015662, 497], [313.66864561877765, 151], [46.64034763401878, 30], [449.8951434405675, 194], [217.4642173011348, 148], [666.5917817808145, 284], [0.9336078301125781, 17], [147.02318399976735, 293], [481.93471134340143, 247], [674.6720439294581, 242], [375.7451645028357, 160], [336.91622067562764, 191], [387.1114190024399, 177], [521.5115469723155, 251], [163.65041095505012, 81], [551.5431707941866, 160], [30.41563200149767, 30], [376.3053655510812, 167], [473.23717300630346, 264], [935.7520269118518, 347], [792.0406056919101, 352], [1066.7661037995845, 446], [1438.156296917536, 506], [127.5420518027272, 160], [425.30597079977633, 263], [15.542357306421756, 78], [77.94370379144243, 22], [319.39921214351557, 142], [53.6003293716453, 38], [1048.574502470933, 426], [1235.5758785209312, 519], [216.3607797927889, 95], [771.696612085288, 362], [76.35290700789017, 31], [44.604015991484175, 31], [109.40593371558077, 46], [136.39501377800886, 83], [1054.0041401796593, 454], [1533.0725524049617, 493], [51.039487861510224, 50], [278.9175575621425, 120], [705.6806694112333, 289], [362.3952244557138, 112], [1013.1364188720718, 439], [505.6933844724583, 223], [236.64987250064667, 205], [91.60743800089676, 81], [233.78616247884702, 102], [60.38518540443465, 22], [185.77675192312142, 88], [283.08437980947974, 110], [120.74155747287296, 70], [484.32076355194044, 231], [7.570844244225555, 35], [69.95910381954843, 42], [344.7935614048233, 169], [583.1595036484191, 300], [290.8614121863111, 150], [1566.196742571748, 745], [165.1616575669549, 88], [49.84889043585417, 38], [367.52661346137734, 195], [1289.8306527008149, 533], [509.779565652545, 225], [339.14731221654165, 140], [153.90634191680647, 90], [164.1579740123325, 105], [97.38573422584705, 50], [121.47861094774089, 61], [91.4850229470976, 75], [475.4769934892428, 199], [187.50863911383522, 94], [10.934865150340556, 97], [457.76481544595345, 212], [206.7875432627893, 236], [1081.703170682028, 447]], "final_state": "tinker://3237e16ec54b87586f4118a972d03f52/weights/confirm-baseline_adamw_s1-final", "t": 1793808590.902091} {"stage": "eval", "arm": "treatment_dimuon_s1", "split": "test", "step": 100, "nll_sum": 197647.1661560484, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.030357345510328, "example_mean": 1.909182655629596, "per_example": [[133.23540463050222, 55], [1247.0172007567007, 555], [576.6554142894586, 233], [1057.675224109531, 416], [504.0194051439955, 287], [122.09166967048282, 60], [713.9590123225553, 468], [132.43469456892763, 71], [81.15957813405385, 65], [616.9215414600592, 271], [45.31161153617688, 35], [23.080240457187756, 31], [181.74157545698742, 107], [387.86067028872776, 112], [9.783808353638051, 11], [239.15382447980937, 86], [130.7246453624233, 105], [441.21399442066786, 407], [187.02734122889717, 132], [725.1613095678613, 231], [287.09239385596993, 268], [394.80645017382494, 155], [85.79186316617779, 102], [133.25626280011647, 74], [240.23769335367058, 83], [357.8455225827811, 135], [951.5294978894626, 390], [869.2595394084998, 284], [26.865711824411818, 44], [337.7643876903421, 137], [1203.9037889623405, 447], [0.9469498938979086, 25], [386.81008910241235, 155], [844.6548202942176, 457], [309.92219682471296, 187], [464.29584735370554, 230], [393.31318445073487, 148], [326.55314341336515, 436], [482.0906916662834, 146], [322.1096196033832, 191], [16.199387766699147, 37], [429.27431313236093, 333], [80.42685909238617, 53], [186.25927119073276, 94], [1074.9938243639606, 521], [318.5810179303726, 175], [133.63785841326444, 79], [55.669066283559, 19], [3.736415648349066, 10], [326.35192793359863, 208], [312.46314128629274, 156], [224.6188824960691, 160], [1162.2156866524256, 420], [764.7845875107491, 285], [84.67041403497933, 31], [413.252470437606, 167], [57.46009547779022, 44], [744.0446730642234, 245], [8.403705624077695, 45], [235.30943759514503, 102], [131.5149082753295, 114], [65.74617615345198, 20], [164.2535834606565, 86], [154.02328116427725, 63], [70.20260813855381, 72], [104.0022080288552, 66], [142.7991372626102, 101], [101.66823212556756, 48], [64.6899177061386, 25], [63.66358477489007, 26], [65.20932693971008, 64], [222.69930449441176, 72], [375.1244497613998, 342], [325.83513607869645, 123], [361.5698789629303, 314], [114.96255063850299, 68], [75.4286096597416, 58], [207.75669616142386, 106], [205.65108512297115, 81], [322.0470969598573, 181], [288.0388322545507, 312], [637.6099478384685, 302], [1273.224817292713, 473], [75.85974837376716, 74], [314.32027189649443, 169], [199.05672820641482, 86], [1481.5066059788296, 663], [97.67931043214685, 81], [579.8714551122775, 272], [577.316869239893, 206], [863.0102643812897, 720], [734.4261345613929, 291], [1282.1348145974034, 562], [181.70253270311918, 117], [145.67413557177542, 106], [551.9395778315511, 216], [74.54140474059909, 45], [385.21858888890324, 220], [305.0710898768684, 134], [1181.637695994483, 454], [83.1781871279236, 57], [203.78736982051305, 101], [69.91469265834888, 22], [138.52210655500767, 74], [629.4030426718373, 294], [412.33998771091683, 150], [547.1051804171657, 203], [368.7365013157946, 166], [723.263621208243, 262], [118.38764201171284, 52], [484.19713814519446, 181], [32.73021678490201, 37], [1180.1389802718018, 642], [254.4588343750395, 176], [213.37314418341487, 113], [538.9210413152095, 194], [112.89544353599649, 72], [4.339048532183369, 10], [176.71554554273735, 123], [397.594769444834, 141], [328.52104672552537, 117], [1320.9767733554113, 576], [119.98369151362476, 93], [308.6305875616781, 137], [581.1214310672123, 240], [38.06275567201715, 61], [127.69082431431207, 123], [188.84211897662624, 98], [268.6969124314114, 120], [6.110668265461186, 32], [880.4023657559928, 334], [2.092705415620003, 26], [54.0114721927298, 35], [231.01124310431987, 72], [639.5348315532192, 263], [651.1494200831626, 247], [192.0236331813676, 66], [571.4556674929445, 265], [1348.2522051611168, 516], [1216.9783805189516, 502], [1396.7325091380164, 492], [301.9328838901415, 141], [1422.5823232624607, 476], [155.0865686464094, 170], [375.9429473433165, 123], [364.1451487877945, 397], [136.188606760546, 57], [795.7722207357256, 411], [610.5701182523198, 227], [60.77014817075815, 42], [59.76411147839099, 32], [184.85664265235664, 89], [633.488796265447, 271], [75.17927579862953, 59], [203.27276036840425, 107], [189.39623407296858, 150], [377.03382350346413, 237], [195.56572629747643, 92], [317.68196565994003, 153], [634.1344970772607, 268], [569.2710733950144, 253], [897.8214081223139, 428], [526.1012411315461, 270], [112.08955487716014, 79], [293.4622371104442, 144], [804.9981638052795, 312], [163.78628664539883, 102], [1017.8937797791259, 554], [76.21676875653361, 71], [797.0784163849521, 306], [1.5150230504509636, 6], [196.8768437184344, 273], [518.0434190160504, 256], [434.00826770528147, 234], [1350.4623181650609, 653], [448.36777197979063, 220], [477.84461423113135, 221], [83.89044541730979, 67], [229.77102278907023, 107], [77.2004168252077, 60], [1108.9825998850845, 517], [91.60206330817755, 66], [409.2899692361573, 185], [33.94197316798454, 47], [212.98140184177765, 138], [33.58775527665921, 37], [708.4679323831283, 372], [3.5665303001278517, 11], [161.83306558142522, 69], [1.349022076352405, 11], [306.3161706956116, 122], [541.7512700533601, 239], [397.6841481097932, 215], [368.88145022837307, 131], [362.73782335943054, 136], [812.7848020366193, 241], [294.4847414534215, 145], [351.08289149506527, 226], [1335.4481365134052, 548], [27.707282955218034, 38], [418.24559413840325, 170], [67.99619088147278, 27], [592.978880455267, 264], [700.1875119440356, 258], [188.1614043689915, 82], [292.2304760111358, 147], [576.0527354852302, 259], [516.6607893056078, 152], [246.7424696596472, 151], [883.4449926186853, 320], [225.85245270042014, 110], [239.99138082180946, 141], [219.22601558202746, 132], [291.6259995958917, 101], [275.1854763067049, 135], [1292.0856981188708, 629], [214.20344710311224, 241], [756.3847225107611, 492], [801.000410136008, 304], [1139.6803520193318, 404], [6.603253644552723, 17], [294.7010702971611, 138], [382.5756582879485, 141], [258.4559758290885, 161], [199.13595201627913, 125], [1196.3227849088953, 639], [617.5898664218366, 315], [190.46999567325133, 102], [47.03333077516413, 25], [821.24063619348, 386], [308.19064063602764, 153], [440.6035934707006, 518], [551.894765004231, 219], [193.5879129090872, 121], [898.7200438872873, 613], [430.50674061606514, 204], [608.3529946757635, 273], [141.01788875031434, 75], [858.6118206405727, 373], [916.3890969120321, 288], [565.0672636626778, 243], [162.1726612742221, 71], [105.19537242772458, 51], [229.88804338042974, 104], [1339.686210882141, 748], [512.8415927957312, 180], [265.4787361313024, 137], [689.6574318909231, 394], [946.0920206045782, 426], [257.4320332340475, 124], [1.4492524103943651, 16], [148.74052087890414, 49], [254.285169215409, 216], [20.50858097006585, 68], [7.569385123411848, 12], [639.710960360113, 216], [789.7789469005597, 331], [252.89528937235332, 129], [610.3356128140854, 238], [623.9080436020508, 247], [220.34655216308875, 108], [195.80394866655934, 133], [211.17516372411768, 116], [12.693831021140625, 30], [974.9682621860497, 537], [1222.1236597867264, 557], [1399.8787248946069, 519], [541.2456475665313, 390], [265.28363098792033, 154], [319.6316763041882, 374], [33.37946601413569, 30], [383.720623766937, 187], [325.02152606953405, 190], [95.2941928275595, 38], [406.42162718760335, 167], [147.31339463047493, 127], [641.8996181856601, 290], [1009.6273605420192, 424], [170.2041974093571, 56], [297.42382676693524, 181], [223.40223838179645, 147], [280.09043988800113, 188], [8.99409148269114, 34], [188.04949057291742, 74], [286.3018042852799, 115], [592.2102315144311, 268], [933.6851742723029, 366], [557.2263091294323, 251], [1524.4698500436175, 517], [75.1988323914336, 54], [1221.9868829917414, 488], [564.7091023410188, 217], [271.0895863600517, 109], [294.0752447646621, 282], [1281.8186759169946, 503], [881.1666347120598, 320], [54.028463914674376, 18], [107.4809057851279, 72], [350.707312372102, 168], [84.2634600118754, 41], [509.3332360300028, 239], [50.231686717957245, 42], [542.2041929802614, 219], [725.0668416034678, 417], [216.23816076111643, 182], [455.5451115520357, 328], [224.27250895346924, 138], [22.40146869341379, 259], [0.9612415568772121, 13], [318.9858525735198, 157], [239.07537879612892, 209], [101.7499312220225, 92], [63.35208310778489, 99], [721.4434393944912, 336], [169.3290323627857, 86], [75.03886620617823, 41], [1158.28904626939, 405], [454.0745198165805, 259], [53.74700051216843, 22], [780.4612616573227, 336], [247.56717719289554, 65], [240.0926730639439, 73], [207.23848275114415, 108], [338.4043816611802, 166], [222.21499136442492, 237], [16.421475475915933, 35], [626.9093516920539, 483], [156.04293338701655, 110], [39.26678548669403, 48], [294.58574467555445, 371], [1069.028848243362, 455], [1215.959210072734, 587], [548.51048405545, 193], [245.65840890088828, 141], [82.85609682610627, 44], [123.02990958907682, 34], [105.53556923984883, 90], [202.8848248641042, 85], [30.86846337501322, 47], [282.4613201312857, 321], [1197.8731729725478, 487], [177.097507554703, 100], [393.5290566841086, 215], [340.6324504086678, 157], [57.954916900916935, 47], [709.7445328330732, 274], [252.62169389328687, 133], [781.268180922194, 369], [214.53592420602172, 110], [88.01597392007022, 75], [87.79525766549693, 37], [427.70527541516987, 916], [968.7814325617246, 370], [334.72397058431574, 167], [343.5268783312779, 204], [441.32484337265623, 211], [908.0779586167619, 465], [16.10644173521905, 27], [1317.1673495060572, 480], [629.6703174760668, 477], [1609.4730357569988, 580], [213.5454689451202, 147], [43.43928878805127, 59], [196.83130172512926, 60], [51.103211420667776, 42], [33.80550322975864, 58], [58.310613918032686, 25], [25.542398040245644, 36], [79.26382526663645, 24], [1.7501013628261717, 75], [467.73796007026954, 219], [258.799787801222, 91], [319.23734671694956, 206], [709.3371860630868, 273], [255.65144516722694, 109], [416.19017215768145, 191], [41.49426695715556, 28], [363.93988611887835, 148], [258.42812698575995, 305], [330.1392639682857, 141], [178.02517644149515, 55], [239.0608243317036, 154], [573.3769280494248, 203], [61.124094849622, 82], [42.167055186720745, 42], [685.7620864336295, 299], [944.2008357986629, 524], [106.2999909116694, 84], [477.5269269855413, 291], [417.6616852313896, 313], [153.67689507404395, 50], [35.174414101675154, 24], [471.408543020445, 236], [19.424310038063595, 32], [337.5186603606562, 163], [187.97820970245493, 78], [67.74904778530612, 38], [109.601354027458, 77], [19.29874052028208, 33], [82.71310236675401, 119], [453.16128944801994, 204], [189.5038760038068, 98], [331.1780252660833, 106], [346.8583227015406, 184], [372.9843897296755, 314], [710.932167667133, 366], [230.52307096854645, 152], [205.2050675452392, 143], [269.2528489625138, 157], [116.8919136984722, 133], [233.17046020977068, 103], [576.3243854089449, 263], [456.3715072226268, 179], [164.4417584732755, 88], [76.64723523115254, 52], [240.5766910190594, 132], [50.84192890581102, 47], [338.62630851285303, 157], [217.24846420890844, 143], [480.11223750113277, 228], [759.9175480593885, 300], [304.8953329795195, 123], [249.75580224765736, 132], [145.9426674825072, 98], [950.6361204491063, 497], [314.9822889152092, 151], [46.39890819534958, 30], [448.6377162609788, 194], [216.00713755610195, 148], [665.2538039067663, 284], [1.11013411050223, 17], [144.30239793721555, 293], [483.550031579387, 247], [674.4711435824993, 242], [376.0237963289178, 160], [333.85628782221454, 191], [386.6793034170637, 177], [521.9614470960605, 251], [163.4180849210943, 81], [550.7707076681471, 160], [30.15898860151856, 30], [375.74611044672054, 167], [474.54255534567653, 264], [935.7245725117918, 347], [795.3524468769447, 352], [1066.8291053113373, 446], [1441.658010814081, 506], [128.37636106194418, 160], [426.2771392326722, 263], [16.344361062519965, 78], [77.70814387405142, 22], [320.1323067282474, 142], [52.632172880852515, 38], [1046.0687347819453, 426], [1237.970508370463, 519], [215.12453520780264, 95], [772.9413786963905, 362], [76.73849728125333, 31], [44.46809504012708, 31], [108.32207428286893, 46], [135.192629575676, 83], [1051.6082812583047, 454], [1531.629442104574, 493], [51.17650902250921, 50], [275.3869888138888, 120], [704.3479455414631, 289], [361.59739202550173, 112], [1010.2292996847218, 439], [505.9648432721616, 223], [236.84861655811162, 205], [91.29885377661537, 81], [235.97253633659057, 102], [59.98450438234886, 22], [184.9594752405496, 88], [283.75730890242585, 110], [120.77997585228331, 70], [483.4464274641118, 231], [8.214626377726063, 35], [70.15371514915182, 42], [344.53877860542707, 169], [583.0677473725946, 300], [292.16901806981514, 150], [1564.663088631739, 745], [167.26727490784646, 88], [48.01455126865767, 38], [365.63624924958094, 195], [1286.2902511636821, 533], [508.8849476586847, 225], [340.3708779333065, 140], [154.46023696460452, 90], [164.00588445279527, 105], [98.40767262123336, 50], [119.31805727041069, 61], [91.29311626709864, 75], [474.1794352785964, 199], [186.52202961714283, 94], [11.08506976255262, 97], [459.04828383186396, 212], [205.37180845008288, 236], [1078.0295934695368, 447]], "final_state": "tinker://08e25db82a092035669aa384182fbeb0/weights/confirm-treatment_dimuon_s1-final", "t": 1793808614.4209175} {"stage": "eval", "arm": "baseline_adamw_s2", "split": "test", "step": 100, "nll_sum": 197699.682991825, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.030896831835155, "example_mean": 1.9100704506768729, "per_example": [[131.20801776592089, 55], [1252.2089208615685, 555], [583.1373520764428, 233], [1058.5372274753681, 416], [509.63591986738356, 287], [121.20018653026455, 60], [704.554559451044, 468], [130.81966605444632, 71], [81.5514566965112, 65], [612.2612337578234, 271], [46.82665413691598, 35], [24.093254043356865, 31], [179.74506258833662, 107], [388.52129349116694, 112], [8.622323842439982, 11], [240.41114164115243, 86], [130.92440904002933, 105], [442.18687705275215, 407], [186.16228249172855, 132], [723.3838619291873, 231], [285.09238878181804, 268], [391.53446382420543, 155], [89.22800758677477, 102], [131.79934325584145, 74], [238.59985769902414, 83], [357.29421559870207, 135], [946.2143577876468, 390], [867.345589422659, 284], [27.785484380494374, 44], [342.44208059575976, 137], [1199.8612724027535, 447], [1.6269197636411263, 25], [388.60398360063664, 155], [850.1367433816285, 457], [310.6871135018664, 187], [465.7383238929906, 230], [392.2123265091145, 148], [326.07694750604105, 436], [479.6233804105359, 146], [323.8410281406959, 191], [10.307763846874877, 37], [432.4187747543144, 333], [81.83485024646666, 53], [185.64427375130708, 94], [1073.3671415550016, 521], [322.75029379553644, 175], [130.2746189669342, 79], [54.59575521675288, 19], [2.7753217884373953, 10], [331.4808779486393, 208], [312.8422745598227, 156], [223.00121191994003, 160], [1162.2211643924452, 420], [765.9705632037476, 285], [86.8729059915604, 31], [411.6657170655708, 167], [55.72536918873084, 44], [742.9408107788945, 245], [9.524894477643102, 45], [233.24365358312207, 102], [128.69399725973017, 114], [63.665252298203995, 20], [165.14583400125593, 86], [153.82700337092683, 63], [70.47799864865726, 72], [101.32064145102049, 66], [143.82239426684964, 101], [101.5391105329054, 48], [68.13028024598316, 25], [64.34765318623249, 26], [64.38855555245118, 64], [220.7928443916826, 72], [378.7333425854181, 342], [320.74192436317753, 123], [363.61310070730906, 314], [115.28742051825611, 68], [71.7858272667363, 58], [208.50224521969722, 106], [202.51200021253646, 81], [323.6232825423931, 181], [287.1030099066993, 312], [640.4507675480982, 302], [1274.5442718939557, 473], [77.61763648511351, 74], [320.0732938909641, 169], [201.74337491567712, 86], [1485.8135593177885, 663], [93.89085291957235, 81], [579.9624869356994, 272], [576.6702374951892, 206], [863.4085309338625, 720], [737.4194215264761, 291], [1279.5914392638783, 562], [180.5113856589769, 117], [146.58953911823892, 106], [555.8055945345532, 216], [76.71504183186744, 45], [386.6041883765779, 220], [305.25069614185577, 134], [1178.8560943125703, 454], [84.46035430620029, 57], [199.09613924366386, 101], [70.05414094355001, 22], [135.80782053713256, 74], [630.3293574813597, 294], [412.9680241469291, 150], [548.325662021608, 203], [364.9306790268365, 166], [719.9540165629369, 262], [117.32347687618585, 52], [483.6311962440932, 181], [34.27073828045286, 37], [1186.0122531717425, 642], [259.24022418752793, 176], [207.71921592748959, 113], [538.2573897595339, 194], [111.09016227041593, 72], [3.3485241035923536, 10], [173.71146710939684, 123], [394.60547815203745, 141], [327.6214659660127, 117], [1326.4262511860043, 576], [122.25317463024658, 93], [308.5781627633367, 137], [571.5415549152804, 240], [39.89365254428776, 61], [126.57137010674614, 123], [190.0828186934666, 98], [266.765663322567, 120], [4.767375739250383, 32], [879.160199520571, 334], [2.2664541781532535, 26], [58.164119078373915, 35], [227.49941916479656, 72], [636.6680230929019, 263], [646.6384889423566, 247], [190.60010959091585, 66], [567.836601730236, 265], [1348.1347217953348, 516], [1211.758794039626, 502], [1396.175453782529, 492], [301.2529601132046, 141], [1422.3069432185112, 476], [150.71274450667715, 170], [374.0405759533405, 123], [372.8421923237602, 397], [135.6554686433592, 57], [805.515977397763, 411], [602.1478537096109, 227], [58.930795855415454, 42], [63.11851533932895, 32], [185.50004728772058, 89], [632.7393675592926, 271], [77.94350563222542, 59], [203.2921025614305, 107], [188.5973047015841, 150], [379.40654450663715, 237], [197.3207873453507, 92], [319.1607171858195, 153], [629.5684155877825, 268], [567.5995013219272, 253], [898.6729238009993, 428], [521.349997712244, 270], [115.99149486462511, 79], [293.49592140410454, 144], [806.1769332871045, 312], [164.11623033617525, 102], [1016.5954297584922, 554], [77.81722406555127, 71], [790.2553059049201, 306], [0.6499457727536537, 6], [199.88385023190858, 273], [511.1568681859226, 256], [437.74571717462095, 234], [1344.2682536775264, 653], [445.63493333857326, 220], [475.66153133326134, 221], [84.73427862091171, 67], [231.1036336090492, 107], [77.0910037335957, 60], [1107.4503875677133, 517], [89.98081498188367, 66], [406.6432310752789, 185], [31.70776835372908, 47], [215.01959911978702, 138], [40.63826517648522, 37], [709.7462561823679, 372], [3.2995723976637237, 11], [163.544396356147, 69], [1.5073863625566446, 11], [308.0523280594698, 122], [542.0209104722089, 239], [402.41037990518635, 215], [373.3860499218863, 131], [361.20930025727057, 136], [811.2693292591321, 241], [293.2741549737766, 145], [345.77190141592655, 226], [1331.0307912183525, 548], [27.619500835153303, 38], [421.44668413489853, 170], [72.26698323402161, 27], [602.9997686664337, 264], [701.3508526499481, 258], [187.8658446475888, 82], [286.56320080468777, 147], [572.5517749395494, 259], [511.7989414835283, 152], [248.49059420086633, 151], [875.9075519809048, 320], [225.42701135869356, 110], [242.1392809378534, 141], [220.6055695668183, 132], [292.3699697768352, 101], [275.1674558366594, 135], [1296.0271968227626, 629], [210.0250517571002, 241], [765.6439012723681, 492], [798.828041960167, 304], [1135.640006349311, 404], [8.498700002659461, 17], [298.0685883491292, 138], [387.0856606821326, 141], [259.956131603074, 161], [202.7076290564305, 125], [1193.773449160851, 639], [614.1845016687012, 315], [190.94203350448151, 102], [50.03292512889311, 25], [817.1727550117762, 386], [308.63174423878445, 153], [443.95846488748396, 518], [544.7285647527515, 219], [189.54764466812776, 121], [902.1539402370763, 613], [428.31291499094914, 204], [612.4791090055551, 273], [143.5329024713801, 75], [859.540882186533, 373], [914.3614394088654, 288], [561.6636008259284, 243], [160.6015244447899, 71], [103.55704895651252, 51], [225.09236009737288, 104], [1339.885131026671, 748], [515.9621684803533, 180], [263.26233605003745, 137], [684.562953806384, 394], [942.0717524194206, 426], [255.95847718021815, 124], [1.8634907478408422, 16], [148.38727712153195, 49], [253.2946940350157, 216], [20.79939963083598, 68], [8.632085636167005, 12], [640.4180419327579, 216], [790.8740524951727, 331], [251.52107623748088, 129], [611.7870263313544, 238], [628.2878631630742, 247], [219.543844339285, 108], [195.75245234518115, 133], [211.09198920673498, 116], [15.567064762659925, 30], [975.2163158959956, 537], [1228.5311452022834, 557], [1396.8912622087446, 519], [543.6016084818311, 390], [271.7933903708954, 154], [318.0917606691728, 374], [34.200594989182264, 30], [381.70779865379143, 187], [327.9697808241617, 190], [94.28199326355207, 38], [404.7847106231575, 167], [146.28046259287657, 127], [645.788697863929, 290], [1014.3427349732492, 424], [168.51973522027947, 56], [297.92506086645153, 181], [234.51477612217423, 147], [281.0060557022498, 188], [9.21469275280515, 34], [189.6566087448591, 74], [288.074003253123, 115], [594.255046227579, 268], [935.1703954080158, 366], [559.4369075300262, 251], [1523.6209840481306, 517], [74.44757946047139, 54], [1226.1969273406148, 488], [576.0063424248801, 217], [269.90623810344186, 109], [294.0879115173984, 282], [1289.2702102739659, 503], [882.8863682043066, 320], [53.612306943075964, 18], [109.17960241962282, 72], [347.79750498855174, 168], [82.71354507832439, 41], [510.301883617165, 239], [51.3823685375537, 42], [539.2814920329183, 219], [728.1222707691668, 417], [215.28110312622312, 182], [456.0602765034115, 328], [225.90074349583483, 138], [22.65461184619471, 259], [1.145221961607433, 13], [320.962397219163, 157], [240.17218567723467, 209], [102.50363371954154, 92], [64.14127797241963, 99], [715.0356947616583, 336], [169.64099490519857, 86], [81.43020389950107, 41], [1152.2412896332007, 405], [456.1171404364595, 259], [54.32459559129711, 22], [785.1080730380756, 336], [246.3943859877345, 65], [238.8912405031433, 73], [204.97542833137686, 108], [338.7679981682113, 166], [229.31294336964856, 237], [20.059277841652147, 35], [635.3217919537583, 483], [154.9485792773503, 110], [41.6085078252072, 48], [291.98123472823045, 371], [1072.6434658273238, 455], [1221.2083667935776, 587], [547.892120869612, 193], [246.1450713992881, 141], [80.29083338250621, 44], [122.73835434548528, 34], [104.94041229829054, 90], [201.4759719765334, 85], [31.56239534317865, 47], [290.9096011048305, 321], [1192.7376731129698, 487], [175.161261912981, 100], [391.50583061976613, 215], [343.84653669057207, 157], [63.10103367777981, 47], [713.9920815449832, 274], [250.36341434649785, 133], [769.3366245436009, 369], [213.6201296832669, 110], [86.27033186150584, 75], [89.04678799312842, 37], [436.56267272516106, 916], [967.6373808897788, 370], [335.91205032220023, 167], [349.48981212773106, 204], [439.76713930950064, 211], [914.2837853506007, 465], [16.991346937909498, 27], [1313.619143414347, 480], [632.1012545594767, 477], [1606.283122234889, 580], [213.86575581687612, 147], [44.25483103211445, 59], [195.1084310520746, 60], [48.23838778729987, 42], [33.84661025743844, 58], [57.08248629637092, 25], [24.809457889816258, 36], [83.3433082130341, 24], [1.6189016343996627, 75], [465.9434855972431, 219], [260.13294164357853, 91], [320.43184653782737, 206], [708.7876729994732, 273], [249.39335129378742, 109], [415.0979452328247, 191], [40.02875590396752, 28], [361.59705404494525, 148], [262.1749453642782, 305], [329.18789939826456, 141], [175.82869338035744, 55], [239.16268298953764, 154], [570.1505732399053, 203], [62.62122929135876, 82], [40.97816209812572, 42], [687.2371277772454, 299], [941.6399236184952, 524], [104.05252925393688, 84], [482.3019918213158, 291], [419.51561117497374, 313], [153.03538868182204, 50], [33.11803137090328, 24], [472.19183061192825, 236], [19.97463039953982, 32], [338.56106880549487, 163], [189.34836512854417, 78], [65.80403641705061, 38], [110.70529884751875, 77], [20.377668652577995, 33], [86.84145805422838, 119], [452.3650459933433, 204], [190.26208320752596, 98], [333.55698899754134, 106], [350.5449884042828, 184], [371.82008316454517, 314], [712.5465887177052, 366], [231.82505873226637, 152], [207.78728487991202, 143], [269.7770120118312, 157], [119.52651270573551, 133], [230.5035141410799, 103], [577.9585428201754, 263], [455.93931939463255, 179], [166.68916793139215, 88], [74.03924147699126, 52], [245.12079047897714, 132], [51.254816571725314, 47], [331.9306368750713, 157], [220.85332007716715, 143], [480.8853156922696, 228], [755.3322461044154, 300], [304.4080110256846, 123], [249.71777272994768, 132], [143.70193023237152, 98], [951.1396159437882, 497], [310.44256082023367, 151], [44.772055799268855, 30], [453.63205768890475, 194], [213.37386902498474, 148], [667.7590350853534, 284], [1.5227788082845564, 17], [144.92561455124576, 293], [479.19487820824907, 247], [671.6063901951693, 242], [375.76633044772336, 160], [336.97298572432464, 191], [389.0740713592428, 177], [517.0863897372574, 251], [161.17825796315446, 81], [556.5418576491611, 160], [29.590499692811136, 30], [374.5345178163989, 167], [476.0048803035502, 264], [939.4377741986771, 347], [798.7914759988435, 352], [1064.7221711815564, 446], [1441.817373720478, 506], [129.39345513390072, 160], [420.30603040428286, 263], [16.789344483770037, 78], [81.23201862250426, 22], [317.6669870604983, 142], [50.596186684821305, 38], [1045.0191485694627, 426], [1237.0177098701947, 519], [222.68022357911832, 95], [774.9544389807543, 362], [77.13134800729176, 31], [44.424098503935966, 31], [105.51847657696999, 46], [134.61275649108165, 83], [1051.0797088804593, 454], [1528.561503894913, 493], [52.75156931741367, 50], [275.70625999379536, 120], [704.9982391397161, 289], [354.6142031336967, 112], [1012.1477325227283, 439], [500.9637788548698, 223], [234.78772126642434, 205], [90.91246971053761, 81], [231.48428013618673, 102], [61.0652662579414, 22], [183.5729579432741, 88], [284.4350507112031, 110], [120.95860750451698, 70], [482.22712256656087, 231], [8.030892249536919, 35], [69.06121628523758, 42], [347.6113310731216, 169], [579.8569196759363, 300], [292.51726413345386, 150], [1563.792121907356, 745], [163.27982573871486, 88], [46.70919127221623, 38], [365.95924721632764, 195], [1295.5137375235886, 533], [509.2096041501791, 225], [341.60587365955234, 140], [155.81400130163092, 90], [167.5608145023798, 105], [100.59206648370491, 50], [115.36798727097721, 61], [91.51149169826385, 75], [477.68781874468914, 199], [184.39975518744177, 94], [10.150480241755417, 97], [457.94308337935945, 212], [209.30882769652817, 236], [1081.3151598042605, 447]], "final_state": "tinker://8eaad4366b3e3f1193bc20115d07490d/weights/confirm-baseline_adamw_s2-final", "t": 1793808639.6271796} {"stage": "eval", "arm": "treatment_dimuon_s2", "split": "test", "step": 100, "nll_sum": 197669.33115667003, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0305850384881765, "example_mean": 1.9098447542370276, "per_example": [[128.89272541956507, 55], [1251.9128180856442, 555], [582.5713416335811, 233], [1054.443317816047, 416], [507.5896778312065, 287], [119.78581373176803, 60], [702.5443005016641, 468], [132.77222911952776, 71], [81.80027611627139, 65], [612.3993036827693, 271], [46.58006779719187, 35], [24.656730322463773, 31], [180.09749317189556, 107], [388.084874165128, 112], [9.048606682008199, 11], [240.8421648455913, 86], [130.37582102727353, 105], [439.7011224471824, 407], [185.9622733363285, 132], [723.532639476678, 231], [286.63227531503253, 268], [392.40887420123124, 155], [89.05557586882242, 102], [132.99924660819295, 74], [238.09199440332486, 83], [357.4250355674394, 135], [947.392154454217, 390], [868.9994165549833, 284], [27.99924349646608, 44], [340.95701456409665, 137], [1196.531305842349, 447], [1.4898147567491762, 25], [393.9187870384775, 155], [847.6348947042134, 457], [311.7524549794216, 187], [465.5255360480478, 230], [392.7452696137143, 148], [324.93847663498855, 436], [475.7783589154999, 146], [322.7746247371724, 191], [11.505249928793091, 37], [428.7657416032634, 333], [81.08034180455792, 53], [186.74107462712254, 94], [1077.7581096526028, 521], [320.33431823258763, 175], [130.98428806120228, 79], [53.962343562190625, 19], [2.5669905386936307, 10], [332.36119409218, 208], [310.76394275326663, 156], [221.89072266562926, 160], [1160.4479644972344, 420], [767.0866043841593, 285], [88.88292497184005, 31], [412.65176011581934, 167], [57.14315635880757, 44], [742.7788116244755, 245], [10.215391079358596, 45], [233.21800451097806, 102], [128.1364091684727, 114], [63.51479837128079, 20], [164.64870588687745, 86], [155.31170447417026, 63], [70.04106075708478, 72], [100.69649353154, 66], [144.15961757988862, 101], [100.87662874318264, 48], [67.86071026508921, 25], [64.12078138828599, 26], [64.28403315115384, 64], [223.4415799157864, 72], [378.1836097737205, 342], [320.8261721285212, 123], [364.5542227159617, 314], [114.62815620840888, 68], [70.62683540835133, 58], [209.5561324763412, 106], [202.31445499412618, 81], [323.4704590106845, 181], [286.27251221079587, 312], [640.5879390663349, 302], [1273.2672411366111, 473], [77.0772296137875, 74], [321.43316937836585, 169], [201.88124895793584, 86], [1485.9105502884086, 663], [93.86370583173357, 81], [580.2871994406605, 272], [575.687972352517, 206], [865.0564473524553, 720], [737.0396738355862, 291], [1278.5326248580093, 562], [181.07415344708136, 117], [144.95688848780947, 106], [556.7389110115905, 216], [77.09432202860614, 45], [385.0731102996248, 220], [305.84646903123996, 134], [1179.0148897309173, 454], [85.14390070662739, 57], [199.24104013296528, 101], [70.76722680449163, 22], [135.89935688785613, 74], [629.6823811173963, 294], [414.0248502958052, 150], [546.3356213236711, 203], [366.37865311529094, 166], [719.7277361750066, 262], [116.79938834042684, 52], [485.04916212723356, 181], [33.734606133066336, 37], [1186.6351772939952, 642], [258.27658220701187, 176], [207.80667681535465, 113], [538.9455208950676, 194], [112.8571740424295, 72], [3.687533070131394, 10], [175.44810465539877, 123], [396.211749069007, 141], [328.3337523891955, 117], [1321.9604485747377, 576], [118.32473680973249, 93], [308.50706424656346, 137], [573.0130554428315, 240], [38.18465443961884, 61], [128.09936916039618, 123], [190.30854076889182, 98], [267.4330428463509, 120], [5.045100428233582, 32], [880.1061502392577, 334], [2.4805243616660846, 26], [56.39968538865435, 35], [226.93422301451187, 72], [639.6140251517569, 263], [646.066698162492, 247], [190.22631953721066, 66], [566.7841479849712, 265], [1349.7677427457256, 516], [1212.579018943596, 502], [1393.7412496174604, 492], [300.059048966471, 141], [1421.507660358529, 476], [150.62406556849373, 170], [374.2255859011839, 123], [369.53844148671806, 397], [136.51288804287242, 57], [803.2803412041058, 411], [599.7124375356107, 227], [58.51490031726951, 42], [62.00946990822899, 32], [185.6685910268784, 89], [635.017423229514, 271], [76.7356137385541, 59], [204.72783845801314, 107], [189.6748805052066, 150], [378.17132404344886, 237], [197.82567735342082, 92], [318.5907469981694, 153], [629.8567019410693, 268], [567.9518957611883, 253], [900.0710701256266, 428], [522.2219576442936, 270], [116.04701277165441, 79], [294.3254476553702, 144], [806.3522488795843, 312], [164.5673391912569, 102], [1019.23747461119, 554], [76.9462738272814, 71], [791.4498646353204, 306], [0.9124058796148802, 6], [199.54818191737283, 273], [513.1278150582898, 256], [438.1743061395973, 234], [1346.767762137766, 653], [444.51383875241663, 220], [474.17666094389904, 221], [83.93312029526712, 67], [230.96140180467773, 107], [78.40268124254715, 60], [1111.0510857323989, 517], [89.77075680163307, 66], [408.0551708187486, 185], [31.44884386660482, 47], [215.69778294903608, 138], [39.87908561351924, 37], [710.6230570268043, 372], [3.132443375101502, 11], [163.72191609554267, 69], [1.8287118262232909, 11], [306.90396837437856, 122], [544.7059435356023, 239], [404.97294437744677, 215], [373.44103860878386, 131], [362.7073926494303, 136], [811.689758924767, 241], [293.7387271040361, 145], [345.7827271351971, 226], [1328.812371439053, 548], [26.93944163746073, 38], [421.2932034703481, 170], [73.10571947322728, 27], [601.024088697767, 264], [699.5861360569821, 258], [187.5428747332403, 82], [288.4231810748995, 147], [571.7478222951286, 259], [511.73383568002646, 152], [248.02556182900935, 151], [876.4459224624215, 320], [223.5349810450025, 110], [241.2660662978044, 141], [220.95288167877482, 132], [290.9501035459389, 101], [273.21553748298174, 135], [1295.0394637826357, 629], [212.1324681941569, 241], [765.1672190158815, 492], [796.1036259270828, 304], [1136.572159910638, 404], [8.236429694150502, 17], [297.9345569959603, 138], [386.16267413456626, 141], [259.60939210403694, 161], [201.23091016881511, 125], [1199.034712247208, 639], [615.9254080773799, 315], [190.12302680548146, 102], [49.188476446087634, 25], [817.5216311938657, 386], [310.2541661379446, 153], [445.40596889066893, 518], [545.9622633134618, 219], [192.2532020607414, 121], [897.6584572882571, 613], [429.7152321043468, 204], [608.6568558156482, 273], [143.08716132416782, 75], [859.4672208685733, 373], [917.839985195902, 288], [562.7068071231661, 243], [160.62601593891986, 71], [103.60599225747796, 51], [225.95804599545772, 104], [1341.0603077851092, 748], [516.153717726425, 180], [261.91033165101135, 137], [680.5130005437206, 394], [943.9546689140489, 426], [257.1922279868086, 124], [1.9269262436346253, 16], [148.02649711062986, 49], [253.7997065530783, 216], [20.07180985686273, 68], [8.219300159173144, 12], [640.741951818789, 216], [790.5801063225833, 331], [252.73299080976903, 129], [615.0198610680018, 238], [627.4314486499604, 247], [220.60590910293922, 108], [193.80459977025743, 133], [211.08786100650462, 116], [12.656159831934815, 30], [971.5778134483262, 537], [1224.8497405614298, 557], [1397.3900909237982, 519], [544.4957287362313, 390], [269.7572801464421, 154], [317.7208083197529, 374], [34.47474750693783, 30], [381.33962949550187, 187], [330.08343693408096, 190], [91.74322372491531, 38], [403.955875883286, 167], [147.07663781957717, 127], [646.6926422122337, 290], [1010.8530137762972, 424], [169.17845814054226, 56], [301.2884852857096, 181], [232.97517817391235, 147], [282.0122795606021, 188], [8.768224909493938, 34], [189.2466303135725, 74], [288.02365447297734, 115], [594.1477287109371, 268], [932.5878793748738, 366], [558.0208078023497, 251], [1524.1539436180456, 517], [74.64738160444085, 54], [1228.7897417014383, 488], [572.3742823996809, 217], [271.3785690012937, 109], [293.6235530377229, 282], [1290.1531988635534, 503], [880.1046184684297, 320], [54.45356681293197, 18], [108.93354184228974, 72], [350.2323952395009, 168], [82.90026483153815, 41], [510.3371807520889, 239], [51.088911738784645, 42], [536.9531067624864, 219], [727.5366128008535, 417], [215.12115049933243, 182], [456.7847018044267, 328], [227.08118240228941, 138], [23.843613295418436, 259], [1.3971597359450243, 13], [321.48656571116373, 157], [239.0946539926881, 209], [101.50671162520212, 92], [63.692670491063836, 99], [716.3806205128058, 336], [169.6954347006299, 86], [81.47048636414183, 41], [1151.0256098496543, 405], [456.9460064400437, 259], [53.750355561219976, 22], [781.9915166525823, 336], [246.8459873706524, 65], [239.86679429137985, 73], [206.5645637574239, 108], [339.43186220481164, 166], [227.36991772144574, 237], [18.755749819285484, 35], [635.4866593459349, 483], [153.67146503998265, 110], [41.26362492651788, 48], [290.7915809059268, 371], [1072.0968609390711, 455], [1220.2523786562379, 587], [547.5727060081477, 193], [245.72218457795407, 141], [80.5668795339952, 44], [122.22441873406203, 34], [106.31116661348369, 90], [201.58272040638246, 85], [33.255005443090795, 47], [288.240882171777, 321], [1190.7287665938748, 487], [176.60664990601526, 100], [393.45590586283265, 215], [344.90777697239537, 157], [61.72061949816435, 47], [713.4742891871574, 274], [251.65479422640328, 133], [770.8120320638773, 369], [213.6228482756884, 110], [87.93563568370882, 75], [89.15860706820717, 37], [431.2309791934755, 916], [968.3759089285346, 370], [338.40908050972666, 167], [349.43116990476074, 204], [439.12294767747335, 211], [909.0680025272883, 465], [15.914872277597112, 27], [1318.039373211017, 480], [634.2774282213823, 477], [1603.3887752843168, 580], [212.35771626228188, 147], [45.58126454370722, 59], [195.67336039907696, 60], [47.698496443781096, 42], [33.70711347426413, 58], [58.36792416896719, 25], [23.524101819288262, 36], [82.49527734119329, 24], [1.9561582693103219, 75], [467.7992697603795, 219], [260.7379230988481, 91], [319.52429259818, 206], [708.0331279791632, 273], [251.08015907230856, 109], [412.6835520492459, 191], [40.16277917629327, 28], [362.7226677051949, 148], [261.126790603671, 305], [329.116271199377, 141], [176.67388193856436, 55], [237.77614997089267, 154], [569.1956500714969, 203], [62.18576176207881, 82], [40.75079378789451, 42], [686.1959796163756, 299], [941.208615177703, 524], [105.36888105204434, 84], [479.64760250555025, 291], [419.07382926342325, 313], [152.79669472807814, 50], [34.0451039564274, 24], [469.6094604610606, 236], [19.317290995468284, 32], [341.06755552359573, 163], [187.32568361585572, 78], [65.57222240424014, 38], [110.31485729201813, 77], [19.640229788487886, 33], [86.47049372823398, 119], [454.49734494160657, 204], [189.98349930609857, 98], [332.7642313386332, 106], [348.1347532554755, 184], [371.4878203128569, 314], [713.2013577403668, 366], [230.14915274452233, 152], [205.66132495078273, 143], [270.246675485972, 157], [119.85762463184028, 133], [230.6770523832347, 103], [576.5051541123667, 263], [454.5486599445121, 179], [168.49787174192898, 88], [75.2031450864124, 52], [244.95810456839718, 132], [51.266516011763315, 47], [333.1104720994949, 157], [218.3609249152778, 143], [481.6491760830886, 228], [755.3552952186255, 300], [304.8587016028041, 123], [249.7928019691701, 132], [145.80777805522212, 98], [951.2219994854213, 497], [310.6534265781638, 151], [45.335196599904066, 30], [450.6364288030554, 194], [213.11594856595184, 148], [671.4145919784974, 284], [1.60725402213572, 17], [147.2198323481757, 293], [479.447693973937, 247], [670.2803487193287, 242], [376.0610892546151, 160], [336.53197118766366, 191], [388.4635840403553, 177], [520.7933504974277, 251], [162.80612403604755, 81], [558.4343277260331, 160], [29.758709924330105, 30], [373.8122674280612, 167], [475.1948315442496, 264], [939.1335772818275, 347], [797.7512034349111, 352], [1066.5351376562794, 446], [1445.1562346375813, 506], [128.29031733355623, 160], [420.28649300430664, 263], [17.597019931632502, 78], [81.36102989126806, 22], [319.0391976029432, 142], [51.04053060248222, 38], [1043.7649396970664, 426], [1238.057626806525, 519], [221.2442674819995, 95], [776.0514164906144, 362], [77.67258996067892, 31], [44.48334217856859, 31], [106.8935211547722, 46], [134.66858694910113, 83], [1051.563297372522, 454], [1529.527598030685, 493], [52.66993014537002, 50], [275.13608811204176, 120], [703.2905676928945, 289], [355.37405387208673, 112], [1016.0268561561766, 439], [502.3800856025937, 223], [234.8453454758303, 205], [91.45619100591762, 81], [232.07343452551137, 102], [60.359811125976194, 22], [184.53084498517273, 88], [282.55509600925507, 110], [120.50898095757611, 70], [479.8273201768957, 231], [8.40273161690493, 35], [69.01203020938914, 42], [346.433168615099, 169], [582.149553924045, 300], [292.85462860661164, 150], [1563.3016727108725, 745], [164.65371411184515, 88], [46.55632902135403, 38], [365.05713487115827, 195], [1291.4437001513106, 533], [507.62937762023125, 225], [341.8899812033144, 140], [154.81251578564115, 90], [165.9723429147192, 105], [100.54766943775758, 50], [114.42359385143934, 61], [91.42208578866484, 75], [475.9428921667122, 199], [183.6250709228425, 94], [10.304234950438286, 97], [455.4138031709326, 212], [211.56471744538425, 236], [1079.7610046769314, 447]], "final_state": "tinker://c8db5bb847cd27aaacea58a0dd7561a8/weights/confirm-treatment_dimuon_s2-final", "t": 1793808663.0627074} {"stage": "eval_done", "seconds": 159.3210573196411, "total_seconds": 1176.2616674900055, "t": 1793808663.0632093}