{"stage": "eval_set", "split": "test", "n": 500, "sha256": "77a0f36db82bf06978bcea4d7d139c42367885e890c59d5081516e05bfc7a85a", "t": 1793744404.4754558} {"stage": "get_info", "arm": "baseline_adamw_s0", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744408.5893903} {"stage": "init_saved", "group": "s0", "path": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-init-s0", "by": "baseline_adamw_s0", "t": 1793744412.5856383} {"stage": "initial_output", "arm": "baseline_adamw_s0", "init": "s0", "init_path": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-init-s0", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744413.825305} {"stage": "step0_saved", "arm": "baseline_adamw_s0", "path": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-baseline_adamw_s0-step0", "before_first_update": true, "t": 1793744415.971526} {"stage": "get_info", "arm": "treatment_dimuon_s0", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744418.3774314} {"stage": "get_info", "arm": "treatment_dimuon_s0", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744421.357137} {"stage": "initial_output", "arm": "treatment_dimuon_s0", "init": "s0", "init_path": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-init-s0", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744422.4745653} {"stage": "step0_saved", "arm": "treatment_dimuon_s0", "path": "tinker://d331297013cae43230697585afa80dc5/weights/confirm-treatment_dimuon_s0-step0", "before_first_update": true, "t": 1793744426.2542925} {"stage": "get_info", "arm": "baseline_adamw_s1", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744622.7628226} {"stage": "init_saved", "group": "s1", "path": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-init-s1", "by": "baseline_adamw_s1", "t": 1793744626.9206297} {"stage": "initial_output", "arm": "baseline_adamw_s1", "init": "s1", "init_path": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-init-s1", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744628.3067217} {"stage": "step0_saved", "arm": "baseline_adamw_s1", "path": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-baseline_adamw_s1-step0", "before_first_update": true, "t": 1793744630.860903} {"stage": "get_info", "arm": "treatment_dimuon_s1", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744633.3837776} {"stage": "get_info", "arm": "treatment_dimuon_s1", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744636.335811} {"stage": "initial_output", "arm": "treatment_dimuon_s1", "init": "s1", "init_path": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-init-s1", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744637.5394404} {"stage": "step0_saved", "arm": "treatment_dimuon_s1", "path": "tinker://64eea06e33ba66329c486ce2de950f32/weights/confirm-treatment_dimuon_s1-step0", "before_first_update": true, "t": 1793744645.4029853} {"stage": "get_info", "arm": "baseline_adamw_s2", "restores": 0, "optimizer": "adamw", "config": {"type": "adamw"}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744648.2563035} {"stage": "init_saved", "group": "s2", "path": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-init-s2", "by": "baseline_adamw_s2", "t": 1793744651.9337375} {"stage": "initial_output", "arm": "baseline_adamw_s2", "init": "s2", "init_path": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-init-s2", "restores": 0, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744653.056134} {"stage": "step0_saved", "arm": "baseline_adamw_s2", "path": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-baseline_adamw_s2-step0", "before_first_update": true, "t": 1793744655.2915735} {"stage": "get_info", "arm": "treatment_dimuon_s2", "restores": 0, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744658.145479} {"stage": "get_info", "arm": "treatment_dimuon_s2", "restores": 1, "optimizer": "dimuon", "config": {"type": "dimuon", "version": 1}, "model": "Qwen/Qwen3.5-2B", "rank": 32, "t": 1793744660.8280602} {"stage": "initial_output", "arm": "treatment_dimuon_s2", "init": "s2", "init_path": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-init-s2", "restores": 1, "output_sha256": "6e2313c4c269801a8b9950b4ebee38fbda850114d334dccc1ea46abd084e51bc", "t": 1793744661.93929} {"stage": "step0_saved", "arm": "treatment_dimuon_s2", "path": "tinker://8e9fef4c99e9c1af8d68a14c2c921011/weights/confirm-treatment_dimuon_s2-step0", "before_first_update": true, "t": 1793744667.0141993} {"stage": "setup_done", "seconds": 266.957839012146, "t": 1793744667.015965} {"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": 36.49266052246094, "t": 1793744674.8645368} {"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": 36.4951286315918, "t": 1793744674.8653486} {"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": 29.418821334838867, "t": 1793744674.8747122} {"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": 29.421293258666992, "t": 1793744674.8755887} {"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": 34.991058349609375, "t": 1793744674.8764133} {"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": 34.9885368347168, "t": 1793744675.183827} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "AdamParams", "train_nll_sum": 13542.939050245477, "train_tokens": 6073.0, "train_token_mean_nll": 2.2300245430998644, "grad_norm": 24.581998825073242, "t": 1793744682.7528088} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 2, "batch_sha256": "3296f064265cd171d6ef153d36aa9aedba44197205d849cfbbbe3e4271481643", "params_type": "DimuonParams", "train_nll_sum": 14161.093528812522, "train_tokens": 6073.0, "train_token_mean_nll": 2.3318118769656713, "grad_norm": 49.50038146972656, "t": 1793744682.847975} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 2, "batch_sha256": "50d9810e7139e0ec50571174bb67f2686423197bf607f62b4173c92b192bca56", "params_type": "AdamParams", "train_nll_sum": 17151.342200608524, "train_tokens": 7364.0, "train_token_mean_nll": 2.3290796035590065, "grad_norm": 22.69020652770996, "t": 1793744682.8491025} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 2, "batch_sha256": "50d9810e7139e0ec50571174bb67f2686423197bf607f62b4173c92b192bca56", "params_type": "DimuonParams", "train_nll_sum": 17879.322218129346, "train_tokens": 7364.0, "train_token_mean_nll": 2.42793620561235, "grad_norm": 33.28688049316406, "t": 1793744682.8501654} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 2, "batch_sha256": "4296296b3ce362f8d77ee2d8a3f8e1f567518fdec3382a588b7a0e74d379e4d2", "params_type": "AdamParams", "train_nll_sum": 12184.805690253394, "train_tokens": 5965.0, "train_token_mean_nll": 2.042716796354299, "grad_norm": 36.32072830200195, "t": 1793744682.8511772} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 2, "batch_sha256": "4296296b3ce362f8d77ee2d8a3f8e1f567518fdec3382a588b7a0e74d379e4d2", "params_type": "DimuonParams", "train_nll_sum": 12725.512773152892, "train_tokens": 5965.0, "train_token_mean_nll": 2.133363415448934, "grad_norm": 52.38929748535156, "t": 1793744683.1405268} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "AdamParams", "train_nll_sum": 12367.308679534812, "train_tokens": 5852.0, "train_token_mean_nll": 2.1133473478357505, "grad_norm": 27.299028396606445, "t": 1793744690.227637} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 3, "batch_sha256": "77fb3b738a4c40f7d67a44baad02a344c684d54996c6204b2bff932d85e02fa5", "params_type": "DimuonParams", "train_nll_sum": 13309.616164022356, "train_tokens": 5852.0, "train_token_mean_nll": 2.274370499662057, "grad_norm": 52.498497009277344, "t": 1793744690.228512} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 3, "batch_sha256": "2db342ac8653a81d68a42b9b183fb3b9aed939bb57d0d1bdecac65d6b1181cac", "params_type": "AdamParams", "train_nll_sum": 12756.367387905677, "train_tokens": 5761.0, "train_token_mean_nll": 2.2142626953490154, "grad_norm": 17.374210357666016, "t": 1793744690.4791338} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 3, "batch_sha256": "2db342ac8653a81d68a42b9b183fb3b9aed939bb57d0d1bdecac65d6b1181cac", "params_type": "DimuonParams", "train_nll_sum": 13730.37030918185, "train_tokens": 5761.0, "train_token_mean_nll": 2.3833310725884136, "grad_norm": 30.466920852661133, "t": 1793744690.4801314} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 3, "batch_sha256": "a6c4910fee3391dd40cdcf358d57ba6873eb4e332b80d45b1df01230ae171087", "params_type": "AdamParams", "train_nll_sum": 12110.149891044619, "train_tokens": 6328.0, "train_token_mean_nll": 1.9137405011132458, "grad_norm": 20.186737060546875, "t": 1793744690.4810002} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 3, "batch_sha256": "a6c4910fee3391dd40cdcf358d57ba6873eb4e332b80d45b1df01230ae171087", "params_type": "DimuonParams", "train_nll_sum": 12956.702348326913, "train_tokens": 6328.0, "train_token_mean_nll": 2.0475193344385136, "grad_norm": 33.353851318359375, "t": 1793744690.4819129} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "AdamParams", "train_nll_sum": 16058.121785537422, "train_tokens": 7125.0, "train_token_mean_nll": 2.253771478671919, "grad_norm": 15.187347412109375, "t": 1793744697.3619566} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 4, "batch_sha256": "46bd4e5740056c494799cba789670261f2b9b81a9aef1f85c17067b689fadb38", "params_type": "DimuonParams", "train_nll_sum": 17064.25016152906, "train_tokens": 7125.0, "train_token_mean_nll": 2.3949824788110963, "grad_norm": 29.03801918029785, "t": 1793744697.3649871} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 4, "batch_sha256": "f721be7f9ab8f69c54fad3c79e81a13aede41a5591f61329128dba053380d7b9", "params_type": "AdamParams", "train_nll_sum": 10986.965461087222, "train_tokens": 5212.0, "train_token_mean_nll": 2.1080133271464354, "grad_norm": 17.590620040893555, "t": 1793744697.3662732} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 4, "batch_sha256": "f721be7f9ab8f69c54fad3c79e81a13aede41a5591f61329128dba053380d7b9", "params_type": "DimuonParams", "train_nll_sum": 11684.64894559433, "train_tokens": 5212.0, "train_token_mean_nll": 2.241874318034215, "grad_norm": 33.57367706298828, "t": 1793744697.5328405} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 4, "batch_sha256": "1647d08d8e432294bb570c4a95cf7480267f9c0c779cf74346b683326fad6fc4", "params_type": "AdamParams", "train_nll_sum": 12362.28200257529, "train_tokens": 5785.0, "train_token_mean_nll": 2.136954538042401, "grad_norm": 18.14097023010254, "t": 1793744697.5336218} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 4, "batch_sha256": "1647d08d8e432294bb570c4a95cf7480267f9c0c779cf74346b683326fad6fc4", "params_type": "DimuonParams", "train_nll_sum": 13263.677883384511, "train_tokens": 5785.0, "train_token_mean_nll": 2.292770593497755, "grad_norm": 37.74432373046875, "t": 1793744697.5343184} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "AdamParams", "train_nll_sum": 15769.668828870843, "train_tokens": 6823.0, "train_token_mean_nll": 2.311251477190509, "grad_norm": 16.019004821777344, "t": 1793744704.6319716} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 5, "batch_sha256": "9b135dae1955f2cc352a8ec6e0e1244b7ad16dc0f2f13ddf32bdc05e9cb4e91c", "params_type": "DimuonParams", "train_nll_sum": 16655.279170630325, "train_tokens": 6823.0, "train_token_mean_nll": 2.4410492702081674, "grad_norm": 29.786319732666016, "t": 1793744704.8631477} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 5, "batch_sha256": "664b97e5939bce1b4a840d90b4f260b25fc57a67fe8a41c35788a775b82681c3", "params_type": "AdamParams", "train_nll_sum": 14220.253345146135, "train_tokens": 6654.0, "train_token_mean_nll": 2.1370984889008318, "grad_norm": 13.954855918884277, "t": 1793744704.8639665} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 5, "batch_sha256": "664b97e5939bce1b4a840d90b4f260b25fc57a67fe8a41c35788a775b82681c3", "params_type": "DimuonParams", "train_nll_sum": 15003.559133781655, "train_tokens": 6654.0, "train_token_mean_nll": 2.254818024313444, "grad_norm": 25.523698806762695, "t": 1793744704.8668404} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 5, "batch_sha256": "bea5e8f11e3528d2034c41e890df9f874b18344ab6dc3886bac4e9645e222c63", "params_type": "AdamParams", "train_nll_sum": 11999.766907418969, "train_tokens": 6010.0, "train_token_mean_nll": 1.9966334288550698, "grad_norm": 17.836698532104492, "t": 1793744704.8675892} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 5, "batch_sha256": "bea5e8f11e3528d2034c41e890df9f874b18344ab6dc3886bac4e9645e222c63", "params_type": "DimuonParams", "train_nll_sum": 12806.03765597986, "train_tokens": 6010.0, "train_token_mean_nll": 2.1307882955041366, "grad_norm": 31.31597137451172, "t": 1793744704.870341} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "AdamParams", "train_nll_sum": 13279.416042015644, "train_tokens": 6097.0, "train_token_mean_nll": 2.178024609154608, "grad_norm": 20.53645896911621, "t": 1793744711.6598554} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 6, "batch_sha256": "fc1b0de8d0963e5528308a2fb5c5f8b73ffa7e2e8fa3875db37c9b73bf106e4a", "params_type": "DimuonParams", "train_nll_sum": 13930.942680314918, "train_tokens": 6097.0, "train_token_mean_nll": 2.284884808974072, "grad_norm": 40.09505844116211, "t": 1793744711.82481} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 6, "batch_sha256": "3518b819b1d63dff7d6bb94000852131c68cb7d52b02f898313b56add0be2493", "params_type": "AdamParams", "train_nll_sum": 13369.720253849111, "train_tokens": 6410.0, "train_token_mean_nll": 2.085759789992061, "grad_norm": 15.104833602905273, "t": 1793744711.8255959} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 6, "batch_sha256": "3518b819b1d63dff7d6bb94000852131c68cb7d52b02f898313b56add0be2493", "params_type": "DimuonParams", "train_nll_sum": 14202.930463491997, "train_tokens": 6410.0, "train_token_mean_nll": 2.215745782136037, "grad_norm": 30.815711975097656, "t": 1793744711.8293467} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 6, "batch_sha256": "0c3ad9f926b09e5f4914db7a0518ac86cb66fdfca48ee01344c08119d3fe618b", "params_type": "AdamParams", "train_nll_sum": 10909.44238543174, "train_tokens": 5732.0, "train_token_mean_nll": 1.903252335211399, "grad_norm": 16.93305206298828, "t": 1793744712.5298471} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 6, "batch_sha256": "0c3ad9f926b09e5f4914db7a0518ac86cb66fdfca48ee01344c08119d3fe618b", "params_type": "DimuonParams", "train_nll_sum": 11581.463371833777, "train_tokens": 5732.0, "train_token_mean_nll": 2.020492563125223, "grad_norm": 34.73917770385742, "t": 1793744712.5307262} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "AdamParams", "train_nll_sum": 12952.114050278591, "train_tokens": 6602.0, "train_token_mean_nll": 1.9618470236714012, "grad_norm": 15.052960395812988, "t": 1793744720.2385168} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 7, "batch_sha256": "d57e02d9d29e010284ca2f8853090d30dfcc284445165e3559525fa5b526b551", "params_type": "DimuonParams", "train_nll_sum": 13647.92014549872, "train_tokens": 6602.0, "train_token_mean_nll": 2.0672402522718447, "grad_norm": 27.182477951049805, "t": 1793744720.3881106} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 7, "batch_sha256": "35dbaf237d42fbc446db7b993bd8883bc7af7c74b6ceae19ec46571aff5808dc", "params_type": "AdamParams", "train_nll_sum": 14675.111880244605, "train_tokens": 6319.0, "train_token_mean_nll": 2.3223788384625106, "grad_norm": 13.527006149291992, "t": 1793744720.3964465} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 7, "batch_sha256": "35dbaf237d42fbc446db7b993bd8883bc7af7c74b6ceae19ec46571aff5808dc", "params_type": "DimuonParams", "train_nll_sum": 15444.372018855056, "train_tokens": 6319.0, "train_token_mean_nll": 2.44411647710952, "grad_norm": 27.103986740112305, "t": 1793744720.397711} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 7, "batch_sha256": "208b68c215448bd900070c92b94743060495eff9af76b7a908c9d612edc71cdb", "params_type": "AdamParams", "train_nll_sum": 14335.192155507471, "train_tokens": 6270.0, "train_token_mean_nll": 2.2863145383584484, "grad_norm": 16.779407501220703, "t": 1793744720.399249} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 7, "batch_sha256": "208b68c215448bd900070c92b94743060495eff9af76b7a908c9d612edc71cdb", "params_type": "DimuonParams", "train_nll_sum": 14848.227020755394, "train_tokens": 6270.0, "train_token_mean_nll": 2.3681382808222318, "grad_norm": 29.94677734375, "t": 1793744720.4002123} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "AdamParams", "train_nll_sum": 13573.14020957469, "train_tokens": 6404.0, "train_token_mean_nll": 2.119478483693737, "grad_norm": 15.03809642791748, "t": 1793744727.507248} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 8, "batch_sha256": "03e80a43582a3d998270df521b0cba46f0e056e234391ff434f7bb42117e760f", "params_type": "DimuonParams", "train_nll_sum": 14110.955711179695, "train_tokens": 6404.0, "train_token_mean_nll": 2.20345966757959, "grad_norm": 30.24681854248047, "t": 1793744727.5246935} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 8, "batch_sha256": "09e5894dc0399de6706a0e11975888debedfe108acedecb4cc135deecf689875", "params_type": "AdamParams", "train_nll_sum": 13512.637421666368, "train_tokens": 5930.0, "train_token_mean_nll": 2.278690964867853, "grad_norm": 15.477513313293457, "t": 1793744727.5442386} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 8, "batch_sha256": "09e5894dc0399de6706a0e11975888debedfe108acedecb4cc135deecf689875", "params_type": "DimuonParams", "train_nll_sum": 14072.541122938288, "train_tokens": 5930.0, "train_token_mean_nll": 2.3731098015073, "grad_norm": 33.635135650634766, "t": 1793744727.5482824} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 8, "batch_sha256": "5bd1bfcb3aed30a8c5da6e8f49183bacee46f6b61b0181bb2eae5a0db0aa7625", "params_type": "AdamParams", "train_nll_sum": 16313.943531216168, "train_tokens": 7756.0, "train_token_mean_nll": 2.103396535742157, "grad_norm": 11.609435081481934, "t": 1793744727.5505657} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 8, "batch_sha256": "5bd1bfcb3aed30a8c5da6e8f49183bacee46f6b61b0181bb2eae5a0db0aa7625", "params_type": "DimuonParams", "train_nll_sum": 16994.914099299025, "train_tokens": 7756.0, "train_token_mean_nll": 2.1911957322458773, "grad_norm": 22.932403564453125, "t": 1793744727.6859903} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "AdamParams", "train_nll_sum": 10705.073681139816, "train_tokens": 5225.0, "train_token_mean_nll": 2.0488179294047497, "grad_norm": 14.84705638885498, "t": 1793744733.6650324} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 9, "batch_sha256": "62219431231071a6320c4819814bd30d49a77c7724469f60d578e381989f1a82", "params_type": "DimuonParams", "train_nll_sum": 11145.58248836834, "train_tokens": 5225.0, "train_token_mean_nll": 2.133125835094419, "grad_norm": 29.779075622558594, "t": 1793744733.677877} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 9, "batch_sha256": "c01c0297794b714d3c768f53d99206463d0ee1c7cd358f38989413163be584b4", "params_type": "AdamParams", "train_nll_sum": 12286.80699050422, "train_tokens": 6087.0, "train_token_mean_nll": 2.018532444636803, "grad_norm": 14.48622989654541, "t": 1793744733.6788101} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 9, "batch_sha256": "c01c0297794b714d3c768f53d99206463d0ee1c7cd358f38989413163be584b4", "params_type": "DimuonParams", "train_nll_sum": 12760.574412522446, "train_tokens": 6087.0, "train_token_mean_nll": 2.0963651080207732, "grad_norm": 25.369375228881836, "t": 1793744733.682851} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 9, "batch_sha256": "ea39bae2e59a90515aec49ba63d547b342512eb78440cd14db1f6f21beac4eb6", "params_type": "AdamParams", "train_nll_sum": 14214.061212960985, "train_tokens": 6743.0, "train_token_mean_nll": 2.1079728923270036, "grad_norm": 12.75426197052002, "t": 1793744733.6838486} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 9, "batch_sha256": "ea39bae2e59a90515aec49ba63d547b342512eb78440cd14db1f6f21beac4eb6", "params_type": "DimuonParams", "train_nll_sum": 14793.37377276895, "train_tokens": 6743.0, "train_token_mean_nll": 2.1938860704091576, "grad_norm": 24.439838409423828, "t": 1793744734.2532277} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "AdamParams", "train_nll_sum": 14493.295187563099, "train_tokens": 7976.0, "train_token_mean_nll": 1.817113238159867, "grad_norm": 13.459924697875977, "t": 1793744741.7731252} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 10, "batch_sha256": "2c79f8c73c12ee2806fc6145bcf11dce79a36540006128fb4958b43ab300686b", "params_type": "DimuonParams", "train_nll_sum": 14957.30773793385, "train_tokens": 7976.0, "train_token_mean_nll": 1.8752893352474738, "grad_norm": 21.818857192993164, "t": 1793744742.0108194} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 10, "batch_sha256": "d4b822a4a3f019be6db05b832270b68fcb610684c5421970715c23882b885b63", "params_type": "AdamParams", "train_nll_sum": 12243.549978637431, "train_tokens": 6005.0, "train_token_mean_nll": 2.038892585951279, "grad_norm": 14.549909591674805, "t": 1793744742.012186} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 10, "batch_sha256": "d4b822a4a3f019be6db05b832270b68fcb610684c5421970715c23882b885b63", "params_type": "DimuonParams", "train_nll_sum": 12628.288509393684, "train_tokens": 6005.0, "train_token_mean_nll": 2.10296228299645, "grad_norm": 25.55936050415039, "t": 1793744742.0129848} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 10, "batch_sha256": "d86636715c462840fcf022632729d33f1ddb20fb80e87702da7ed1fe5d526723", "params_type": "AdamParams", "train_nll_sum": 12391.06061915845, "train_tokens": 6039.0, "train_token_mean_nll": 2.051839811087672, "grad_norm": 15.198826789855957, "t": 1793744742.0137806} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 10, "batch_sha256": "d86636715c462840fcf022632729d33f1ddb20fb80e87702da7ed1fe5d526723", "params_type": "DimuonParams", "train_nll_sum": 12821.948899844552, "train_tokens": 6039.0, "train_token_mean_nll": 2.1231907434748387, "grad_norm": 23.17941665649414, "t": 1793744742.0145571} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "AdamParams", "train_nll_sum": 10234.800394356713, "train_tokens": 5826.0, "train_token_mean_nll": 1.7567456907581038, "grad_norm": 14.784461975097656, "t": 1793744748.880499} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 11, "batch_sha256": "7a9a3c4b7dadadb157ad4fe8a589b604214073bcdc3d4561d2caf6ada0e8899e", "params_type": "DimuonParams", "train_nll_sum": 10504.621017194371, "train_tokens": 5826.0, "train_token_mean_nll": 1.8030588769643616, "grad_norm": 20.463502883911133, "t": 1793744748.8822513} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 11, "batch_sha256": "fdafeb58ece6d6612065223f0d70874c13bab7412fec68406df5061b1e269afd", "params_type": "AdamParams", "train_nll_sum": 13407.628039299312, "train_tokens": 6275.0, "train_token_mean_nll": 2.136673791123396, "grad_norm": 12.71263599395752, "t": 1793744748.8830667} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 11, "batch_sha256": "fdafeb58ece6d6612065223f0d70874c13bab7412fec68406df5061b1e269afd", "params_type": "DimuonParams", "train_nll_sum": 13814.190033559013, "train_tokens": 6275.0, "train_token_mean_nll": 2.201464547180719, "grad_norm": 24.983074188232422, "t": 1793744748.8838315} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 11, "batch_sha256": "d47fc04c014ee56646778ed8fee8639fe096625feac016599668fd13125cc75b", "params_type": "AdamParams", "train_nll_sum": 12201.507078615738, "train_tokens": 5544.0, "train_token_mean_nll": 2.200849040154354, "grad_norm": 16.656728744506836, "t": 1793744748.9694118} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 11, "batch_sha256": "d47fc04c014ee56646778ed8fee8639fe096625feac016599668fd13125cc75b", "params_type": "DimuonParams", "train_nll_sum": 12584.125612222475, "train_tokens": 5544.0, "train_token_mean_nll": 2.269863927168556, "grad_norm": 23.6632022857666, "t": 1793744748.970173} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "AdamParams", "train_nll_sum": 13001.980488037554, "train_tokens": 6074.0, "train_token_mean_nll": 2.140596063226466, "grad_norm": 15.275980949401855, "t": 1793744755.285527} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 12, "batch_sha256": "55a1f97387ed5d71d917089d541f48bdaa66f535eaae09ee38a668d09976c092", "params_type": "DimuonParams", "train_nll_sum": 13259.268828573377, "train_tokens": 6074.0, "train_token_mean_nll": 2.182955026106911, "grad_norm": 19.493864059448242, "t": 1793744755.2937922} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 12, "batch_sha256": "0cd0deb0bce10bc07bff8a5c4a7d37e4799794ee2bc407de243dcbd6a0212b4e", "params_type": "AdamParams", "train_nll_sum": 13479.02300910784, "train_tokens": 6439.0, "train_token_mean_nll": 2.0933410481608696, "grad_norm": 14.102581024169922, "t": 1793744755.2959342} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 12, "batch_sha256": "0cd0deb0bce10bc07bff8a5c4a7d37e4799794ee2bc407de243dcbd6a0212b4e", "params_type": "DimuonParams", "train_nll_sum": 13758.794186729874, "train_tokens": 6439.0, "train_token_mean_nll": 2.1367905244183683, "grad_norm": 16.982994079589844, "t": 1793744755.2967577} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 12, "batch_sha256": "ddbcb9d52ea63bd8f116a9702b9cb6fcd512ffaa97cbc81dcc8e8904b4548fc1", "params_type": "AdamParams", "train_nll_sum": 10618.133554227632, "train_tokens": 5308.0, "train_token_mean_nll": 2.000401950683427, "grad_norm": 14.369380950927734, "t": 1793744755.3005214} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 12, "batch_sha256": "ddbcb9d52ea63bd8f116a9702b9cb6fcd512ffaa97cbc81dcc8e8904b4548fc1", "params_type": "DimuonParams", "train_nll_sum": 10960.588666880982, "train_tokens": 5308.0, "train_token_mean_nll": 2.064918739050675, "grad_norm": 20.320425033569336, "t": 1793744755.3012073} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "AdamParams", "train_nll_sum": 10638.9676916345, "train_tokens": 5144.0, "train_token_mean_nll": 2.068228555916505, "grad_norm": 17.328767776489258, "t": 1793744761.973648} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 13, "batch_sha256": "c5afab1caded3915cf5ba67a9af2aa943a2756983fcf570c9f022f33c1320f4c", "params_type": "DimuonParams", "train_nll_sum": 10892.112215864872, "train_tokens": 5144.0, "train_token_mean_nll": 2.117440166381196, "grad_norm": 20.355712890625, "t": 1793744761.9765742} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 13, "batch_sha256": "4423e1e3a317c841cb928c4929bb731d0920644e6c3f753b2a9e023ac9ab38b7", "params_type": "AdamParams", "train_nll_sum": 8164.105611538828, "train_tokens": 5083.0, "train_token_mean_nll": 1.6061588848197577, "grad_norm": 19.101449966430664, "t": 1793744761.977507} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 13, "batch_sha256": "4423e1e3a317c841cb928c4929bb731d0920644e6c3f753b2a9e023ac9ab38b7", "params_type": "DimuonParams", "train_nll_sum": 8360.395911322697, "train_tokens": 5083.0, "train_token_mean_nll": 1.6447759022865822, "grad_norm": 21.913076400756836, "t": 1793744761.9814818} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 13, "batch_sha256": "4d47bc552e47814dea16e7defd1726fb0d4fb8d532e51ac2b9dad13a727befab", "params_type": "AdamParams", "train_nll_sum": 11937.506236096442, "train_tokens": 5894.0, "train_token_mean_nll": 2.025365835781548, "grad_norm": 14.83884334564209, "t": 1793744761.982407} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 13, "batch_sha256": "4d47bc552e47814dea16e7defd1726fb0d4fb8d532e51ac2b9dad13a727befab", "params_type": "DimuonParams", "train_nll_sum": 12196.587162734962, "train_tokens": 5894.0, "train_token_mean_nll": 2.0693225589981274, "grad_norm": 20.854494094848633, "t": 1793744761.9854534} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "AdamParams", "train_nll_sum": 10500.962174086957, "train_tokens": 4753.0, "train_token_mean_nll": 2.209333510222377, "grad_norm": 16.545351028442383, "t": 1793744768.8814454} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 14, "batch_sha256": "3d6ef01f9b643d5006158c757015d5abb6ae450a20239f6ef6f8d79e272f3666", "params_type": "DimuonParams", "train_nll_sum": 10735.22222748364, "train_tokens": 4753.0, "train_token_mean_nll": 2.2586202877095816, "grad_norm": 20.50674819946289, "t": 1793744768.9690592} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 14, "batch_sha256": "aa7752ed07735b56cf0c4c339590b15cb1bfd240f46c0444b72245147624dd3a", "params_type": "AdamParams", "train_nll_sum": 9713.861363028198, "train_tokens": 4931.0, "train_token_mean_nll": 1.9699576887098353, "grad_norm": 17.49318504333496, "t": 1793744768.977451} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 14, "batch_sha256": "aa7752ed07735b56cf0c4c339590b15cb1bfd240f46c0444b72245147624dd3a", "params_type": "DimuonParams", "train_nll_sum": 9924.148685837465, "train_tokens": 4931.0, "train_token_mean_nll": 2.012603667782897, "grad_norm": 20.93214988708496, "t": 1793744769.1454494} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 14, "batch_sha256": "b2bbfb7b0c1c3b67b120d25bb4dade56026cfe54b3675a187bdd0b6d449cc152", "params_type": "AdamParams", "train_nll_sum": 14884.713998568535, "train_tokens": 7087.0, "train_token_mean_nll": 2.1002841821036453, "grad_norm": 15.726339340209961, "t": 1793744769.1464682} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 14, "batch_sha256": "b2bbfb7b0c1c3b67b120d25bb4dade56026cfe54b3675a187bdd0b6d449cc152", "params_type": "DimuonParams", "train_nll_sum": 15123.326871654728, "train_tokens": 7087.0, "train_token_mean_nll": 2.133953276655105, "grad_norm": 17.604185104370117, "t": 1793744769.1474187} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "AdamParams", "train_nll_sum": 13888.830980091374, "train_tokens": 6492.0, "train_token_mean_nll": 2.1393763062371187, "grad_norm": 11.561424255371094, "t": 1793744775.5515695} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 15, "batch_sha256": "9678303031296c5d71c9e603712e5968c3bc3a8f2c41eb6501ecfa4ef84301e6", "params_type": "DimuonParams", "train_nll_sum": 14188.80392968251, "train_tokens": 6492.0, "train_token_mean_nll": 2.1855828603947183, "grad_norm": 15.134860038757324, "t": 1793744775.5524228} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 15, "batch_sha256": "3a2e7dd389accb68efa700655bd64767cde1ba73660f5de804de1d3caf6e8c26", "params_type": "AdamParams", "train_nll_sum": 9333.646097322919, "train_tokens": 4025.0, "train_token_mean_nll": 2.3189182850491723, "grad_norm": 18.953166961669922, "t": 1793744775.5530071} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 15, "batch_sha256": "3a2e7dd389accb68efa700655bd64767cde1ba73660f5de804de1d3caf6e8c26", "params_type": "DimuonParams", "train_nll_sum": 9451.030159288535, "train_tokens": 4025.0, "train_token_mean_nll": 2.348082027152431, "grad_norm": 21.01995277404785, "t": 1793744775.5535688} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 15, "batch_sha256": "7c8d69ae74171bd47517682cf751adff52070c502e3fb972333422746e92bf13", "params_type": "AdamParams", "train_nll_sum": 12592.579851556326, "train_tokens": 6778.0, "train_token_mean_nll": 1.8578607039770323, "grad_norm": 13.87459659576416, "t": 1793744775.5542529} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 15, "batch_sha256": "7c8d69ae74171bd47517682cf751adff52070c502e3fb972333422746e92bf13", "params_type": "DimuonParams", "train_nll_sum": 12757.024164858256, "train_tokens": 6778.0, "train_token_mean_nll": 1.8821221842517344, "grad_norm": 17.143936157226562, "t": 1793744775.5549238} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "AdamParams", "train_nll_sum": 14228.731356796696, "train_tokens": 7021.0, "train_token_mean_nll": 2.02659611975455, "grad_norm": 14.982884407043457, "t": 1793744782.301625} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 16, "batch_sha256": "955e23c50cb1564b322c0af7cddf92ebc95f902e48cdc45e2cc2c66dd26b7e2e", "params_type": "DimuonParams", "train_nll_sum": 14427.738517370679, "train_tokens": 7021.0, "train_token_mean_nll": 2.054940680440205, "grad_norm": 17.307981491088867, "t": 1793744782.334501} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 16, "batch_sha256": "7f2e4a214ff2c0c95a557bc04375287e34bf3802d513b23d68f86f098c69fed3", "params_type": "AdamParams", "train_nll_sum": 11862.779662321394, "train_tokens": 5540.0, "train_token_mean_nll": 2.1412959679280497, "grad_norm": 13.98622989654541, "t": 1793744782.336761} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 16, "batch_sha256": "7f2e4a214ff2c0c95a557bc04375287e34bf3802d513b23d68f86f098c69fed3", "params_type": "DimuonParams", "train_nll_sum": 12008.373121058814, "train_tokens": 5540.0, "train_token_mean_nll": 2.167576375642385, "grad_norm": 16.895864486694336, "t": 1793744782.337572} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 16, "batch_sha256": "6fb7db5c5b1c64fc5265dd2a612ddab163046f5079d43ee4b57ab775be873efc", "params_type": "AdamParams", "train_nll_sum": 11249.740018058, "train_tokens": 5632.0, "train_token_mean_nll": 1.9974680429790483, "grad_norm": 14.23918342590332, "t": 1793744782.3416867} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 16, "batch_sha256": "6fb7db5c5b1c64fc5265dd2a612ddab163046f5079d43ee4b57ab775be873efc", "params_type": "DimuonParams", "train_nll_sum": 11411.811683623378, "train_tokens": 5632.0, "train_token_mean_nll": 2.026244972234265, "grad_norm": 17.48583221435547, "t": 1793744782.3426356} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "AdamParams", "train_nll_sum": 13633.352978996569, "train_tokens": 6222.0, "train_token_mean_nll": 2.1911528413687833, "grad_norm": 14.878304481506348, "t": 1793744789.3748355} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 17, "batch_sha256": "4fa0cd41078486e0102f53d07491ef951bde45293095bd7a56f810ed33d52dfb", "params_type": "DimuonParams", "train_nll_sum": 13745.288332053708, "train_tokens": 6222.0, "train_token_mean_nll": 2.209143094190567, "grad_norm": 16.153898239135742, "t": 1793744789.3756301} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 17, "batch_sha256": "26861da4cd0ccc024108c0d89731e307706c8e6dd91c071b2ac2ef5d47fcc390", "params_type": "AdamParams", "train_nll_sum": 15724.802000311764, "train_tokens": 7278.0, "train_token_mean_nll": 2.160593844505601, "grad_norm": 15.842449188232422, "t": 1793744789.7196708} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 17, "batch_sha256": "26861da4cd0ccc024108c0d89731e307706c8e6dd91c071b2ac2ef5d47fcc390", "params_type": "DimuonParams", "train_nll_sum": 15948.065952129886, "train_tokens": 7278.0, "train_token_mean_nll": 2.191270397379759, "grad_norm": 14.669234275817871, "t": 1793744789.720812} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 17, "batch_sha256": "94ede2a87189f21723e09b068412dea94fd5727bb0c19c1a9a04afef6bea6c5c", "params_type": "AdamParams", "train_nll_sum": 12555.008217061832, "train_tokens": 6431.0, "train_token_mean_nll": 1.9522637563461098, "grad_norm": 17.983198165893555, "t": 1793744789.7257123} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 17, "batch_sha256": "94ede2a87189f21723e09b068412dea94fd5727bb0c19c1a9a04afef6bea6c5c", "params_type": "DimuonParams", "train_nll_sum": 12781.770376819231, "train_tokens": 6431.0, "train_token_mean_nll": 1.987524549342129, "grad_norm": 20.398529052734375, "t": 1793744789.7266107} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "AdamParams", "train_nll_sum": 11782.264267489483, "train_tokens": 5713.0, "train_token_mean_nll": 2.062360277873181, "grad_norm": 15.591710090637207, "t": 1793744797.0788} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 18, "batch_sha256": "ca58c7d2dd5d28b37bf96f44cac71137c5cb43342b86de0bea9b435824b29360", "params_type": "DimuonParams", "train_nll_sum": 11992.905681281702, "train_tokens": 5713.0, "train_token_mean_nll": 2.0992308211590585, "grad_norm": 19.3336238861084, "t": 1793744797.2151587} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 18, "batch_sha256": "a107ac6f23ac22babc3d7f6b1141ce15f5213599cb252f9000d39ffbfe03bb5a", "params_type": "AdamParams", "train_nll_sum": 11379.586337711127, "train_tokens": 5378.0, "train_token_mean_nll": 2.1159513457997634, "grad_norm": 16.669015884399414, "t": 1793744797.216022} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 18, "batch_sha256": "a107ac6f23ac22babc3d7f6b1141ce15f5213599cb252f9000d39ffbfe03bb5a", "params_type": "DimuonParams", "train_nll_sum": 11533.808303013191, "train_tokens": 5378.0, "train_token_mean_nll": 2.144627798998362, "grad_norm": 18.709585189819336, "t": 1793744797.4742863} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 18, "batch_sha256": "40bb127b4698166381926adbca87a57c25c0ba6d372723ceab0d4be586f022f3", "params_type": "AdamParams", "train_nll_sum": 12586.128012346195, "train_tokens": 6227.0, "train_token_mean_nll": 2.021218566299373, "grad_norm": 12.35844898223877, "t": 1793744797.4753933} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 18, "batch_sha256": "40bb127b4698166381926adbca87a57c25c0ba6d372723ceab0d4be586f022f3", "params_type": "DimuonParams", "train_nll_sum": 12710.894023906196, "train_tokens": 6227.0, "train_token_mean_nll": 2.041254861716107, "grad_norm": 14.74113655090332, "t": 1793744797.7771134} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "AdamParams", "train_nll_sum": 12790.152815268357, "train_tokens": 6187.0, "train_token_mean_nll": 2.067262455999411, "grad_norm": 13.36772346496582, "t": 1793744804.288001} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 19, "batch_sha256": "0d5a61c753b25f4ce6f6faf0e90eb1b3639a0e6b3f2b9a0a3ac0252a6bb164c5", "params_type": "DimuonParams", "train_nll_sum": 12917.826982273451, "train_tokens": 6187.0, "train_token_mean_nll": 2.087898332353879, "grad_norm": 15.557781219482422, "t": 1793744804.2888348} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 19, "batch_sha256": "c76d31a2c124cb095fdb5fbabb4c535f52c0f96574554f03ae070386e37047ac", "params_type": "AdamParams", "train_nll_sum": 10983.349877296116, "train_tokens": 5041.0, "train_token_mean_nll": 2.1788037844269224, "grad_norm": 16.346359252929688, "t": 1793744804.396433} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 19, "batch_sha256": "c76d31a2c124cb095fdb5fbabb4c535f52c0f96574554f03ae070386e37047ac", "params_type": "DimuonParams", "train_nll_sum": 11163.495761269565, "train_tokens": 5041.0, "train_token_mean_nll": 2.214539924869979, "grad_norm": 19.709043502807617, "t": 1793744804.4275908} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 19, "batch_sha256": "dffa2501a13c2c9fe6911d2218f77792b9892b0472e1b3af56c4bb29f55228ae", "params_type": "AdamParams", "train_nll_sum": 13814.938417095565, "train_tokens": 6188.0, "train_token_mean_nll": 2.2325369129113715, "grad_norm": 14.245837211608887, "t": 1793744804.428323} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 19, "batch_sha256": "dffa2501a13c2c9fe6911d2218f77792b9892b0472e1b3af56c4bb29f55228ae", "params_type": "DimuonParams", "train_nll_sum": 13992.436167712263, "train_tokens": 6188.0, "train_token_mean_nll": 2.2612211001474245, "grad_norm": 17.521377563476562, "t": 1793744804.4290354} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "AdamParams", "train_nll_sum": 15087.329604921551, "train_tokens": 6765.0, "train_token_mean_nll": 2.2302039327304586, "grad_norm": 12.380341529846191, "t": 1793744812.2485917} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 20, "batch_sha256": "43422eff988b4d1a9a512af3b37e31eae93838623e7bae048419236f51d17e3c", "params_type": "DimuonParams", "train_nll_sum": 15276.148506148018, "train_tokens": 6765.0, "train_token_mean_nll": 2.2581150785141193, "grad_norm": 14.932745933532715, "t": 1793744812.2495072} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 20, "batch_sha256": "9faf371ccb1bf94db32b7b9b2cc23fd53bdedf7dbc9a9bc6538e7da8deb64c18", "params_type": "AdamParams", "train_nll_sum": 14074.000779278676, "train_tokens": 6592.0, "train_token_mean_nll": 2.135012254138149, "grad_norm": 12.251794815063477, "t": 1793744812.2897549} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 20, "batch_sha256": "9faf371ccb1bf94db32b7b9b2cc23fd53bdedf7dbc9a9bc6538e7da8deb64c18", "params_type": "DimuonParams", "train_nll_sum": 14216.81382846363, "train_tokens": 6592.0, "train_token_mean_nll": 2.15667685504606, "grad_norm": 14.014068603515625, "t": 1793744812.290694} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 20, "batch_sha256": "549ac0dbf8e211188ac19f5d08cf14f600894fb80e0f6d6fe3316549d7459aa7", "params_type": "AdamParams", "train_nll_sum": 11078.927933428038, "train_tokens": 5851.0, "train_token_mean_nll": 1.8935101578239681, "grad_norm": 15.521048545837402, "t": 1793744812.2914588} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 20, "batch_sha256": "549ac0dbf8e211188ac19f5d08cf14f600894fb80e0f6d6fe3316549d7459aa7", "params_type": "DimuonParams", "train_nll_sum": 11220.294562310923, "train_tokens": 5851.0, "train_token_mean_nll": 1.9176712634269224, "grad_norm": 19.497451782226562, "t": 1793744812.5193229} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "AdamParams", "train_nll_sum": 12080.486322856155, "train_tokens": 5786.0, "train_token_mean_nll": 2.0878821850771097, "grad_norm": 16.026317596435547, "t": 1793744818.2278807} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 21, "batch_sha256": "17a809b119e3bedd9ef0f79092d05334499024a409c4d30039a688cc6945db18", "params_type": "DimuonParams", "train_nll_sum": 12175.957076820074, "train_tokens": 5786.0, "train_token_mean_nll": 2.1043824882163973, "grad_norm": 19.23750877380371, "t": 1793744818.228694} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 21, "batch_sha256": "2c846678f04d4fb796bea82f40b1c860287b8a9b121e6e1a8a1204124c0b8d43", "params_type": "AdamParams", "train_nll_sum": 12593.655324721181, "train_tokens": 5935.0, "train_token_mean_nll": 2.121930130534319, "grad_norm": 15.95445728302002, "t": 1793744818.2295287} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 21, "batch_sha256": "2c846678f04d4fb796bea82f40b1c860287b8a9b121e6e1a8a1204124c0b8d43", "params_type": "DimuonParams", "train_nll_sum": 12730.987410545888, "train_tokens": 5935.0, "train_token_mean_nll": 2.145069487876308, "grad_norm": 19.218955993652344, "t": 1793744819.1730924} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 21, "batch_sha256": "3e1541a82d312b97698cf3b601d7c9605881f4bbaffeaff8a980c9d8690e713d", "params_type": "AdamParams", "train_nll_sum": 14378.198683741164, "train_tokens": 6780.0, "train_token_mean_nll": 2.1206782719382247, "grad_norm": 12.86996078491211, "t": 1793744819.1749444} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 21, "batch_sha256": "3e1541a82d312b97698cf3b601d7c9605881f4bbaffeaff8a980c9d8690e713d", "params_type": "DimuonParams", "train_nll_sum": 14623.409571344882, "train_tokens": 6780.0, "train_token_mean_nll": 2.156845069519894, "grad_norm": 16.846282958984375, "t": 1793744819.1758316} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "AdamParams", "train_nll_sum": 10647.613373896556, "train_tokens": 4783.0, "train_token_mean_nll": 2.2261370215129745, "grad_norm": 14.188185691833496, "t": 1793744848.4487076} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 22, "batch_sha256": "ae1f260d9025b66345714b4485363537d166a7bd000b244c7f4a577957957439", "params_type": "DimuonParams", "train_nll_sum": 10759.773149747221, "train_tokens": 4783.0, "train_token_mean_nll": 2.2495866923995864, "grad_norm": 17.408571243286133, "t": 1793744848.4497383} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 22, "batch_sha256": "4ca082b2732b5b72116083a4ecf1a7909fb87b24b99f7ce5f2434aace8550e20", "params_type": "AdamParams", "train_nll_sum": 13988.188393059485, "train_tokens": 6488.0, "train_token_mean_nll": 2.156009308424705, "grad_norm": 12.139153480529785, "t": 1793744848.4504886} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 22, "batch_sha256": "4ca082b2732b5b72116083a4ecf1a7909fb87b24b99f7ce5f2434aace8550e20", "params_type": "DimuonParams", "train_nll_sum": 14172.8285271786, "train_tokens": 6488.0, "train_token_mean_nll": 2.184468022068218, "grad_norm": 14.349724769592285, "t": 1793744848.451209} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 22, "batch_sha256": "631e9fc53beefaa4bb4a57ff58ee2a4cbc3c9e9bfd52cdd07de2cead5be6b596", "params_type": "AdamParams", "train_nll_sum": 13500.554570798231, "train_tokens": 6759.0, "train_token_mean_nll": 1.9974189333922518, "grad_norm": 13.212099075317383, "t": 1793744848.4520383} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 22, "batch_sha256": "631e9fc53beefaa4bb4a57ff58ee2a4cbc3c9e9bfd52cdd07de2cead5be6b596", "params_type": "DimuonParams", "train_nll_sum": 13675.165670872304, "train_tokens": 6759.0, "train_token_mean_nll": 2.0232527993597134, "grad_norm": 16.00263786315918, "t": 1793744848.720796} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "AdamParams", "train_nll_sum": 15394.366272813106, "train_tokens": 7466.0, "train_token_mean_nll": 2.0619295838217395, "grad_norm": 12.075847625732422, "t": 1793744855.3586376} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 23, "batch_sha256": "d1964f2f271f51c3347b3b064a87d93a7fca0b7427069145fec82c490e820ab7", "params_type": "DimuonParams", "train_nll_sum": 15500.64980598236, "train_tokens": 7466.0, "train_token_mean_nll": 2.076165256627694, "grad_norm": 14.660655975341797, "t": 1793744855.3596127} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 23, "batch_sha256": "f7eb5328998ed2d1f45d2cb6f01cfca2decf6c21fb815fe1048d0dd9516edf04", "params_type": "AdamParams", "train_nll_sum": 15038.00668546233, "train_tokens": 7322.0, "train_token_mean_nll": 2.053811347372621, "grad_norm": 9.892936706542969, "t": 1793744855.3623233} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 23, "batch_sha256": "f7eb5328998ed2d1f45d2cb6f01cfca2decf6c21fb815fe1048d0dd9516edf04", "params_type": "DimuonParams", "train_nll_sum": 15196.477210688707, "train_tokens": 7322.0, "train_token_mean_nll": 2.0754544128228227, "grad_norm": 12.666028022766113, "t": 1793744855.363103} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 23, "batch_sha256": "f5f3aac8480c147807a2b076a4e782a916bb46fdb705b61af6532fb96bf0cfca", "params_type": "AdamParams", "train_nll_sum": 16084.295735489699, "train_tokens": 7542.0, "train_token_mean_nll": 2.1326300365274062, "grad_norm": 10.91710090637207, "t": 1793744855.3638115} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 23, "batch_sha256": "f5f3aac8480c147807a2b076a4e782a916bb46fdb705b61af6532fb96bf0cfca", "params_type": "DimuonParams", "train_nll_sum": 16221.140661965612, "train_tokens": 7542.0, "train_token_mean_nll": 2.1507744181869017, "grad_norm": 13.791036605834961, "t": 1793744855.5361576} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "AdamParams", "train_nll_sum": 10764.200221814117, "train_tokens": 6100.0, "train_token_mean_nll": 1.7646229871826422, "grad_norm": 12.962532043457031, "t": 1793744862.467689} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 24, "batch_sha256": "9250231cd0aac1a8113e6380e6165a81d4e58ca593a4f7be06670ce1a3d7680d", "params_type": "DimuonParams", "train_nll_sum": 10906.810878263434, "train_tokens": 6100.0, "train_token_mean_nll": 1.7880017833218744, "grad_norm": 15.652393341064453, "t": 1793744862.5052688} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 24, "batch_sha256": "38216f071a1c7edc7cea56b21d21520825c740154de3fae90b75b42009176166", "params_type": "AdamParams", "train_nll_sum": 11987.601314846592, "train_tokens": 6063.0, "train_token_mean_nll": 1.9771732335224463, "grad_norm": 12.10952091217041, "t": 1793744862.6338122} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 24, "batch_sha256": "38216f071a1c7edc7cea56b21d21520825c740154de3fae90b75b42009176166", "params_type": "DimuonParams", "train_nll_sum": 12151.017964512135, "train_tokens": 6063.0, "train_token_mean_nll": 2.0041263342424767, "grad_norm": 15.07475471496582, "t": 1793744862.6345263} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 24, "batch_sha256": "a2b88d8394109399d9625c8387ddaa171ebb319892add1606f7e7c49c9fc4f0f", "params_type": "AdamParams", "train_nll_sum": 14950.409957567683, "train_tokens": 7510.0, "train_token_mean_nll": 1.9907336827653372, "grad_norm": 12.134308815002441, "t": 1793744862.6352966} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 24, "batch_sha256": "a2b88d8394109399d9625c8387ddaa171ebb319892add1606f7e7c49c9fc4f0f", "params_type": "DimuonParams", "train_nll_sum": 15036.751240951668, "train_tokens": 7510.0, "train_token_mean_nll": 2.0022305247605416, "grad_norm": 14.221280097961426, "t": 1793744862.636028} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "AdamParams", "train_nll_sum": 12286.139136548089, "train_tokens": 6108.0, "train_token_mean_nll": 2.0114831592252926, "grad_norm": 11.682426452636719, "t": 1793744870.210198} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 25, "batch_sha256": "6749d25f8b2b298acb87e143efba1560528c74491bef785df7ed733f6ffc64a8", "params_type": "DimuonParams", "train_nll_sum": 12432.814117323036, "train_tokens": 6108.0, "train_token_mean_nll": 2.0354967448138566, "grad_norm": 13.829959869384766, "t": 1793744870.254084} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 25, "batch_sha256": "7046ac44d17c0a8332b66b37ae61e5681ed0ad53bea9e4457d5c4167491dd011", "params_type": "AdamParams", "train_nll_sum": 14014.062021625883, "train_tokens": 6578.0, "train_token_mean_nll": 2.130444211253555, "grad_norm": 11.34316635131836, "t": 1793744870.2548766} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 25, "batch_sha256": "7046ac44d17c0a8332b66b37ae61e5681ed0ad53bea9e4457d5c4167491dd011", "params_type": "DimuonParams", "train_nll_sum": 14077.657085790044, "train_tokens": 6578.0, "train_token_mean_nll": 2.140112053175744, "grad_norm": 13.409036636352539, "t": 1793744870.2556093} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 25, "batch_sha256": "55604a4a2bd9dbbeb79d77300a1061608aaabfeafd7df0789d390d8e39c4ff10", "params_type": "AdamParams", "train_nll_sum": 9918.24528921223, "train_tokens": 4699.0, "train_token_mean_nll": 2.1107140432458458, "grad_norm": 15.076595306396484, "t": 1793744870.2592044} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 25, "batch_sha256": "55604a4a2bd9dbbeb79d77300a1061608aaabfeafd7df0789d390d8e39c4ff10", "params_type": "DimuonParams", "train_nll_sum": 9978.232351569417, "train_tokens": 4699.0, "train_token_mean_nll": 2.1234799641560795, "grad_norm": 18.825763702392578, "t": 1793744870.2598102} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "AdamParams", "train_nll_sum": 11219.705573081006, "train_tokens": 5073.0, "train_token_mean_nll": 2.211651009872069, "grad_norm": 14.337950706481934, "t": 1793744876.7890007} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 26, "batch_sha256": "474d17a5d6bbd92bd3912e8663d3dffd720ca2dc9447178f1e7ff4c8a44c0bb9", "params_type": "DimuonParams", "train_nll_sum": 11311.452036907913, "train_tokens": 5073.0, "train_token_mean_nll": 2.2297362580145696, "grad_norm": 17.90301513671875, "t": 1793744876.8313203} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 26, "batch_sha256": "2245785e935cba39c24aa1945d2e95f3231fb700f493538307472a79b7774874", "params_type": "AdamParams", "train_nll_sum": 12569.1796180376, "train_tokens": 5799.0, "train_token_mean_nll": 2.167473636495534, "grad_norm": 16.36977195739746, "t": 1793744876.8328187} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 26, "batch_sha256": "2245785e935cba39c24aa1945d2e95f3231fb700f493538307472a79b7774874", "params_type": "DimuonParams", "train_nll_sum": 12651.468117246925, "train_tokens": 5799.0, "train_token_mean_nll": 2.1816637553452187, "grad_norm": 19.184680938720703, "t": 1793744876.833648} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 26, "batch_sha256": "df1d0fc3e81e5794ccb9c607fc5436d83da8d7ff594139ec2cfeb6e3dc14ea64", "params_type": "AdamParams", "train_nll_sum": 11513.333278228285, "train_tokens": 5480.0, "train_token_mean_nll": 2.1009732259540668, "grad_norm": 12.272730827331543, "t": 1793744876.8374882} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 26, "batch_sha256": "df1d0fc3e81e5794ccb9c607fc5436d83da8d7ff594139ec2cfeb6e3dc14ea64", "params_type": "DimuonParams", "train_nll_sum": 11601.079659436626, "train_tokens": 5480.0, "train_token_mean_nll": 2.1169853393132527, "grad_norm": 15.640395164489746, "t": 1793744876.8382998} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "AdamParams", "train_nll_sum": 13410.423471005315, "train_tokens": 6392.0, "train_token_mean_nll": 2.0980011688055873, "grad_norm": 15.02497673034668, "t": 1793744883.4289443} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 27, "batch_sha256": "4489175e07916bccfea20457b73401f71c6d5ca20e2b48a06ad5d316c3b85338", "params_type": "DimuonParams", "train_nll_sum": 13541.849027828794, "train_tokens": 6392.0, "train_token_mean_nll": 2.1185621132397987, "grad_norm": 17.389846801757812, "t": 1793744883.4305556} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 27, "batch_sha256": "bfac5dff1b18924a2809d7a0f8fe674f7c6a8281dd4f7aeccbc060906b45bc53", "params_type": "AdamParams", "train_nll_sum": 9136.086129715099, "train_tokens": 4557.0, "train_token_mean_nll": 2.0048466380766072, "grad_norm": 13.583945274353027, "t": 1793744883.4311805} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 27, "batch_sha256": "bfac5dff1b18924a2809d7a0f8fe674f7c6a8281dd4f7aeccbc060906b45bc53", "params_type": "DimuonParams", "train_nll_sum": 9196.241895299, "train_tokens": 4557.0, "train_token_mean_nll": 2.018047376629142, "grad_norm": 16.749160766601562, "t": 1793744883.4321182} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 27, "batch_sha256": "2b0f0cfb33d9de4252034260ca69016a867c5e1b46ee3703d30a9f71566282d2", "params_type": "AdamParams", "train_nll_sum": 9526.496299890925, "train_tokens": 5429.0, "train_token_mean_nll": 1.75474236505635, "grad_norm": 11.998358726501465, "t": 1793744883.4335299} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 27, "batch_sha256": "2b0f0cfb33d9de4252034260ca69016a867c5e1b46ee3703d30a9f71566282d2", "params_type": "DimuonParams", "train_nll_sum": 9607.955536362339, "train_tokens": 5429.0, "train_token_mean_nll": 1.7697468293170637, "grad_norm": 14.811576843261719, "t": 1793744883.437} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "AdamParams", "train_nll_sum": 14567.414979946194, "train_tokens": 7271.0, "train_token_mean_nll": 2.003495389897702, "grad_norm": 14.703927993774414, "t": 1793744890.282442} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 28, "batch_sha256": "9e6e93629dff62bddfd9de502369e9b8bd1e486258d5ad3211dc6dbcc091e6c9", "params_type": "DimuonParams", "train_nll_sum": 14652.450764005349, "train_tokens": 7271.0, "train_token_mean_nll": 2.0151905878153418, "grad_norm": 17.261110305786133, "t": 1793744890.2834973} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 28, "batch_sha256": "76f812b9ed722f204b923417d1a3c5ff5887084676ef9257cf57b5509b78cdf7", "params_type": "AdamParams", "train_nll_sum": 11838.945441605916, "train_tokens": 6179.0, "train_token_mean_nll": 1.9159969965376138, "grad_norm": 12.35195541381836, "t": 1793744890.2898564} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 28, "batch_sha256": "76f812b9ed722f204b923417d1a3c5ff5887084676ef9257cf57b5509b78cdf7", "params_type": "DimuonParams", "train_nll_sum": 11927.773111391094, "train_tokens": 6179.0, "train_token_mean_nll": 1.9303727320587627, "grad_norm": 14.672255516052246, "t": 1793744890.2955024} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 28, "batch_sha256": "1a0ca50431d8528bd18fe295215d92723f8b5c5d7abb88369f062dd14e1de718", "params_type": "AdamParams", "train_nll_sum": 9304.019826750638, "train_tokens": 4864.0, "train_token_mean_nll": 1.9128330235918254, "grad_norm": 11.518627166748047, "t": 1793744890.2983837} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 28, "batch_sha256": "1a0ca50431d8528bd18fe295215d92723f8b5c5d7abb88369f062dd14e1de718", "params_type": "DimuonParams", "train_nll_sum": 9352.923480915008, "train_tokens": 4864.0, "train_token_mean_nll": 1.9228872288065393, "grad_norm": 14.015170097351074, "t": 1793744890.299155} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "AdamParams", "train_nll_sum": 11121.509778083397, "train_tokens": 5476.0, "train_token_mean_nll": 2.030955036173009, "grad_norm": 13.363584518432617, "t": 1793744897.4836335} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 29, "batch_sha256": "8d82c926ac29c697dd7302262ba0ab8852380c6c23d5934c2d35bd3e90fa823b", "params_type": "DimuonParams", "train_nll_sum": 11199.584417382, "train_tokens": 5476.0, "train_token_mean_nll": 2.0452126401355004, "grad_norm": 16.29781150817871, "t": 1793744897.6003354} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 29, "batch_sha256": "c10cf607c8e0353ac912ff03cae32c4f040dcd3b42f351a402de35fa9abfcb3a", "params_type": "AdamParams", "train_nll_sum": 12895.499597103011, "train_tokens": 6609.0, "train_token_mean_nll": 1.9512028441675004, "grad_norm": 11.101959228515625, "t": 1793744897.6015368} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 29, "batch_sha256": "c10cf607c8e0353ac912ff03cae32c4f040dcd3b42f351a402de35fa9abfcb3a", "params_type": "DimuonParams", "train_nll_sum": 13018.899759854634, "train_tokens": 6609.0, "train_token_mean_nll": 1.9698743773422052, "grad_norm": 13.115461349487305, "t": 1793744897.6025794} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 29, "batch_sha256": "c13f8bfd3555f9604975b00db1c266c4d482aafa0fac79056a28aba33bfe32fd", "params_type": "AdamParams", "train_nll_sum": 13190.195145974652, "train_tokens": 6135.0, "train_token_mean_nll": 2.149991058838574, "grad_norm": 11.677578926086426, "t": 1793744897.6034484} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 29, "batch_sha256": "c13f8bfd3555f9604975b00db1c266c4d482aafa0fac79056a28aba33bfe32fd", "params_type": "DimuonParams", "train_nll_sum": 13251.489290479, "train_tokens": 6135.0, "train_token_mean_nll": 2.1599819544383045, "grad_norm": 14.195528984069824, "t": 1793744897.6045082} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "AdamParams", "train_nll_sum": 16814.581842345724, "train_tokens": 7466.0, "train_token_mean_nll": 2.2521540104936677, "grad_norm": 11.211922645568848, "t": 1793744905.7439442} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 30, "batch_sha256": "a11b4371759dbf71ef2cfaedafa9be8ac5e9c553c3c5e00c9cbdd6580f0f8175", "params_type": "DimuonParams", "train_nll_sum": 16867.03187576464, "train_tokens": 7466.0, "train_token_mean_nll": 2.259179195789531, "grad_norm": 13.986042022705078, "t": 1793744905.7456925} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 30, "batch_sha256": "ef8017d8d6971a6056552434051494aebbd3c97ebf74ea29dbc7b354ac632938", "params_type": "AdamParams", "train_nll_sum": 17476.224841782197, "train_tokens": 7852.0, "train_token_mean_nll": 2.225703622234106, "grad_norm": 11.376513481140137, "t": 1793744905.7468145} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 30, "batch_sha256": "ef8017d8d6971a6056552434051494aebbd3c97ebf74ea29dbc7b354ac632938", "params_type": "DimuonParams", "train_nll_sum": 17541.454969746555, "train_tokens": 7852.0, "train_token_mean_nll": 2.2340110761266625, "grad_norm": 14.151628494262695, "t": 1793744905.7476904} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 30, "batch_sha256": "8c7d731af9ce8704942b2d759bc515a94ba2819930db2aa3b59ace586a674110", "params_type": "AdamParams", "train_nll_sum": 15456.450415455973, "train_tokens": 7486.0, "train_token_mean_nll": 2.0647141885460822, "grad_norm": 12.391098022460938, "t": 1793744905.992211} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 30, "batch_sha256": "8c7d731af9ce8704942b2d759bc515a94ba2819930db2aa3b59ace586a674110", "params_type": "DimuonParams", "train_nll_sum": 15525.536434902802, "train_tokens": 7486.0, "train_token_mean_nll": 2.0739428847051564, "grad_norm": 15.71099853515625, "t": 1793744905.9931653} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "AdamParams", "train_nll_sum": 11596.368867083056, "train_tokens": 5656.0, "train_token_mean_nll": 2.050277381026, "grad_norm": 13.161993026733398, "t": 1793744913.1678145} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 31, "batch_sha256": "cbc6bae8e0049fbab599edcfd6dc9789dac98495e70c9bc3a5bee82009c28a5c", "params_type": "DimuonParams", "train_nll_sum": 11653.945683456068, "train_tokens": 5656.0, "train_token_mean_nll": 2.060457157612459, "grad_norm": 15.60794734954834, "t": 1793744913.16921} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 31, "batch_sha256": "3d9f778073a0e6dc418cd06c96c0f36f6670df17b89a552e5a0e25c1145ad1d2", "params_type": "AdamParams", "train_nll_sum": 16354.771211045727, "train_tokens": 7619.0, "train_token_mean_nll": 2.146577137556861, "grad_norm": 11.230374336242676, "t": 1793744913.2630916} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 31, "batch_sha256": "3d9f778073a0e6dc418cd06c96c0f36f6670df17b89a552e5a0e25c1145ad1d2", "params_type": "DimuonParams", "train_nll_sum": 16433.67294968449, "train_tokens": 7619.0, "train_token_mean_nll": 2.156933055477686, "grad_norm": 13.505012512207031, "t": 1793744913.2639601} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 31, "batch_sha256": "87b2917df5b1b280054655f2cb0edb78b831b980d9c016af6e1cf59a3063f923", "params_type": "AdamParams", "train_nll_sum": 14193.210982256864, "train_tokens": 6531.0, "train_token_mean_nll": 2.173206397528229, "grad_norm": 13.80398178100586, "t": 1793744913.2646852} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 31, "batch_sha256": "87b2917df5b1b280054655f2cb0edb78b831b980d9c016af6e1cf59a3063f923", "params_type": "DimuonParams", "train_nll_sum": 14253.807170148435, "train_tokens": 6531.0, "train_token_mean_nll": 2.182484637903604, "grad_norm": 17.074907302856445, "t": 1793744913.2653465} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "AdamParams", "train_nll_sum": 9861.454292586723, "train_tokens": 5681.0, "train_token_mean_nll": 1.7358659201877702, "grad_norm": 14.156752586364746, "t": 1793744919.889954} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 32, "batch_sha256": "08fb9100f42898c6e612d6c330aa239f1aed6745af5fdfa16e6c38afba7986fe", "params_type": "DimuonParams", "train_nll_sum": 9916.354591362884, "train_tokens": 5681.0, "train_token_mean_nll": 1.7455297643659362, "grad_norm": 17.69487762451172, "t": 1793744919.891016} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 32, "batch_sha256": "b31754ba08f728234a5e32c0e6b1070918f41aa49b7f459c2b140a6930b9e116", "params_type": "AdamParams", "train_nll_sum": 14393.572051271272, "train_tokens": 6289.0, "train_token_mean_nll": 2.288690101967129, "grad_norm": 15.594719886779785, "t": 1793744919.8918953} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 32, "batch_sha256": "b31754ba08f728234a5e32c0e6b1070918f41aa49b7f459c2b140a6930b9e116", "params_type": "DimuonParams", "train_nll_sum": 14447.353058283994, "train_tokens": 6289.0, "train_token_mean_nll": 2.2972417011105093, "grad_norm": 17.8782901763916, "t": 1793744919.8926864} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 32, "batch_sha256": "b771daa9d49e7abf074c3787597e45a5758d526bc848a25d3feee34493f877cd", "params_type": "AdamParams", "train_nll_sum": 11509.170916087429, "train_tokens": 5626.0, "train_token_mean_nll": 2.045711147544868, "grad_norm": 13.160592079162598, "t": 1793744919.893446} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 32, "batch_sha256": "b771daa9d49e7abf074c3787597e45a5758d526bc848a25d3feee34493f877cd", "params_type": "DimuonParams", "train_nll_sum": 11556.971427051605, "train_tokens": 5626.0, "train_token_mean_nll": 2.0542075056970504, "grad_norm": 16.077260971069336, "t": 1793744919.8942044} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "AdamParams", "train_nll_sum": 11635.897771008385, "train_tokens": 6193.0, "train_token_mean_nll": 1.8788790200239602, "grad_norm": 13.200177192687988, "t": 1793744925.7868228} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 33, "batch_sha256": "8f0a0f9385871a9ffb74affbae4805abfaa484561171c327efecddd512adc7d0", "params_type": "DimuonParams", "train_nll_sum": 11705.525978312076, "train_tokens": 6193.0, "train_token_mean_nll": 1.8901220698065682, "grad_norm": 15.852071762084961, "t": 1793744925.7877088} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 33, "batch_sha256": "aac7d009a518f7eca3cda3c5e2fb180dda59369611b1346d8f27463da28f78cb", "params_type": "AdamParams", "train_nll_sum": 10798.44156436393, "train_tokens": 5605.0, "train_token_mean_nll": 1.9265729820453041, "grad_norm": 12.429201126098633, "t": 1793744925.7885003} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 33, "batch_sha256": "aac7d009a518f7eca3cda3c5e2fb180dda59369611b1346d8f27463da28f78cb", "params_type": "DimuonParams", "train_nll_sum": 10822.066940323259, "train_tokens": 5605.0, "train_token_mean_nll": 1.9307880357400997, "grad_norm": 15.383115768432617, "t": 1793744925.7892776} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 33, "batch_sha256": "b4fcbad313dbdd8afee98ab00795d0c6c4562935d75f765a9048e881dde5ca8b", "params_type": "AdamParams", "train_nll_sum": 11956.968204779036, "train_tokens": 5595.0, "train_token_mean_nll": 2.137081001747817, "grad_norm": 12.416875839233398, "t": 1793744925.7902026} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 33, "batch_sha256": "b4fcbad313dbdd8afee98ab00795d0c6c4562935d75f765a9048e881dde5ca8b", "params_type": "DimuonParams", "train_nll_sum": 12005.00050858186, "train_tokens": 5595.0, "train_token_mean_nll": 2.145665863910967, "grad_norm": 14.894481658935547, "t": 1793744925.791032} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "AdamParams", "train_nll_sum": 10215.66381997503, "train_tokens": 4524.0, "train_token_mean_nll": 2.258104292655842, "grad_norm": 14.422473907470703, "t": 1793744932.733311} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 34, "batch_sha256": "1684f2e2cb2a7bf324deb688b43e797ccc482071ac9f774aaa9cda6aef3aa9c6", "params_type": "DimuonParams", "train_nll_sum": 10274.576391051103, "train_tokens": 4524.0, "train_token_mean_nll": 2.271126523220845, "grad_norm": 17.410987854003906, "t": 1793744932.8631928} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 34, "batch_sha256": "a1c29dd355cb78ae299df82f938b4cda40af76d69a5ea7d39207ef77237b424c", "params_type": "AdamParams", "train_nll_sum": 14384.163070577088, "train_tokens": 7042.0, "train_token_mean_nll": 2.042624690510805, "grad_norm": 14.257954597473145, "t": 1793744932.864026} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 34, "batch_sha256": "a1c29dd355cb78ae299df82f938b4cda40af76d69a5ea7d39207ef77237b424c", "params_type": "DimuonParams", "train_nll_sum": 14434.88245975886, "train_tokens": 7042.0, "train_token_mean_nll": 2.0498271030614683, "grad_norm": 16.231977462768555, "t": 1793744932.8679907} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 34, "batch_sha256": "109d2849aafe2f34b4d81285a3168965d17e254f7dab377e9eccfd6d23726f68", "params_type": "AdamParams", "train_nll_sum": 11360.545120442943, "train_tokens": 6634.0, "train_token_mean_nll": 1.7124728852039408, "grad_norm": 10.531512260437012, "t": 1793744932.8688016} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 34, "batch_sha256": "109d2849aafe2f34b4d81285a3168965d17e254f7dab377e9eccfd6d23726f68", "params_type": "DimuonParams", "train_nll_sum": 11380.684574711735, "train_tokens": 6634.0, "train_token_mean_nll": 1.7155086787325498, "grad_norm": 12.785350799560547, "t": 1793744932.8695216} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "AdamParams", "train_nll_sum": 11933.957047506354, "train_tokens": 5628.0, "train_token_mean_nll": 2.1204614512271416, "grad_norm": 15.098795890808105, "t": 1793744939.3060873} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 35, "batch_sha256": "ab6bc8ca068506afc3f9ca441db49dacec08f8b8d30025056f70b6c25053fa95", "params_type": "DimuonParams", "train_nll_sum": 11980.46878998362, "train_tokens": 5628.0, "train_token_mean_nll": 2.1287257977938205, "grad_norm": 18.093753814697266, "t": 1793744939.307934} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 35, "batch_sha256": "1103c34bea7d7fa593ff2edd3a50d6bb5ba9fbb7bc465274b611f3f0446bf440", "params_type": "AdamParams", "train_nll_sum": 9972.832565618453, "train_tokens": 5136.0, "train_token_mean_nll": 1.9417508889444028, "grad_norm": 17.68431282043457, "t": 1793744939.3512354} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 35, "batch_sha256": "1103c34bea7d7fa593ff2edd3a50d6bb5ba9fbb7bc465274b611f3f0446bf440", "params_type": "DimuonParams", "train_nll_sum": 10004.710369370463, "train_tokens": 5136.0, "train_token_mean_nll": 1.947957626435059, "grad_norm": 22.087087631225586, "t": 1793744939.3528218} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 35, "batch_sha256": "dfb7cdfd3b999a11489a28e0e5586b4876ff73cb030560d462017ceb7c77eb41", "params_type": "AdamParams", "train_nll_sum": 12218.651712151775, "train_tokens": 5939.0, "train_token_mean_nll": 2.0573584293907685, "grad_norm": 11.653803825378418, "t": 1793744939.3541362} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 35, "batch_sha256": "dfb7cdfd3b999a11489a28e0e5586b4876ff73cb030560d462017ceb7c77eb41", "params_type": "DimuonParams", "train_nll_sum": 12271.837217442093, "train_tokens": 5939.0, "train_token_mean_nll": 2.066313725785838, "grad_norm": 14.166629791259766, "t": 1793744939.35533} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "AdamParams", "train_nll_sum": 13013.585439873874, "train_tokens": 6703.0, "train_token_mean_nll": 1.9414568760068438, "grad_norm": 11.378917694091797, "t": 1793744946.5275767} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 36, "batch_sha256": "1690ec2132eba6c188274710d50adb19ae954ecabfd81a83ad983aef1ce083d2", "params_type": "DimuonParams", "train_nll_sum": 13049.672463037585, "train_tokens": 6703.0, "train_token_mean_nll": 1.9468405882496769, "grad_norm": 13.047386169433594, "t": 1793744946.5320196} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 36, "batch_sha256": "b10df2ca4fe56463dab4451a52beff79f71e206db4b282fc209c24a9ba25b8d1", "params_type": "AdamParams", "train_nll_sum": 11999.302061455235, "train_tokens": 6087.0, "train_token_mean_nll": 1.9712998293831503, "grad_norm": 12.002683639526367, "t": 1793744946.5334806} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 36, "batch_sha256": "b10df2ca4fe56463dab4451a52beff79f71e206db4b282fc209c24a9ba25b8d1", "params_type": "DimuonParams", "train_nll_sum": 12039.104964526552, "train_tokens": 6087.0, "train_token_mean_nll": 1.977838831037712, "grad_norm": 14.506646156311035, "t": 1793744946.535236} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 36, "batch_sha256": "d34730f7c5881f96897302573746eb674f7301deefded373dba6d324770f634d", "params_type": "AdamParams", "train_nll_sum": 14136.946122006462, "train_tokens": 7181.0, "train_token_mean_nll": 1.9686598136758755, "grad_norm": 10.880638122558594, "t": 1793744947.5759487} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 36, "batch_sha256": "d34730f7c5881f96897302573746eb674f7301deefded373dba6d324770f634d", "params_type": "DimuonParams", "train_nll_sum": 14211.21397189766, "train_tokens": 7181.0, "train_token_mean_nll": 1.9790020849321348, "grad_norm": 13.122570037841797, "t": 1793744947.5768316} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "AdamParams", "train_nll_sum": 11502.686195249727, "train_tokens": 5733.0, "train_token_mean_nll": 2.0063991270276866, "grad_norm": 12.889239311218262, "t": 1793744954.4359906} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 37, "batch_sha256": "b7364ea1bf8098fdeb9bcc932c656809aa2c0bb0a6bca3f54b056b8f6e8e82af", "params_type": "DimuonParams", "train_nll_sum": 11527.66396921629, "train_tokens": 5733.0, "train_token_mean_nll": 2.0107559688149816, "grad_norm": 15.392267227172852, "t": 1793744954.4471676} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 37, "batch_sha256": "2e39851f7ccb072a299b237a2bfffa27b1070a549d935080531865880ab7b693", "params_type": "AdamParams", "train_nll_sum": 14497.479172953492, "train_tokens": 6860.0, "train_token_mean_nll": 2.1133351564072145, "grad_norm": 10.997443199157715, "t": 1793744954.6055782} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 37, "batch_sha256": "2e39851f7ccb072a299b237a2bfffa27b1070a549d935080531865880ab7b693", "params_type": "DimuonParams", "train_nll_sum": 14516.11149379141, "train_tokens": 6860.0, "train_token_mean_nll": 2.116051238162013, "grad_norm": 13.172069549560547, "t": 1793744954.6065428} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 37, "batch_sha256": "6d6986ad469c9bcacaac9f043e8a80069a72e4d33b2997e8116028154a2890f7", "params_type": "AdamParams", "train_nll_sum": 12005.583853504339, "train_tokens": 5621.0, "train_token_mean_nll": 2.1358448413990994, "grad_norm": 16.809473037719727, "t": 1793744954.6072674} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 37, "batch_sha256": "6d6986ad469c9bcacaac9f043e8a80069a72e4d33b2997e8116028154a2890f7", "params_type": "DimuonParams", "train_nll_sum": 12081.599122564132, "train_tokens": 5621.0, "train_token_mean_nll": 2.1493682836797956, "grad_norm": 20.539426803588867, "t": 1793744954.6079245} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "AdamParams", "train_nll_sum": 14682.707861315343, "train_tokens": 6763.0, "train_token_mean_nll": 2.1710347273865653, "grad_norm": 10.42146110534668, "t": 1793744960.9984493} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 38, "batch_sha256": "bb5d03b68b7837a42e61be5aaa51e3e000565a7237fc4357555f37b59f4b5455", "params_type": "DimuonParams", "train_nll_sum": 14708.734869926682, "train_tokens": 6763.0, "train_token_mean_nll": 2.174883168701269, "grad_norm": 12.649744033813477, "t": 1793744960.9993103} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 38, "batch_sha256": "8d8c9e2a13bbea71ea15b8f30a12f447d3c13ec8239354a931a2f1373cea4e5a", "params_type": "AdamParams", "train_nll_sum": 8320.113716352835, "train_tokens": 3948.0, "train_token_mean_nll": 2.107424953483494, "grad_norm": 15.548867225646973, "t": 1793744961.0000174} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 38, "batch_sha256": "8d8c9e2a13bbea71ea15b8f30a12f447d3c13ec8239354a931a2f1373cea4e5a", "params_type": "DimuonParams", "train_nll_sum": 8352.677068414789, "train_tokens": 3948.0, "train_token_mean_nll": 2.1156730163158026, "grad_norm": 19.777135848999023, "t": 1793744961.0926917} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 38, "batch_sha256": "98be2d605f07f587af79327ea4389f4e6e118a3ea7fce3bbabdd703e1611ecf4", "params_type": "AdamParams", "train_nll_sum": 12266.327195347618, "train_tokens": 5742.0, "train_token_mean_nll": 2.1362464638362275, "grad_norm": 12.922868728637695, "t": 1793744961.0935862} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 38, "batch_sha256": "98be2d605f07f587af79327ea4389f4e6e118a3ea7fce3bbabdd703e1611ecf4", "params_type": "DimuonParams", "train_nll_sum": 12301.917664551955, "train_tokens": 5742.0, "train_token_mean_nll": 2.1424447343350668, "grad_norm": 16.0795841217041, "t": 1793744961.0945334} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "AdamParams", "train_nll_sum": 10420.383197627212, "train_tokens": 5394.0, "train_token_mean_nll": 1.9318470889186525, "grad_norm": 15.381718635559082, "t": 1793744968.4113364} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 39, "batch_sha256": "e487cfae7cbc167b27142926277e646fa0b967dd35412dde946b6a4ae2fccada", "params_type": "DimuonParams", "train_nll_sum": 10448.296581146795, "train_tokens": 5394.0, "train_token_mean_nll": 1.9370219838981821, "grad_norm": 19.26299476623535, "t": 1793744968.4121325} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 39, "batch_sha256": "281962a115600e1f0685f37ed364e6e78cc0fb24a91ef45a6536a383c9b27189", "params_type": "AdamParams", "train_nll_sum": 13592.051664038647, "train_tokens": 6636.0, "train_token_mean_nll": 2.048229605792442, "grad_norm": 13.662566184997559, "t": 1793744968.447527} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 39, "batch_sha256": "281962a115600e1f0685f37ed364e6e78cc0fb24a91ef45a6536a383c9b27189", "params_type": "DimuonParams", "train_nll_sum": 13641.662463987312, "train_tokens": 6636.0, "train_token_mean_nll": 2.0557056154290705, "grad_norm": 16.529560089111328, "t": 1793744968.448326} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 39, "batch_sha256": "288465aed676b97b80e3937c1d0b03f3c25022dafdc8684fb9cf38822c1dea86", "params_type": "AdamParams", "train_nll_sum": 13443.092406999214, "train_tokens": 6388.0, "train_token_mean_nll": 2.1044289929554187, "grad_norm": 16.22262191772461, "t": 1793744968.449075} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 39, "batch_sha256": "288465aed676b97b80e3937c1d0b03f3c25022dafdc8684fb9cf38822c1dea86", "params_type": "DimuonParams", "train_nll_sum": 13471.81473014778, "train_tokens": 6388.0, "train_token_mean_nll": 2.108925286497774, "grad_norm": 20.898513793945312, "t": 1793744968.4497843} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "AdamParams", "train_nll_sum": 8520.11526412362, "train_tokens": 4573.0, "train_token_mean_nll": 1.8631347614527927, "grad_norm": 15.312602043151855, "t": 1793744975.6238308} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 40, "batch_sha256": "5b4bd1d5c3ca96df3d38290506edc095c2a5d6a235d1c2481cc3a3e4169c68df", "params_type": "DimuonParams", "train_nll_sum": 8528.666290705536, "train_tokens": 4573.0, "train_token_mean_nll": 1.8650046557414248, "grad_norm": 18.026466369628906, "t": 1793744975.7302423} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 40, "batch_sha256": "3e12b2e3c711a8f33a8deba24d3336e42c39a6b62a4f61280bff34f09b984214", "params_type": "AdamParams", "train_nll_sum": 10540.41327145392, "train_tokens": 5120.0, "train_token_mean_nll": 2.0586744670808437, "grad_norm": 11.10454273223877, "t": 1793744975.7314935} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 40, "batch_sha256": "3e12b2e3c711a8f33a8deba24d3336e42c39a6b62a4f61280bff34f09b984214", "params_type": "DimuonParams", "train_nll_sum": 10587.00838928746, "train_tokens": 5120.0, "train_token_mean_nll": 2.0677750760327074, "grad_norm": 13.587179183959961, "t": 1793744975.73687} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 40, "batch_sha256": "df734de2fd38e35f6b377032490db76976ef0544f0d025aa45eea4cce51c196b", "params_type": "AdamParams", "train_nll_sum": 13931.635879225987, "train_tokens": 7110.0, "train_token_mean_nll": 1.9594424584002794, "grad_norm": 13.28250503540039, "t": 1793744975.8776956} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 40, "batch_sha256": "df734de2fd38e35f6b377032490db76976ef0544f0d025aa45eea4cce51c196b", "params_type": "DimuonParams", "train_nll_sum": 13962.61848033021, "train_tokens": 7110.0, "train_token_mean_nll": 1.9638000675569915, "grad_norm": 15.9873685836792, "t": 1793744975.8786435} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 41, "batch_sha256": "339671525396af887b30be0ae36f8174726683630fe0194cdbbeb3fb395eefe1", "params_type": "AdamParams", "train_nll_sum": 11904.201085125216, "train_tokens": 5807.0, "train_token_mean_nll": 2.049974355971279, "grad_norm": 11.880419731140137, "t": 1793744982.9505131} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 41, "batch_sha256": "339671525396af887b30be0ae36f8174726683630fe0194cdbbeb3fb395eefe1", "params_type": "DimuonParams", "train_nll_sum": 11921.059167363777, "train_tokens": 5807.0, "train_token_mean_nll": 2.0528774181787113, "grad_norm": 13.967077255249023, "t": 1793744982.9526067} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 41, "batch_sha256": "5eda7f4a3fc1631bb4066bd841dfed0989c3cf5c72d43f901bd07da76cbb3fdf", "params_type": "AdamParams", "train_nll_sum": 12346.245553989278, "train_tokens": 5911.0, "train_token_mean_nll": 2.0886898247317336, "grad_norm": 12.253961563110352, "t": 1793744983.256981} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 41, "batch_sha256": "5eda7f4a3fc1631bb4066bd841dfed0989c3cf5c72d43f901bd07da76cbb3fdf", "params_type": "DimuonParams", "train_nll_sum": 12384.592100702517, "train_tokens": 5911.0, "train_token_mean_nll": 2.095177144426073, "grad_norm": 14.52517318725586, "t": 1793744983.2577412} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 41, "batch_sha256": "bf3e18e6a21e99d2c95b7b9ed8157d4c551bbf6b58910e3b41d9de2cc16ab439", "params_type": "AdamParams", "train_nll_sum": 13721.442508191423, "train_tokens": 7472.0, "train_token_mean_nll": 1.83638149199564, "grad_norm": 10.983908653259277, "t": 1793744983.2587373} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 41, "batch_sha256": "bf3e18e6a21e99d2c95b7b9ed8157d4c551bbf6b58910e3b41d9de2cc16ab439", "params_type": "DimuonParams", "train_nll_sum": 13758.798174634609, "train_tokens": 7472.0, "train_token_mean_nll": 1.841380912022833, "grad_norm": 13.049750328063965, "t": 1793744983.2596138} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 42, "batch_sha256": "8464fe6ea784ffc8ff5c8e028c8dc4fb41e2349adbe88c3a36b6768ec0eb9a4d", "params_type": "AdamParams", "train_nll_sum": 13766.02770361925, "train_tokens": 6410.0, "train_token_mean_nll": 2.1475862252136113, "grad_norm": 12.022568702697754, "t": 1793744990.0396855} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 42, "batch_sha256": "8464fe6ea784ffc8ff5c8e028c8dc4fb41e2349adbe88c3a36b6768ec0eb9a4d", "params_type": "DimuonParams", "train_nll_sum": 13778.084168837266, "train_tokens": 6410.0, "train_token_mean_nll": 2.149467109022974, "grad_norm": 14.39959716796875, "t": 1793744990.2428176} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 42, "batch_sha256": "e88ea0308e5ece07f8ab20875cd7f894ae223dc5da3e34c56eaa9744944efde7", "params_type": "AdamParams", "train_nll_sum": 9058.717147619092, "train_tokens": 4482.0, "train_token_mean_nll": 2.0211327861711497, "grad_norm": 13.939098358154297, "t": 1793744990.2435265} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 42, "batch_sha256": "e88ea0308e5ece07f8ab20875cd7f894ae223dc5da3e34c56eaa9744944efde7", "params_type": "DimuonParams", "train_nll_sum": 9086.29309077865, "train_tokens": 4482.0, "train_token_mean_nll": 2.0272853839309795, "grad_norm": 16.970645904541016, "t": 1793744990.2441666} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 42, "batch_sha256": "1e5e82e19a70831651e61cc8108b557d5812578d7abcd0e2e36d261aa8beb0cb", "params_type": "AdamParams", "train_nll_sum": 13314.538445482109, "train_tokens": 6160.0, "train_token_mean_nll": 2.161451046344498, "grad_norm": 11.609899520874023, "t": 1793744990.2449465} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 42, "batch_sha256": "1e5e82e19a70831651e61cc8108b557d5812578d7abcd0e2e36d261aa8beb0cb", "params_type": "DimuonParams", "train_nll_sum": 13344.832734197891, "train_tokens": 6160.0, "train_token_mean_nll": 2.1663689503568007, "grad_norm": 13.938703536987305, "t": 1793744990.2456872} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 43, "batch_sha256": "ea6aa48fe7e75e4ffc0aaac0df296392ebde870f06b23509ea8aad0d5baea62a", "params_type": "AdamParams", "train_nll_sum": 12180.979271409346, "train_tokens": 5708.0, "train_token_mean_nll": 2.1340187931691217, "grad_norm": 13.823162078857422, "t": 1793744996.9985945} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 43, "batch_sha256": "ea6aa48fe7e75e4ffc0aaac0df296392ebde870f06b23509ea8aad0d5baea62a", "params_type": "DimuonParams", "train_nll_sum": 12208.789612787212, "train_tokens": 5708.0, "train_token_mean_nll": 2.138890962296288, "grad_norm": 17.283550262451172, "t": 1793744996.9995894} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 43, "batch_sha256": "b8012ae367c707efab98f1400374dacd2c60c00b50d150d6f2e79ab55d5242f2", "params_type": "AdamParams", "train_nll_sum": 10541.954706135006, "train_tokens": 5690.0, "train_token_mean_nll": 1.8527161170711786, "grad_norm": 11.842854499816895, "t": 1793744997.0003252} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 43, "batch_sha256": "b8012ae367c707efab98f1400374dacd2c60c00b50d150d6f2e79ab55d5242f2", "params_type": "DimuonParams", "train_nll_sum": 10570.736226077943, "train_tokens": 5690.0, "train_token_mean_nll": 1.8577743806815366, "grad_norm": 14.117696762084961, "t": 1793744997.0123403} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 43, "batch_sha256": "e50aaa379b9d9a19abc98ff935f9d56dbea2fab19de5e2ec7cc3332f1c35b07b", "params_type": "AdamParams", "train_nll_sum": 10789.62198252684, "train_tokens": 5433.0, "train_token_mean_nll": 1.9859418337063943, "grad_norm": 14.10137939453125, "t": 1793744997.0131807} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 43, "batch_sha256": "e50aaa379b9d9a19abc98ff935f9d56dbea2fab19de5e2ec7cc3332f1c35b07b", "params_type": "DimuonParams", "train_nll_sum": 10823.117820702235, "train_tokens": 5433.0, "train_token_mean_nll": 1.9921070901347755, "grad_norm": 16.289764404296875, "t": 1793744997.0139494} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 44, "batch_sha256": "571260dd784d9d1571e7faa5b3a02012a61c5d570a192b122f92d4c35c6f463d", "params_type": "AdamParams", "train_nll_sum": 9865.322912829868, "train_tokens": 4980.0, "train_token_mean_nll": 1.9809885367128248, "grad_norm": 13.84416389465332, "t": 1793745004.0735292} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 44, "batch_sha256": "571260dd784d9d1571e7faa5b3a02012a61c5d570a192b122f92d4c35c6f463d", "params_type": "DimuonParams", "train_nll_sum": 9894.318889583645, "train_tokens": 4980.0, "train_token_mean_nll": 1.986811022004748, "grad_norm": 16.50821304321289, "t": 1793745004.074695} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 44, "batch_sha256": "b99e5da46e23dc920ec070d8e23fb3b0db2141823f1bad6e91556272faac4ddc", "params_type": "AdamParams", "train_nll_sum": 10567.196693583244, "train_tokens": 5455.0, "train_token_mean_nll": 1.937157963993262, "grad_norm": 13.179425239562988, "t": 1793745004.0755029} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 44, "batch_sha256": "b99e5da46e23dc920ec070d8e23fb3b0db2141823f1bad6e91556272faac4ddc", "params_type": "DimuonParams", "train_nll_sum": 10587.748210828919, "train_tokens": 5455.0, "train_token_mean_nll": 1.9409254281996184, "grad_norm": 16.24152374267578, "t": 1793745004.076284} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 44, "batch_sha256": "3d712158c7db25f034d9cd1a3800eb81bb33057aa2f90fff19885e876daa0166", "params_type": "AdamParams", "train_nll_sum": 13113.631031660429, "train_tokens": 6252.0, "train_token_mean_nll": 2.097509761941847, "grad_norm": 12.346400260925293, "t": 1793745004.3158553} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 44, "batch_sha256": "3d712158c7db25f034d9cd1a3800eb81bb33057aa2f90fff19885e876daa0166", "params_type": "DimuonParams", "train_nll_sum": 13123.561573208895, "train_tokens": 6252.0, "train_token_mean_nll": 2.0990981403085245, "grad_norm": 14.783464431762695, "t": 1793745004.3166602} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 45, "batch_sha256": "ac4fde0ee46427dddeaf1f726c2f25c16747febd84fa91d5756a91c8523f4f56", "params_type": "AdamParams", "train_nll_sum": 10446.67302323942, "train_tokens": 6240.0, "train_token_mean_nll": 1.67414631782683, "grad_norm": 12.708710670471191, "t": 1793745010.5951135} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 45, "batch_sha256": "ac4fde0ee46427dddeaf1f726c2f25c16747febd84fa91d5756a91c8523f4f56", "params_type": "DimuonParams", "train_nll_sum": 10484.948394357825, "train_tokens": 6240.0, "train_token_mean_nll": 1.6802801914034977, "grad_norm": 14.961370468139648, "t": 1793745010.5960333} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 45, "batch_sha256": "e3343e3ed07bd11bd9e81ee5587508abb48dee6c3c460d850887b02a74ece5ff", "params_type": "AdamParams", "train_nll_sum": 12628.350435957262, "train_tokens": 6377.0, "train_token_mean_nll": 1.9802964459710306, "grad_norm": 11.824024200439453, "t": 1793745010.5967352} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 45, "batch_sha256": "e3343e3ed07bd11bd9e81ee5587508abb48dee6c3c460d850887b02a74ece5ff", "params_type": "DimuonParams", "train_nll_sum": 12654.20503748782, "train_tokens": 6377.0, "train_token_mean_nll": 1.984350797787019, "grad_norm": 14.26161003112793, "t": 1793745010.5973682} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 45, "batch_sha256": "eb2c9989bedddbeb687480b8c55fa29d8da49869f7eb6430191d1e390a19d58a", "params_type": "AdamParams", "train_nll_sum": 10255.088078974675, "train_tokens": 5771.0, "train_token_mean_nll": 1.7770036525688226, "grad_norm": 14.370986938476562, "t": 1793745010.6997058} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 45, "batch_sha256": "eb2c9989bedddbeb687480b8c55fa29d8da49869f7eb6430191d1e390a19d58a", "params_type": "DimuonParams", "train_nll_sum": 10286.41431506989, "train_tokens": 5771.0, "train_token_mean_nll": 1.7824318688390035, "grad_norm": 16.87906837463379, "t": 1793745010.7005136} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 46, "batch_sha256": "452717908a729bafc21f3fe73beb9fd4b2df1164c3f4b5d5759ef625bb44b9b5", "params_type": "AdamParams", "train_nll_sum": 10407.064711035206, "train_tokens": 5492.0, "train_token_mean_nll": 1.8949498745512028, "grad_norm": 14.064199447631836, "t": 1793745017.8865776} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 46, "batch_sha256": "452717908a729bafc21f3fe73beb9fd4b2df1164c3f4b5d5759ef625bb44b9b5", "params_type": "DimuonParams", "train_nll_sum": 10427.447464216328, "train_tokens": 5492.0, "train_token_mean_nll": 1.898661228007343, "grad_norm": 17.032880783081055, "t": 1793745018.057756} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 46, "batch_sha256": "87f50bbfd4aff7020c69c0cb63483225b677ce7d449ebf370aa8ad3c1025f49b", "params_type": "AdamParams", "train_nll_sum": 14807.092559197252, "train_tokens": 7802.0, "train_token_mean_nll": 1.897858569494649, "grad_norm": 12.264023780822754, "t": 1793745018.0592244} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 46, "batch_sha256": "87f50bbfd4aff7020c69c0cb63483225b677ce7d449ebf370aa8ad3c1025f49b", "params_type": "DimuonParams", "train_nll_sum": 14806.029867343625, "train_tokens": 7802.0, "train_token_mean_nll": 1.897722361874343, "grad_norm": 14.724358558654785, "t": 1793745018.0600991} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 46, "batch_sha256": "b1162906812423743284d2196d5fa85d7e57a187bde09251a80e96ef2da6de3d", "params_type": "AdamParams", "train_nll_sum": 12583.963941589845, "train_tokens": 6333.0, "train_token_mean_nll": 1.9870462563697846, "grad_norm": 11.969943046569824, "t": 1793745018.0612915} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 46, "batch_sha256": "b1162906812423743284d2196d5fa85d7e57a187bde09251a80e96ef2da6de3d", "params_type": "DimuonParams", "train_nll_sum": 12605.682758169432, "train_tokens": 6333.0, "train_token_mean_nll": 1.9904757236964208, "grad_norm": 14.304387092590332, "t": 1793745018.0621097} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 47, "batch_sha256": "a3fc858866347e7cf23eca30ffd19e339946335315a654875063f4b511f67a0b", "params_type": "AdamParams", "train_nll_sum": 13754.111234662018, "train_tokens": 6595.0, "train_token_mean_nll": 2.0855361993422314, "grad_norm": 15.030438423156738, "t": 1793745025.0007992} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 47, "batch_sha256": "a3fc858866347e7cf23eca30ffd19e339946335315a654875063f4b511f67a0b", "params_type": "DimuonParams", "train_nll_sum": 13795.826914795476, "train_tokens": 6595.0, "train_token_mean_nll": 2.0918615488696704, "grad_norm": 18.859298706054688, "t": 1793745025.0136633} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 47, "batch_sha256": "afa410be048591736b1a4b51c5c5f9a4c6ef7eb207347682582f031b1c97abaf", "params_type": "AdamParams", "train_nll_sum": 9554.344988438188, "train_tokens": 4572.0, "train_token_mean_nll": 2.089751747252447, "grad_norm": 13.004950523376465, "t": 1793745025.014369} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 47, "batch_sha256": "afa410be048591736b1a4b51c5c5f9a4c6ef7eb207347682582f031b1c97abaf", "params_type": "DimuonParams", "train_nll_sum": 9567.241859820471, "train_tokens": 4572.0, "train_token_mean_nll": 2.09257258526257, "grad_norm": 15.857614517211914, "t": 1793745025.0194225} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 47, "batch_sha256": "e06f267d76b04fc06bc99679c9b6d50afe7b5227773bd805b7e5eab66fc14f8f", "params_type": "AdamParams", "train_nll_sum": 14337.579910985274, "train_tokens": 7065.0, "train_token_mean_nll": 2.029381445291617, "grad_norm": 12.495453834533691, "t": 1793745025.3227499} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 47, "batch_sha256": "e06f267d76b04fc06bc99679c9b6d50afe7b5227773bd805b7e5eab66fc14f8f", "params_type": "DimuonParams", "train_nll_sum": 14358.03614737422, "train_tokens": 7065.0, "train_token_mean_nll": 2.0322768786092316, "grad_norm": 16.154525756835938, "t": 1793745025.3236141} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 48, "batch_sha256": "d770c94db4de84e375b45953ef68fcffaed96e8f25c1e73a0b0fa9c27ebe5fcf", "params_type": "AdamParams", "train_nll_sum": 13645.851463457511, "train_tokens": 5920.0, "train_token_mean_nll": 2.3050424769353905, "grad_norm": 14.622312545776367, "t": 1793745032.675186} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 48, "batch_sha256": "d770c94db4de84e375b45953ef68fcffaed96e8f25c1e73a0b0fa9c27ebe5fcf", "params_type": "DimuonParams", "train_nll_sum": 13675.79590249888, "train_tokens": 5920.0, "train_token_mean_nll": 2.310100659205892, "grad_norm": 16.983530044555664, "t": 1793745032.810598} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 48, "batch_sha256": "fcc19d505abbb050c58bbb2f4c03e8d3bfdd3b92b2fdf643a9b5cd40115f464d", "params_type": "AdamParams", "train_nll_sum": 14551.10603988552, "train_tokens": 7694.0, "train_token_mean_nll": 1.8912277150877983, "grad_norm": 11.262595176696777, "t": 1793745032.8117373} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 48, "batch_sha256": "fcc19d505abbb050c58bbb2f4c03e8d3bfdd3b92b2fdf643a9b5cd40115f464d", "params_type": "DimuonParams", "train_nll_sum": 14593.278918595006, "train_tokens": 7694.0, "train_token_mean_nll": 1.8967089834409938, "grad_norm": 14.031426429748535, "t": 1793745032.815377} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 48, "batch_sha256": "461f9c6da9be76e6059bbe46dd6605dd176e53cac71afb9f057998bc5ea30896", "params_type": "AdamParams", "train_nll_sum": 11292.147908453588, "train_tokens": 5997.0, "train_token_mean_nll": 1.8829661344761695, "grad_norm": 13.190299987792969, "t": 1793745032.8162289} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 48, "batch_sha256": "461f9c6da9be76e6059bbe46dd6605dd176e53cac71afb9f057998bc5ea30896", "params_type": "DimuonParams", "train_nll_sum": 11331.539324429514, "train_tokens": 5997.0, "train_token_mean_nll": 1.889534654732285, "grad_norm": 15.59181022644043, "t": 1793745032.8174753} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 49, "batch_sha256": "ba7db5470f88d4979a5a6a2584c26bd2bbfc960b243ed9ec8dac64d9448dd5a7", "params_type": "AdamParams", "train_nll_sum": 17338.768870707627, "train_tokens": 7880.0, "train_token_mean_nll": 2.200351379531425, "grad_norm": 11.516594886779785, "t": 1793745040.3847623} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 49, "batch_sha256": "ba7db5470f88d4979a5a6a2584c26bd2bbfc960b243ed9ec8dac64d9448dd5a7", "params_type": "DimuonParams", "train_nll_sum": 17356.21558240904, "train_tokens": 7880.0, "train_token_mean_nll": 2.202565429239726, "grad_norm": 13.94556713104248, "t": 1793745040.590199} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 49, "batch_sha256": "4cd6fdd0fe5096a1ab25701e21a4cde624e35dacf45c6928611d4b098fd5dcb2", "params_type": "AdamParams", "train_nll_sum": 9112.712225335643, "train_tokens": 4908.0, "train_token_mean_nll": 1.8567058323829753, "grad_norm": 15.499946594238281, "t": 1793745040.5910141} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 49, "batch_sha256": "4cd6fdd0fe5096a1ab25701e21a4cde624e35dacf45c6928611d4b098fd5dcb2", "params_type": "DimuonParams", "train_nll_sum": 9128.748439881252, "train_tokens": 4908.0, "train_token_mean_nll": 1.8599731947598312, "grad_norm": 19.353404998779297, "t": 1793745040.591759} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 49, "batch_sha256": "915697b4316d1780b4a2064e301fc13b18e45b64a6a1401e68be8f391c4e7ef6", "params_type": "AdamParams", "train_nll_sum": 12118.180953263021, "train_tokens": 6193.0, "train_token_mean_nll": 1.9567545540550657, "grad_norm": 11.9120454788208, "t": 1793745040.5926971} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 49, "batch_sha256": "915697b4316d1780b4a2064e301fc13b18e45b64a6a1401e68be8f391c4e7ef6", "params_type": "DimuonParams", "train_nll_sum": 12130.465780770359, "train_tokens": 6193.0, "train_token_mean_nll": 1.9587382174665524, "grad_norm": 14.382169723510742, "t": 1793745040.5935013} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 50, "batch_sha256": "0b8cc65a4c9000f996b2d259b4f87d9dd0c79a134a9d8b0c5212a6cc61c9ba85", "params_type": "AdamParams", "train_nll_sum": 8143.723929120592, "train_tokens": 4184.0, "train_token_mean_nll": 1.9463967325814036, "grad_norm": 15.816635131835938, "t": 1793745088.0610914} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 50, "batch_sha256": "0b8cc65a4c9000f996b2d259b4f87d9dd0c79a134a9d8b0c5212a6cc61c9ba85", "params_type": "DimuonParams", "train_nll_sum": 8168.795122044359, "train_tokens": 4184.0, "train_token_mean_nll": 1.952388891501998, "grad_norm": 18.6695556640625, "t": 1793745088.443459} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 50, "batch_sha256": "5ca0310f6f999a5dd13bd1a7bb96761abd2255780ed60a287b4a962ade52406c", "params_type": "AdamParams", "train_nll_sum": 10503.197165997377, "train_tokens": 5054.0, "train_token_mean_nll": 2.07819492797732, "grad_norm": 14.030472755432129, "t": 1793745088.4441848} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 50, "batch_sha256": "5ca0310f6f999a5dd13bd1a7bb96761abd2255780ed60a287b4a962ade52406c", "params_type": "DimuonParams", "train_nll_sum": 10523.171435695343, "train_tokens": 5054.0, "train_token_mean_nll": 2.082147098475533, "grad_norm": 17.028839111328125, "t": 1793745088.4448485} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 50, "batch_sha256": "e11d80bb297f4199e95694db678dfb639c1432c297d816c18f0aeedb6456f506", "params_type": "AdamParams", "train_nll_sum": 14897.741309340541, "train_tokens": 7991.0, "train_token_mean_nll": 1.8643150180628885, "grad_norm": 12.609180450439453, "t": 1793745088.4459105} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 50, "batch_sha256": "e11d80bb297f4199e95694db678dfb639c1432c297d816c18f0aeedb6456f506", "params_type": "DimuonParams", "train_nll_sum": 14907.7127789488, "train_tokens": 7991.0, "train_token_mean_nll": 1.8655628555811288, "grad_norm": 15.337074279785156, "t": 1793745089.0731955} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 51, "batch_sha256": "d4c4746d6ffe262c69a670d91d33dbc8a24fedd42d48fa944f56bb96142af76f", "params_type": "AdamParams", "train_nll_sum": 9980.753814270032, "train_tokens": 5102.0, "train_token_mean_nll": 1.9562433975441067, "grad_norm": 13.67424201965332, "t": 1793745096.1257446} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 51, "batch_sha256": "d4c4746d6ffe262c69a670d91d33dbc8a24fedd42d48fa944f56bb96142af76f", "params_type": "DimuonParams", "train_nll_sum": 9985.872795785473, "train_tokens": 5102.0, "train_token_mean_nll": 1.9572467259477604, "grad_norm": 16.59938621520996, "t": 1793745096.12662} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 51, "batch_sha256": "2683793f1ca94cc8c4169bac8ef2be2e08181316cfe6dd2ddaae3d027c1c9db8", "params_type": "AdamParams", "train_nll_sum": 10761.724935078484, "train_tokens": 5794.0, "train_token_mean_nll": 1.8573912556227967, "grad_norm": 12.827828407287598, "t": 1793745096.12741} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 51, "batch_sha256": "2683793f1ca94cc8c4169bac8ef2be2e08181316cfe6dd2ddaae3d027c1c9db8", "params_type": "DimuonParams", "train_nll_sum": 10791.55019528449, "train_tokens": 5794.0, "train_token_mean_nll": 1.862538866980409, "grad_norm": 15.818266868591309, "t": 1793745096.129768} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 51, "batch_sha256": "ea8c2c5a9360a342a54d181df5f21dace18284302fcb2fa6a33babfe160b7795", "params_type": "AdamParams", "train_nll_sum": 10566.699259091414, "train_tokens": 4973.0, "train_token_mean_nll": 2.124813846589868, "grad_norm": 13.279812812805176, "t": 1793745096.1306505} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 51, "batch_sha256": "ea8c2c5a9360a342a54d181df5f21dace18284302fcb2fa6a33babfe160b7795", "params_type": "DimuonParams", "train_nll_sum": 10586.322124099623, "train_tokens": 4973.0, "train_token_mean_nll": 2.1287597273476018, "grad_norm": 15.903162956237793, "t": 1793745096.1316202} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 52, "batch_sha256": "58c87ab3984c900e7be6da1094f414c97c752c083788408db43a960bf12a8bfa", "params_type": "AdamParams", "train_nll_sum": 12019.41285039406, "train_tokens": 6744.0, "train_token_mean_nll": 1.7822379671402817, "grad_norm": 12.306178092956543, "t": 1793745104.679167} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 52, "batch_sha256": "58c87ab3984c900e7be6da1094f414c97c752c083788408db43a960bf12a8bfa", "params_type": "DimuonParams", "train_nll_sum": 12047.617382516277, "train_tokens": 6744.0, "train_token_mean_nll": 1.7864201338250707, "grad_norm": 14.776739120483398, "t": 1793745104.6834838} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 52, "batch_sha256": "cd73d35dd56402db8eb3d076682a3ccbbf957272cccf43dd4da79957d2b25c1d", "params_type": "AdamParams", "train_nll_sum": 13487.9821102907, "train_tokens": 6427.0, "train_token_mean_nll": 2.0986435522468803, "grad_norm": 12.548337936401367, "t": 1793745104.685544} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 52, "batch_sha256": "cd73d35dd56402db8eb3d076682a3ccbbf957272cccf43dd4da79957d2b25c1d", "params_type": "DimuonParams", "train_nll_sum": 13507.79008747295, "train_tokens": 6427.0, "train_token_mean_nll": 2.1017255465182743, "grad_norm": 15.352736473083496, "t": 1793745104.6883674} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 52, "batch_sha256": "23dbf584484307d81a5d8d133c1c409876e9e4f25b0afd4bac8b0467ee1d6556", "params_type": "AdamParams", "train_nll_sum": 14827.782633679502, "train_tokens": 6489.0, "train_token_mean_nll": 2.2850643602526586, "grad_norm": 14.390093803405762, "t": 1793745104.6901588} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 52, "batch_sha256": "23dbf584484307d81a5d8d133c1c409876e9e4f25b0afd4bac8b0467ee1d6556", "params_type": "DimuonParams", "train_nll_sum": 14866.812317888805, "train_tokens": 6489.0, "train_token_mean_nll": 2.291079105854339, "grad_norm": 17.622385025024414, "t": 1793745104.690971} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 53, "batch_sha256": "924a94410de7c2aa94f211e78a9f0be874dd4b81f0a9535ade17060ecab392f9", "params_type": "AdamParams", "train_nll_sum": 11425.272508421003, "train_tokens": 5768.0, "train_token_mean_nll": 1.980803139462726, "grad_norm": 11.94514274597168, "t": 1793745112.1809654} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 53, "batch_sha256": "924a94410de7c2aa94f211e78a9f0be874dd4b81f0a9535ade17060ecab392f9", "params_type": "DimuonParams", "train_nll_sum": 11446.412425717292, "train_tokens": 5768.0, "train_token_mean_nll": 1.9844681736680465, "grad_norm": 14.426100730895996, "t": 1793745112.1817544} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 53, "batch_sha256": "75a56968870425969dc1d832050236bf78207fa76a300186bf2e28bcd63c0c93", "params_type": "AdamParams", "train_nll_sum": 12874.799676765208, "train_tokens": 6335.0, "train_token_mean_nll": 2.0323282836251315, "grad_norm": 12.735662460327148, "t": 1793745112.1827533} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 53, "batch_sha256": "75a56968870425969dc1d832050236bf78207fa76a300186bf2e28bcd63c0c93", "params_type": "DimuonParams", "train_nll_sum": 12883.144694935203, "train_tokens": 6335.0, "train_token_mean_nll": 2.0336455714183432, "grad_norm": 15.394211769104004, "t": 1793745112.183729} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 53, "batch_sha256": "9818b4e8f3a801166e376d843b3207233d1abac2b5b5f3e72867a5568808c747", "params_type": "AdamParams", "train_nll_sum": 12239.346772184344, "train_tokens": 5923.0, "train_token_mean_nll": 2.066410057772133, "grad_norm": 12.13182544708252, "t": 1793745112.184675} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 53, "batch_sha256": "9818b4e8f3a801166e376d843b3207233d1abac2b5b5f3e72867a5568808c747", "params_type": "DimuonParams", "train_nll_sum": 12269.23636647938, "train_tokens": 5923.0, "train_token_mean_nll": 2.071456418450005, "grad_norm": 14.948954582214355, "t": 1793745112.185403} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 54, "batch_sha256": "33d38653b89d346b1528e2e66ddd8373e2f5329c336659e48c5562a9ee6facc1", "params_type": "AdamParams", "train_nll_sum": 13302.56565619923, "train_tokens": 5996.0, "train_token_mean_nll": 2.2185733249164823, "grad_norm": 14.253649711608887, "t": 1793745118.9928055} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 54, "batch_sha256": "33d38653b89d346b1528e2e66ddd8373e2f5329c336659e48c5562a9ee6facc1", "params_type": "DimuonParams", "train_nll_sum": 13309.80372980508, "train_tokens": 5996.0, "train_token_mean_nll": 2.2197804752843697, "grad_norm": 17.772994995117188, "t": 1793745119.361836} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 54, "batch_sha256": "eb245a85346dfeff19f368dbd71c324f4b28ef2d7739d9255275694fecaa32da", "params_type": "AdamParams", "train_nll_sum": 15309.7209578772, "train_tokens": 8072.0, "train_token_mean_nll": 1.8966453119273043, "grad_norm": 10.797967910766602, "t": 1793745119.3627765} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 54, "batch_sha256": "eb245a85346dfeff19f368dbd71c324f4b28ef2d7739d9255275694fecaa32da", "params_type": "DimuonParams", "train_nll_sum": 15322.1344476809, "train_tokens": 8072.0, "train_token_mean_nll": 1.8981831575422325, "grad_norm": 12.941010475158691, "t": 1793745119.363653} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 54, "batch_sha256": "8566a5fb9dfe9f83495a563bc35295f97bfbcbbddd9ab91d4a377ca6e71999e4", "params_type": "AdamParams", "train_nll_sum": 11567.052059041744, "train_tokens": 5626.0, "train_token_mean_nll": 2.0559992995097303, "grad_norm": 10.543400764465332, "t": 1793745119.3643765} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 54, "batch_sha256": "8566a5fb9dfe9f83495a563bc35295f97bfbcbbddd9ab91d4a377ca6e71999e4", "params_type": "DimuonParams", "train_nll_sum": 11580.031942244306, "train_tokens": 5626.0, "train_token_mean_nll": 2.0583064241458064, "grad_norm": 12.627946853637695, "t": 1793745119.3650596} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 55, "batch_sha256": "67365c869861e69978c9789d9732de30126f8627ace03a5d82813a2ea5e55f3d", "params_type": "AdamParams", "train_nll_sum": 15158.706518292689, "train_tokens": 7249.0, "train_token_mean_nll": 2.091144505213504, "grad_norm": 12.56959056854248, "t": 1793745126.9325435} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 55, "batch_sha256": "67365c869861e69978c9789d9732de30126f8627ace03a5d82813a2ea5e55f3d", "params_type": "DimuonParams", "train_nll_sum": 15145.808601796347, "train_tokens": 7249.0, "train_token_mean_nll": 2.0893652368321627, "grad_norm": 15.743131637573242, "t": 1793745127.2019634} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 55, "batch_sha256": "ce038285eb1ab0a136a1a8f446080222d7297e6ab6f1e68c3a075d8959a4e5c9", "params_type": "AdamParams", "train_nll_sum": 8208.553260185787, "train_tokens": 4556.0, "train_token_mean_nll": 1.8017017691364765, "grad_norm": 14.278499603271484, "t": 1793745127.2028162} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 55, "batch_sha256": "ce038285eb1ab0a136a1a8f446080222d7297e6ab6f1e68c3a075d8959a4e5c9", "params_type": "DimuonParams", "train_nll_sum": 8202.852980789932, "train_tokens": 4556.0, "train_token_mean_nll": 1.800450610357755, "grad_norm": 17.257518768310547, "t": 1793745127.2056844} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 55, "batch_sha256": "f4337c0aee81e9893abcd9cfa7e3d3e9223b9c3b9d53bd30a70028bffe01de11", "params_type": "AdamParams", "train_nll_sum": 14650.446731747825, "train_tokens": 7693.0, "train_token_mean_nll": 1.904386680325988, "grad_norm": 10.197639465332031, "t": 1793745127.2066622} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 55, "batch_sha256": "f4337c0aee81e9893abcd9cfa7e3d3e9223b9c3b9d53bd30a70028bffe01de11", "params_type": "DimuonParams", "train_nll_sum": 14668.452112358684, "train_tokens": 7693.0, "train_token_mean_nll": 1.9067271691614043, "grad_norm": 12.077615737915039, "t": 1793745127.208678} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 56, "batch_sha256": "442323b97a1f746694139f935b1b8bd281e064f0b7ebb7df225272e3d9879506", "params_type": "AdamParams", "train_nll_sum": 12165.008827941096, "train_tokens": 6083.0, "train_token_mean_nll": 1.999837058678464, "grad_norm": 12.571270942687988, "t": 1793745134.4661627} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 56, "batch_sha256": "442323b97a1f746694139f935b1b8bd281e064f0b7ebb7df225272e3d9879506", "params_type": "DimuonParams", "train_nll_sum": 12182.37008749891, "train_tokens": 6083.0, "train_token_mean_nll": 2.002691120746163, "grad_norm": 15.315774917602539, "t": 1793745134.467036} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 56, "batch_sha256": "ffb0f262c27feed79d48b2ed1f1560ff9faa82d4f9f156445ae81f72a332b74b", "params_type": "AdamParams", "train_nll_sum": 15201.308548378927, "train_tokens": 6843.0, "train_token_mean_nll": 2.2214392150195716, "grad_norm": 10.84128475189209, "t": 1793745134.467978} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 56, "batch_sha256": "ffb0f262c27feed79d48b2ed1f1560ff9faa82d4f9f156445ae81f72a332b74b", "params_type": "DimuonParams", "train_nll_sum": 15201.80213667664, "train_tokens": 6843.0, "train_token_mean_nll": 2.2215113454152626, "grad_norm": 12.914155006408691, "t": 1793745134.4690325} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 56, "batch_sha256": "dd292ab1238253bc9dc821f9cff79c83b3593dc6901e9a40d0a19ef0b95f893b", "params_type": "AdamParams", "train_nll_sum": 8972.833147464062, "train_tokens": 4644.0, "train_token_mean_nll": 1.9321346140103492, "grad_norm": 12.304959297180176, "t": 1793745134.4698567} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 56, "batch_sha256": "dd292ab1238253bc9dc821f9cff79c83b3593dc6901e9a40d0a19ef0b95f893b", "params_type": "DimuonParams", "train_nll_sum": 8988.830663136301, "train_tokens": 4644.0, "train_token_mean_nll": 1.9355793848269383, "grad_norm": 14.826292037963867, "t": 1793745134.4708135} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 57, "batch_sha256": "df2b34ab38fbf88495c3529fa6ccc58bc5211f21d877e81ee67683e5c3163edd", "params_type": "AdamParams", "train_nll_sum": 11866.21829052989, "train_tokens": 5255.0, "train_token_mean_nll": 2.2580815015280478, "grad_norm": 13.960714340209961, "t": 1793745140.7690153} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 57, "batch_sha256": "df2b34ab38fbf88495c3529fa6ccc58bc5211f21d877e81ee67683e5c3163edd", "params_type": "DimuonParams", "train_nll_sum": 11867.951039167529, "train_tokens": 5255.0, "train_token_mean_nll": 2.258411234855857, "grad_norm": 16.586938858032227, "t": 1793745140.769838} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 57, "batch_sha256": "b2b59aadbff1a3b4d85e09548769bcdde8cf7762770f022ff2bb6c0c29772fb0", "params_type": "AdamParams", "train_nll_sum": 8095.708459777688, "train_tokens": 4835.0, "train_token_mean_nll": 1.6743967858899045, "grad_norm": 12.659235000610352, "t": 1793745140.770652} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 57, "batch_sha256": "b2b59aadbff1a3b4d85e09548769bcdde8cf7762770f022ff2bb6c0c29772fb0", "params_type": "DimuonParams", "train_nll_sum": 8112.082345036208, "train_tokens": 4835.0, "train_token_mean_nll": 1.677783318518347, "grad_norm": 15.44468879699707, "t": 1793745141.035545} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 57, "batch_sha256": "f8923317aa79fc644209ed7ac8c30b3bff57a25ab7de7a57b40cae49aefde094", "params_type": "AdamParams", "train_nll_sum": 11630.247730654763, "train_tokens": 5855.0, "train_token_mean_nll": 1.9863787755174658, "grad_norm": 13.941693305969238, "t": 1793745141.0363} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 57, "batch_sha256": "f8923317aa79fc644209ed7ac8c30b3bff57a25ab7de7a57b40cae49aefde094", "params_type": "DimuonParams", "train_nll_sum": 11627.950063853337, "train_tokens": 5855.0, "train_token_mean_nll": 1.9859863473703394, "grad_norm": 16.641130447387695, "t": 1793745141.0369093} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 58, "batch_sha256": "42bfa915dd9a0e0797259ee04a6cc756bffc38eb6a29282303da52c398a07dd5", "params_type": "AdamParams", "train_nll_sum": 15081.993771957073, "train_tokens": 7436.0, "train_token_mean_nll": 2.0282401522266102, "grad_norm": 12.8840913772583, "t": 1793745148.9891703} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 58, "batch_sha256": "42bfa915dd9a0e0797259ee04a6cc756bffc38eb6a29282303da52c398a07dd5", "params_type": "DimuonParams", "train_nll_sum": 15083.202051765174, "train_tokens": 7436.0, "train_token_mean_nll": 2.02840264278714, "grad_norm": 14.043195724487305, "t": 1793745148.990598} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 58, "batch_sha256": "92de68b1084b74488964372b5b5088c844114fc351e796590e8ca43d59d1fd67", "params_type": "AdamParams", "train_nll_sum": 13091.906015668123, "train_tokens": 6307.0, "train_token_mean_nll": 2.075773904497879, "grad_norm": 13.948612213134766, "t": 1793745148.991588} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 58, "batch_sha256": "92de68b1084b74488964372b5b5088c844114fc351e796590e8ca43d59d1fd67", "params_type": "DimuonParams", "train_nll_sum": 13103.138721251868, "train_tokens": 6307.0, "train_token_mean_nll": 2.077554894760087, "grad_norm": 17.06639862060547, "t": 1793745148.9975834} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 58, "batch_sha256": "ac84e4b3520df2bef792c1b7507445d208bb9b181fe63180c0328380dc2a7937", "params_type": "AdamParams", "train_nll_sum": 15548.013481799506, "train_tokens": 7010.0, "train_token_mean_nll": 2.2179762456204717, "grad_norm": 13.5874662399292, "t": 1793745148.9984782} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 58, "batch_sha256": "ac84e4b3520df2bef792c1b7507445d208bb9b181fe63180c0328380dc2a7937", "params_type": "DimuonParams", "train_nll_sum": 15579.513499845578, "train_tokens": 7010.0, "train_token_mean_nll": 2.2224698287939484, "grad_norm": 16.206159591674805, "t": 1793745149.1049066} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 59, "batch_sha256": "7e36e4533a60548c38d7ab09aeb459cca41b02e616e75af696e703c98834022c", "params_type": "AdamParams", "train_nll_sum": 14662.202337836077, "train_tokens": 6825.0, "train_token_mean_nll": 2.1483080348477768, "grad_norm": 13.397965431213379, "t": 1793745155.5279195} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 59, "batch_sha256": "7e36e4533a60548c38d7ab09aeb459cca41b02e616e75af696e703c98834022c", "params_type": "DimuonParams", "train_nll_sum": 14665.849656567476, "train_tokens": 6825.0, "train_token_mean_nll": 2.148842440522707, "grad_norm": 15.966212272644043, "t": 1793745155.5287054} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 59, "batch_sha256": "45d4b19855f88f217bef9b805c9958abd41e9b6fb63cbad886fba64feaf4145d", "params_type": "AdamParams", "train_nll_sum": 12025.022924196546, "train_tokens": 5787.0, "train_token_mean_nll": 2.077937260099628, "grad_norm": 14.892230033874512, "t": 1793745155.637411} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 59, "batch_sha256": "45d4b19855f88f217bef9b805c9958abd41e9b6fb63cbad886fba64feaf4145d", "params_type": "DimuonParams", "train_nll_sum": 12052.99387246532, "train_tokens": 5787.0, "train_token_mean_nll": 2.082770670894301, "grad_norm": 17.816686630249023, "t": 1793745155.639911} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 59, "batch_sha256": "06559cc7797dd6c3569c8b9f5fd27ad01268ca5bd53ffa29346f6c2d24bceb6c", "params_type": "AdamParams", "train_nll_sum": 10650.017307996386, "train_tokens": 5189.0, "train_token_mean_nll": 2.0524219132773918, "grad_norm": 11.611623764038086, "t": 1793745155.6438167} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 59, "batch_sha256": "06559cc7797dd6c3569c8b9f5fd27ad01268ca5bd53ffa29346f6c2d24bceb6c", "params_type": "DimuonParams", "train_nll_sum": 10644.694762783729, "train_tokens": 5189.0, "train_token_mean_nll": 2.0513961770637366, "grad_norm": 13.830243110656738, "t": 1793745155.6444514} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 60, "batch_sha256": "35a1a0ce33cfc9cc60babf4114304737eeb335fee4c71a93b2e298f9f6b895b6", "params_type": "AdamParams", "train_nll_sum": 10698.867232572404, "train_tokens": 5293.0, "train_token_mean_nll": 2.0213238678580017, "grad_norm": 13.041245460510254, "t": 1793745162.93038} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 60, "batch_sha256": "35a1a0ce33cfc9cc60babf4114304737eeb335fee4c71a93b2e298f9f6b895b6", "params_type": "DimuonParams", "train_nll_sum": 10699.953943238685, "train_tokens": 5293.0, "train_token_mean_nll": 2.0215291787717145, "grad_norm": 15.915160179138184, "t": 1793745162.9961834} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 60, "batch_sha256": "7cc763ed0221157d2f1854d4a7356392b7a66b15efff6a64d39b9acc7af94074", "params_type": "AdamParams", "train_nll_sum": 14764.870798993357, "train_tokens": 7450.0, "train_token_mean_nll": 1.9818618522138736, "grad_norm": 11.832709312438965, "t": 1793745162.9971592} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 60, "batch_sha256": "7cc763ed0221157d2f1854d4a7356392b7a66b15efff6a64d39b9acc7af94074", "params_type": "DimuonParams", "train_nll_sum": 14781.506501268448, "train_tokens": 7450.0, "train_token_mean_nll": 1.9840948323850265, "grad_norm": 13.8636474609375, "t": 1793745163.2796583} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 60, "batch_sha256": "b54b8ecf5e37fa0bffaf3e7c6edc4c0a820d77b480cca14a09fd248755573706", "params_type": "AdamParams", "train_nll_sum": 12305.822619951758, "train_tokens": 5734.0, "train_token_mean_nll": 2.1461148622169093, "grad_norm": 16.35148811340332, "t": 1793745163.2812474} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 60, "batch_sha256": "b54b8ecf5e37fa0bffaf3e7c6edc4c0a820d77b480cca14a09fd248755573706", "params_type": "DimuonParams", "train_nll_sum": 12323.709907242097, "train_tokens": 5734.0, "train_token_mean_nll": 2.14923437517302, "grad_norm": 19.654603958129883, "t": 1793745163.2821476} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 61, "batch_sha256": "172033af6f0097382622e7e8b5769a342ff17e8ba56a3b8a79c8277c864b2f46", "params_type": "AdamParams", "train_nll_sum": 14553.902109765026, "train_tokens": 7139.0, "train_token_mean_nll": 2.038647164836115, "grad_norm": 10.865150451660156, "t": 1793745170.5017986} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 61, "batch_sha256": "172033af6f0097382622e7e8b5769a342ff17e8ba56a3b8a79c8277c864b2f46", "params_type": "DimuonParams", "train_nll_sum": 14572.118741961325, "train_tokens": 7139.0, "train_token_mean_nll": 2.0411988712650686, "grad_norm": 13.29304313659668, "t": 1793745170.7213442} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 61, "batch_sha256": "a0e1d24923037faeebccb273654744ec7e0dc60d92c4a0447ab8418aff0a058d", "params_type": "AdamParams", "train_nll_sum": 13718.995683329997, "train_tokens": 6700.0, "train_token_mean_nll": 2.0476112960194026, "grad_norm": 12.036506652832031, "t": 1793745170.7224908} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 61, "batch_sha256": "a0e1d24923037faeebccb273654744ec7e0dc60d92c4a0447ab8418aff0a058d", "params_type": "DimuonParams", "train_nll_sum": 13737.754985699068, "train_tokens": 6700.0, "train_token_mean_nll": 2.050411191895383, "grad_norm": 14.27449893951416, "t": 1793745170.7249868} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 61, "batch_sha256": "da09fe44b16a2c0f53f238e3b9becd3a9d9ef37b9a42f84f0b668554a5aec62d", "params_type": "AdamParams", "train_nll_sum": 11849.853275487909, "train_tokens": 5879.0, "train_token_mean_nll": 2.015623962491565, "grad_norm": 14.2072172164917, "t": 1793745170.725835} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 61, "batch_sha256": "da09fe44b16a2c0f53f238e3b9becd3a9d9ef37b9a42f84f0b668554a5aec62d", "params_type": "DimuonParams", "train_nll_sum": 11840.81816298262, "train_tokens": 5879.0, "train_token_mean_nll": 2.014087117363943, "grad_norm": 17.196327209472656, "t": 1793745170.726593} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 62, "batch_sha256": "12931d50e4a9167b83c280c25fdd98d71ca670a34ea52e1ad1e1de32d7d261a6", "params_type": "AdamParams", "train_nll_sum": 12323.190101570803, "train_tokens": 5817.0, "train_token_mean_nll": 2.118478614676088, "grad_norm": 13.061095237731934, "t": 1793745177.6434865} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 62, "batch_sha256": "12931d50e4a9167b83c280c25fdd98d71ca670a34ea52e1ad1e1de32d7d261a6", "params_type": "DimuonParams", "train_nll_sum": 12325.251114455314, "train_tokens": 5817.0, "train_token_mean_nll": 2.118832923234539, "grad_norm": 15.785224914550781, "t": 1793745177.8129196} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 62, "batch_sha256": "83ded23e73f43d4314cc8df2748a83456d05af3e595399224d2b550511070784", "params_type": "AdamParams", "train_nll_sum": 14960.957867165806, "train_tokens": 7142.0, "train_token_mean_nll": 2.094785475660292, "grad_norm": 12.207659721374512, "t": 1793745177.813799} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 62, "batch_sha256": "83ded23e73f43d4314cc8df2748a83456d05af3e595399224d2b550511070784", "params_type": "DimuonParams", "train_nll_sum": 14982.115099737322, "train_tokens": 7142.0, "train_token_mean_nll": 2.09774784370447, "grad_norm": 14.48569107055664, "t": 1793745177.8145292} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 62, "batch_sha256": "dafb298a769a3f378640e034ccec846502cec774aba766dd8007b267a2896c9d", "params_type": "AdamParams", "train_nll_sum": 13204.398007442345, "train_tokens": 6801.0, "train_token_mean_nll": 1.9415377161362073, "grad_norm": 10.510465621948242, "t": 1793745177.8152611} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 62, "batch_sha256": "dafb298a769a3f378640e034ccec846502cec774aba766dd8007b267a2896c9d", "params_type": "DimuonParams", "train_nll_sum": 13220.743260492089, "train_tokens": 6801.0, "train_token_mean_nll": 1.9439410763846623, "grad_norm": 12.53777027130127, "t": 1793745177.8159506} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 63, "batch_sha256": "a19a60a3c3a8810232eff4f115941cc10853ff4490ad2c3db9f5ef287172c717", "params_type": "AdamParams", "train_nll_sum": 13768.43718017936, "train_tokens": 6921.0, "train_token_mean_nll": 1.989371070680445, "grad_norm": 13.043630599975586, "t": 1793745185.1898906} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 63, "batch_sha256": "a19a60a3c3a8810232eff4f115941cc10853ff4490ad2c3db9f5ef287172c717", "params_type": "DimuonParams", "train_nll_sum": 13785.670294920035, "train_tokens": 6921.0, "train_token_mean_nll": 1.9918610453576124, "grad_norm": 15.474954605102539, "t": 1793745185.368661} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 63, "batch_sha256": "b8aa6ce5f8551b870fa30e4879a2cfaf59a74ede21260be63beee05657372b70", "params_type": "AdamParams", "train_nll_sum": 10595.894925510125, "train_tokens": 5712.0, "train_token_mean_nll": 1.855023621412837, "grad_norm": 12.979809761047363, "t": 1793745185.3739336} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 63, "batch_sha256": "b8aa6ce5f8551b870fa30e4879a2cfaf59a74ede21260be63beee05657372b70", "params_type": "DimuonParams", "train_nll_sum": 10603.350683442028, "train_tokens": 5712.0, "train_token_mean_nll": 1.85632890116282, "grad_norm": 15.715913772583008, "t": 1793745185.3749347} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 63, "batch_sha256": "f42e10d4ff925c13e7c4b55778f62ef66e9a763e692d6994f56d5d0970beedcb", "params_type": "AdamParams", "train_nll_sum": 13193.667289032277, "train_tokens": 6575.0, "train_token_mean_nll": 2.0066414127805743, "grad_norm": 10.412931442260742, "t": 1793745185.3762286} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 63, "batch_sha256": "f42e10d4ff925c13e7c4b55778f62ef66e9a763e692d6994f56d5d0970beedcb", "params_type": "DimuonParams", "train_nll_sum": 13200.014773459421, "train_tokens": 6575.0, "train_token_mean_nll": 2.007606809651623, "grad_norm": 12.765161514282227, "t": 1793745185.37745} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 64, "batch_sha256": "59e2dd2f0afe0126082063c81b854e14e1b61ce36b978ae27369abc57be787cd", "params_type": "AdamParams", "train_nll_sum": 10880.837363615843, "train_tokens": 5307.0, "train_token_mean_nll": 2.0502802644838596, "grad_norm": 12.71037769317627, "t": 1793745191.6392205} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 64, "batch_sha256": "59e2dd2f0afe0126082063c81b854e14e1b61ce36b978ae27369abc57be787cd", "params_type": "DimuonParams", "train_nll_sum": 10898.600725177388, "train_tokens": 5307.0, "train_token_mean_nll": 2.0536274213637435, "grad_norm": 15.254040718078613, "t": 1793745191.639971} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 64, "batch_sha256": "f8d1408a42b9b4d9b25b437bc46100b2b053f9aa14df05ab80728963ae46ed85", "params_type": "AdamParams", "train_nll_sum": 14115.199173952424, "train_tokens": 6388.0, "train_token_mean_nll": 2.2096429514640614, "grad_norm": 12.894388198852539, "t": 1793745191.6443837} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 64, "batch_sha256": "f8d1408a42b9b4d9b25b437bc46100b2b053f9aa14df05ab80728963ae46ed85", "params_type": "DimuonParams", "train_nll_sum": 14091.982349442396, "train_tokens": 6388.0, "train_token_mean_nll": 2.2060085080529737, "grad_norm": 14.86203670501709, "t": 1793745191.6451743} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 64, "batch_sha256": "9e1afbfae446904171689b9a35240e0167ca216f927db0cb22396520559596d8", "params_type": "AdamParams", "train_nll_sum": 10994.760145378496, "train_tokens": 5309.0, "train_token_mean_nll": 2.0709663110526457, "grad_norm": 15.80267333984375, "t": 1793745191.6459801} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 64, "batch_sha256": "9e1afbfae446904171689b9a35240e0167ca216f927db0cb22396520559596d8", "params_type": "DimuonParams", "train_nll_sum": 11003.755861981475, "train_tokens": 5309.0, "train_token_mean_nll": 2.0726607387420373, "grad_norm": 17.94193458557129, "t": 1793745191.648567} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 65, "batch_sha256": "dad50f8ee2029dc3bb8a70600cf062eb3042adb487dfea8efe9d59363a279184", "params_type": "AdamParams", "train_nll_sum": 12204.918219610376, "train_tokens": 6452.0, "train_token_mean_nll": 1.8916488251101016, "grad_norm": 10.271293640136719, "t": 1793745198.8365529} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 65, "batch_sha256": "dad50f8ee2029dc3bb8a70600cf062eb3042adb487dfea8efe9d59363a279184", "params_type": "DimuonParams", "train_nll_sum": 12207.01946732845, "train_tokens": 6452.0, "train_token_mean_nll": 1.8919744989659717, "grad_norm": 12.120491027832031, "t": 1793745198.8416228} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 65, "batch_sha256": "e37db63e946c144b131bd257e19827e1280756dbd5915df16a02d780a4ddb3cd", "params_type": "AdamParams", "train_nll_sum": 11856.65946499266, "train_tokens": 6328.0, "train_token_mean_nll": 1.873681963494415, "grad_norm": 13.230533599853516, "t": 1793745198.8441284} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 65, "batch_sha256": "e37db63e946c144b131bd257e19827e1280756dbd5915df16a02d780a4ddb3cd", "params_type": "DimuonParams", "train_nll_sum": 11846.234690313995, "train_tokens": 6328.0, "train_token_mean_nll": 1.872034559152022, "grad_norm": 15.749103546142578, "t": 1793745198.8460639} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 65, "batch_sha256": "042cfef915388be326507be5c13cdb917607e8c0c2831bef000d728303d28e41", "params_type": "AdamParams", "train_nll_sum": 14241.082449209109, "train_tokens": 7109.0, "train_token_mean_nll": 2.00324693335337, "grad_norm": 10.818771362304688, "t": 1793745198.8467987} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 65, "batch_sha256": "042cfef915388be326507be5c13cdb917607e8c0c2831bef000d728303d28e41", "params_type": "DimuonParams", "train_nll_sum": 14254.148164960676, "train_tokens": 7109.0, "train_token_mean_nll": 2.005084845261032, "grad_norm": 12.988933563232422, "t": 1793745198.84749} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 66, "batch_sha256": "0a28d3341341628e2845ec34ab5df350d048b251d0d1eed68132b24229c995f1", "params_type": "AdamParams", "train_nll_sum": 13350.021515907001, "train_tokens": 7161.0, "train_token_mean_nll": 1.864267772085882, "grad_norm": 12.24716567993164, "t": 1793745206.2322738} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 66, "batch_sha256": "0a28d3341341628e2845ec34ab5df350d048b251d0d1eed68132b24229c995f1", "params_type": "DimuonParams", "train_nll_sum": 13343.458334132458, "train_tokens": 7161.0, "train_token_mean_nll": 1.8633512545918807, "grad_norm": 14.381446838378906, "t": 1793745206.4540887} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 66, "batch_sha256": "83fdf895e532b1c4ade42b802dcaa52bfcaa2f8e37b011732901ea5e8a8c1737", "params_type": "AdamParams", "train_nll_sum": 12740.345001090678, "train_tokens": 6001.0, "train_token_mean_nll": 2.1230369940161102, "grad_norm": 12.787422180175781, "t": 1793745206.4874947} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 66, "batch_sha256": "83fdf895e532b1c4ade42b802dcaa52bfcaa2f8e37b011732901ea5e8a8c1737", "params_type": "DimuonParams", "train_nll_sum": 12740.250582036495, "train_tokens": 6001.0, "train_token_mean_nll": 2.123021260129394, "grad_norm": 15.254188537597656, "t": 1793745206.4887652} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 66, "batch_sha256": "a747a066d9a81bdf974a033cbd0bcf5bd46aa72c2cf32e3eba2761df9c9c90d6", "params_type": "AdamParams", "train_nll_sum": 9210.725764888803, "train_tokens": 5206.0, "train_token_mean_nll": 1.7692519717419906, "grad_norm": 10.972002029418945, "t": 1793745206.4896283} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 66, "batch_sha256": "a747a066d9a81bdf974a033cbd0bcf5bd46aa72c2cf32e3eba2761df9c9c90d6", "params_type": "DimuonParams", "train_nll_sum": 9225.666592051115, "train_tokens": 5206.0, "train_token_mean_nll": 1.772121896283349, "grad_norm": 13.926655769348145, "t": 1793745206.4926019} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 67, "batch_sha256": "ff1501c3c883e795527b8a5d101dcdadb78e546b6ecdc81e40d7628b98ca00e6", "params_type": "AdamParams", "train_nll_sum": 14104.69840427676, "train_tokens": 6707.0, "train_token_mean_nll": 2.102981721228084, "grad_norm": 10.821505546569824, "t": 1793745213.2211926} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 67, "batch_sha256": "ff1501c3c883e795527b8a5d101dcdadb78e546b6ecdc81e40d7628b98ca00e6", "params_type": "DimuonParams", "train_nll_sum": 14117.732319701656, "train_tokens": 6707.0, "train_token_mean_nll": 2.104925051394313, "grad_norm": 12.983717918395996, "t": 1793745213.2220047} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 67, "batch_sha256": "8b299423205210277a1d3a8e9cc52a13da7f143845fef0362432010466a32229", "params_type": "AdamParams", "train_nll_sum": 13835.81991245356, "train_tokens": 6242.0, "train_token_mean_nll": 2.216568393536296, "grad_norm": 11.65343952178955, "t": 1793745213.222751} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 67, "batch_sha256": "8b299423205210277a1d3a8e9cc52a13da7f143845fef0362432010466a32229", "params_type": "DimuonParams", "train_nll_sum": 13848.515968095864, "train_tokens": 6242.0, "train_token_mean_nll": 2.2186023659237204, "grad_norm": 13.798462867736816, "t": 1793745213.2238238} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 67, "batch_sha256": "298e4ad35888877d437721f52193d3e0263c1df1772dc57d231b8cfaba99d5d1", "params_type": "AdamParams", "train_nll_sum": 11647.338815050072, "train_tokens": 5220.0, "train_token_mean_nll": 2.231290960737562, "grad_norm": 13.84898567199707, "t": 1793745213.3027306} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 67, "batch_sha256": "298e4ad35888877d437721f52193d3e0263c1df1772dc57d231b8cfaba99d5d1", "params_type": "DimuonParams", "train_nll_sum": 11653.922374225322, "train_tokens": 5220.0, "train_token_mean_nll": 2.232552178970368, "grad_norm": 16.46110725402832, "t": 1793745213.303492} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 68, "batch_sha256": "76f4ab79119ee76dcf92087a903f4c150ee53331bdc723e27ed00628b8b0e926", "params_type": "AdamParams", "train_nll_sum": 10190.660730736425, "train_tokens": 5066.0, "train_token_mean_nll": 2.0115792993952675, "grad_norm": 14.1373929977417, "t": 1793745220.023676} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 68, "batch_sha256": "76f4ab79119ee76dcf92087a903f4c150ee53331bdc723e27ed00628b8b0e926", "params_type": "DimuonParams", "train_nll_sum": 10186.155174156016, "train_tokens": 5066.0, "train_token_mean_nll": 2.0106899277844485, "grad_norm": 16.624202728271484, "t": 1793745220.0243754} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 68, "batch_sha256": "dacc04c37e4c29d43c6fc57331ec00e4bc46bf797750fc0afb90065756afb5d3", "params_type": "AdamParams", "train_nll_sum": 10162.98834228127, "train_tokens": 5375.0, "train_token_mean_nll": 1.8907885287965156, "grad_norm": 12.610620498657227, "t": 1793745220.0282495} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 68, "batch_sha256": "dacc04c37e4c29d43c6fc57331ec00e4bc46bf797750fc0afb90065756afb5d3", "params_type": "DimuonParams", "train_nll_sum": 10165.643783418578, "train_tokens": 5375.0, "train_token_mean_nll": 1.8912825643569449, "grad_norm": 15.133340835571289, "t": 1793745220.0290933} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 68, "batch_sha256": "92eb41d46a75fd48fbc6e93d741aba0181d033edd25cdde5b1fd5c948c0f809f", "params_type": "AdamParams", "train_nll_sum": 11551.875400755694, "train_tokens": 5483.0, "train_token_mean_nll": 2.10685307327297, "grad_norm": 14.022994041442871, "t": 1793745220.0297856} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 68, "batch_sha256": "92eb41d46a75fd48fbc6e93d741aba0181d033edd25cdde5b1fd5c948c0f809f", "params_type": "DimuonParams", "train_nll_sum": 11558.520812107565, "train_tokens": 5483.0, "train_token_mean_nll": 2.108065076072873, "grad_norm": 16.472951889038086, "t": 1793745220.8699622} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 69, "batch_sha256": "6958d5a5adc6c3355cbf8c47a33b021708a7f5dbf682bc9cdbae0dd722e5b9ac", "params_type": "AdamParams", "train_nll_sum": 10761.250973127717, "train_tokens": 5101.0, "train_token_mean_nll": 2.1096355563865354, "grad_norm": 14.39922046661377, "t": 1793745227.995769} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 69, "batch_sha256": "6958d5a5adc6c3355cbf8c47a33b021708a7f5dbf682bc9cdbae0dd722e5b9ac", "params_type": "DimuonParams", "train_nll_sum": 10759.46418709041, "train_tokens": 5101.0, "train_token_mean_nll": 2.109285274865793, "grad_norm": 17.066650390625, "t": 1793745228.0892222} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 69, "batch_sha256": "0ae5b47d5455f49f235c7a93469e2f9e1b7fba91b0ed58ce01c331c27d8dab4b", "params_type": "AdamParams", "train_nll_sum": 13836.667969677284, "train_tokens": 6656.0, "train_token_mean_nll": 2.078826317559688, "grad_norm": 11.319969177246094, "t": 1793745228.0905595} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 69, "batch_sha256": "0ae5b47d5455f49f235c7a93469e2f9e1b7fba91b0ed58ce01c331c27d8dab4b", "params_type": "DimuonParams", "train_nll_sum": 13841.842863492468, "train_tokens": 6656.0, "train_token_mean_nll": 2.079603795596825, "grad_norm": 13.42658805847168, "t": 1793745228.3493407} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 69, "batch_sha256": "6e947572117dcddff783c84a986bcedefc66656da9fbaeff38fbde8d2b218f29", "params_type": "AdamParams", "train_nll_sum": 15023.459774977859, "train_tokens": 8128.0, "train_token_mean_nll": 1.848358732157709, "grad_norm": 11.130921363830566, "t": 1793745228.3504097} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 69, "batch_sha256": "6e947572117dcddff783c84a986bcedefc66656da9fbaeff38fbde8d2b218f29", "params_type": "DimuonParams", "train_nll_sum": 15030.888095186458, "train_tokens": 8128.0, "train_token_mean_nll": 1.849272649506208, "grad_norm": 13.103469848632812, "t": 1793745228.3513408} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 70, "batch_sha256": "eba75e9aaa57ca7c9892a829562930ea4ec0211d6d12fae3ed1cab7f9b3cb67b", "params_type": "AdamParams", "train_nll_sum": 12708.680370532595, "train_tokens": 6820.0, "train_token_mean_nll": 1.8634428695795593, "grad_norm": 13.553832054138184, "t": 1793745235.4163244} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 70, "batch_sha256": "eba75e9aaa57ca7c9892a829562930ea4ec0211d6d12fae3ed1cab7f9b3cb67b", "params_type": "DimuonParams", "train_nll_sum": 12708.960685134143, "train_tokens": 6820.0, "train_token_mean_nll": 1.8634839714272937, "grad_norm": 14.6055326461792, "t": 1793745235.4172852} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 70, "batch_sha256": "cd2688e8efa1666bdb45ed99f1f6fe6408b19d6f0c10d999728fa9d233485cfe", "params_type": "AdamParams", "train_nll_sum": 13137.619432892669, "train_tokens": 5501.0, "train_token_mean_nll": 2.388223856188451, "grad_norm": 15.120969772338867, "t": 1793745235.4180572} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 70, "batch_sha256": "cd2688e8efa1666bdb45ed99f1f6fe6408b19d6f0c10d999728fa9d233485cfe", "params_type": "DimuonParams", "train_nll_sum": 13121.395165038708, "train_tokens": 5501.0, "train_token_mean_nll": 2.3852745255478474, "grad_norm": 17.136459350585938, "t": 1793745235.418736} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 70, "batch_sha256": "d3fbec652b1795837b526caeefbf6785f5440c8f4a361b88ca28e7f4d2b0fed9", "params_type": "AdamParams", "train_nll_sum": 10225.005592212941, "train_tokens": 4661.0, "train_token_mean_nll": 2.193736449734594, "grad_norm": 30.994632720947266, "t": 1793745235.4194076} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 70, "batch_sha256": "d3fbec652b1795837b526caeefbf6785f5440c8f4a361b88ca28e7f4d2b0fed9", "params_type": "DimuonParams", "train_nll_sum": 10232.679050158908, "train_tokens": 4661.0, "train_token_mean_nll": 2.195382761244134, "grad_norm": 41.40523910522461, "t": 1793745235.420017} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 71, "batch_sha256": "e451ed7e9994d8d90d343c1a3535b67ee9fd607a3f804186647cd89be28e16b6", "params_type": "AdamParams", "train_nll_sum": 11896.365921085086, "train_tokens": 5812.0, "train_token_mean_nll": 2.0468626842885556, "grad_norm": 13.587483406066895, "t": 1793745242.9800699} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 71, "batch_sha256": "e451ed7e9994d8d90d343c1a3535b67ee9fd607a3f804186647cd89be28e16b6", "params_type": "DimuonParams", "train_nll_sum": 11886.773266069249, "train_tokens": 5812.0, "train_token_mean_nll": 2.045212193060779, "grad_norm": 16.328222274780273, "t": 1793745242.98176} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 71, "batch_sha256": "d8d3096e1cebfc2a1fe49db798e7edf3e3209730ac74b037832f441c68786a23", "params_type": "AdamParams", "train_nll_sum": 11576.271679686077, "train_tokens": 6201.0, "train_token_mean_nll": 1.8668394903541488, "grad_norm": 10.244392395019531, "t": 1793745242.9828138} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 71, "batch_sha256": "d8d3096e1cebfc2a1fe49db798e7edf3e3209730ac74b037832f441c68786a23", "params_type": "DimuonParams", "train_nll_sum": 11584.712157408543, "train_tokens": 6201.0, "train_token_mean_nll": 1.8682006381887668, "grad_norm": 12.061627388000488, "t": 1793745243.0108035} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 71, "batch_sha256": "8c74b87a6fe70775b4273b685480b5d7634f15d2e7dc8a2ada6ed0d1dc5aa4aa", "params_type": "AdamParams", "train_nll_sum": 15838.167128922729, "train_tokens": 7584.0, "train_token_mean_nll": 2.088365918898039, "grad_norm": 10.334372520446777, "t": 1793745243.01292} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 71, "batch_sha256": "8c74b87a6fe70775b4273b685480b5d7634f15d2e7dc8a2ada6ed0d1dc5aa4aa", "params_type": "DimuonParams", "train_nll_sum": 15845.825469404253, "train_tokens": 7584.0, "train_token_mean_nll": 2.089375721176721, "grad_norm": 12.17882251739502, "t": 1793745243.0149717} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 72, "batch_sha256": "e2e32646fe9b89f98880192f2e54646fe848abadd686769abdc626a348b7efbd", "params_type": "AdamParams", "train_nll_sum": 10491.422634668696, "train_tokens": 5108.0, "train_token_mean_nll": 2.0539198580009193, "grad_norm": 12.70982837677002, "t": 1793745249.70726} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 72, "batch_sha256": "e2e32646fe9b89f98880192f2e54646fe848abadd686769abdc626a348b7efbd", "params_type": "DimuonParams", "train_nll_sum": 10494.04793988629, "train_tokens": 5108.0, "train_token_mean_nll": 2.054433817518851, "grad_norm": 15.212495803833008, "t": 1793745249.7080264} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 72, "batch_sha256": "ba48ecef7852c8b833fa3db54d89937b633b454824a690e39f88caaae117a011", "params_type": "AdamParams", "train_nll_sum": 11281.957498620495, "train_tokens": 5553.0, "train_token_mean_nll": 2.0316869257375285, "grad_norm": 12.477081298828125, "t": 1793745249.7089102} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 72, "batch_sha256": "ba48ecef7852c8b833fa3db54d89937b633b454824a690e39f88caaae117a011", "params_type": "DimuonParams", "train_nll_sum": 11275.684911101791, "train_tokens": 5553.0, "train_token_mean_nll": 2.030557340374895, "grad_norm": 14.915962219238281, "t": 1793745249.7097201} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 72, "batch_sha256": "e2f234d1c013f3c77d26182505ca017e566908681f4cd3739b0907ec512982b3", "params_type": "AdamParams", "train_nll_sum": 13645.958794140442, "train_tokens": 6639.0, "train_token_mean_nll": 2.0554238280072967, "grad_norm": 10.578371047973633, "t": 1793745249.7935183} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 72, "batch_sha256": "e2f234d1c013f3c77d26182505ca017e566908681f4cd3739b0907ec512982b3", "params_type": "DimuonParams", "train_nll_sum": 13648.321068667798, "train_tokens": 6639.0, "train_token_mean_nll": 2.055779645830366, "grad_norm": 12.688536643981934, "t": 1793745249.7942927} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 73, "batch_sha256": "47408e1be8f671ac5602ced2a90c0e9a9d29b54060104a1163c39d115b854452", "params_type": "AdamParams", "train_nll_sum": 13657.97290358739, "train_tokens": 6351.0, "train_token_mean_nll": 2.1505232095083278, "grad_norm": 14.870101928710938, "t": 1793745256.1968489} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 73, "batch_sha256": "47408e1be8f671ac5602ced2a90c0e9a9d29b54060104a1163c39d115b854452", "params_type": "DimuonParams", "train_nll_sum": 13658.744292869245, "train_tokens": 6351.0, "train_token_mean_nll": 2.1506446690079115, "grad_norm": 17.428373336791992, "t": 1793745256.1976259} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 73, "batch_sha256": "5abeb8b89ff745a51e5cf91c6434b8f0e47b38effd01a63ee51ae753300b07bb", "params_type": "AdamParams", "train_nll_sum": 12237.395303222776, "train_tokens": 5780.0, "train_token_mean_nll": 2.117196419242695, "grad_norm": 13.470232009887695, "t": 1793745256.2183464} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 73, "batch_sha256": "5abeb8b89ff745a51e5cf91c6434b8f0e47b38effd01a63ee51ae753300b07bb", "params_type": "DimuonParams", "train_nll_sum": 12250.233757659571, "train_tokens": 5780.0, "train_token_mean_nll": 2.1194176051314138, "grad_norm": 16.30714988708496, "t": 1793745256.2190807} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 73, "batch_sha256": "f80d0fbb6d238b129631ff15be3c6fb1cb1ee87c526059d30ed3704b018f2e88", "params_type": "AdamParams", "train_nll_sum": 8277.252509438918, "train_tokens": 3876.0, "train_token_mean_nll": 2.1355140633227343, "grad_norm": 13.736653327941895, "t": 1793745256.2218566} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 73, "batch_sha256": "f80d0fbb6d238b129631ff15be3c6fb1cb1ee87c526059d30ed3704b018f2e88", "params_type": "DimuonParams", "train_nll_sum": 8276.535688768261, "train_tokens": 3876.0, "train_token_mean_nll": 2.1353291250692106, "grad_norm": 16.491971969604492, "t": 1793745256.3066027} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 74, "batch_sha256": "8a85c32a692f01f63a963e75fa2ef264210000057ed7a191834127b292a253e4", "params_type": "AdamParams", "train_nll_sum": 15461.142799520845, "train_tokens": 7393.0, "train_token_mean_nll": 2.0913218990289253, "grad_norm": 13.797465324401855, "t": 1793745263.71214} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 74, "batch_sha256": "8a85c32a692f01f63a963e75fa2ef264210000057ed7a191834127b292a253e4", "params_type": "DimuonParams", "train_nll_sum": 15451.092426354378, "train_tokens": 7393.0, "train_token_mean_nll": 2.0899624545319058, "grad_norm": 15.373629570007324, "t": 1793745263.927504} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 74, "batch_sha256": "fcff70d4fa91234e8ca01a7602c55163ef21b57067d665f385b4989053c067dd", "params_type": "AdamParams", "train_nll_sum": 9163.559790787296, "train_tokens": 5283.0, "train_token_mean_nll": 1.734537155174578, "grad_norm": 14.01591682434082, "t": 1793745263.9286768} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 74, "batch_sha256": "fcff70d4fa91234e8ca01a7602c55163ef21b57067d665f385b4989053c067dd", "params_type": "DimuonParams", "train_nll_sum": 9180.912872203282, "train_tokens": 5283.0, "train_token_mean_nll": 1.7378218573165403, "grad_norm": 16.73194122314453, "t": 1793745263.929531} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 74, "batch_sha256": "9b48e9065c50173c8f5db494ea5f118133953e4b365c9090c28fc8fd8e2c01cb", "params_type": "AdamParams", "train_nll_sum": 12759.895696628457, "train_tokens": 6348.0, "train_token_mean_nll": 2.0100654846610677, "grad_norm": 11.6029052734375, "t": 1793745263.9307957} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 74, "batch_sha256": "9b48e9065c50173c8f5db494ea5f118133953e4b365c9090c28fc8fd8e2c01cb", "params_type": "DimuonParams", "train_nll_sum": 12764.982849505075, "train_tokens": 6348.0, "train_token_mean_nll": 2.0108668635011147, "grad_norm": 13.861800193786621, "t": 1793745263.9345741} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 75, "batch_sha256": "98e2ab98d53e633310b0d7fb4e76345dd953e4024952c818fc9b30f42320ef00", "params_type": "AdamParams", "train_nll_sum": 14645.00192176636, "train_tokens": 7446.0, "train_token_mean_nll": 1.9668280851150093, "grad_norm": 11.19489574432373, "t": 1793745271.8702736} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 75, "batch_sha256": "98e2ab98d53e633310b0d7fb4e76345dd953e4024952c818fc9b30f42320ef00", "params_type": "DimuonParams", "train_nll_sum": 14631.425447430742, "train_tokens": 7446.0, "train_token_mean_nll": 1.965004760600422, "grad_norm": 13.320965766906738, "t": 1793745271.905864} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 75, "batch_sha256": "41e1195a76137d8c02df92b2718e5717d296b443a267a02b6bd7488c0959ada0", "params_type": "AdamParams", "train_nll_sum": 13127.776772487008, "train_tokens": 6953.0, "train_token_mean_nll": 1.8880737483801249, "grad_norm": 11.689085006713867, "t": 1793745271.9067097} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 75, "batch_sha256": "41e1195a76137d8c02df92b2718e5717d296b443a267a02b6bd7488c0959ada0", "params_type": "DimuonParams", "train_nll_sum": 13122.335600513745, "train_tokens": 6953.0, "train_token_mean_nll": 1.887291183735617, "grad_norm": 13.929357528686523, "t": 1793745271.9075534} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 75, "batch_sha256": "8adc07ca50fe888c7ffe991ad44563043f98da34e867d1c80a77b41ec6d1d087", "params_type": "AdamParams", "train_nll_sum": 10950.714779278243, "train_tokens": 5698.0, "train_token_mean_nll": 1.9218523656156974, "grad_norm": 12.840128898620605, "t": 1793745272.0665703} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 75, "batch_sha256": "8adc07ca50fe888c7ffe991ad44563043f98da34e867d1c80a77b41ec6d1d087", "params_type": "DimuonParams", "train_nll_sum": 10956.475634167065, "train_tokens": 5698.0, "train_token_mean_nll": 1.9228633966597166, "grad_norm": 15.399463653564453, "t": 1793745272.0674105} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 76, "batch_sha256": "7396544ede609941d10f15b1cd0c1ea82042ed5677d913f78e48ea17c6ae646e", "params_type": "AdamParams", "train_nll_sum": 11057.415028766554, "train_tokens": 6245.0, "train_token_mean_nll": 1.7706028869121784, "grad_norm": 12.469627380371094, "t": 1793745279.0074434} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 76, "batch_sha256": "7396544ede609941d10f15b1cd0c1ea82042ed5677d913f78e48ea17c6ae646e", "params_type": "DimuonParams", "train_nll_sum": 11064.938108964878, "train_tokens": 6245.0, "train_token_mean_nll": 1.7718075434691558, "grad_norm": 14.96532917022705, "t": 1793745279.1120958} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 76, "batch_sha256": "4607619119d4f632dae68711d1dc71c77702952862369bbd78cc502ccb86952b", "params_type": "AdamParams", "train_nll_sum": 9836.489234478355, "train_tokens": 5546.0, "train_token_mean_nll": 1.7736186863466201, "grad_norm": 11.69991683959961, "t": 1793745279.1130092} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 76, "batch_sha256": "4607619119d4f632dae68711d1dc71c77702952862369bbd78cc502ccb86952b", "params_type": "DimuonParams", "train_nll_sum": 9851.47086232485, "train_tokens": 5546.0, "train_token_mean_nll": 1.7763200256626126, "grad_norm": 13.922737121582031, "t": 1793745279.1137223} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 76, "batch_sha256": "d0c6fe96542f673a53705a4cc7e217076386418518d73df1f244412d75400172", "params_type": "AdamParams", "train_nll_sum": 13577.011777036725, "train_tokens": 6870.0, "train_token_mean_nll": 1.9762753678364957, "grad_norm": 11.717439651489258, "t": 1793745279.1154168} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 76, "batch_sha256": "d0c6fe96542f673a53705a4cc7e217076386418518d73df1f244412d75400172", "params_type": "DimuonParams", "train_nll_sum": 13563.306837468243, "train_tokens": 6870.0, "train_token_mean_nll": 1.9742804712471969, "grad_norm": 14.251822471618652, "t": 1793745279.3685007} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 77, "batch_sha256": "8ddf313dfbe5747f96dfdf062ae88da84e0819226fca3f720cc0a4c4fa108aba", "params_type": "AdamParams", "train_nll_sum": 10264.867062444904, "train_tokens": 4859.0, "train_token_mean_nll": 2.1125472447921188, "grad_norm": 13.281329154968262, "t": 1793745286.0132227} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 77, "batch_sha256": "8ddf313dfbe5747f96dfdf062ae88da84e0819226fca3f720cc0a4c4fa108aba", "params_type": "DimuonParams", "train_nll_sum": 10266.054683930826, "train_tokens": 4859.0, "train_token_mean_nll": 2.1127916616445415, "grad_norm": 15.773157119750977, "t": 1793745286.0140557} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 77, "batch_sha256": "f2991e5a78368522628e691160810b631299b8410f64779ceae5b5815cbcbe5a", "params_type": "AdamParams", "train_nll_sum": 14722.637170775412, "train_tokens": 6800.0, "train_token_mean_nll": 2.1650937015846194, "grad_norm": 12.431339263916016, "t": 1793745286.017025} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 77, "batch_sha256": "f2991e5a78368522628e691160810b631299b8410f64779ceae5b5815cbcbe5a", "params_type": "DimuonParams", "train_nll_sum": 14708.419374852629, "train_tokens": 6800.0, "train_token_mean_nll": 2.1630028492430338, "grad_norm": 15.251462936401367, "t": 1793745286.0178978} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 77, "batch_sha256": "45393a98e3c8cd54c599fa2e676ff4bd16866ef95ad197bbdf4a6267a197cafd", "params_type": "AdamParams", "train_nll_sum": 11872.295118640031, "train_tokens": 5545.0, "train_token_mean_nll": 2.1410811755888246, "grad_norm": 12.069969177246094, "t": 1793745286.0207822} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 77, "batch_sha256": "45393a98e3c8cd54c599fa2e676ff4bd16866ef95ad197bbdf4a6267a197cafd", "params_type": "DimuonParams", "train_nll_sum": 11870.558448058562, "train_tokens": 5545.0, "train_token_mean_nll": 2.140767979812184, "grad_norm": 14.724410057067871, "t": 1793745286.8466618} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 78, "batch_sha256": "da9e20abd2abe29a1fa8e83594b6617ae95171781a478da3da480ea0447f929d", "params_type": "AdamParams", "train_nll_sum": 12797.986492332895, "train_tokens": 6786.0, "train_token_mean_nll": 1.8859396540425721, "grad_norm": 11.308110237121582, "t": 1793745294.3535793} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 78, "batch_sha256": "da9e20abd2abe29a1fa8e83594b6617ae95171781a478da3da480ea0447f929d", "params_type": "DimuonParams", "train_nll_sum": 12800.63213967044, "train_tokens": 6786.0, "train_token_mean_nll": 1.8863295224978545, "grad_norm": 13.452617645263672, "t": 1793745294.3832788} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 78, "batch_sha256": "310c767f0ee543d4c825c4793e0b27e89818bf0bfe0d68adba86b9beebed9517", "params_type": "AdamParams", "train_nll_sum": 13408.640300398267, "train_tokens": 6655.0, "train_token_mean_nll": 2.0148219835309193, "grad_norm": 11.178689002990723, "t": 1793745294.3870084} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 78, "batch_sha256": "310c767f0ee543d4c825c4793e0b27e89818bf0bfe0d68adba86b9beebed9517", "params_type": "DimuonParams", "train_nll_sum": 13402.225118874787, "train_tokens": 6655.0, "train_token_mean_nll": 2.0138580193651068, "grad_norm": 13.174248695373535, "t": 1793745294.3880513} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 78, "batch_sha256": "70edcf9da1500d5af7812ad7d6dfbb04a1739e209a70e6c12ee4f8c187f72f28", "params_type": "AdamParams", "train_nll_sum": 11735.17141145857, "train_tokens": 6620.0, "train_token_mean_nll": 1.772684503241476, "grad_norm": 11.951926231384277, "t": 1793745294.4890354} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 78, "batch_sha256": "70edcf9da1500d5af7812ad7d6dfbb04a1739e209a70e6c12ee4f8c187f72f28", "params_type": "DimuonParams", "train_nll_sum": 11722.780032966253, "train_tokens": 6620.0, "train_token_mean_nll": 1.770812693801549, "grad_norm": 14.535768508911133, "t": 1793745294.4900892} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 79, "batch_sha256": "834142a0e097109fe53a00e94c1ee4446c7a700fe4e81fc38bad7865c0a44b36", "params_type": "AdamParams", "train_nll_sum": 13139.949980545282, "train_tokens": 6504.0, "train_token_mean_nll": 2.0202875123839608, "grad_norm": 13.094855308532715, "t": 1793745301.4760973} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 79, "batch_sha256": "834142a0e097109fe53a00e94c1ee4446c7a700fe4e81fc38bad7865c0a44b36", "params_type": "DimuonParams", "train_nll_sum": 13144.565454113726, "train_tokens": 6504.0, "train_token_mean_nll": 2.020997148541471, "grad_norm": 15.4951753616333, "t": 1793745301.477} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 79, "batch_sha256": "a7398358fae1394c6b5ecf33395a38d23eb065096a0713de8094f034ccf3d1f8", "params_type": "AdamParams", "train_nll_sum": 13462.105689830072, "train_tokens": 6616.0, "train_token_mean_nll": 2.0347801828642793, "grad_norm": 12.075126647949219, "t": 1793745301.4778285} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 79, "batch_sha256": "a7398358fae1394c6b5ecf33395a38d23eb065096a0713de8094f034ccf3d1f8", "params_type": "DimuonParams", "train_nll_sum": 13462.08336553554, "train_tokens": 6616.0, "train_token_mean_nll": 2.0347768085755047, "grad_norm": 14.175235748291016, "t": 1793745301.4785888} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 79, "batch_sha256": "b3b98a72ceed0a956ef8225c0a6e28047b1fd0ebb6390015c5aa828ca480d509", "params_type": "AdamParams", "train_nll_sum": 11565.374101786538, "train_tokens": 5483.0, "train_token_mean_nll": 2.1093149921186463, "grad_norm": 14.182982444763184, "t": 1793745301.4792426} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 79, "batch_sha256": "b3b98a72ceed0a956ef8225c0a6e28047b1fd0ebb6390015c5aa828ca480d509", "params_type": "DimuonParams", "train_nll_sum": 11562.177779829464, "train_tokens": 5483.0, "train_token_mean_nll": 2.108732040822445, "grad_norm": 17.56406593322754, "t": 1793745301.4799259} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 80, "batch_sha256": "031a15d3f6ba066158ebd6d6d3a78f565b92545c72330c797964ebb0d9042068", "params_type": "AdamParams", "train_nll_sum": 15957.01578800055, "train_tokens": 7894.0, "train_token_mean_nll": 2.0214106648087853, "grad_norm": 11.0610990524292, "t": 1793745308.728312} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 80, "batch_sha256": "031a15d3f6ba066158ebd6d6d3a78f565b92545c72330c797964ebb0d9042068", "params_type": "DimuonParams", "train_nll_sum": 15932.7654955062, "train_tokens": 7894.0, "train_token_mean_nll": 2.018338674373727, "grad_norm": 13.44176197052002, "t": 1793745308.7635875} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 80, "batch_sha256": "52ca14dfe9ee5ea69d0ec2f5bec34d9578f4e7c7e151b214cab0e9bdbd1d06b6", "params_type": "AdamParams", "train_nll_sum": 10520.9465098709, "train_tokens": 5108.0, "train_token_mean_nll": 2.0596997865839666, "grad_norm": 14.220805168151855, "t": 1793745308.7643268} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 80, "batch_sha256": "52ca14dfe9ee5ea69d0ec2f5bec34d9578f4e7c7e151b214cab0e9bdbd1d06b6", "params_type": "DimuonParams", "train_nll_sum": 10514.546254530544, "train_tokens": 5108.0, "train_token_mean_nll": 2.058446800025557, "grad_norm": 17.060270309448242, "t": 1793745308.765002} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 80, "batch_sha256": "1ab2241740041c9c851abb2dcfc31278ac635a388f3e433827f230123834fa5d", "params_type": "AdamParams", "train_nll_sum": 13383.464017174598, "train_tokens": 6162.0, "train_token_mean_nll": 2.1719350887982145, "grad_norm": 13.280694961547852, "t": 1793745308.9710224} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 80, "batch_sha256": "1ab2241740041c9c851abb2dcfc31278ac635a388f3e433827f230123834fa5d", "params_type": "DimuonParams", "train_nll_sum": 13368.836143089004, "train_tokens": 6162.0, "train_token_mean_nll": 2.169561204655794, "grad_norm": 15.760180473327637, "t": 1793745308.9721694} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 81, "batch_sha256": "8cadf76329cc80f4828d49e5424389a6c6bdaed2dc58c75c93478317248c3cd3", "params_type": "AdamParams", "train_nll_sum": 10337.37775079505, "train_tokens": 5358.0, "train_token_mean_nll": 1.9293351531905656, "grad_norm": 15.916473388671875, "t": 1793745315.7478595} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 81, "batch_sha256": "8cadf76329cc80f4828d49e5424389a6c6bdaed2dc58c75c93478317248c3cd3", "params_type": "DimuonParams", "train_nll_sum": 10355.463527821768, "train_tokens": 5358.0, "train_token_mean_nll": 1.9327106248267578, "grad_norm": 19.948284149169922, "t": 1793745316.0839539} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 81, "batch_sha256": "5471aa7b8f1735d98788c6e78ea82d0a0fc4a09281041534414a5ef03a3e6a57", "params_type": "AdamParams", "train_nll_sum": 9782.836978216585, "train_tokens": 5289.0, "train_token_mean_nll": 1.8496572089651322, "grad_norm": 11.865866661071777, "t": 1793745316.0848145} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 81, "batch_sha256": "5471aa7b8f1735d98788c6e78ea82d0a0fc4a09281041534414a5ef03a3e6a57", "params_type": "DimuonParams", "train_nll_sum": 9783.67039890831, "train_tokens": 5289.0, "train_token_mean_nll": 1.8498147851972604, "grad_norm": 14.320820808410645, "t": 1793745316.0876307} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 81, "batch_sha256": "597597ef427e9e289d6b75dc2837ef86813457c68e77f4eb29fd890f07a60e3a", "params_type": "AdamParams", "train_nll_sum": 12015.160637478288, "train_tokens": 5647.0, "train_token_mean_nll": 2.127706859833237, "grad_norm": 16.858856201171875, "t": 1793745316.0886047} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 81, "batch_sha256": "597597ef427e9e289d6b75dc2837ef86813457c68e77f4eb29fd890f07a60e3a", "params_type": "DimuonParams", "train_nll_sum": 12017.600314786738, "train_tokens": 5647.0, "train_token_mean_nll": 2.1281388905235943, "grad_norm": 18.607192993164062, "t": 1793745316.0895755} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 82, "batch_sha256": "78af3496648e639b5d8c420222527047062017ed14bc61871ae8c1912361aabd", "params_type": "AdamParams", "train_nll_sum": 11182.11103406723, "train_tokens": 5359.0, "train_token_mean_nll": 2.086604036959737, "grad_norm": 11.611794471740723, "t": 1793745323.4361176} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 82, "batch_sha256": "78af3496648e639b5d8c420222527047062017ed14bc61871ae8c1912361aabd", "params_type": "DimuonParams", "train_nll_sum": 11185.689207357413, "train_tokens": 5359.0, "train_token_mean_nll": 2.0872717311732436, "grad_norm": 14.04818058013916, "t": 1793745323.477291} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 82, "batch_sha256": "0c45b4d6a3d5b026ac6d649b5ec9deaa2bb4fa541590981a755448018fb8990a", "params_type": "AdamParams", "train_nll_sum": 13968.42684362191, "train_tokens": 6713.0, "train_token_mean_nll": 2.0808024495191284, "grad_norm": 12.391444206237793, "t": 1793745323.4780946} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 82, "batch_sha256": "0c45b4d6a3d5b026ac6d649b5ec9deaa2bb4fa541590981a755448018fb8990a", "params_type": "DimuonParams", "train_nll_sum": 13969.621057570384, "train_tokens": 6713.0, "train_token_mean_nll": 2.080980345236166, "grad_norm": 14.537883758544922, "t": 1793745323.480928} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 82, "batch_sha256": "1859b464479511530f2c8284721c1471f540431c4c9b844cbf9b41892d3fdd05", "params_type": "AdamParams", "train_nll_sum": 14691.287281417446, "train_tokens": 7080.0, "train_token_mean_nll": 2.0750405764713906, "grad_norm": 12.20995807647705, "t": 1793745323.4818554} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 82, "batch_sha256": "1859b464479511530f2c8284721c1471f540431c4c9b844cbf9b41892d3fdd05", "params_type": "DimuonParams", "train_nll_sum": 14707.556356691503, "train_tokens": 7080.0, "train_token_mean_nll": 2.077338468459252, "grad_norm": 14.901934623718262, "t": 1793745323.4838636} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 83, "batch_sha256": "f59b804c13d2b71aa1fced4a9fff0a37748118927fb1d9b3e094d4a7c8fd8792", "params_type": "AdamParams", "train_nll_sum": 14223.555045296243, "train_tokens": 7632.0, "train_token_mean_nll": 1.8636733549916462, "grad_norm": 14.833830833435059, "t": 1793745330.638824} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 83, "batch_sha256": "f59b804c13d2b71aa1fced4a9fff0a37748118927fb1d9b3e094d4a7c8fd8792", "params_type": "DimuonParams", "train_nll_sum": 14239.503617353988, "train_tokens": 7632.0, "train_token_mean_nll": 1.8657630525883109, "grad_norm": 20.835403442382812, "t": 1793745330.7545192} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 83, "batch_sha256": "ca3aada1721de6d1a8dccef68fc56d5b49af2235002329e4f4bbea6db74a44ad", "params_type": "AdamParams", "train_nll_sum": 10832.65984095936, "train_tokens": 5331.0, "train_token_mean_nll": 2.0320127257473946, "grad_norm": 11.86154556274414, "t": 1793745331.0074418} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 83, "batch_sha256": "ca3aada1721de6d1a8dccef68fc56d5b49af2235002329e4f4bbea6db74a44ad", "params_type": "DimuonParams", "train_nll_sum": 10825.60455254178, "train_tokens": 5331.0, "train_token_mean_nll": 2.0306892801616545, "grad_norm": 14.603023529052734, "t": 1793745331.008713} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 83, "batch_sha256": "db6b336ddeff56dac99f9c139490e039d5d89ff4eb68d6bd12654e404847e86a", "params_type": "AdamParams", "train_nll_sum": 9759.827572271985, "train_tokens": 4605.0, "train_token_mean_nll": 2.119397952719215, "grad_norm": 16.608741760253906, "t": 1793745331.009643} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 83, "batch_sha256": "db6b336ddeff56dac99f9c139490e039d5d89ff4eb68d6bd12654e404847e86a", "params_type": "DimuonParams", "train_nll_sum": 9746.98164958314, "train_tokens": 4605.0, "train_token_mean_nll": 2.116608392960508, "grad_norm": 19.055479049682617, "t": 1793745331.0103981} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 84, "batch_sha256": "45c26c7290e67a38d919151c1eb779d9e29e11b008ee18cae033577b5ab0a739", "params_type": "AdamParams", "train_nll_sum": 12666.407714487283, "train_tokens": 6150.0, "train_token_mean_nll": 2.0595784901605336, "grad_norm": 11.295867919921875, "t": 1793745338.7994034} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 84, "batch_sha256": "45c26c7290e67a38d919151c1eb779d9e29e11b008ee18cae033577b5ab0a739", "params_type": "DimuonParams", "train_nll_sum": 12659.705858477206, "train_tokens": 6150.0, "train_token_mean_nll": 2.0584887574759683, "grad_norm": 13.361083984375, "t": 1793745338.8220575} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 84, "batch_sha256": "a242c52aec9e51ffab293fed7314b75e7674c9c10912b684d0b5e740be7b2045", "params_type": "AdamParams", "train_nll_sum": 12918.395883917547, "train_tokens": 7223.0, "train_token_mean_nll": 1.7885083599498195, "grad_norm": 11.69979190826416, "t": 1793745338.8231215} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 84, "batch_sha256": "a242c52aec9e51ffab293fed7314b75e7674c9c10912b684d0b5e740be7b2045", "params_type": "DimuonParams", "train_nll_sum": 12909.173414181374, "train_tokens": 7223.0, "train_token_mean_nll": 1.7872315401054097, "grad_norm": 13.51761245727539, "t": 1793745338.8240497} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 84, "batch_sha256": "b4494969997db67ca0a52af20d94ae0139e897a5ae2c91460bda9d7f750b16a2", "params_type": "AdamParams", "train_nll_sum": 9729.630221228024, "train_tokens": 4689.0, "train_token_mean_nll": 2.0749904502512315, "grad_norm": 13.112966537475586, "t": 1793745338.82493} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 84, "batch_sha256": "b4494969997db67ca0a52af20d94ae0139e897a5ae2c91460bda9d7f750b16a2", "params_type": "DimuonParams", "train_nll_sum": 9720.44286856416, "train_tokens": 4689.0, "train_token_mean_nll": 2.0730311086722457, "grad_norm": 16.407434463500977, "t": 1793745338.9627807} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 85, "batch_sha256": "ba3a57ddeff9c44ee72c3876e20ea766dfb74638998f18555be0a5f5e586b473", "params_type": "AdamParams", "train_nll_sum": 12444.9900450366, "train_tokens": 6340.0, "train_token_mean_nll": 1.9629321837597162, "grad_norm": 12.29582691192627, "t": 1793745345.5924773} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 85, "batch_sha256": "ba3a57ddeff9c44ee72c3876e20ea766dfb74638998f18555be0a5f5e586b473", "params_type": "DimuonParams", "train_nll_sum": 12455.453593396698, "train_tokens": 6340.0, "train_token_mean_nll": 1.9645825857092585, "grad_norm": 15.140914916992188, "t": 1793745345.6028392} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 85, "batch_sha256": "93ce321d8fe4574841eafdb65f91e6f2669bf0dd0324ac9b8087ee26765de9cf", "params_type": "AdamParams", "train_nll_sum": 11940.764009468856, "train_tokens": 5793.0, "train_token_mean_nll": 2.0612401190175826, "grad_norm": 14.2402925491333, "t": 1793745345.6040227} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 85, "batch_sha256": "93ce321d8fe4574841eafdb65f91e6f2669bf0dd0324ac9b8087ee26765de9cf", "params_type": "DimuonParams", "train_nll_sum": 11943.146484510447, "train_tokens": 5793.0, "train_token_mean_nll": 2.061651386934308, "grad_norm": 17.453561782836914, "t": 1793745345.6048663} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 85, "batch_sha256": "d362d3fdf33d84be2db29a62e6573ea7b609a6a5fdf893e6e454e866a5076073", "params_type": "AdamParams", "train_nll_sum": 12062.24486563028, "train_tokens": 6278.0, "train_token_mean_nll": 1.9213515236747818, "grad_norm": 14.578194618225098, "t": 1793745345.6056776} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 85, "batch_sha256": "d362d3fdf33d84be2db29a62e6573ea7b609a6a5fdf893e6e454e866a5076073", "params_type": "DimuonParams", "train_nll_sum": 12060.67661769538, "train_tokens": 6278.0, "train_token_mean_nll": 1.9211017231117204, "grad_norm": 18.29613494873047, "t": 1793745345.6064665} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 86, "batch_sha256": "44c953142ba0a45c0962597342d79d69a2158cac69472217e000c7467f3fde06", "params_type": "AdamParams", "train_nll_sum": 13230.72771777994, "train_tokens": 6502.0, "train_token_mean_nll": 2.0348704579790744, "grad_norm": 11.268898963928223, "t": 1793745351.4914627} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 86, "batch_sha256": "44c953142ba0a45c0962597342d79d69a2158cac69472217e000c7467f3fde06", "params_type": "DimuonParams", "train_nll_sum": 13221.213961806152, "train_tokens": 6502.0, "train_token_mean_nll": 2.03340725343066, "grad_norm": 13.396872520446777, "t": 1793745351.532691} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 86, "batch_sha256": "625dae2156dec386dce338c0e0cc1c91f79a4b376f205d7e757ade86c22dd822", "params_type": "AdamParams", "train_nll_sum": 10682.530913600443, "train_tokens": 5820.0, "train_token_mean_nll": 1.8354864112715539, "grad_norm": 13.210797309875488, "t": 1793745351.5344274} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 86, "batch_sha256": "625dae2156dec386dce338c0e0cc1c91f79a4b376f205d7e757ade86c22dd822", "params_type": "DimuonParams", "train_nll_sum": 10683.754081159466, "train_tokens": 5820.0, "train_token_mean_nll": 1.8356965775188085, "grad_norm": 15.550955772399902, "t": 1793745351.5363843} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 86, "batch_sha256": "d9d47e899a207a224c8e2b39ca4be9bd760615d99e41b29cf5c069a500cd9b91", "params_type": "AdamParams", "train_nll_sum": 11046.076057949484, "train_tokens": 5781.0, "train_token_mean_nll": 1.9107552426828376, "grad_norm": 13.004501342773438, "t": 1793745351.8481526} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 86, "batch_sha256": "d9d47e899a207a224c8e2b39ca4be9bd760615d99e41b29cf5c069a500cd9b91", "params_type": "DimuonParams", "train_nll_sum": 11034.101812405124, "train_tokens": 5781.0, "train_token_mean_nll": 1.9086839322617408, "grad_norm": 15.33857250213623, "t": 1793745352.485087} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 87, "batch_sha256": "585a24332d63793dc03e6fb9cbefcd3427bb588fd94ec163d2c48bc46a641954", "params_type": "AdamParams", "train_nll_sum": 12967.52322763856, "train_tokens": 6398.0, "train_token_mean_nll": 2.0268088820941794, "grad_norm": 11.274292945861816, "t": 1793745359.4684846} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 87, "batch_sha256": "585a24332d63793dc03e6fb9cbefcd3427bb588fd94ec163d2c48bc46a641954", "params_type": "DimuonParams", "train_nll_sum": 12966.761936461602, "train_tokens": 6398.0, "train_token_mean_nll": 2.026689893163739, "grad_norm": 13.505993843078613, "t": 1793745359.4706917} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 87, "batch_sha256": "11b1fd45279eacc7545f854ee7cddacc08f1c03cd16482d195e0d7660c831e4b", "params_type": "AdamParams", "train_nll_sum": 12855.332767909229, "train_tokens": 6206.0, "train_token_mean_nll": 2.071436153385309, "grad_norm": 12.156885147094727, "t": 1793745359.4719615} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 87, "batch_sha256": "11b1fd45279eacc7545f854ee7cddacc08f1c03cd16482d195e0d7660c831e4b", "params_type": "DimuonParams", "train_nll_sum": 12853.831301305569, "train_tokens": 6206.0, "train_token_mean_nll": 2.071194215485912, "grad_norm": 15.031485557556152, "t": 1793745359.4727104} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 87, "batch_sha256": "6e03885797c80c45cb97af9fe7bf5bc69403ba9f27f1d693a3460055a7990a4b", "params_type": "AdamParams", "train_nll_sum": 12715.062481876668, "train_tokens": 6187.0, "train_token_mean_nll": 2.055125663791283, "grad_norm": 11.863655090332031, "t": 1793745359.473412} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 87, "batch_sha256": "6e03885797c80c45cb97af9fe7bf5bc69403ba9f27f1d693a3460055a7990a4b", "params_type": "DimuonParams", "train_nll_sum": 12714.810396328496, "train_tokens": 6187.0, "train_token_mean_nll": 2.0550849194001124, "grad_norm": 14.500508308410645, "t": 1793745360.33344} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 88, "batch_sha256": "edcf8dc5478f15f631d62bbf0cb019a2703f304d276f04a86a460ed3092363b6", "params_type": "AdamParams", "train_nll_sum": 13165.464887973303, "train_tokens": 6765.0, "train_token_mean_nll": 1.9461145436767633, "grad_norm": 10.967156410217285, "t": 1793745367.7227445} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 88, "batch_sha256": "edcf8dc5478f15f631d62bbf0cb019a2703f304d276f04a86a460ed3092363b6", "params_type": "DimuonParams", "train_nll_sum": 13184.484577663272, "train_tokens": 6765.0, "train_token_mean_nll": 1.948926027740321, "grad_norm": 13.360069274902344, "t": 1793745367.7236123} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 88, "batch_sha256": "70c14f5ae1d176b4c1830f898d93817dffcdb59221d685e63b450d273ff08a6f", "params_type": "AdamParams", "train_nll_sum": 12864.986080968552, "train_tokens": 6293.0, "train_token_mean_nll": 2.0443327635418007, "grad_norm": 13.291857719421387, "t": 1793745367.9704123} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 88, "batch_sha256": "70c14f5ae1d176b4c1830f898d93817dffcdb59221d685e63b450d273ff08a6f", "params_type": "DimuonParams", "train_nll_sum": 12872.479179159125, "train_tokens": 6293.0, "train_token_mean_nll": 2.045523467211048, "grad_norm": 16.16363525390625, "t": 1793745367.971188} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 88, "batch_sha256": "5b5556509a5eb61bc33cf059dc51c7f14f00a8de778437c7660e12ab35895404", "params_type": "AdamParams", "train_nll_sum": 13974.663768052, "train_tokens": 7455.0, "train_token_mean_nll": 1.8745357167071763, "grad_norm": 10.666199684143066, "t": 1793745367.972019} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 88, "batch_sha256": "5b5556509a5eb61bc33cf059dc51c7f14f00a8de778437c7660e12ab35895404", "params_type": "DimuonParams", "train_nll_sum": 13965.92794524503, "train_tokens": 7455.0, "train_token_mean_nll": 1.8733639094896084, "grad_norm": 12.74435806274414, "t": 1793745367.9727943} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 89, "batch_sha256": "894acb0dbcb70a7d4df665e7efa3e8eef238cdc4650a6cd7b68cdfbf16118a01", "params_type": "AdamParams", "train_nll_sum": 11208.143641513258, "train_tokens": 5346.0, "train_token_mean_nll": 2.096547632157362, "grad_norm": 14.641670227050781, "t": 1793745374.5217357} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 89, "batch_sha256": "894acb0dbcb70a7d4df665e7efa3e8eef238cdc4650a6cd7b68cdfbf16118a01", "params_type": "DimuonParams", "train_nll_sum": 11218.39891347537, "train_tokens": 5346.0, "train_token_mean_nll": 2.0984659396699157, "grad_norm": 17.716529846191406, "t": 1793745374.6695006} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 89, "batch_sha256": "1043f2607cfca2d05c771c869e92c203e0c4b5ee95b3689b2b85927b2b559ec0", "params_type": "AdamParams", "train_nll_sum": 12505.4323546302, "train_tokens": 5762.0, "train_token_mean_nll": 2.170328419755328, "grad_norm": 13.180727005004883, "t": 1793745374.6702845} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 89, "batch_sha256": "1043f2607cfca2d05c771c869e92c203e0c4b5ee95b3689b2b85927b2b559ec0", "params_type": "DimuonParams", "train_nll_sum": 12502.947745518053, "train_tokens": 5762.0, "train_token_mean_nll": 2.1698972137310055, "grad_norm": 15.862128257751465, "t": 1793745374.670991} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 89, "batch_sha256": "37ae2eafaa05b2e124c9076f2e9541ed5437ea04c59e1a53ff07401239e5ff64", "params_type": "AdamParams", "train_nll_sum": 12566.647972881898, "train_tokens": 6263.0, "train_token_mean_nll": 2.0064901760948266, "grad_norm": 15.826444625854492, "t": 1793745374.6717145} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 89, "batch_sha256": "37ae2eafaa05b2e124c9076f2e9541ed5437ea04c59e1a53ff07401239e5ff64", "params_type": "DimuonParams", "train_nll_sum": 12566.54047961875, "train_tokens": 6263.0, "train_token_mean_nll": 2.0064730128722257, "grad_norm": 19.778602600097656, "t": 1793745374.6724126} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 90, "batch_sha256": "c7255f31ac403d5e223864c6c87d0769ce70b28ec4d28b9387285c9721b60067", "params_type": "AdamParams", "train_nll_sum": 11214.000322586495, "train_tokens": 5236.0, "train_token_mean_nll": 2.141711291555862, "grad_norm": 12.94703197479248, "t": 1793745382.0676637} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 90, "batch_sha256": "c7255f31ac403d5e223864c6c87d0769ce70b28ec4d28b9387285c9721b60067", "params_type": "DimuonParams", "train_nll_sum": 11221.568278574203, "train_tokens": 5236.0, "train_token_mean_nll": 2.143156661301414, "grad_norm": 15.21663761138916, "t": 1793745382.1087976} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 90, "batch_sha256": "fe2d278c75dd378d8fd82bd3a42a8dcc6054e951403e6dda5e0fc2ea74150349", "params_type": "AdamParams", "train_nll_sum": 14454.194456976518, "train_tokens": 6695.0, "train_token_mean_nll": 2.1589536156798386, "grad_norm": 12.34907054901123, "t": 1793745382.1098316} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 90, "batch_sha256": "fe2d278c75dd378d8fd82bd3a42a8dcc6054e951403e6dda5e0fc2ea74150349", "params_type": "DimuonParams", "train_nll_sum": 14455.08187853339, "train_tokens": 6695.0, "train_token_mean_nll": 2.1590861655763094, "grad_norm": 15.157295227050781, "t": 1793745382.1108205} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 90, "batch_sha256": "8307b4b51f30c34ad6e32a09f5df1ded1d380a6bee16059996fa45095493021e", "params_type": "AdamParams", "train_nll_sum": 13471.051739104392, "train_tokens": 6685.0, "train_token_mean_nll": 2.0151161913394753, "grad_norm": 12.79021167755127, "t": 1793745382.1117022} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 90, "batch_sha256": "8307b4b51f30c34ad6e32a09f5df1ded1d380a6bee16059996fa45095493021e", "params_type": "DimuonParams", "train_nll_sum": 13485.165244256095, "train_tokens": 6685.0, "train_token_mean_nll": 2.017227411257456, "grad_norm": 14.93402099609375, "t": 1793745382.1125867} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 91, "batch_sha256": "4a627b6b95c505341771bbd8491c6e9beac55eb7f896643572e7590dce0b2126", "params_type": "AdamParams", "train_nll_sum": 13105.133090908159, "train_tokens": 7044.0, "train_token_mean_nll": 1.8604675029682225, "grad_norm": 11.099966049194336, "t": 1793745387.8929412} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 91, "batch_sha256": "4a627b6b95c505341771bbd8491c6e9beac55eb7f896643572e7590dce0b2126", "params_type": "DimuonParams", "train_nll_sum": 13100.758170968926, "train_tokens": 7044.0, "train_token_mean_nll": 1.8598464183658328, "grad_norm": 13.361479759216309, "t": 1793745387.8992412} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 91, "batch_sha256": "def8b5041675a0a5a79f849ff0be47c3508c3fca8f899cf64f338411a349eb4a", "params_type": "AdamParams", "train_nll_sum": 12083.26244466857, "train_tokens": 5715.0, "train_token_mean_nll": 2.1143066394870638, "grad_norm": 12.55800724029541, "t": 1793745387.9049687} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 91, "batch_sha256": "def8b5041675a0a5a79f849ff0be47c3508c3fca8f899cf64f338411a349eb4a", "params_type": "DimuonParams", "train_nll_sum": 12078.82862605604, "train_tokens": 5715.0, "train_token_mean_nll": 2.113530818207531, "grad_norm": 14.99129581451416, "t": 1793745388.4576757} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 91, "batch_sha256": "7eee93e82cdc9c2f32f811842764b4a46b00beb4f4423a5260037aca086d0af2", "params_type": "AdamParams", "train_nll_sum": 9415.352740148792, "train_tokens": 4538.0, "train_token_mean_nll": 2.07478024243032, "grad_norm": 15.6414155960083, "t": 1793745388.4585638} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 91, "batch_sha256": "7eee93e82cdc9c2f32f811842764b4a46b00beb4f4423a5260037aca086d0af2", "params_type": "DimuonParams", "train_nll_sum": 9419.251991399535, "train_tokens": 4538.0, "train_token_mean_nll": 2.0756394868663586, "grad_norm": 19.157461166381836, "t": 1793745388.4593875} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 92, "batch_sha256": "fa1afc69b11e95f5e1a7b884b52eef8c51a919327c050b36874acb8f0ac9a8e3", "params_type": "AdamParams", "train_nll_sum": 12027.418778574824, "train_tokens": 5961.0, "train_token_mean_nll": 2.0176847472864994, "grad_norm": 11.057717323303223, "t": 1793745395.231065} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 92, "batch_sha256": "fa1afc69b11e95f5e1a7b884b52eef8c51a919327c050b36874acb8f0ac9a8e3", "params_type": "DimuonParams", "train_nll_sum": 12035.688648004476, "train_tokens": 5961.0, "train_token_mean_nll": 2.019072076497983, "grad_norm": 13.582040786743164, "t": 1793745395.2327769} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 92, "batch_sha256": "317221ed6d5140e055eff37f8806b761709e7b039e992a770008ed8c1faa2e11", "params_type": "AdamParams", "train_nll_sum": 13355.579730791314, "train_tokens": 6439.0, "train_token_mean_nll": 2.0741698603496372, "grad_norm": 13.122736930847168, "t": 1793745395.2336807} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 92, "batch_sha256": "317221ed6d5140e055eff37f8806b761709e7b039e992a770008ed8c1faa2e11", "params_type": "DimuonParams", "train_nll_sum": 13362.660105436351, "train_tokens": 6439.0, "train_token_mean_nll": 2.0752694681528734, "grad_norm": 15.752378463745117, "t": 1793745395.2344868} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 92, "batch_sha256": "a39132d5f5caafd6652de8719120968afdd460a3eb39ba4d2f9c16ac9f03a138", "params_type": "AdamParams", "train_nll_sum": 10301.546626497593, "train_tokens": 4550.0, "train_token_mean_nll": 2.2640761816478228, "grad_norm": 15.952446937561035, "t": 1793745395.5775847} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 92, "batch_sha256": "a39132d5f5caafd6652de8719120968afdd460a3eb39ba4d2f9c16ac9f03a138", "params_type": "DimuonParams", "train_nll_sum": 10305.308559408359, "train_tokens": 4550.0, "train_token_mean_nll": 2.264902980089749, "grad_norm": 19.255247116088867, "t": 1793745395.5783217} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 93, "batch_sha256": "ad679c87fce8184c7030d1c8436d6af026ab828cbbb5cc93812141e1cfb17e9c", "params_type": "AdamParams", "train_nll_sum": 9323.984991681775, "train_tokens": 4879.0, "train_token_mean_nll": 1.9110442696621797, "grad_norm": 12.326416969299316, "t": 1793745402.5577884} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 93, "batch_sha256": "ad679c87fce8184c7030d1c8436d6af026ab828cbbb5cc93812141e1cfb17e9c", "params_type": "DimuonParams", "train_nll_sum": 9328.39430543721, "train_tokens": 4879.0, "train_token_mean_nll": 1.9119480027540912, "grad_norm": 14.613442420959473, "t": 1793745402.7017083} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 93, "batch_sha256": "634a1ca235f93cd5919c6573911f630a5e273177361ab46a8a3f73dd57194069", "params_type": "AdamParams", "train_nll_sum": 10378.824310708247, "train_tokens": 5439.0, "train_token_mean_nll": 1.9082228922059656, "grad_norm": 14.478669166564941, "t": 1793745402.702456} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 93, "batch_sha256": "634a1ca235f93cd5919c6573911f630a5e273177361ab46a8a3f73dd57194069", "params_type": "DimuonParams", "train_nll_sum": 10381.901949493205, "train_tokens": 5439.0, "train_token_mean_nll": 1.9087887386455609, "grad_norm": 17.190261840820312, "t": 1793745402.7033064} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 93, "batch_sha256": "e4b6c88196f77cd291666fb8196b2cf3b95747069c3fe0c726c7004f0589f7bc", "params_type": "AdamParams", "train_nll_sum": 9427.753056574304, "train_tokens": 5303.0, "train_token_mean_nll": 1.777815021039846, "grad_norm": 13.790982246398926, "t": 1793745402.7042441} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 93, "batch_sha256": "e4b6c88196f77cd291666fb8196b2cf3b95747069c3fe0c726c7004f0589f7bc", "params_type": "DimuonParams", "train_nll_sum": 9435.691462568775, "train_tokens": 5303.0, "train_token_mean_nll": 1.7793119861528899, "grad_norm": 16.4626522064209, "t": 1793745402.7051632} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 94, "batch_sha256": "fe781b9987c5a69aac42ad06a47ea5a161c4ea6d43c9eba76a58a60fa19b965a", "params_type": "AdamParams", "train_nll_sum": 9226.754589906748, "train_tokens": 4760.0, "train_token_mean_nll": 1.9383938214089806, "grad_norm": 18.903043746948242, "t": 1793745410.1388016} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 94, "batch_sha256": "fe781b9987c5a69aac42ad06a47ea5a161c4ea6d43c9eba76a58a60fa19b965a", "params_type": "DimuonParams", "train_nll_sum": 9238.914042052449, "train_tokens": 4760.0, "train_token_mean_nll": 1.9409483281622792, "grad_norm": 25.78391456604004, "t": 1793745410.3260987} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 94, "batch_sha256": "6f503f5ef20c2eaeaa36b74f95c14ffad64cf262438245a149b2e3f7daabde82", "params_type": "AdamParams", "train_nll_sum": 9856.987725204996, "train_tokens": 5676.0, "train_token_mean_nll": 1.7366081263574693, "grad_norm": 11.325799942016602, "t": 1793745410.326934} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 94, "batch_sha256": "6f503f5ef20c2eaeaa36b74f95c14ffad64cf262438245a149b2e3f7daabde82", "params_type": "DimuonParams", "train_nll_sum": 9855.798644016098, "train_tokens": 5676.0, "train_token_mean_nll": 1.736398633547586, "grad_norm": 13.71658706665039, "t": 1793745410.3284328} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 94, "batch_sha256": "2bd932f50c2c1ce8d5ee44a3a4fd650179cf04387e7748d6115bb0d10e890755", "params_type": "AdamParams", "train_nll_sum": 13152.228216250254, "train_tokens": 6994.0, "train_token_mean_nll": 1.8805016036960616, "grad_norm": 14.086702346801758, "t": 1793745410.3300905} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 94, "batch_sha256": "2bd932f50c2c1ce8d5ee44a3a4fd650179cf04387e7748d6115bb0d10e890755", "params_type": "DimuonParams", "train_nll_sum": 13142.332438789435, "train_tokens": 6994.0, "train_token_mean_nll": 1.8790867084342915, "grad_norm": 16.826271057128906, "t": 1793745410.3309758} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 95, "batch_sha256": "6b39689f46263c458b3ee4671540327b5f07e3b1ed0ac58a6b9e8a6fdab0f28e", "params_type": "AdamParams", "train_nll_sum": 10704.35923939204, "train_tokens": 5251.0, "train_token_mean_nll": 2.0385372765934187, "grad_norm": 14.050140380859375, "t": 1793745416.5926538} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 95, "batch_sha256": "6b39689f46263c458b3ee4671540327b5f07e3b1ed0ac58a6b9e8a6fdab0f28e", "params_type": "DimuonParams", "train_nll_sum": 10711.046996499397, "train_tokens": 5251.0, "train_token_mean_nll": 2.0398108924965523, "grad_norm": 16.883947372436523, "t": 1793745416.630043} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 95, "batch_sha256": "37c83d3bb0070f11891d9fc8d0dbb47f65a5c93f90bad12e10fc9e8386c93eee", "params_type": "AdamParams", "train_nll_sum": 13730.166176105036, "train_tokens": 6231.0, "train_token_mean_nll": 2.203525305104323, "grad_norm": 14.411674499511719, "t": 1793745416.6314971} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 95, "batch_sha256": "37c83d3bb0070f11891d9fc8d0dbb47f65a5c93f90bad12e10fc9e8386c93eee", "params_type": "DimuonParams", "train_nll_sum": 13732.745729659124, "train_tokens": 6231.0, "train_token_mean_nll": 2.203939292193729, "grad_norm": 16.112476348876953, "t": 1793745416.6334379} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 95, "batch_sha256": "92a604a9e5ea5b1fc225d143e3a5885072f746cbce6de6d45d40dc6c48a8a040", "params_type": "AdamParams", "train_nll_sum": 11177.966676281534, "train_tokens": 5441.0, "train_token_mean_nll": 2.0543956398238437, "grad_norm": 13.826761245727539, "t": 1793745416.6352303} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 95, "batch_sha256": "92a604a9e5ea5b1fc225d143e3a5885072f746cbce6de6d45d40dc6c48a8a040", "params_type": "DimuonParams", "train_nll_sum": 11190.336986701242, "train_tokens": 5441.0, "train_token_mean_nll": 2.056669176015667, "grad_norm": 16.939756393432617, "t": 1793745416.6379173} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 96, "batch_sha256": "9dadf9e3f68346862a9ed9d9f039ef74bbdbb79bc6b73818e8c1ad4ded42c9a7", "params_type": "AdamParams", "train_nll_sum": 13900.113246846908, "train_tokens": 6757.0, "train_token_mean_nll": 2.05714270339602, "grad_norm": 11.635104179382324, "t": 1793745423.4979382} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 96, "batch_sha256": "9dadf9e3f68346862a9ed9d9f039ef74bbdbb79bc6b73818e8c1ad4ded42c9a7", "params_type": "DimuonParams", "train_nll_sum": 13900.337890405948, "train_tokens": 6757.0, "train_token_mean_nll": 2.0571759494459, "grad_norm": 13.882770538330078, "t": 1793745423.4988973} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 96, "batch_sha256": "dc73b229533a192368027de1f6f6eeaf1a36b79e605f020798d359a0f9173cab", "params_type": "AdamParams", "train_nll_sum": 13348.8872697197, "train_tokens": 6755.0, "train_token_mean_nll": 1.9761491146883345, "grad_norm": 13.280769348144531, "t": 1793745423.4999337} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 96, "batch_sha256": "dc73b229533a192368027de1f6f6eeaf1a36b79e605f020798d359a0f9173cab", "params_type": "DimuonParams", "train_nll_sum": 13362.301894969853, "train_tokens": 6755.0, "train_token_mean_nll": 1.9781349955543823, "grad_norm": 16.38722801208496, "t": 1793745423.501784} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 96, "batch_sha256": "8bc47d09542be0f506b287717e55d98533a00c7450cbceae033f09df62eac5c6", "params_type": "AdamParams", "train_nll_sum": 11873.985998162569, "train_tokens": 5610.0, "train_token_mean_nll": 2.116575044235752, "grad_norm": 12.424314498901367, "t": 1793745423.5032604} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 96, "batch_sha256": "8bc47d09542be0f506b287717e55d98533a00c7450cbceae033f09df62eac5c6", "params_type": "DimuonParams", "train_nll_sum": 11879.127434627844, "train_tokens": 5610.0, "train_token_mean_nll": 2.1174915213240366, "grad_norm": 15.012261390686035, "t": 1793745423.6448383} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 97, "batch_sha256": "4c7efe2fd446504fc38d57f98c6e33340b1c3497447a6453198ec9f9e1daaa36", "params_type": "AdamParams", "train_nll_sum": 13751.22930171384, "train_tokens": 6288.0, "train_token_mean_nll": 2.186900334242023, "grad_norm": 15.710395812988281, "t": 1793745430.760002} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 97, "batch_sha256": "4c7efe2fd446504fc38d57f98c6e33340b1c3497447a6453198ec9f9e1daaa36", "params_type": "DimuonParams", "train_nll_sum": 13758.4249269465, "train_tokens": 6288.0, "train_token_mean_nll": 2.1880446766772423, "grad_norm": 18.567058563232422, "t": 1793745430.7608674} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 97, "batch_sha256": "73f7e6a2160529759394e428b75ed5ab51621b52bb389895d2828a7264b646eb", "params_type": "AdamParams", "train_nll_sum": 11622.24198298492, "train_tokens": 6549.0, "train_token_mean_nll": 1.7746590293151505, "grad_norm": 11.73435115814209, "t": 1793745431.16665} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 97, "batch_sha256": "73f7e6a2160529759394e428b75ed5ab51621b52bb389895d2828a7264b646eb", "params_type": "DimuonParams", "train_nll_sum": 11637.95765196372, "train_tokens": 6549.0, "train_token_mean_nll": 1.7770587344577369, "grad_norm": 14.38369083404541, "t": 1793745431.1698654} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 97, "batch_sha256": "163a01e6491ae116506694035443c762b404f661d12c0929592130fb004fa61d", "params_type": "AdamParams", "train_nll_sum": 13599.964107022848, "train_tokens": 6547.0, "train_token_mean_nll": 2.077281824808744, "grad_norm": 16.709470748901367, "t": 1793745431.1711452} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 97, "batch_sha256": "163a01e6491ae116506694035443c762b404f661d12c0929592130fb004fa61d", "params_type": "DimuonParams", "train_nll_sum": 13591.435857447994, "train_tokens": 6547.0, "train_token_mean_nll": 2.0759792053532906, "grad_norm": 16.68842887878418, "t": 1793745431.174787} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 98, "batch_sha256": "81980b68fa31cb512325571f4d74da0f06cfcfe2304e59533da1ee7b64763923", "params_type": "AdamParams", "train_nll_sum": 13995.078941446822, "train_tokens": 6652.0, "train_token_mean_nll": 2.1038904000972374, "grad_norm": 12.504842758178711, "t": 1793745438.4664054} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 98, "batch_sha256": "81980b68fa31cb512325571f4d74da0f06cfcfe2304e59533da1ee7b64763923", "params_type": "DimuonParams", "train_nll_sum": 14003.64182966672, "train_tokens": 6652.0, "train_token_mean_nll": 2.105177665313698, "grad_norm": 14.826364517211914, "t": 1793745438.623434} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 98, "batch_sha256": "97541c0bed6d2b39ceeb33fd1499c7ecf80026d94bc67a13af90e77ad97c0bed", "params_type": "AdamParams", "train_nll_sum": 12445.564870700106, "train_tokens": 6410.0, "train_token_mean_nll": 1.941585783260547, "grad_norm": 11.371912002563477, "t": 1793745438.6305249} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 98, "batch_sha256": "97541c0bed6d2b39ceeb33fd1499c7ecf80026d94bc67a13af90e77ad97c0bed", "params_type": "DimuonParams", "train_nll_sum": 12452.225988158312, "train_tokens": 6410.0, "train_token_mean_nll": 1.9426249591510627, "grad_norm": 13.57336711883545, "t": 1793745438.6314547} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 98, "batch_sha256": "9cd991678f4a6e7e3d097fe7a6029f3017e58b2444ab66ae40cd09c020a72448", "params_type": "AdamParams", "train_nll_sum": 14965.080639069096, "train_tokens": 6436.0, "train_token_mean_nll": 2.325214518189729, "grad_norm": 14.449365615844727, "t": 1793745438.665356} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 98, "batch_sha256": "9cd991678f4a6e7e3d097fe7a6029f3017e58b2444ab66ae40cd09c020a72448", "params_type": "DimuonParams", "train_nll_sum": 14965.611076913958, "train_tokens": 6436.0, "train_token_mean_nll": 2.325296935505587, "grad_norm": 17.464771270751953, "t": 1793745438.6662931} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 99, "batch_sha256": "41f2d7e9951654925375c067b36022c7d00bc54affb20deb2096e538b4c3405f", "params_type": "AdamParams", "train_nll_sum": 14956.193253718015, "train_tokens": 7581.0, "train_token_mean_nll": 1.9728522957021521, "grad_norm": 11.73127555847168, "t": 1793745446.0517993} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 99, "batch_sha256": "41f2d7e9951654925375c067b36022c7d00bc54affb20deb2096e538b4c3405f", "params_type": "DimuonParams", "train_nll_sum": 14955.000128832202, "train_tokens": 7581.0, "train_token_mean_nll": 1.972694912126659, "grad_norm": 13.88369369506836, "t": 1793745446.0557618} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 99, "batch_sha256": "a315bbb959c26656549bfcf19c43736f24bd5dd6c69c98b1b7431de5575620c7", "params_type": "AdamParams", "train_nll_sum": 14070.076363953609, "train_tokens": 6627.0, "train_token_mean_nll": 2.1231441623590777, "grad_norm": 11.219865798950195, "t": 1793745446.0566676} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 99, "batch_sha256": "a315bbb959c26656549bfcf19c43736f24bd5dd6c69c98b1b7431de5575620c7", "params_type": "DimuonParams", "train_nll_sum": 14085.544766288112, "train_tokens": 6627.0, "train_token_mean_nll": 2.12547831089303, "grad_norm": 13.662245750427246, "t": 1793745446.0783336} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 99, "batch_sha256": "6e2d5435ca2e7ca820af7cd57a2c6c51d9aea28f6c00384c9f5bddcb725419c4", "params_type": "AdamParams", "train_nll_sum": 12256.404560835612, "train_tokens": 6113.0, "train_token_mean_nll": 2.0049737544308215, "grad_norm": 10.8590087890625, "t": 1793745446.3346355} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 99, "batch_sha256": "6e2d5435ca2e7ca820af7cd57a2c6c51d9aea28f6c00384c9f5bddcb725419c4", "params_type": "DimuonParams", "train_nll_sum": 12252.301886013953, "train_tokens": 6113.0, "train_token_mean_nll": 2.0043026150848933, "grad_norm": 13.060302734375, "t": 1793745446.3354456} {"stage": "train_step", "arm": "baseline_adamw_s0", "step": 100, "batch_sha256": "48a6e7030d06dee7cfa73048eda791aca35f3999b64ee370cc078e51c2a5bdb2", "params_type": "AdamParams", "train_nll_sum": 13590.785019321871, "train_tokens": 6117.0, "train_token_mean_nll": 2.2218056268304514, "grad_norm": 12.224512100219727, "t": 1793745453.572292} {"stage": "train_step", "arm": "treatment_dimuon_s0", "step": 100, "batch_sha256": "48a6e7030d06dee7cfa73048eda791aca35f3999b64ee370cc078e51c2a5bdb2", "params_type": "DimuonParams", "train_nll_sum": 13593.451194106514, "train_tokens": 6117.0, "train_token_mean_nll": 2.222241489963465, "grad_norm": 14.773348808288574, "t": 1793745453.5744598} {"stage": "train_step", "arm": "baseline_adamw_s1", "step": 100, "batch_sha256": "03d96d89099faac92ea492a2c9d6399389b9ea0a04e7d345d140690918367ed3", "params_type": "AdamParams", "train_nll_sum": 8829.796681620372, "train_tokens": 4547.0, "train_token_mean_nll": 1.9418950256477616, "grad_norm": 13.969414710998535, "t": 1793745453.5752442} {"stage": "train_step", "arm": "treatment_dimuon_s1", "step": 100, "batch_sha256": "03d96d89099faac92ea492a2c9d6399389b9ea0a04e7d345d140690918367ed3", "params_type": "DimuonParams", "train_nll_sum": 8824.143032243122, "train_tokens": 4547.0, "train_token_mean_nll": 1.9406516455340053, "grad_norm": 17.19895362854004, "t": 1793745453.5759654} {"stage": "train_step", "arm": "baseline_adamw_s2", "step": 100, "batch_sha256": "93b47ab28a3053481df98795dbf0b456db0ff979c1b9ff2449928f6637c4d95a", "params_type": "AdamParams", "train_nll_sum": 14213.448628930102, "train_tokens": 6463.0, "train_token_mean_nll": 2.1992029442874985, "grad_norm": 11.931547164916992, "t": 1793745453.5793197} {"stage": "train_step", "arm": "treatment_dimuon_s2", "step": 100, "batch_sha256": "93b47ab28a3053481df98795dbf0b456db0ff979c1b9ff2449928f6637c4d95a", "params_type": "DimuonParams", "train_nll_sum": 14213.792452036487, "train_tokens": 6463.0, "train_token_mean_nll": 2.1992561429733075, "grad_norm": 14.326032638549805, "t": 1793745453.5800588} {"stage": "train_done", "seconds": 786.5640952587128, "steps": 100, "arms": 6, "t": 1793745453.5800886} {"stage": "eval", "arm": "baseline_adamw_s0", "split": "test", "step": 100, "nll_sum": 197907.03459912218, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0330268793696935, "example_mean": 1.9118371781051087, "per_example": [[129.83305756729465, 55], [1254.148268243027, 555], [575.6916164498925, 233], [1056.276922524967, 416], [503.4196944882467, 287], [123.44178630235541, 60], [706.3933148427304, 468], [134.60657883450654, 71], [81.09212818099559, 65], [615.6335222613507, 271], [47.599664992252315, 35], [21.614298799574954, 31], [180.304180637454, 107], [389.8067005515894, 112], [10.609793526082115, 11], [241.61578794802313, 86], [130.6662037398661, 105], [451.10063691280493, 407], [189.74404338753857, 132], [727.5732414215522, 231], [289.84467841494177, 268], [391.1919062664897, 155], [90.40817472840308, 102], [132.3948184438318, 74], [239.80578872075466, 83], [362.00486213088095, 135], [945.9667590953104, 390], [871.1412755953468, 284], [26.646260947436417, 44], [337.30055556261505, 137], [1204.440440017626, 447], [0.9901553229709634, 25], [388.31278320994056, 155], [847.9185040641865, 457], [309.8839360508912, 187], [463.5626372911811, 230], [390.5023359998613, 148], [321.7540634546049, 436], [486.1633124130183, 146], [316.042716511605, 191], [13.103124518981076, 37], [431.08356287997685, 333], [80.4096046818413, 53], [188.62025194363582, 94], [1074.227716107558, 521], [319.5595364490009, 175], [136.24078124762855, 79], [54.0597150623953, 19], [3.010884157716646, 10], [328.78679044961564, 208], [309.68062377089404, 156], [224.99943819131227, 160], [1159.1160745397974, 420], [764.4099217260459, 285], [84.65327947666128, 31], [410.09470376134493, 167], [54.71192247858983, 44], [739.767720678833, 245], [9.497298939754273, 45], [235.2995529082733, 102], [127.89291357239426, 114], [63.37457959157132, 20], [166.7317958203471, 86], [151.7134032768156, 63], [72.30102999216115, 72], [100.56939656246686, 66], [142.6347775824629, 101], [100.56126494148793, 48], [65.37625145551783, 25], [64.20840130866236, 26], [65.69349698224698, 64], [223.1345838090316, 72], [381.742263804146, 342], [323.4606985226195, 123], [364.01837790916795, 314], [115.03367628498404, 68], [72.27018617478814, 58], [210.72962589410037, 106], [204.45202035363945, 81], [322.3027891071956, 181], [285.1683783334388, 312], [639.0265098554496, 302], [1273.7469099452314, 473], [76.72479893059221, 74], [315.610502642769, 169], [196.38740583607887, 86], [1483.9070573852869, 663], [96.16363035737459, 81], [581.0271970736635, 272], [576.4379818217526, 206], [870.2692801295825, 720], [736.5658177188975, 291], [1279.3417657921198, 562], [178.80179689135275, 117], [148.58710298207006, 106], [548.1971179286766, 216], [74.20942197094314, 45], [387.63814798619524, 220], [305.1829731345101, 134], [1182.6674555787472, 454], [79.7943189401071, 57], [202.18068595853345, 101], [70.44083709573306, 22], [136.70450248706447, 74], [629.8471693208658, 294], [412.21330437703773, 150], [544.2156856617103, 203], [368.28262521960005, 166], [721.8789947770483, 262], [118.24276983921527, 52], [484.7271224087717, 181], [32.10979059530837, 37], [1177.868459498619, 642], [258.5787618643594, 176], [208.8337224594643, 113], [539.7731192238252, 194], [118.34620065343711, 72], [4.9159425661076455, 10], [174.26569479366208, 123], [397.53778722228867, 141], [329.31093349662524, 117], [1326.1483320640182, 576], [122.0623304963433, 93], [312.4700194556849, 137], [572.6147410891429, 240], [39.5045696710975, 61], [124.0257240310666, 123], [192.68433801415028, 98], [269.8132720816144, 120], [5.672303345177625, 32], [876.1039363607874, 334], [2.0343594520077204, 26], [54.2812882348901, 35], [235.26758787297558, 72], [640.3918480648799, 263], [648.4469001547475, 247], [191.67550151603518, 66], [568.4395611021837, 265], [1347.1645074966978, 516], [1212.5143637812407, 502], [1396.0677896118632, 492], [300.9660736942849, 141], [1417.5778236710812, 476], [152.9896663301074, 170], [372.84083870256995, 123], [380.4192168788604, 397], [138.83813011075313, 57], [802.2827917691807, 411], [605.213887696246, 227], [61.117459061930276, 42], [59.690824857209236, 32], [187.87963989215177, 89], [630.2804254601087, 271], [77.32502969070993, 59], [201.30363713620181, 107], [190.0920246841788, 150], [383.90440024983275, 237], [197.25424734058697, 92], [321.25240298385995, 153], [635.9880922858782, 268], [566.2660757576255, 253], [906.9861629025136, 428], [524.8624303306118, 270], [112.00401014333193, 79], [291.52157134266344, 144], [805.9146928367162, 312], [162.95812547772994, 102], [1021.5979119285414, 554], [78.34883358139905, 71], [796.9542395471585, 306], [2.0421660561496537, 6], [198.8314680080057, 273], [511.699636785861, 256], [439.6822027458711, 234], [1350.1703607056966, 653], [447.8545224925699, 220], [480.756886450283, 221], [82.9596370837121, 67], [231.20102006578873, 107], [74.87623625620563, 60], [1108.0970709299127, 517], [91.59332553872878, 66], [409.93944452594224, 185], [33.1215595355269, 47], [216.24766823995242, 138], [39.37920305194689, 37], [707.0349107334712, 372], [3.5131893063753523, 11], [162.7374699673136, 69], [1.5399217289163971, 11], [306.9070253502896, 122], [542.0175525290861, 239], [400.62899267243506, 215], [371.1885870177416, 131], [363.853654665907, 136], [810.3860466085571, 241], [296.6819172486755, 145], [350.0912568459303, 226], [1329.458126493231, 548], [26.47941558587536, 38], [418.73481340445346, 170], [65.81572025064042, 27], [599.2177023345835, 264], [700.0833861335855, 258], [188.96125309944705, 82], [289.933212879273, 147], [578.8477205140344, 259], [515.5900272767444, 152], [250.2012667444901, 151], [876.321569233724, 320], [229.15972407604613, 110], [238.19996139220484, 141], [221.49810300101262, 132], [292.1400316805698, 101], [272.78005534345084, 135], [1288.1312313446715, 629], [214.06080097248193, 241], [777.4095344225814, 492], [803.0501525467107, 304], [1136.182192790095, 404], [6.5785830732206705, 17], [295.6532416902867, 138], [382.12074804745316, 141], [261.3836355704234, 161], [199.48043309931245, 125], [1196.764472051707, 639], [615.4256561194143, 315], [192.45924600867193, 102], [53.597467852857335, 25], [828.1353875207769, 386], [307.8692870183668, 153], [444.2076120692033, 518], [550.0288119665256, 219], [193.6579055027105, 121], [894.0828564060006, 613], [430.07584478297053, 204], [614.1700681878342, 273], [141.92031554355026, 75], [860.2830311954513, 373], [912.4743957506098, 288], [579.7008109655981, 243], [158.59916619067917, 71], [103.12508011682894, 51], [226.84132915898056, 104], [1338.1501408395661, 748], [517.1526798063342, 180], [269.32997174121317, 137], [691.2940444229098, 394], [947.1710210431761, 426], [257.2095183498518, 124], [0.7887590254098313, 16], [148.18513882624097, 49], [248.458867396556, 216], [21.25096278707383, 68], [9.160700052648053, 12], [649.0371714937673, 216], [792.6923361838512, 331], [254.24730146597472, 129], [613.7541105221746, 238], [624.453518911434, 247], [220.0277963162539, 108], [195.30264312686904, 133], [213.11591098555527, 116], [15.418525411094834, 30], [972.6034814707145, 537], [1228.991678817709, 557], [1395.731395175762, 519], [548.7574166294326, 390], [272.35111218103646, 154], [322.0002168831302, 374], [32.07318152601101, 30], [381.3003178305171, 187], [324.1599008311199, 190], [95.26372187229003, 38], [406.6251134097047, 167], [149.06478708220902, 127], [642.1509552026491, 290], [1019.9064743776175, 424], [169.52831167776503, 56], [300.31838626290846, 181], [229.50233773816626, 147], [281.9390465595875, 188], [8.507390411301003, 34], [185.692604885552, 74], [287.00112056726357, 115], [594.1533508061489, 268], [934.5181734399162, 366], [561.2790914604993, 251], [1515.2382985889567, 517], [76.0974635288851, 54], [1223.8305002502002, 488], [565.631125860632, 217], [273.9646600668775, 109], [296.5295781431829, 282], [1289.7181083197465, 503], [885.5580775724231, 320], [53.576075742350895, 18], [110.63475316233007, 72], [351.1520288558968, 168], [83.6008658952693, 41], [508.75857564749094, 239], [50.40451598210484, 42], [537.2555553721256, 219], [731.0101935619696, 417], [215.58610932852184, 182], [461.16881400252805, 328], [224.67606628755084, 138], [24.663699467994434, 259], [3.1980527736960767, 13], [318.0608559302823, 157], [240.17203268900676, 209], [101.25188640662816, 92], [66.17999118409693, 99], [714.6181764429693, 336], [169.85089694873386, 86], [76.03715136418373, 41], [1157.781176082803, 405], [453.33235180037013, 259], [51.52098565960341, 22], [781.8235321341624, 336], [246.17275031831196, 65], [240.28017793461868, 73], [207.75830903250198, 108], [338.43223163842777, 166], [226.66968440765004, 237], [16.23696468143362, 35], [631.6443745078645, 483], [157.98435605560462, 110], [39.40285347799772, 48], [295.5080773947608, 371], [1073.808893881493, 455], [1216.2194401825827, 587], [553.4227251499224, 193], [247.80876128103046, 141], [79.33425295153393, 44], [123.28046525893706, 34], [105.23241956104266, 90], [202.12559745165254, 85], [33.36538745379491, 47], [287.9215163399365, 321], [1189.7443797740734, 487], [175.74800271898403, 100], [391.8393943493861, 215], [340.940865096803, 157], [60.69391023779309, 47], [710.6997562200936, 274], [250.23697241639724, 133], [774.8032457063305, 369], [214.14078323382773, 110], [88.16393383401919, 75], [87.5754208853291, 37], [444.6899656402554, 916], [969.3853827852613, 370], [335.1665136130273, 167], [345.67580627277357, 204], [442.3567900772109, 211], [912.0444431711519, 465], [15.357665116592216, 27], [1313.993410561497, 480], [636.5479803037301, 477], [1611.3424766869805, 580], [208.50770512224153, 147], [44.490427301079706, 59], [198.61439122076263, 60], [49.037790632149154, 42], [35.11062832946709, 58], [57.257211188851215, 25], [23.920022234614407, 36], [78.4411492595516, 24], [1.199839089178795, 75], [470.3031311003622, 219], [254.28940845292345, 91], [321.6596785286912, 206], [711.0303936689737, 273], [252.32380381974258, 109], [407.49705617726795, 191], [39.8718759126059, 28], [367.53810582309916, 148], [261.1674437191268, 305], [331.1105014249649, 141], [179.41981383926304, 55], [237.6292771185956, 154], [572.2140501159431, 203], [60.977924954906825, 82], [42.15126278628577, 42], [688.0307582148739, 299], [940.6786079036983, 524], [105.78020134491248, 84], [480.23921027200913, 291], [420.9125272082234, 313], [153.917168866868, 50], [32.912998702492814, 24], [472.950154734805, 236], [19.441923068386586, 32], [336.3726784930793, 163], [188.72857627886606, 78], [67.60566104142617, 38], [109.0895705230513, 77], [20.839466165108888, 33], [81.87400427944203, 119], [454.4989638558618, 204], [192.64365035267724, 98], [334.9196102935489, 106], [352.22740225393545, 184], [373.4444190192642, 314], [711.3911243270127, 366], [233.14658847484907, 152], [204.28525846363482, 143], [268.70286213981626, 157], [119.45761744234596, 133], [233.71485396981097, 103], [571.6921358985471, 263], [456.43827912781944, 179], [164.97943980923674, 88], [76.16916993444823, 52], [254.56211701993152, 132], [50.614160065361375, 47], [338.52864598663996, 157], [221.46172240614328, 143], [482.3927573966471, 228], [757.5933900045993, 300], [302.59113233738753, 123], [250.35457711412437, 132], [146.567378035851, 98], [951.2677297404828, 497], [311.6700962893856, 151], [46.509557937788486, 30], [453.7293388029477, 194], [216.4694335756651, 148], [663.2839777074273, 284], [1.2775754847166354, 17], [144.51662363604544, 293], [480.0589374727897, 247], [672.3959200963941, 242], [373.5590414062899, 160], [336.8649922966988, 191], [386.8051717699109, 177], [523.7939040767337, 251], [162.0813531366707, 81], [556.8500619144961, 160], [28.423750365734577, 30], [377.35268973290295, 167], [478.00503820442987, 264], [934.187467355508, 347], [803.0730883282376, 352], [1068.9767828214426, 446], [1443.2844802998263, 506], [127.23808927662253, 160], [423.5718743318889, 263], [15.648031242659727, 78], [80.52072073082172, 22], [317.44730285803644, 142], [51.890304613075386, 38], [1051.3115182581648, 426], [1240.1032974182672, 519], [220.84419389300842, 95], [774.8486831772611, 362], [75.26138000663673, 31], [44.52942425361198, 31], [108.94935570880807, 46], [139.0700035638024, 83], [1054.41805947292, 454], [1530.4635475386117, 493], [51.83892695688792, 50], [273.29586866906965, 120], [706.3000182018686, 289], [358.9165962752545, 112], [1010.591883567151, 439], [505.69618528457113, 223], [236.23262980192726, 205], [91.46184753686248, 81], [232.69292571399546, 102], [60.678374607798105, 22], [183.81031171193035, 88], [282.84294146984166, 110], [121.84954079968679, 70], [472.42619325904104, 231], [7.931585266993807, 35], [69.5978441397724, 42], [348.56815276201223, 169], [583.1661938751358, 300], [293.04684769980327, 150], [1566.7006051522917, 745], [164.7804036139828, 88], [48.73912769689889, 38], [366.01267971110747, 195], [1284.4290505257723, 533], [508.5824021342396, 225], [340.71492872294857, 140], [157.73348921371507, 90], [166.596979754348, 105], [101.593034654711, 50], [118.0866528300171, 61], [92.90284201050099, 75], [469.91233765283687, 199], [186.18606363335857, 94], [11.02531351313769, 97], [458.32734868852367, 212], [209.1623334331922, 236], [1089.6291222928876, 447]], "final_state": "tinker://b61dfd929fd09745b512c7224450cbde/weights/confirm-baseline_adamw_s0-final", "t": 1793745479.58926} {"stage": "eval", "arm": "treatment_dimuon_s0", "split": "test", "step": 100, "nll_sum": 197837.93334339152, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0323170273395057, "example_mean": 1.9111400255469455, "per_example": [[130.1654448276522, 55], [1254.0697727730221, 555], [574.0622943281857, 233], [1055.7994217956439, 416], [503.77875434108387, 287], [123.71654581139774, 60], [704.4300640598863, 468], [133.23620543393008, 71], [81.38484294131695, 65], [613.5218596762006, 271], [47.37292351027577, 35], [21.64480032080246, 31], [178.47252912862587, 107], [389.67641390038807, 112], [10.313185186793817, 11], [239.72337623890735, 86], [131.1805873068838, 105], [447.1111649526083, 407], [188.5338147085863, 132], [725.5658604448204, 231], [291.6194111737759, 268], [391.6861574242489, 155], [90.32161300792131, 102], [133.24534428666527, 74], [240.1410785396115, 83], [362.2396011580204, 135], [946.5052941058043, 390], [869.6952967428051, 284], [27.08809718866359, 44], [335.003821098818, 137], [1200.9544970879147, 447], [0.9916842240545236, 25], [391.28106256815624, 155], [847.8472299921032, 457], [310.3862027156101, 187], [467.3353489033361, 230], [391.85139222437283, 148], [324.784887806323, 436], [482.42079262148104, 146], [313.38811189258104, 191], [14.455879620945325, 37], [429.95354369564666, 333], [80.12202093401709, 53], [189.03394807884797, 94], [1080.7627020751552, 521], [320.48298388435796, 175], [135.79636864943495, 79], [53.36496905927742, 19], [3.107172354172235, 10], [331.2221924487458, 208], [309.7308040327771, 156], [226.20251122509626, 160], [1158.633188303756, 420], [762.9465681813781, 285], [85.30146199116825, 31], [412.1558362759115, 167], [55.34200389437501, 44], [739.7168802260562, 245], [9.002647656588579, 45], [234.97365473313585, 102], [128.3222836321729, 114], [62.251586784739175, 20], [167.4475353543121, 86], [152.07581931741333, 63], [72.22823138137025, 72], [99.77854302555897, 66], [141.97755549654175, 101], [101.6269471631972, 48], [66.28063831045051, 25], [65.04403599588636, 26], [65.0329624055878, 64], [222.7959688558774, 72], [380.6891473573269, 342], [325.1084914867297, 123], [363.0024143718956, 314], [115.73556772365191, 68], [70.30899869972814, 58], [209.0413314371599, 106], [201.93291193768255, 81], [320.8909501985827, 181], [285.9915972097242, 312], [641.495258734944, 302], [1270.405607983731, 473], [77.17243605977455, 74], [314.0787625514349, 169], [198.3516978167895, 86], [1477.1015231442634, 663], [96.94338980345674, 81], [582.8607162563712, 272], [576.2953674440563, 206], [871.1703121591481, 720], [735.2273300839715, 291], [1275.5322867930026, 562], [178.93496096404306, 117], [146.92499453778748, 106], [551.1383419565373, 216], [72.92016577764252, 45], [384.25490122214217, 220], [306.5513385968379, 134], [1181.7680765541613, 454], [81.42992801955734, 57], [202.10280584646262, 101], [70.56656483049647, 22], [136.41191937923304, 74], [629.1791206876892, 294], [411.23599757757984, 150], [543.6171221263121, 203], [368.84791869734727, 166], [723.8241357569023, 262], [116.86656450265525, 52], [485.60430738381456, 181], [32.18005889548658, 37], [1177.3645552425232, 642], [258.2982602318716, 176], [210.322721205557, 113], [540.359357528836, 194], [118.83386046624037, 72], [4.5823862236229616, 10], [175.72457269871302, 123], [396.7725579635362, 141], [328.5569910734348, 117], [1323.7992150590437, 576], [121.13277383169566, 93], [313.29701960927457, 137], [571.4096321242141, 240], [38.73534198681955, 61], [124.72853684897495, 123], [189.90314537674112, 98], [267.2400300905301, 120], [5.321635907026575, 32], [875.467728315466, 334], [2.126243825481538, 26], [53.36668089768091, 35], [233.52365567614765, 72], [638.4494340446569, 263], [646.9684663614025, 247], [193.18503723326273, 66], [567.5872854296722, 265], [1345.1206509013753, 516], [1211.4949084998607, 502], [1396.259171627818, 492], [301.3955187176225, 141], [1415.9952531474223, 476], [154.08624062799936, 170], [374.5865362726745, 123], [374.6387016655599, 397], [139.72796097270702, 57], [804.2544121232204, 411], [603.74558678625, 227], [61.13371164691307, 42], [59.801975293071564, 32], [188.85844704288138, 89], [631.0612091492345, 271], [77.05486450646276, 59], [202.6872905663704, 107], [189.80718566311248, 150], [380.71794127062765, 237], [198.0914268289016, 92], [320.88441050259735, 153], [636.4516277647599, 268], [566.1812182425729, 253], [905.2430570082461, 428], [525.8260245449451, 270], [112.09329340657854, 79], [292.16168251804356, 144], [805.3148452760943, 312], [163.04289604725636, 102], [1021.6810371385909, 554], [75.97543343264624, 71], [793.2535055203957, 306], [1.6032292368581693, 6], [197.6886782485126, 273], [514.9029955914739, 256], [437.4313778760843, 234], [1349.8806959253534, 653], [447.9387833612818, 220], [479.89790020793316, 221], [84.67299665276363, 67], [229.9853077530147, 107], [75.09630017109703, 60], [1108.1288521034317, 517], [92.31406864979772, 66], [408.8903906038322, 185], [33.03365058046802, 47], [215.64919683207336, 138], [40.400758059810414, 37], [705.5205984841537, 372], [4.046546304767617, 11], [163.00963434295886, 69], [1.626310529638431, 11], [307.6724946512386, 122], [540.8046469312599, 239], [400.2961981113817, 215], [369.903405798279, 131], [366.0187264888009, 136], [807.9115199265593, 241], [295.0438396764175, 145], [351.3050550839689, 226], [1328.63955020514, 548], [26.715570978910364, 38], [421.68263231097626, 170], [65.99106090638793, 27], [598.5707790699398, 264], [699.241447101911, 258], [189.45942716709476, 82], [289.94505591387133, 147], [578.5068147121096, 259], [517.2761492929194, 152], [249.45104666010002, 151], [874.993573041711, 320], [229.49943834613168, 110], [240.45436364704938, 141], [221.46890520423926, 132], [292.68481709440584, 101], [271.3875453674036, 135], [1291.1217611793454, 629], [215.54907354353367, 241], [776.4089619943406, 492], [803.4973952550863, 304], [1135.7509723598, 404], [6.267860818390545, 17], [297.9209928352502, 138], [381.36266455753685, 141], [259.8223154783724, 161], [199.602268707571, 125], [1197.3342968773404, 639], [616.7508209916123, 315], [194.29398568026818, 102], [51.8578114532404, 25], [826.786235926416, 386], [308.5451946701014, 153], [445.13371196744924, 518], [550.6899360883235, 219], [193.91097421739096, 121], [895.3886751197574, 613], [431.44300286174985, 204], [610.91681192539, 273], [140.87461454215463, 75], [858.87326214215, 373], [911.7445777573175, 288], [575.2088196263228, 243], [159.61062761973517, 71], [103.89332988375554, 51], [226.1814369415788, 104], [1342.952108724956, 748], [515.0030855776636, 180], [270.1729341376772, 137], [690.6407371011219, 394], [949.1414712402766, 426], [257.41923083815186, 124], [0.8385273137209879, 16], [147.86025233620592, 49], [251.94838909259624, 216], [20.043743823713157, 68], [8.49023022799156, 12], [644.9584645517604, 216], [794.5869410854502, 331], [255.9479362870004, 129], [612.8033643151543, 238], [625.125885956907, 247], [220.73976432290465, 108], [193.4872398841435, 133], [214.01687521235124, 116], [11.980861042407014, 30], [973.9838614584833, 537], [1227.568269241243, 557], [1397.5776276683846, 519], [547.5996611675255, 390], [272.07518750909003, 154], [320.85750521036334, 374], [31.829456415938694, 30], [379.97026119770874, 187], [325.63280999485687, 190], [94.17508284033374, 38], [405.2027010749898, 167], [148.85048627998822, 127], [643.1160988325973, 290], [1018.0765759909011, 424], [168.49708412446216, 56], [301.01069450314753, 181], [230.17442869794831, 147], [282.48450332851735, 188], [8.444095747388928, 34], [184.13580536384416, 74], [288.81643975987936, 115], [597.885678625243, 268], [936.2091059671709, 366], [559.0511816947844, 251], [1517.0376008017179, 517], [76.68229035091576, 54], [1222.8838281278913, 488], [565.900533677066, 217], [272.9441216069463, 109], [296.20007744687973, 282], [1286.2798686727292, 503], [883.4879106234052, 320], [54.76589279309883, 18], [111.08698847879896, 72], [351.5622752172203, 168], [83.85232598744187, 41], [509.3705586101353, 239], [49.87146872606445, 42], [541.5785999690356, 219], [729.503948692357, 417], [217.12131286485055, 182], [461.9154643234101, 328], [225.7685679656679, 138], [24.999388699642623, 259], [2.266828921583503, 13], [320.01855275014714, 157], [238.33276963198978, 209], [103.38705034358463, 92], [65.61750160948577, 99], [714.3876827708589, 336], [171.0042739217388, 86], [76.10127258337252, 41], [1155.949074879842, 405], [453.8783632804052, 259], [51.45365886170816, 22], [781.7546543892304, 336], [245.099838160434, 65], [240.62573373105533, 73], [207.08011448827347, 108], [338.6104265093536, 166], [223.974939781353, 237], [15.992963901884536, 35], [632.3818354757714, 483], [157.4890717247872, 110], [39.62402422313062, 48], [296.6980136472502, 371], [1072.6444565966995, 455], [1212.8585865183902, 587], [549.5347626741554, 193], [244.45934690416016, 141], [79.14710681643578, 44], [124.05357698741665, 34], [107.13796587820093, 90], [202.64592193598196, 85], [34.233615516730254, 47], [287.74396060233175, 321], [1193.2884169771796, 487], [175.616290409449, 100], [392.05843828980767, 215], [341.6328713218188, 157], [60.94771510713144, 47], [708.3861444852791, 274], [250.88585359142485, 133], [777.2760161692972, 369], [213.66927050414472, 110], [87.04868382541463, 75], [88.2405977793444, 37], [433.75878778594506, 916], [969.7153905837404, 370], [334.41386572741703, 167], [343.50471892289715, 204], [439.1172568409547, 211], [907.6139154836455, 465], [15.939862621745647, 27], [1313.4510095291503, 480], [637.6839498474847, 477], [1608.063131466948, 580], [209.01619305615895, 147], [43.49034644425228, 59], [197.84931535826718, 60], [48.62254801650488, 42], [34.727427454231474, 58], [57.37947244755969, 25], [24.978524843583727, 36], [76.41224864294645, 24], [1.6892648571210813, 75], [468.1566832507324, 219], [255.1672792179606, 91], [322.2494060711597, 206], [710.0102129744851, 273], [254.34661342633626, 109], [407.42683088031106, 191], [40.43196453492328, 28], [366.7988896019705, 148], [261.2659410615812, 305], [329.8996461973484, 141], [177.6496512029562, 55], [237.33049530030257, 154], [571.988110998786, 203], [61.440897413998755, 82], [42.33325968934878, 42], [689.8976535213842, 299], [938.689371276083, 524], [106.60718194195397, 84], [480.80525382067117, 291], [418.562843779335, 313], [154.38286023914588, 50], [33.59161028232552, 24], [471.8146271204332, 236], [19.403858924002634, 32], [338.21528636820403, 163], [189.46268358001817, 78], [67.71885647487852, 38], [108.63779716941269, 77], [20.206646703496517, 33], [80.52617734969937, 119], [455.47803074057083, 204], [191.82162950769452, 98], [332.2073118236467, 106], [351.20318270145435, 184], [375.6339404852959, 314], [711.6928236358065, 366], [233.49540323198016, 152], [206.0953379797652, 143], [270.02468776822525, 157], [118.78998016871583, 133], [235.12535706164806, 103], [570.5731082987704, 263], [456.6375770450354, 179], [165.46136603481045, 88], [76.97538813725873, 52], [255.10018191529457, 132], [51.294021363939464, 47], [340.4138043498383, 157], [221.3236667731221, 143], [482.1622715580297, 228], [759.6927848323994, 300], [302.8334131703268, 123], [250.39138435702807, 132], [146.85851205954668, 98], [951.2542750729217, 497], [311.6280874799377, 151], [46.60181379780806, 30], [452.7811118715638, 194], [217.24281113616235, 148], [663.4487182903322, 284], [1.3263067283551209, 17], [145.70395378973615, 293], [484.6934447397507, 247], [672.9215023685028, 242], [374.2770667471782, 160], [338.46921285463395, 191], [386.1511638437614, 177], [524.1121906605085, 251], [162.6627278326632, 81], [555.9089406974612, 160], [29.53862471973116, 30], [376.7882962079361, 167], [478.475899590592, 264], [933.2804339158117, 347], [800.9478363748985, 352], [1066.9620747343038, 446], [1440.082955103344, 506], [127.0853868436352, 160], [423.75742375673144, 263], [16.331573733771165, 78], [80.02906913357731, 22], [319.88340285868526, 142], [51.123411055477845, 38], [1050.5306543119286, 426], [1240.2560769371016, 519], [221.6257935362696, 95], [775.6302002518751, 362], [75.51411119825735, 31], [45.39652778222808, 31], [108.92600269881916, 46], [136.47991858687033, 83], [1052.8611203829478, 454], [1531.9392209159664, 493], [51.3108884772937, 50], [273.80449478058745, 120], [703.2521393722473, 289], [360.290855105482, 112], [1012.479696092536, 439], [509.0709092693419, 223], [239.19213655224985, 205], [92.155746703359, 81], [232.5118170202727, 102], [61.338189763678656, 22], [184.8383513939243, 88], [283.2477110435407, 110], [122.67111890284286, 70], [472.5098728781968, 231], [8.106461743999716, 35], [69.9950868876183, 42], [346.22659745398414, 169], [583.7835030518818, 300], [295.0521095465224, 150], [1562.4418778197178, 745], [165.01789515860946, 88], [48.222759712095694, 38], [365.3474361905828, 195], [1284.2184495924892, 533], [507.21332523297133, 225], [340.62691718970746, 140], [157.59522751128316, 90], [166.77961481837065, 105], [101.70577270731883, 50], [116.88715436422444, 61], [92.44420501729292, 75], [471.91253246375527, 199], [185.7765178511563, 94], [11.509385314147607, 97], [456.2344173892452, 212], [208.8509986179497, 236], [1085.035496425422, 447]], "final_state": "tinker://d331297013cae43230697585afa80dc5/weights/confirm-treatment_dimuon_s0-final", "t": 1793745500.109125} {"stage": "eval", "arm": "baseline_adamw_s1", "split": "test", "step": 100, "nll_sum": 197759.10670072702, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0315072699517907, "example_mean": 1.9122966738185496, "per_example": [[136.62178905995552, 55], [1249.527894906375, 555], [573.9240938081712, 233], [1055.8392796151861, 416], [502.9950249889472, 287], [123.08786371262215, 60], [711.7356094956376, 468], [131.7414629514526, 71], [81.47816064597384, 65], [617.7624570857442, 271], [45.67501713943216, 35], [23.401438585596225, 31], [181.51808528949266, 107], [388.9087018436735, 112], [10.317291232382559, 11], [240.74869757162242, 86], [129.69132187261243, 105], [441.75229933216747, 407], [188.668594055222, 132], [727.2344304449215, 231], [289.00184518520905, 268], [394.6771067078116, 155], [84.22860419153403, 102], [132.83438431841478, 74], [239.71330230484983, 83], [358.2272918875915, 135], [951.2331119592369, 390], [868.3823112149444, 284], [27.07423770722619, 44], [336.40588708971734, 137], [1205.6538078051021, 447], [1.0397719062366377, 25], [387.231306632192, 155], [839.682974039571, 457], [309.2932754656913, 187], [467.4422207204443, 230], [393.29634612651034, 148], [326.836328552822, 436], [485.04265312826374, 146], [323.6682045109583, 191], [15.337712478962203, 37], [427.4192043613523, 333], [81.74049970211843, 53], [185.12450933818764, 94], [1073.9680937216363, 521], [319.0610134386952, 175], [135.0753206827294, 79], [56.97969109712352, 19], [3.2880148428059783, 10], [328.3438029845197, 208], [316.0123572655464, 156], [224.0913491611118, 160], [1160.753298644704, 420], [765.5667799968296, 285], [84.36768723292195, 31], [412.94464033905115, 167], [57.91837026298788, 44], [745.3650630813408, 245], [9.20114647364926, 45], [235.56776915457976, 102], [131.546429887755, 114], [65.45814439969456, 20], [164.449761873606, 86], [152.93892766159115, 63], [70.43204295935391, 72], [103.9898658007387, 66], [142.31084717280737, 101], [100.9431587527929, 48], [66.05989008841937, 25], [65.18272451254552, 26], [65.29658816951064, 64], [222.97333973620312, 72], [377.42016975575444, 342], [324.695843051456, 123], [363.13882269095643, 314], [115.749108306974, 68], [75.39588327835236, 58], [208.99308152741833, 106], [205.00185549124876, 81], [322.83238624032674, 181], [290.2509011671805, 312], [639.4347296553219, 302], [1275.3996569328137, 473], [77.15338635241983, 74], [313.78060011143225, 169], [200.08106799622044, 86], [1484.243504944896, 663], [98.92335231093875, 81], [577.540127996006, 272], [577.254981547611, 206], [861.0080672602412, 720], [734.3650546807139, 291], [1278.3581719515196, 562], [180.1711907823094, 117], [146.12027911424036, 106], [551.3005654334975, 216], [74.54331870906526, 45], [386.275658446584, 220], [303.1447504140117, 134], [1182.4231051728016, 454], [81.83535597234822, 57], [201.1963457011093, 101], [69.7309983710868, 22], [138.2464659353932, 74], [629.0146527452237, 294], [413.21183561866746, 150], [548.7468727424384, 203], [368.75209404013685, 166], [723.0072586894898, 262], [117.63101203355086, 52], [483.78423040297093, 181], [32.94301798591482, 37], [1177.8654272756758, 642], [256.03234300076986, 176], [212.09636799063264, 113], [539.088978765561, 194], [111.89103148128652, 72], [4.342783149614661, 10], [177.0707503629551, 123], [398.82163499645117, 141], [329.1428587233122, 117], [1323.9542381116457, 576], [122.50782946493649, 93], [310.73503256098775, 137], [579.3770198044587, 240], [38.70622117254413, 61], [126.58039458283565, 123], [188.9944828170258, 98], [271.384918103382, 120], [6.23531518913569, 32], [881.3604719713263, 334], [2.1196697201555708, 26], [54.943775760995095, 35], [230.91145801029393, 72], [638.2225460748414, 263], [649.7639721968508, 247], [189.27707426200288, 66], [570.4702095417724, 265], [1348.325730577756, 516], [1215.7551676532187, 502], [1397.1015527490893, 492], [302.02270167458164, 141], [1424.7993981683394, 476], [155.70608407728633, 170], [376.00612152572467, 123], [365.7781236199513, 397], [136.68509546378755, 57], [796.9290636459605, 411], [612.6577092787702, 227], [61.29733905530645, 42], [60.67528525896884, 32], [185.4483909787075, 89], [632.1501442676063, 271], [74.83833551484531, 59], [200.11428707749644, 107], [189.18724813596327, 150], [376.1016597039261, 237], [196.13951603776468, 92], [318.5348343733258, 153], [634.0728965324479, 268], [570.7352921878157, 253], [901.0433197179659, 428], [522.8634925995509, 270], [112.30986492247877, 79], [293.92660707726736, 144], [808.6678026984864, 312], [162.69068677101814, 102], [1019.5857477575537, 554], [76.19387922846454, 71], [796.5361329004882, 306], [1.7046342751095835, 6], [199.9072443890454, 273], [515.1829982478457, 256], [435.2474786458215, 234], [1348.4919554912526, 653], [446.60180397332624, 220], [478.4447035218893, 221], [84.84470347429169, 67], [229.3447611062029, 107], [78.69743948244002, 60], [1109.2747102708472, 517], [91.36599626771442, 66], [409.3850668192058, 185], [33.84527222729591, 47], [214.47535143954542, 138], [37.991128914299225, 37], [711.6572040150061, 372], [3.301808647031521, 11], [162.84101956012864, 69], [1.422202169762329, 11], [305.159441223811, 122], [540.7694680662531, 239], [397.96967581751744, 215], [369.25403070980883, 131], [361.8250573576979, 136], [816.3106683567817, 241], [293.8866977218231, 145], [350.89214460742824, 226], [1331.5179877284154, 548], [28.08383767147734, 38], [417.56144183383094, 170], [68.14400899433042, 27], [596.5347334028277, 264], [701.6984236704029, 258], [189.05766577668328, 82], [290.93746564661114, 147], [575.3712912498431, 259], [515.362694786443, 152], [248.8398369289307, 151], [883.1652038202337, 320], [226.66567727148117, 110], [238.51385707744987, 141], [219.28145866585055, 132], [293.0739129966459, 101], [276.3642188411891, 135], [1292.3810551344304, 629], [214.6076184353031, 241], [751.3182645284749, 492], [804.1555222452384, 304], [1140.1295337791644, 404], [7.295548871083156, 17], [295.0086110482614, 138], [387.1874751502578, 141], [256.1086023139869, 161], [198.4452494349764, 125], [1195.2344338669793, 639], [611.8278185763825, 315], [190.49232372795177, 102], [46.8020305596736, 25], [820.9494540552287, 386], [307.5099955550522, 153], [442.4686306769501, 518], [550.954249349272, 219], [193.56840723862206, 121], [900.4104874447439, 613], [430.13674790078494, 204], [609.4097200244667, 273], [142.01741947617984, 75], [862.0634134931588, 373], [917.702108963148, 288], [565.80092644866, 243], [163.79683290445962, 71], [105.35297635415418, 51], [229.81724115446832, 104], [1330.2119541230386, 748], [516.8695280897617, 180], [263.65275485337315, 137], [685.3376198713619, 394], [946.9053820116583, 426], [256.30056589416336, 124], [1.549326770497828, 16], [148.75995982829565, 49], [253.71719182883123, 216], [20.000052335505416, 68], [7.622364205941267, 12], [639.896376083241, 216], [787.0023019719674, 331], [254.3066166994904, 129], [613.5019281974337, 238], [626.5802330570325, 247], [220.20778378861678, 108], [196.45870170876424, 133], [206.1106382073902, 116], [15.251662181936354, 30], [983.5738512625628, 537], [1222.2485642406718, 557], [1399.8288750469992, 519], [541.6320586537486, 390], [267.3733235428058, 154], [319.0906667461991, 374], [32.876001283411654, 30], [382.9209532842035, 187], [324.74703782304005, 190], [99.1872716296561, 38], [405.21725471218497, 167], [148.3173648498863, 127], [642.1977216955765, 290], [1007.3393488538936, 424], [170.42926177207892, 56], [299.9286863558227, 181], [220.3457717644012, 147], [280.0160615946131, 188], [8.796359525527237, 34], [189.32541256102604, 74], [289.06251827723327, 115], [592.2939609828254, 268], [935.8386921889214, 366], [557.2712005117581, 251], [1524.0454309219751, 517], [74.45983703705394, 54], [1222.2315444487663, 488], [568.0410692954031, 217], [269.60024452021116, 109], [294.40154786779914, 282], [1280.6962155976914, 503], [881.0700126827004, 320], [54.795239393896736, 18], [107.49815839984831, 72], [351.1744237156736, 168], [85.26870695351295, 41], [508.6027855110847, 239], [51.40571331485603, 42], [545.4699170760184, 219], [725.7988922253232, 417], [216.5102199447124, 182], [452.0650665482065, 328], [224.9689624322432, 138], [22.825330350564798, 259], [1.0031874239903118, 13], [317.27822743481784, 157], [241.28605011462423, 209], [103.27041334350224, 92], [63.04693014525219, 99], [719.2671060625503, 336], [171.23100713814324, 86], [74.67873808893984, 41], [1159.2377468300456, 405], [454.05128133875223, 259], [54.158264321156025, 22], [780.706146518993, 336], [248.38718147824147, 65], [238.62200688996097, 73], [207.40615397409624, 108], [339.35663309478764, 166], [223.84903011322967, 237], [16.871253325240986, 35], [626.1477613006864, 483], [156.7385338483873, 110], [38.948843735005994, 48], [291.94778628552916, 371], [1068.5908290648122, 455], [1219.7571343912296, 587], [545.6170318767113, 193], [246.12691424455966, 141], [82.52086915149562, 44], [124.7926784019927, 34], [104.0009379242432, 90], [203.89289326070863, 85], [30.180923031140992, 47], [284.1004418205033, 321], [1196.1025294572491, 487], [176.12091485087262, 100], [391.7870023341138, 215], [341.0715370392672, 157], [59.70504295977827, 47], [711.0254257342986, 274], [252.1869945465903, 133], [782.3446227851782, 369], [214.38851646057037, 110], [87.73302183127998, 75], [87.4146025936468, 37], [429.7588222386879, 916], [966.1510843533958, 370], [336.156262338617, 167], [341.5300551073817, 204], [442.2719048302188, 211], [910.7543213799581, 465], [16.097871036792633, 27], [1318.0565953313371, 480], [628.6521495120899, 477], [1613.4714954843275, 580], [210.8425438640336, 147], [45.27873578744493, 59], [198.08846330532288, 60], [51.96231893723416, 42], [34.1051249652628, 58], [59.91998208879659, 25], [24.49661035155077, 36], [82.09990071082711, 24], [1.7707892236830958, 75], [468.2486828160404, 219], [258.2421721655883, 91], [320.56435824110747, 206], [710.0657650636294, 273], [252.68888831234744, 109], [413.3425146763093, 191], [40.85635572445483, 28], [364.22791624721503, 148], [258.55821175364656, 305], [328.8084185623244, 141], [177.99425463156376, 55], [238.1924329713902, 154], [573.5252141363657, 203], [62.29210095875714, 82], [42.240970108309284, 42], [687.0546680066814, 299], [941.207824729122, 524], [105.39885593987765, 84], [477.0615520931842, 291], [419.4463680102507, 313], [153.5129991228373, 50], [35.366373529098894, 24], [476.54355046964247, 236], [19.522889388033946, 32], [336.60026860701055, 163], [188.6910806980195, 78], [67.91012470693147, 38], [109.20977367125545, 77], [19.936403315223288, 33], [83.68798818410093, 119], [454.23467003996393, 204], [191.47666512480532, 98], [331.82879231930747, 106], [349.72547804983515, 184], [369.5153291929764, 314], [711.5347275850676, 366], [230.71504724394345, 152], [204.96723915598824, 143], [268.1516243146202, 157], [117.07184225099081, 133], [233.8182833160272, 103], [576.9907731579839, 263], [457.46631454053295, 179], [162.8128659492836, 88], [76.30441831207463, 52], [240.574523891888, 132], [50.88024495296463, 47], [336.9353781602325, 157], [218.53897123118895, 143], [479.9452464144283, 228], [760.1906852874299, 300], [305.61558544937907, 123], [251.07551771012277, 132], [145.16622655811034, 98], [953.0089933007457, 497], [314.2095920304855, 151], [46.516154766684394, 30], [451.39279077286426, 194], [217.23557146623943, 148], [667.1356298146434, 284], [0.9218838539023864, 17], [146.72072928353163, 293], [481.2977078118274, 247], [673.9825376229528, 242], [375.4889684211994, 160], [336.96713507304185, 191], [386.80725963855224, 177], [521.7892047583252, 251], [163.3883046629776, 81], [551.5535000653067, 160], [30.433987977708966, 30], [376.2779824851373, 167], [472.84541205055393, 264], [935.4630022559122, 347], [792.353417164491, 352], [1068.1432183822785, 446], [1440.392889396513, 506], [127.81218109159727, 160], [424.8261510283728, 263], [15.612252534463543, 78], [77.98608248617239, 22], [319.3056435021531, 142], [53.811555331310444, 38], [1047.8482991012415, 426], [1236.4813299730563, 519], [216.17327424524, 95], [772.1707171556404, 362], [75.88153647812618, 31], [44.68267813150669, 31], [109.59152608438751, 46], [135.98085195295468, 83], [1053.2932115249073, 454], [1534.1360873048675, 493], [51.410102166203615, 50], [278.76718933209304, 120], [705.6711144882634, 289], [362.5132337175048, 112], [1013.7711221521749, 439], [505.21967903572295, 223], [237.07695554512787, 205], [91.72139999424917, 81], [233.20956447537947, 102], [60.48867694826322, 22], [185.83482455277806, 88], [283.0351011745147, 110], [120.69489419923684, 70], [484.6181644061985, 231], [7.608588887494989, 35], [70.11529120134696, 42], [344.2948035573181, 169], [583.7070942874643, 300], [290.51043445843607, 150], [1567.2854466038366, 745], [165.0759274636115, 88], [50.0962085207957, 38], [366.43340194526127, 195], [1290.2386015340726, 533], [509.66303991583277, 225], [339.6188384844104, 140], [153.7606395624457, 90], [164.08843149341465, 105], [97.50612721799189, 50], [121.5934135015234, 61], [91.68244450206839, 75], [475.10483546392965, 199], [187.36279349230017, 94], [10.982540729543643, 97], [458.2911523949424, 212], [206.23713822194077, 236], [1081.5164604252805, 447]], "final_state": "tinker://9c18b804f21a06705c6da69577f80b4e/weights/confirm-baseline_adamw_s1-final", "t": 1793745523.824746} {"stage": "eval", "arm": "treatment_dimuon_s1", "split": "test", "step": 100, "nll_sum": 197651.79774024937, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.0304049240877835, "example_mean": 1.909386036657386, "per_example": [[132.9833178740978, 55], [1248.0758358377097, 555], [577.5981398528705, 233], [1058.2245366066272, 416], [503.2820693289957, 287], [121.53492942190405, 60], [711.3134140817606, 468], [132.1642450334507, 71], [81.2803077364315, 65], [617.3657685489097, 271], [45.37020645823122, 35], [23.01894049319617, 31], [181.7229191962724, 107], [388.3789676717993, 112], [9.754644649786314, 11], [239.1548361148616, 86], [130.7785373528354, 105], [441.42408426235943, 407], [186.96954954134435, 132], [725.6105772817691, 231], [287.94360812190826, 268], [395.4184999882241, 155], [85.66886004092521, 102], [133.32367450308675, 74], [239.84282216221794, 83], [357.50562303461106, 135], [952.1020275672499, 390], [869.7480891673184, 284], [26.621169067286218, 44], [337.88914289067577, 137], [1202.0300180865866, 447], [0.89987274455234, 25], [387.0375760784518, 155], [842.8330620432353, 457], [309.2459504750823, 187], [464.6583772685499, 230], [393.19333916284063, 148], [327.2485927613465, 436], [481.64571059045375, 146], [321.8157193513698, 191], [16.12987271892416, 37], [429.8923338845916, 333], [80.2501190015854, 53], [186.59877058132133, 94], [1075.9792313124422, 521], [319.53379769033563, 175], [133.94281990842114, 79], [55.659564364137616, 19], [3.7926498417518815, 10], [326.6342622547712, 208], [312.3454002242197, 156], [225.10680813573254, 160], [1162.6543199931348, 420], [765.112306036292, 285], [84.96702763376379, 31], [412.67540040825816, 167], [57.7040662156669, 44], [744.4429294863376, 245], [8.37976951496875, 45], [235.1231533413802, 102], [131.68156791160618, 114], [65.75847164140009, 20], [164.0798038774551, 86], [154.04421189810455, 63], [70.47376578269902, 72], [104.26205079733973, 66], [142.21605816924875, 101], [101.70233836113403, 48], [64.77609232583742, 25], [63.65594434582431, 26], [65.64677210947548, 64], [222.6177402646672, 72], [374.7472700108674, 342], [326.8387079029744, 123], [361.4300528738646, 314], [115.05801590185115, 68], [75.69461412345072, 58], [208.28883745391977, 106], [205.6266879928296, 81], [321.7837685194936, 181], [287.4979795477352, 312], [637.2167372293989, 302], [1274.038786981535, 473], [76.1421289865848, 74], [314.2520683235689, 169], [198.98558004387266, 86], [1481.3534541618765, 663], [98.05181314619131, 81], [579.528611940279, 272], [577.347764163007, 206], [863.8611465651275, 720], [734.2793959607075, 291], [1281.5682074189172, 562], [181.55104050511721, 117], [145.1621990917024, 106], [551.5253721539402, 216], [74.79188210475854, 45], [385.05781572616206, 220], [304.40713237301316, 134], [1181.5533215178023, 454], [83.26278873279261, 57], [203.09071381331114, 101], [70.36748021271157, 22], [138.35748707981656, 74], [629.9795823388042, 294], [412.49688249133305, 150], [547.5549814526285, 203], [368.5987545940461, 166], [724.1406340703638, 262], [118.39795463891642, 52], [484.223110991843, 181], [33.01267828934942, 37], [1179.411450462038, 642], [254.858657210611, 176], [213.26983697375567, 113], [539.4949742009267, 194], [113.46457743478368, 72], [4.360102643713617, 10], [176.8067015046072, 123], [397.6715756851913, 141], [328.88644821434514, 117], [1320.392176479363, 576], [119.9677037725478, 93], [308.850197513033, 137], [580.9837516554173, 240], [38.11768705432996, 61], [127.49411533815146, 123], [188.24785481693084, 98], [269.18837187299823, 120], [6.15678736808195, 32], [880.3191445141867, 334], [2.2172611819023587, 26], [54.53690137589956, 35], [231.39476744777494, 72], [639.7936244926213, 263], [649.8166694420893, 247], [191.68360911781178, 66], [571.1652771567515, 265], [1346.951308177262, 516], [1216.4913484112692, 502], [1396.3286685452745, 492], [302.0855834558056, 141], [1422.3232208968793, 476], [155.11285887460596, 170], [375.5801514820041, 123], [364.0711322662397, 397], [136.66421338759392, 57], [796.155475440788, 411], [610.1089578596761, 227], [60.592176332697136, 42], [59.92387120785497, 32], [184.7263519883045, 89], [632.5103595109713, 271], [74.878420197178, 59], [203.15676576916118, 107], [189.27749491737904, 150], [376.9736861097381, 237], [196.1328653324099, 92], [317.92346708888226, 153], [635.6160443461222, 268], [569.7689429862003, 253], [897.4262689736654, 428], [524.7055526868966, 270], [112.51870740306333, 79], [291.89524895140084, 144], [804.9431680107791, 312], [163.65423514304348, 102], [1017.2424227660413, 554], [76.33030003791589, 71], [796.876109187654, 306], [1.4154087754186548, 6], [197.33973498863543, 273], [518.5776056027271, 256], [435.54077229308496, 234], [1349.5937186943515, 653], [447.4683753142908, 220], [477.70488458738964, 221], [84.25722950714771, 67], [230.08295647976593, 107], [76.87382598175077, 60], [1107.5299754208788, 517], [91.90646936289522, 66], [409.0431500965592, 185], [34.13902603358292, 47], [212.8454568485584, 138], [33.702717008253785, 37], [708.2294972716818, 372], [3.622043791365286, 11], [162.00939452125203, 69], [1.3141035570879467, 11], [306.710261903394, 122], [541.9975240361739, 239], [398.32804796884625, 215], [369.39985165754115, 131], [362.3934013412256, 136], [813.4128030490151, 241], [295.0201144031762, 145], [350.3632850440172, 226], [1337.0265908036727, 548], [27.442264220961988, 38], [417.8154947553958, 170], [68.2122627150892, 27], [593.376779185083, 264], [700.2833377683396, 258], [188.4467410917532, 82], [292.16710511135034, 147], [576.452485553657, 259], [516.9566312049972, 152], [246.78884261567146, 151], [883.8428562094059, 320], [226.23746894267788, 110], [240.4388193003466, 141], [219.45149660827542, 132], [291.61494864181805, 101], [275.3499554089076, 135], [1291.2564738736428, 629], [214.1472581102655, 241], [756.9896356152622, 492], [800.7697879676214, 304], [1139.0857886896406, 404], [6.625787146047486, 17], [294.0304198091344, 138], [383.2514780280944, 141], [258.5182530745785, 161], [198.49383861554952, 125], [1196.4248015606418, 639], [617.3061898239066, 315], [190.60214591462545, 102], [46.95547009819876, 25], [821.0330215936119, 386], [308.3011150140637, 153], [441.5406358695732, 518], [552.3224069891558, 219], [193.81549960234543, 121], [898.7971993141072, 613], [429.3509823609302, 204], [608.2265599951279, 273], [140.88223086928792, 75], [858.3839576401369, 373], [916.5525054599852, 288], [565.3811482290203, 243], [162.46922908135627, 71], [105.36799141566917, 51], [229.51669374072026, 104], [1339.982423891025, 748], [512.6976700592986, 180], [265.2796705034607, 137], [690.7981307382859, 394], [945.6548740283341, 426], [257.43151757782914, 124], [1.4768628326742146, 16], [148.5340085235748, 49], [255.41191229371358, 216], [20.360108576556286, 68], [7.533838029439721, 12], [640.2824986434771, 216], [790.3492811266292, 331], [252.93296928044606, 129], [609.7138827054366, 238], [624.8424920745082, 247], [220.315245099182, 108], [196.30473139238745, 133], [210.95624282275543, 116], [12.521195919063587, 30], [973.6229961032782, 537], [1221.7667242328062, 557], [1399.4314352951221, 519], [541.7759857534611, 390], [266.7615149883386, 154], [319.47416282385393, 374], [33.27559350470983, 30], [383.81249472569493, 187], [325.25793054029464, 190], [95.42524585440876, 38], [405.33287096408696, 167], [148.3901490210244, 127], [642.2179465866047, 290], [1008.3431213192689, 424], [170.37116573767975, 56], [297.4249121847133, 181], [223.09161802464882, 147], [280.4664438359737, 188], [9.011122547861298, 34], [187.9030796970942, 74], [287.60842425129727, 115], [592.2638588440832, 268], [935.2777729419577, 366], [556.4352446039951, 251], [1524.7967219875582, 517], [74.67551152852798, 54], [1221.907331958283, 488], [564.9484121728868, 217], [271.015989999074, 109], [293.81953602108, 282], [1281.278132737273, 503], [882.9008881777362, 320], [53.9925867578213, 18], [107.98288823062364, 72], [350.99563908374694, 168], [84.33513941603724, 41], [509.74074012399365, 239], [50.41226719536894, 42], [541.9964884943334, 219], [725.1249824969682, 417], [216.07676519774895, 182], [456.0862463433116, 328], [224.23236604676504, 138], [22.07259414620512, 259], [1.0355677417210245, 13], [319.5832356222181, 157], [238.6622426244553, 209], [101.91021254042516, 92], [63.37492083096868, 99], [720.7267674918216, 336], [169.5286384433184, 86], [75.15273673961701, 41], [1158.1923524585022, 405], [452.86250258628013, 259], [53.88561853587254, 22], [780.0072298230764, 336], [247.7066676233917, 65], [240.2930061192655, 73], [207.09396276150392, 108], [338.7634009979146, 166], [222.0794942956686, 237], [16.763603983166824, 35], [627.4842486010657, 483], [156.04007341093893, 110], [39.04361625452108, 48], [294.1242947006331, 371], [1070.0384018643863, 455], [1215.5115064989077, 587], [549.0849594158205, 193], [245.30866009548424, 141], [82.72145621169054, 44], [123.07597848015573, 34], [105.05074239355596, 90], [202.76057182113243, 85], [30.986744789420868, 47], [282.92243085102245, 321], [1196.6760168632172, 487], [176.85258835654525, 100], [392.9766287878065, 215], [340.1723466768635, 157], [58.207321600692005, 47], [709.4059332485622, 274], [252.8245508061782, 133], [782.6885566902838, 369], [214.35284221394613, 110], [88.04183782561222, 75], [87.70747145017219, 37], [428.4921134483864, 916], [968.2280069736053, 370], [335.11777137625535, 167], [343.22617350491987, 204], [441.7339390640882, 211], [907.5220867314929, 465], [16.02488765500857, 27], [1316.3955592916514, 480], [630.3320010435882, 477], [1610.2653126318837, 580], [213.3827911175439, 147], [43.18025209118787, 59], [196.92305912567724, 60], [51.15291344823481, 42], [33.653595243518566, 58], [58.21901024584258, 25], [25.259258921841592, 36], [79.14054191977715, 24], [1.7899115976233588, 75], [467.8153726961425, 219], [258.9832476126239, 91], [319.2399201596779, 206], [708.6114123470543, 273], [255.5652115242765, 109], [415.63153421684274, 191], [41.64333100834847, 28], [363.7448363210333, 148], [258.41654652761906, 305], [330.2800648561141, 141], [178.52638296289655, 55], [238.54016869921622, 154], [572.5554611092626, 203], [61.042662576048315, 82], [42.18847184755532, 42], [686.3255399282461, 299], [942.8267578778441, 524], [106.81349300670081, 84], [477.24022062147947, 291], [417.48505753671066, 313], [153.7183345938821, 50], [35.09096201860655, 24], [471.94466360535284, 236], [19.44293304587609, 32], [337.5751181409405, 163], [188.65218317093058, 78], [67.52506919667206, 38], [109.77551940759486, 77], [19.175090829505507, 33], [82.67478753253886, 119], [453.08057606261445, 204], [189.81361933608957, 98], [331.36050662423986, 106], [346.0590757907812, 184], [373.21228678108764, 314], [709.1455305205304, 366], [231.3920737158349, 152], [205.78721498166124, 143], [269.200344137363, 157], [117.45778343827254, 133], [231.72789183318037, 103], [576.9540728708978, 263], [456.5115483431641, 179], [163.9991243463155, 88], [76.59249807232618, 52], [241.35954098668827, 132], [50.57075133871325, 47], [338.8142408301933, 157], [216.77912946470656, 143], [479.74463443413924, 228], [760.1773757850315, 300], [304.98749780570097, 123], [249.89529621122756, 132], [145.94606070573627, 98], [950.5119255425598, 497], [314.9423741825467, 151], [46.45184267005243, 30], [449.3340312451028, 194], [216.051399387733, 148], [665.3886467693656, 284], [1.0413685524908871, 17], [144.23978802735448, 293], [483.3784682445603, 247], [674.4123405270293, 242], [374.9874661425879, 160], [333.9059569371034, 191], [386.1293963140522, 177], [523.2157799869101, 251], [162.7996482936378, 81], [549.913580003982, 160], [29.963787301974094, 30], [375.50587445127326, 167], [475.3524301498469, 264], [936.078017348017, 347], [794.7448156295404, 352], [1066.437850580034, 446], [1440.923757436763, 506], [128.56729868927368, 160], [424.85446257295916, 263], [16.296186065457732, 78], [77.43986040272819, 22], [320.21991724763166, 142], [52.60387835533401, 38], [1044.9225454735438, 426], [1237.7536109735875, 519], [216.41464634766635, 95], [772.8203570004189, 362], [76.90564282732612, 31], [44.45890963936017, 31], [108.02651503220477, 46], [135.6634373407491, 83], [1052.0049757205163, 454], [1531.685108599726, 493], [51.164983495373235, 50], [275.59141666102914, 120], [704.4814943265778, 289], [361.4972906986457, 112], [1011.6985271204753, 439], [505.25311194038005, 223], [237.20492852408276, 205], [91.68301903476424, 81], [235.22307768975224, 102], [60.0309462140915, 22], [185.08054147825985, 88], [283.57543237842174, 110], [120.91277048235816, 70], [482.6962564219375, 231], [8.237475551505668, 35], [70.21419810080238, 42], [344.8357208161706, 169], [583.4263551798713, 300], [292.94884383438966, 150], [1564.6930557606975, 745], [166.75045064166437, 88], [47.67470443682214, 38], [366.6861917744718, 195], [1286.0434941547537, 533], [509.8083893244698, 225], [340.5479270277365, 140], [154.29034786067132, 90], [164.19580903237193, 105], [98.20448415199462, 50], [119.30156387423767, 61], [91.0981198492168, 75], [474.2328716446864, 199], [186.29904659468775, 94], [11.207499224758749, 97], [458.80664047919345, 212], [205.45195909286508, 236], [1078.2878950276909, 447]], "final_state": "tinker://64eea06e33ba66329c486ce2de950f32/weights/confirm-treatment_dimuon_s1-final", "t": 1793745543.8306766} {"stage": "eval", "arm": "baseline_adamw_s2", "split": "test", "step": 100, "nll_sum": 197686.70805221066, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.030763545006581, "example_mean": 1.9098644363144255, "per_example": [[130.46821285390251, 55], [1252.0391052836635, 555], [582.0837699570075, 233], [1055.9889049745489, 416], [508.5416793765726, 287], [120.56352456280274, 60], [705.023439020104, 468], [130.93940456675227, 71], [81.67705468647182, 65], [611.7357507034762, 271], [46.652614474740176, 35], [24.10019804750482, 31], [179.86243854689747, 107], [388.9354851584685, 112], [8.68717371307821, 11], [240.6577802837835, 86], [130.8802212026685, 105], [442.60397748639025, 407], [186.6723891212423, 132], [722.7538047982141, 231], [285.7528075806713, 268], [392.0537425928669, 155], [89.1305005936083, 102], [131.76286905190727, 74], [238.28299305175824, 83], [357.9620733171996, 135], [946.480517962762, 390], [867.5675721782936, 284], [27.834484078475718, 44], [341.68922569251845, 137], [1199.1801392106427, 447], [1.6904541945450546, 25], [389.1001279388274, 155], [849.514485683947, 457], [310.11731614025666, 187], [466.5677535971072, 230], [392.25983932161216, 148], [326.84578496346535, 436], [479.79310509147035, 146], [323.3511254913865, 191], [10.384090218034544, 37], [431.37326168593154, 333], [81.61970946595943, 53], [185.2043239839977, 94], [1072.7272335083799, 521], [322.2704970795003, 175], [130.46255175010447, 79], [54.75726101755208, 19], [2.7428067844548423, 10], [331.39229816291163, 208], [313.1147298485457, 156], [222.58914308790918, 160], [1162.749017535148, 420], [766.5887168273457, 285], [86.70272578683216, 31], [412.006810640858, 167], [55.68761298701793, 44], [743.1674861830302, 245], [9.63751700267676, 45], [233.28218237340297, 102], [128.8735538754936, 114], [63.63072914358054, 20], [165.44436711743765, 86], [153.96276254508393, 63], [70.208480500696, 72], [101.4131262449373, 66], [144.0080864621441, 101], [101.46431497904905, 48], [67.83679152351397, 25], [64.09586312293686, 26], [64.43232922327934, 64], [221.24153661422224, 72], [379.3512797536341, 342], [320.2224600530735, 123], [363.6640319184444, 314], [115.48238603307436, 68], [71.16250740039504, 58], [208.42260058175634, 106], [201.8270765219562, 81], [324.0519667958588, 181], [286.1573141384142, 312], [640.3558239748381, 302], [1274.4948935516168, 473], [77.13110192969043, 74], [320.6350709412268, 169], [201.7321503856365, 86], [1486.6125251061894, 663], [94.23569475598924, 81], [579.6293035106355, 272], [576.2640940608217, 206], [861.5634585306707, 720], [736.938036255955, 291], [1280.2046964939614, 562], [180.67243157101166, 117], [146.9059399014991, 106], [555.4773880581797, 216], [76.42692738755682, 45], [386.8672239588136, 220], [304.89491708029334, 134], [1177.9069422879911, 454], [84.49753510119442, 57], [199.46223332329646, 101], [70.09054108696364, 22], [135.47260244198787, 74], [629.9809706667279, 294], [412.4628362931812, 150], [548.1339499666974, 203], [365.11199164763093, 166], [719.83405867279, 262], [117.95083056875319, 52], [483.82305449996056, 181], [34.14075671604587, 37], [1186.5566435280598, 642], [259.4069840917473, 176], [207.40076714209226, 113], [538.4761801634613, 194], [111.2276334245571, 72], [3.3356646824668132, 10], [173.4930403442445, 123], [394.84740874139845, 141], [327.91923055093685, 117], [1326.466022639529, 576], [123.09496886098509, 93], [308.52343506065864, 137], [572.945490034569, 240], [39.82769696426294, 61], [126.08003505261831, 123], [190.30355003471755, 98], [266.4809468701769, 120], [4.72159532864498, 32], [879.1609676450862, 334], [2.1960349002820294, 26], [57.594002539493886, 35], [227.6445441049873, 72], [636.0524059323129, 263], [647.0902084745937, 247], [190.64131672469364, 66], [568.3839077852535, 265], [1347.9704107680877, 516], [1210.0297249343585, 502], [1396.6393589839745, 492], [300.9554217516361, 141], [1422.941045789597, 476], [150.424815876484, 170], [374.14762055959727, 123], [372.6898468799809, 397], [135.50933935454668, 57], [805.0461153840461, 411], [602.6486428092539, 227], [59.107653214124184, 42], [63.11448341439245, 32], [186.0215811817094, 89], [632.655053911169, 271], [77.99257395469795, 59], [203.01704320777935, 107], [189.20634337693264, 150], [379.61953117083794, 237], [197.3162565011071, 92], [319.07430160021704, 153], [630.9759289944122, 268], [567.7747688868203, 253], [899.7853644646311, 428], [521.4434725511846, 270], [115.48013226106491, 79], [293.9867601106707, 144], [806.4607862454286, 312], [164.39011785956427, 102], [1017.155915250838, 554], [77.88688280342103, 71], [790.5953414880751, 306], [0.7368830809866722, 6], [199.82028162535016, 273], [511.1700172756682, 256], [438.14708685252845, 234], [1343.8504790141342, 653], [445.8949030578805, 220], [475.5075863098414, 221], [84.55358741704163, 67], [232.05554098881476, 107], [77.28111047239054, 60], [1107.7286795836958, 517], [89.94820865313159, 66], [406.04861232213625, 185], [31.304032591134273, 47], [215.15076475068963, 138], [40.710536481003146, 37], [709.5089033307634, 372], [3.2718687655560643, 11], [163.628490807856, 69], [1.4654897239217917, 11], [308.5011567042784, 122], [541.9626110114186, 239], [403.82301438300783, 215], [373.38694521656726, 131], [360.9437909381618, 136], [811.4562208992584, 241], [293.3534600396524, 145], [346.0650864136187, 226], [1329.7189958993404, 548], [27.711941905639833, 38], [421.58048961497116, 170], [72.30198662718612, 27], [602.3236611534339, 264], [701.9033433232689, 258], [187.95836963079228, 82], [286.354432681077, 147], [572.9044164187371, 259], [512.4024429486453, 152], [248.8448010508746, 151], [876.0697859719876, 320], [225.0545517422688, 110], [240.63992797614935, 141], [220.65729019163882, 132], [292.5407854522691, 101], [274.4764866886253, 135], [1296.8258484308553, 629], [210.6302630055643, 241], [765.5382475616216, 492], [798.6314857019697, 304], [1133.1774600114118, 404], [8.394127989999106, 17], [298.7281595956374, 138], [387.3434036870458, 141], [259.8908409468386, 161], [202.81258451963595, 125], [1194.1637099946538, 639], [614.1544452911876, 315], [191.34497399815154, 102], [49.523158187985246, 25], [817.3006633504131, 386], [308.56574047964386, 153], [444.01296550938196, 518], [543.7179375516971, 219], [189.52975918245284, 121], [901.7876514398704, 613], [427.96964546970776, 204], [612.911987136099, 273], [143.32542939497307, 75], [859.2063493671958, 373], [914.6973079074378, 288], [561.7080069070453, 243], [160.7681222892843, 71], [103.45305674034444, 51], [225.21777403675515, 104], [1339.9739051018223, 748], [515.6571974844373, 180], [263.75466162354405, 137], [684.5738557446912, 394], [941.1039652433174, 426], [255.72268558814892, 124], [1.9211178971982008, 16], [147.77240562121278, 49], [253.01820512538688, 216], [20.811974656498933, 68], [8.729317073040704, 12], [640.2010579188254, 216], [791.3539967361539, 331], [251.44875949679044, 129], [612.7209871190171, 238], [628.4529574928301, 247], [219.66796383465407, 108], [195.1925139034065, 133], [211.71780686825787, 116], [13.86495596233965, 30], [975.7243681907148, 537], [1228.886417234853, 557], [1396.3997996546786, 519], [544.3124267984094, 390], [271.4564945160673, 154], [318.1138978859635, 374], [34.13459956839233, 30], [381.7585532506872, 187], [328.5458916285206, 190], [94.61366148302113, 38], [405.83209365459334, 167], [145.7864115886623, 127], [645.1905416300215, 290], [1013.2889199041285, 424], [168.64213724891124, 56], [297.22078756002156, 181], [234.35033799372468, 147], [281.1496809962682, 188], [9.069810660620533, 34], [189.96192759993573, 74], [288.17872992825505, 115], [593.8158995856811, 268], [934.7856473871661, 366], [558.762678029829, 251], [1524.4070129626816, 517], [74.40974616055928, 54], [1227.4301165238548, 488], [575.1751614738387, 217], [269.6884049218934, 109], [293.50287051408986, 282], [1288.8351554839646, 503], [882.9667036687297, 320], [53.72231051744893, 18], [109.16801407804269, 72], [347.11137496682204, 168], [82.72902598442124, 41], [511.38761674814396, 239], [51.38014032869705, 42], [540.1099560509292, 219], [727.9710495569343, 417], [214.75195626497725, 182], [456.34730465822656, 328], [225.79903969323914, 138], [22.46745179450727, 259], [1.2271567236598457, 13], [321.4347678411177, 157], [240.10701720172074, 209], [102.14764818102958, 92], [64.0220958763748, 99], [715.1008492442979, 336], [169.75381571098296, 86], [81.44052717617524, 41], [1151.0148970375558, 405], [456.4781367578853, 259], [54.30957796452276, 22], [785.0629157742967, 336], [246.2724279173226, 65], [238.8636481493395, 73], [205.0701191392286, 108], [338.56991923452415, 166], [229.14824235173182, 237], [19.967891441014217, 35], [634.0629621509561, 483], [155.10656162597843, 110], [41.80952958781927, 48], [291.74177350599075, 371], [1071.1629853495479, 455], [1222.8350071333603, 587], [548.9744561952393, 193], [246.41946166023445, 141], [80.33999619633323, 44], [122.59319715125457, 34], [104.41638816363047, 90], [201.6645151025789, 85], [31.541473601208054, 47], [291.094671721492, 321], [1193.1083038114102, 487], [174.79960614497577, 100], [392.2391509283734, 215], [343.5572232263605, 157], [63.355655889317745, 47], [714.1328718308778, 274], [250.02229825880295, 133], [770.6125604728277, 369], [214.29986872540394, 110], [86.51438895247702, 75], [88.92951374253812, 37], [437.1053709611133, 916], [968.2090652645875, 370], [335.9827993408435, 167], [349.36059967188476, 204], [439.0115275409462, 211], [913.1368972702712, 465], [16.604002135278108, 27], [1314.8689675109968, 480], [633.7060990114796, 477], [1605.302396394237, 580], [212.92527491805686, 147], [44.23257270566137, 59], [194.87820397409814, 60], [48.34500412186753, 42], [34.31245545819638, 58], [57.15459199799079, 25], [24.611122156498823, 36], [83.39165528607555, 24], [1.6431473354291484, 75], [465.9674611631126, 219], [260.36995413545174, 91], [319.9003009709645, 206], [708.6903509289095, 273], [249.83169360618194, 109], [414.91709580834504, 191], [40.313214915406206, 28], [361.4459430525312, 148], [262.540824258513, 305], [329.3288760059222, 141], [175.8487220383322, 55], [239.1150407915602, 154], [569.8300136741834, 203], [62.69154382271745, 82], [40.82353165738698, 42], [686.6291365295256, 299], [941.206902506894, 524], [104.22155137996833, 84], [481.60348856379096, 291], [419.82632877496553, 313], [152.5448129303477, 50], [33.15112104759373, 24], [471.68805853948743, 236], [20.07167419893449, 32], [338.59386371047367, 163], [189.7393103253089, 78], [65.59477167103478, 38], [110.56259591347208, 77], [20.290216910096206, 33], [87.3572000062012, 119], [451.95526644290476, 204], [190.55588961047897, 98], [333.9576979077174, 106], [350.53067290350737, 184], [371.3428131150191, 314], [713.3959299758162, 366], [231.82558207178226, 152], [208.4093434257478, 143], [269.8021278333854, 157], [118.82680084700723, 133], [230.8255628313084, 103], [576.6384961422673, 263], [455.74837470300827, 179], [166.5079097240232, 88], [74.44601930323779, 52], [244.81672008199894, 132], [51.3656393891888, 47], [332.5552824856486, 157], [219.98743519360505, 143], [480.9667522107511, 228], [754.4175544111495, 300], [304.8592019318594, 123], [249.82210794367757, 132], [143.68747269517007, 98], [951.5210232782283, 497], [310.3351695073525, 151], [44.75292713592171, 30], [453.6086050871818, 194], [213.43159615127297, 148], [668.3006281319977, 284], [1.55062928563666, 17], [145.19197401622398, 293], [479.40931507573623, 247], [671.3788770400497, 242], [376.06354163903495, 160], [337.3599014915617, 191], [389.25798783079426, 177], [516.8566869260248, 251], [161.5396037429091, 81], [556.6602076704512, 160], [29.71745684949019, 30], [374.997193934847, 167], [474.70508969913953, 264], [939.9742792689447, 347], [797.5521508256998, 352], [1064.2391291634685, 446], [1440.9632539885024, 506], [129.3579650780248, 160], [420.56963366220043, 263], [16.969211053070467, 78], [81.2679184732333, 22], [317.7586279220168, 142], [50.49116640263537, 38], [1044.5151929015096, 426], [1236.165359263582, 519], [223.25948336018882, 95], [775.2717563841143, 362], [77.01748282151311, 31], [44.510211482080194, 31], [105.63258012727601, 46], [134.55364806257603, 83], [1051.3456194033097, 454], [1529.090076159343, 493], [52.86898503003977, 50], [275.94995861046925, 120], [704.3111145487769, 289], [355.0054975494604, 112], [1011.5367770309363, 439], [500.25692609549515, 223], [235.28313060277833, 205], [90.67530887772341, 81], [231.3858960694388, 102], [61.08859610640866, 22], [183.3283161223253, 88], [283.91003630499836, 110], [121.19272415068644, 70], [481.4068707187471, 231], [8.092805982156278, 35], [69.04049443543045, 42], [347.9079122276926, 169], [579.2163334903325, 300], [291.76619769860736, 150], [1562.3898713914832, 745], [163.60713607405705, 88], [46.38294647078419, 38], [365.79520779435006, 195], [1294.2139786538096, 533], [509.4324389657886, 225], [342.03485401315083, 140], [155.9092205233078, 90], [167.52154847405654, 105], [100.69172249455187, 50], [115.26490253108932, 61], [91.57410471801995, 75], [477.91115251409974, 199], [183.97133990008206, 94], [10.26466945700588, 97], [457.4302373741248, 212], [209.22070731875647, 236], [1081.5616252519849, 447]], "final_state": "tinker://581c1850d38ffa76474e2c6c7f2a3fb1/weights/confirm-baseline_adamw_s2-final", "t": 1793745568.1746085} {"stage": "eval", "arm": "treatment_dimuon_s2", "split": "test", "step": 100, "nll_sum": 197678.0521026264, "n_tokens": 97346.0, "n_examples": 500, "token_mean": 2.030674625589407, "example_mean": 1.9099000514950915, "per_example": [[128.3800331855591, 55], [1251.8820903302872, 555], [582.03425204872, 233], [1055.966547707014, 416], [508.0384400332325, 287], [119.32039385729877, 60], [703.0632879364857, 468], [132.50794384816618, 71], [82.02447062508128, 65], [612.5569556789184, 271], [46.31153345024654, 35], [24.725217061934018, 31], [179.66240655348878, 107], [388.57354416996714, 112], [8.929211216577983, 11], [241.43320075457802, 86], [130.98967464528684, 105], [440.78072335205417, 407], [186.12341672267394, 132], [723.8634033752169, 231], [286.8690110069474, 268], [392.76350064347105, 155], [88.8325714178718, 102], [133.01573080447253, 74], [237.81721203599045, 83], [357.87848785765345, 135], [949.0087109887606, 390], [869.0953750062336, 284], [28.131867552845506, 44], [341.8914985197109, 137], [1196.924004622335, 447], [1.4881121886755295, 25], [393.0518461357313, 155], [848.0179678183194, 457], [312.039585316335, 187], [465.41360113245173, 230], [392.64081733648754, 148], [324.6988301105921, 436], [475.9254377684691, 146], [323.5112672274299, 191], [11.694092828638532, 37], [428.8795288158453, 333], [80.65180554542889, 53], [186.58075853622313, 94], [1076.5166837841189, 521], [320.63783818054037, 175], [130.7570056999566, 79], [54.08277103045836, 19], [2.570206556013204, 10], [332.1991402996454, 208], [310.39503469001266, 156], [222.0514176038414, 160], [1161.9877306336857, 420], [768.2617370395515, 285], [88.91893452673679, 31], [412.7090224666026, 167], [57.1955248021618, 44], [743.3132329846519, 245], [10.354999132933244, 45], [232.67152541857286, 102], [128.3109330424037, 114], [63.620976403842405, 20], [164.41321464421162, 86], [155.7716648861424, 63], [70.373064490057, 72], [100.70309295672996, 66], [144.05365396766024, 101], [100.97678908940722, 48], [68.0205364792007, 25], [64.34153000330775, 26], [64.06100956519697, 64], [223.47896382873978, 72], [379.2549187325376, 342], [320.08610890479076, 123], [364.5094628365782, 314], [114.86188333829159, 68], [70.12051919561964, 58], [209.2621556591439, 106], [202.28813757555324, 81], [322.76039641489456, 181], [285.3078142368049, 312], [639.9856056130557, 302], [1273.4270480002451, 473], [77.21252814316995, 74], [321.3399056118467, 169], [202.1870558555965, 86], [1487.3686743609724, 663], [94.22647185343158, 81], [580.1965779782913, 272], [575.5445579398869, 206], [866.0422033014011, 720], [737.1994379671903, 291], [1278.7092833997156, 562], [180.9772116414905, 117], [145.3666632029848, 106], [556.563805574373, 216], [76.64959463043476, 45], [385.09133830459507, 220], [306.00947408092964, 134], [1178.699594541174, 454], [85.2613326674018, 57], [198.42011035828364, 101], [70.79273508048934, 22], [135.73461950705519, 74], [629.6083813946243, 294], [414.0771224807834, 150], [546.3322692428355, 203], [366.4415588533866, 166], [719.8640453953949, 262], [116.63560031340955, 52], [484.63755830914283, 181], [33.76866867559329, 37], [1186.737618411624, 642], [258.22680283492355, 176], [208.60530644622827, 113], [538.5235058478024, 194], [113.10949207257238, 72], [3.645788174590052, 10], [175.08473655731223, 123], [395.88946692008903, 141], [327.7016099715056, 117], [1323.7858545281445, 576], [118.44591946843849, 93], [308.2646015261198, 137], [572.8424978300545, 240], [37.952050867499, 61], [127.80341943932018, 123], [189.88304825556907, 98], [267.37646728281834, 120], [5.100233474249535, 32], [879.1973099557054, 334], [2.531534538959022, 26], [56.20538123556946, 35], [227.27698841861252, 72], [639.1578842404684, 263], [646.1689398331794, 247], [189.91900516291207, 66], [566.5727854810962, 265], [1347.8171433724674, 516], [1211.758885725113, 502], [1393.5247800677364, 492], [300.47142547481235, 141], [1421.295447517901, 476], [150.69053668895071, 170], [374.05289746695826, 123], [369.6994171393044, 397], [136.05475803613763, 57], [802.0000589099182, 411], [600.392749061245, 227], [58.58067582645117, 42], [61.58637899065047, 32], [185.0375382882662, 89], [635.3652473362672, 271], [76.4689504000662, 59], [205.0647083178219, 107], [188.86316695215646, 150], [377.887444092308, 237], [197.57032831719152, 92], [318.6402382923379, 153], [629.9285035088797, 268], [567.6250224397313, 253], [900.2665359765069, 428], [521.814027396684, 270], [115.99831305847329, 79], [294.5322631995605, 144], [807.1698799069982, 312], [164.9299796540563, 102], [1019.4023847530252, 554], [76.70010930094668, 71], [791.3479223590402, 306], [0.9094627099570971, 6], [199.93031229971163, 273], [513.5635548230698, 256], [437.3254177889976, 234], [1346.3263518040221, 653], [444.59007285376356, 220], [475.1047604784534, 221], [84.04806474785798, 67], [231.2663648644666, 107], [77.92767364177405, 60], [1112.3236953861124, 517], [89.49575407449265, 66], [408.7769352934929, 185], [31.44922590757048, 47], [215.6165366950181, 138], [39.7321326546853, 37], [710.5138830235992, 372], [3.069657208281569, 11], [163.27534691159588, 69], [1.7478487905900622, 11], [307.16943904709115, 122], [545.0096125099099, 239], [404.66672771855065, 215], [373.22003246309396, 131], [362.9043304815768, 136], [811.9683844630742, 241], [294.06243039675337, 145], [345.3559108992795, 226], [1328.1132000637226, 548], [27.23625643203377, 38], [420.9233564548631, 170], [73.34280862109131, 27], [600.3046885236056, 264], [700.2715355179055, 258], [187.81102554681956, 82], [288.6659984928192, 147], [572.5667550672351, 259], [511.1720782710886, 152], [248.49882304665607, 151], [876.2691227784089, 320], [223.67290511479587, 110], [241.18926999082328, 141], [221.39466561248605, 132], [290.715940466388, 101], [273.30713096973705, 135], [1294.2335028687012, 629], [211.94080058105465, 241], [766.153504276187, 492], [797.2893060337034, 304], [1137.0551606096246, 404], [8.269516875294357, 17], [298.29086879104375, 138], [386.4641692862806, 141], [259.5531209191207, 161], [201.08526705413522, 125], [1199.8442246365446, 639], [615.520137129065, 315], [190.2624372577593, 102], [49.327714923015265, 25], [818.3971683431682, 386], [310.1346219140114, 153], [444.5684785773408, 518], [545.5122076538696, 219], [192.99546059684872, 121], [898.1288717165423, 613], [430.41127754276386, 204], [608.8030515173882, 273], [143.37079561795917, 75], [857.1688750552175, 373], [916.9641451717498, 288], [561.7964813465223, 243], [160.93060717946696, 71], [103.37029619360624, 51], [225.39184656287216, 104], [1340.7968479212464, 748], [516.5518746187952, 180], [262.31745681631764, 137], [681.0940293082767, 394], [943.8969323899801, 426], [257.01201616034086, 124], [2.031971668976439, 16], [147.95430143046542, 49], [253.91437448705437, 216], [19.978064060954694, 68], [8.392764202857506, 12], [640.3178387442385, 216], [790.3493814560632, 331], [252.92170438362655, 129], [614.8476463068318, 238], [627.808314682941, 247], [220.39993420760766, 108], [193.6218059762104, 133], [210.7240928201099, 116], [12.638245050376895, 30], [971.7147704257786, 537], [1224.9113557524795, 557], [1396.6934327257432, 519], [545.8484378750873, 390], [268.77389521451005, 154], [316.808693627062, 374], [34.58781559008804, 30], [381.3599263289361, 187], [330.69725537171325, 190], [92.28872623122788, 38], [404.1107607679585, 167], [147.03132350463136, 127], [646.6012960326739, 290], [1010.4210070449224, 424], [169.0057175142906, 56], [301.64293597110736, 181], [232.7310405989865, 147], [281.57164042936256, 188], [8.980107464518596, 34], [188.95716268028264, 74], [286.9230590012726, 115], [594.8026103240406, 268], [933.1094454033093, 366], [558.2976123186745, 251], [1523.5818797943245, 517], [74.17978031595135, 54], [1227.982608650912, 488], [572.3365833731627, 217], [271.1252649057469, 109], [294.30363004350454, 282], [1289.5986495066104, 503], [880.9671155607598, 320], [54.51813995374232, 18], [108.89675022818301, 72], [349.95130562963004, 168], [82.92556687127308, 41], [510.9112095889477, 239], [51.13368676680989, 42], [537.449777266133, 219], [726.048751288159, 417], [215.77819042716965, 182], [457.8678668352149, 328], [227.88169541492425, 138], [23.733477465249507, 259], [1.3758912856137613, 13], [321.98660283498043, 157], [239.07694918506832, 209], [101.12048554980584, 92], [64.3379030387623, 99], [714.9320275774844, 336], [170.09454781419845, 86], [81.7719018876287, 41], [1150.6683696594278, 405], [457.2869548521535, 259], [53.63913927242845, 22], [781.8956914331172, 336], [247.16774363387228, 65], [240.11898127290078, 73], [206.98447979011644, 108], [339.11281672212624, 166], [227.99410577065646, 237], [18.80387848023838, 35], [634.2688035889889, 483], [153.62501316879752, 110], [41.19331332698812, 48], [290.57100029358844, 371], [1073.5064908644545, 455], [1221.2560647217251, 587], [547.7415541891672, 193], [246.17899904366095, 141], [80.13231487978555, 44], [122.03669708035156, 34], [106.37250228322046, 90], [201.79658993898914, 85], [33.2773941771444, 47], [287.9222995860855, 321], [1191.056480756406, 487], [176.64326529546042, 100], [393.5053451726451, 215], [345.2787900452604, 157], [61.51705862613005, 47], [713.6450095788823, 274], [252.09926145348527, 133], [769.875236759708, 369], [213.65218539863747, 110], [87.94349996077926, 75], [89.22065764744127, 37], [431.965916147505, 916], [968.3922275302217, 370], [338.0444027752119, 167], [349.8518536434799, 204], [439.6304762786094, 211], [910.4807261502426, 465], [15.877503635238071, 27], [1316.7478113457255, 480], [633.5696233716435, 477], [1603.4457278733737, 580], [212.25469581522475, 147], [45.633703025843715, 59], [195.5482742342483, 60], [47.41959006841353, 42], [34.12660039868706, 58], [58.27101371057438, 25], [23.49956337447111, 36], [82.48151800202186, 24], [1.9682826244196576, 75], [468.80844458745537, 219], [261.3770100889924, 91], [319.0921771572538, 206], [707.5808833005203, 273], [250.71644072828803, 109], [412.3973270892675, 191], [40.13725169487452, 28], [361.8281580984185, 148], [260.73276640458846, 305], [329.13679076074595, 141], [177.14469907598652, 55], [238.2925721628883, 154], [568.5221626791008, 203], [61.8224308983643, 82], [41.0130655594985, 42], [686.9583012661988, 299], [941.3841365146818, 524], [104.94240716653894, 84], [479.47557401538256, 291], [419.1600986326739, 313], [153.20883929618003, 50], [33.83922301229052, 24], [469.6955092719745, 236], [19.403995444624343, 32], [339.9681013111367, 163], [187.56873407124795, 78], [65.32576397236699, 38], [110.28098180322013, 77], [19.60231952715003, 33], [86.80186444002078, 119], [454.4132407873867, 204], [189.68078300887692, 98], [332.6145761139942, 106], [347.93591276893676, 184], [371.62187480990633, 314], [712.7394317022699, 366], [230.49957862391602, 152], [205.13913928595684, 143], [269.6872458064936, 157], [119.65501243186691, 133], [230.00021155527793, 103], [577.0674213739348, 263], [454.80292733378815, 179], [168.25053201935953, 88], [75.18119564932385, 52], [244.8110125642579, 132], [51.14538801431104, 47], [332.40407447853386, 157], [218.52390474066215, 143], [480.6715201246536, 228], [755.8784396946376, 300], [305.5268779637672, 123], [250.02143913149962, 132], [145.59313558035865, 98], [950.0749570427338, 497], [310.62739855970176, 151], [45.288360353814824, 30], [451.1432120137388, 194], [213.14043259220398, 148], [671.3985145860922, 284], [1.558288935324498, 17], [147.16808328198928, 293], [480.7649385499449, 247], [670.6446170456093, 242], [376.04213587364325, 160], [336.69130530002394, 191], [388.3103683236822, 177], [520.7801170808705, 251], [162.92955018201974, 81], [557.9307699666379, 160], [29.662372269725893, 30], [374.2981151386198, 167], [475.0212988135954, 264], [939.1101447937252, 347], [798.2276231835194, 352], [1065.0984769844026, 446], [1444.4097410973845, 506], [128.28039482200165, 160], [420.4350773721958, 263], [17.580356758793613, 78], [81.38260257791245, 22], [319.19442646025163, 142], [51.0803815962463, 38], [1043.7201814014934, 426], [1238.8686622201983, 519], [221.2857052682093, 95], [775.8034719475363, 362], [77.83680309175713, 31], [44.82087993620871, 31], [107.30879817035736, 46], [135.04062378503656, 83], [1052.4669232296658, 454], [1528.3865024503411, 493], [52.83066552406808, 50], [275.1131741747049, 120], [702.296667522441, 289], [355.6737687474142, 112], [1015.486984783653, 439], [502.90087708593273, 223], [234.9680186100154, 205], [90.96918323153454, 81], [232.4202991003476, 102], [60.326764624359384, 22], [184.60710923838815, 88], [282.39031830240486, 110], [120.63419710636708, 70], [479.36818516283347, 231], [8.250650695556033, 35], [68.91973024052635, 42], [346.55635571180756, 169], [582.405002777984, 300], [292.5589331571723, 150], [1564.8264064357018, 745], [165.14635271927818, 88], [46.49597615143648, 38], [365.1288601885876, 195], [1293.394873615929, 533], [507.31696992048774, 225], [342.0602672314362, 140], [155.15451404533087, 90], [165.83366464627716, 105], [100.92569294308487, 50], [114.80689430723575, 61], [91.20977330847745, 75], [475.96469693214624, 199], [184.04761856734285, 94], [10.18959660032806, 97], [454.8777314294657, 212], [211.4178332124356, 236], [1080.0322163479996, 447]], "final_state": "tinker://8e9fef4c99e9c1af8d68a14c2c921011/weights/confirm-treatment_dimuon_s2-final", "t": 1793745587.9855993} {"stage": "eval_done", "seconds": 134.40599060058594, "total_seconds": 1187.9279692173004, "t": 1793745587.9860942}