{"timestamp": 1774091071.9870658, "event": "train_step", "step": 10, "epoch": 1, "metrics": {"train/step_loss": 1.5507386380975896, "train/step_real_loss": 1.2866992354393005, "train/lr": 4.761904761904762e-05, "train/step_canary_loss": 10.0, "perf/step_duration_sec": 8.244300998747349, "perf/samples_per_sec": 8.00553012438873, "perf/tokens_per_sec": 6440.812872803661, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 53100.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.16860580444336}} {"timestamp": 1774091154.380765, "event": "train_step", "step": 20, "epoch": 1, "metrics": {"train/step_loss": 1.4504926845208923, "train/step_real_loss": 1.2006134390830994, "train/lr": 9.523809523809524e-05, "train/step_canary_loss": 6.78125, "perf/step_duration_sec": 8.244972918182611, "perf/samples_per_sec": 8.126163744242886, "perf/tokens_per_sec": 6422.095078472549, "perf/logical_batch_size": 67.0, "perf/logical_token_count": 52950.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.911073684692383, "system/cuda_max_memory_allocated_gb": 82.16860580444336}} {"timestamp": 1774091235.6533117, "event": "train_step", "step": 30, "epoch": 1, "metrics": {"train/step_loss": 0.9861254319548607, "train/step_real_loss": 0.9861254319548607, "train/lr": 9.98706541985615e-05, "perf/step_duration_sec": 7.973596462979913, "perf/samples_per_sec": 8.026490968929942, "perf/tokens_per_sec": 7148.9697609673985, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 57003.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.16860580444336}} {"timestamp": 1774091318.662035, "event": "train_step", "step": 40, "epoch": 1, "metrics": {"train/step_loss": 1.0557814985513687, "train/step_real_loss": 1.0557814985513687, "train/lr": 9.942439201095397e-05, "perf/step_duration_sec": 8.119743634015322, "perf/samples_per_sec": 7.882022251526572, "perf/tokens_per_sec": 6340.347961767047, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 51482.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091402.0365882, "event": "train_step", "step": 50, "epoch": 1, "metrics": {"train/step_loss": 1.017115435233483, "train/step_real_loss": 0.9500000476837158, "train/lr": 9.866246608261724e-05, "train/step_canary_loss": 5.3125, "perf/step_duration_sec": 8.119036318734288, "perf/samples_per_sec": 8.005876245437603, "perf/tokens_per_sec": 6307.645142790008, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 51212.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091429.1958544, "event": "eval_step", "step": 50, "epoch": 1, "metrics": {"eval/loss": 0.8033588177513802, "eval/duration_sec": 27.156014366075397}} {"timestamp": 1774091511.9092546, "event": "train_step", "step": 60, "epoch": 1, "metrics": {"train/step_loss": 1.2237938749256418, "train/step_real_loss": 0.9667061120271683, "train/lr": 9.7589742682592e-05, "train/step_canary_loss": 6.708333333333333, "perf/step_duration_sec": 8.495171755552292, "perf/samples_per_sec": 7.886832889071372, "perf/tokens_per_sec": 6228.008276044599, "perf/logical_batch_size": 67.0, "perf/logical_token_count": 52908.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091593.5344725, "event": "train_step", "step": 70, "epoch": 1, "metrics": {"train/step_loss": 1.0743033794256358, "train/step_real_loss": 0.9387456253170967, "train/lr": 9.621307308142384e-05, "train/step_canary_loss": 9.75, "perf/step_duration_sec": 8.257235972210765, "perf/samples_per_sec": 7.8718835478062665, "perf/tokens_per_sec": 6568.057420488078, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 54234.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091676.5485113, "event": "train_step", "step": 80, "epoch": 1, "metrics": {"train/step_loss": 0.8626528829336166, "train/step_real_loss": 0.8626528829336166, "train/lr": 9.454124979346391e-05, "perf/step_duration_sec": 8.386640733107924, "perf/samples_per_sec": 7.631184169765056, "perf/tokens_per_sec": 6658.446662625317, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 55842.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091757.879373, "event": "train_step", "step": 90, "epoch": 1, "metrics": {"train/step_loss": 0.9340124875307083, "train/step_real_loss": 0.9340124875307083, "train/lr": 9.258495042083221e-05, "perf/step_duration_sec": 8.493970146402717, "perf/samples_per_sec": 7.534756880103312, "perf/tokens_per_sec": 5785.162786428072, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 49139.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091839.6918592, "event": "train_step", "step": 100, "epoch": 1, "metrics": {"train/step_loss": 0.9577739440477812, "train/step_real_loss": 0.880453996360302, "train/lr": 9.035666945770107e-05, "train/step_canary_loss": 5.90625, "perf/step_duration_sec": 8.234961070120335, "perf/samples_per_sec": 7.893176354633353, "perf/tokens_per_sec": 6771.616711381143, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 55764.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774091866.8768253, "event": "eval_step", "step": 100, "epoch": 1, "metrics": {"eval/loss": 0.7754902612717671, "eval/duration_sec": 27.182465851306915}} {"timestamp": 1774091950.1670244, "event": "train_step", "step": 110, "epoch": 1, "metrics": {"train/step_loss": 0.9567192720644402, "train/step_real_loss": 0.860762245953083, "train/lr": 8.787063849045118e-05, "train/step_canary_loss": 4.02734375, "perf/step_duration_sec": 8.036363879218698, "perf/samples_per_sec": 8.21266943507498, "perf/tokens_per_sec": 6478.054102878841, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 52060.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092031.8751383, "event": "train_step", "step": 120, "epoch": 1, "metrics": {"train/step_loss": 0.9170611575245857, "train/step_real_loss": 0.9170611575245857, "train/lr": 8.5142735303366e-05, "perf/step_duration_sec": 7.79720464348793, "perf/samples_per_sec": 8.208069805305357, "perf/tokens_per_sec": 6600.4423832818775, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 51465.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092114.4179726, "event": "train_step", "step": 130, "epoch": 1, "metrics": {"train/step_loss": 0.9158061426697355, "train/step_real_loss": 0.8711828961968422, "train/lr": 8.219038247038819e-05, "train/step_canary_loss": 2.34375, "perf/step_duration_sec": 8.22744246572256, "perf/samples_per_sec": 8.021933945447975, "perf/tokens_per_sec": 6342.311139506375, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 52181.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092196.3902268, "event": "train_step", "step": 140, "epoch": 1, "metrics": {"train/step_loss": 0.9856266433542425, "train/step_real_loss": 0.8489470109343529, "train/lr": 7.903243608061246e-05, "train/step_canary_loss": 5.359375, "perf/step_duration_sec": 8.333684524521232, "perf/samples_per_sec": 7.9196662419605675, "perf/tokens_per_sec": 6461.007714123103, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 53844.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092278.982639, "event": "train_step", "step": 150, "epoch": 1, "metrics": {"train/step_loss": 0.94221530854702, "train/step_real_loss": 0.94221530854702, "train/lr": 7.568906530820282e-05, "perf/step_duration_sec": 8.388992108404636, "perf/samples_per_sec": 7.629045202686584, "perf/tokens_per_sec": 6081.421861022835, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 51017.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092306.1516783, "event": "eval_step", "step": 150, "epoch": 1, "metrics": {"eval/loss": 0.7622188641422096, "eval/duration_sec": 27.166858203709126}} {"timestamp": 1774092388.1349308, "event": "train_step", "step": 160, "epoch": 1, "metrics": {"train/step_loss": 0.9667639210820198, "train/step_real_loss": 0.9667639210820198, "train/lr": 7.21816235958972e-05, "perf/step_duration_sec": 8.235355000942945, "perf/samples_per_sec": 7.771371117902267, "perf/tokens_per_sec": 6008.24129552819, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 49480.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092469.9282126, "event": "train_step", "step": 170, "epoch": 1, "metrics": {"train/step_loss": 0.9262635037302971, "train/step_real_loss": 0.9262635037302971, "train/lr": 6.853251227482479e-05, "perf/step_duration_sec": 7.9527543764561415, "perf/samples_per_sec": 8.047526299752175, "perf/tokens_per_sec": 6280.842791759705, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 49950.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092551.943189, "event": "train_step", "step": 180, "epoch": 1, "metrics": {"train/step_loss": 0.8705217910535408, "train/step_real_loss": 0.8467002063989639, "train/lr": 6.476503749166904e-05, "train/step_canary_loss": 1.6328125, "perf/step_duration_sec": 8.540382800623775, "perf/samples_per_sec": 7.7279908337574135, "perf/tokens_per_sec": 6385.076790236751, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 54531.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092634.1860914, "event": "train_step", "step": 190, "epoch": 1, "metrics": {"train/step_loss": 0.8329041105050307, "train/step_real_loss": 0.830781526863575, "train/lr": 6.090326135695403e-05, "train/step_canary_loss": 0.96875, "perf/step_duration_sec": 7.938739079982042, "perf/samples_per_sec": 8.18769824088324, "perf/tokens_per_sec": 6963.07051322375, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 55278.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092717.69117, "event": "train_step", "step": 200, "epoch": 1, "metrics": {"train/step_loss": 0.9225348509274997, "train/step_real_loss": 0.8622424304485321, "train/lr": 5.697184826514057e-05, "train/step_canary_loss": 4.78125, "perf/step_duration_sec": 8.257816776633263, "perf/samples_per_sec": 7.871329887571168, "perf/tokens_per_sec": 6772.4922352662325, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 55926.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774092744.8800561, "event": "eval_step", "step": 200, "epoch": 1, "metrics": {"eval/loss": 0.7524948388166811, "eval/duration_sec": 27.18629032932222}} {"timestamp": 1774092830.2611096, "event": "train_epoch", "step": 207, "epoch": 1, "metrics": {"train/epoch_loss": 1.036294524908722, "train/epoch_real_loss": 0.957591299003593, "train/epoch_canary_loss": 5.154934052784185, "perf/epoch_duration_sec": 1814.8832574244589, "perf/epoch_samples_per_sec": 29.762244915220545, "perf/epoch_tokens_per_sec": 24175.732417227537, "perf/epoch_samples": 54015.0, "perf/epoch_tokens": 43876132.0, "system/cuda_epoch_peak_memory_gb": 88.38552379608154, "eval/loss": 0.7516984458284817, "eval/duration_sec": 27.281295781955123}} {"timestamp": 1774092840.935869, "event": "audit_epoch", "step": 207, "epoch": 1, "metrics": {"audit/delta": 1e-05, "audit/num_canaries": 500.0, "audit/num_members": 250.0, "audit/paper_guess_fraction": 0.2, "audit/paper_guess_steps": 20.0, "audit/loss/auc": 0.998072, "audit/loss/empirical_epsilon/0.05": 3.4791953936219215, "audit/loss/empirical_epsilon/0.01": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/loss/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/correct_guesses": 100.0, "audit/embedding/auc": 0.96, "audit/embedding/empirical_epsilon/0.05": 3.4791953936219215, "audit/embedding/empirical_epsilon/0.01": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/embedding/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/correct_guesses": 100.0, "perf/audit_duration_sec": 6.3129072319716215}} {"timestamp": 1774092866.0795767, "event": "train_step", "step": 210, "epoch": 2, "metrics": {"train/step_loss": 0.8786039505944108, "train/step_real_loss": 0.8291560411453247, "train/lr": 5.29959073680547e-05, "train/step_canary_loss": 2.4609375, "perf/step_duration_sec": 8.105620637536049, "perf/samples_per_sec": 8.142498020985931, "perf/tokens_per_sec": 6755.805933775599, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 54760.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.911073684692383, "system/cuda_max_memory_allocated_gb": 75.98184061050415}} {"timestamp": 1774092947.7881637, "event": "train_step", "step": 220, "epoch": 2, "metrics": {"train/step_loss": 0.8338463682394761, "train/step_real_loss": 0.8286867365241051, "train/lr": 4.9000832207739676e-05, "train/step_canary_loss": 1.1640625, "perf/step_duration_sec": 8.100939376279712, "perf/samples_per_sec": 8.023760823383757, "perf/tokens_per_sec": 6522.083124668936, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 52835.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093029.3670137, "event": "train_step", "step": 230, "epoch": 2, "metrics": {"train/step_loss": 0.7926744809517494, "train/step_real_loss": 0.8034120723605156, "train/lr": 4.501213853296425e-05, "train/step_canary_loss": 0.10546875, "perf/step_duration_sec": 8.09845926053822, "perf/samples_per_sec": 8.026218063073905, "perf/tokens_per_sec": 6708.683497950849, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 54330.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093111.4853563, "event": "train_step", "step": 240, "epoch": 2, "metrics": {"train/step_loss": 0.8129148510369387, "train/step_real_loss": 0.7906041964888573, "train/lr": 4.1055301335220955e-05, "train/step_canary_loss": 1.52685546875, "perf/step_duration_sec": 8.505769751966, "perf/samples_per_sec": 7.75943881913156, "perf/tokens_per_sec": 6383.901937558238, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 54300.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093192.88336, "event": "train_step", "step": 250, "epoch": 2, "metrics": {"train/step_loss": 0.8410789425556476, "train/step_real_loss": 0.850802831351757, "train/lr": 3.715559214503298e-05, "train/step_canary_loss": 0.21875, "perf/step_duration_sec": 8.232771871611476, "perf/samples_per_sec": 7.895275250385015, "perf/tokens_per_sec": 6654.745309889904, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 54787.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093220.0732572, "event": "eval_step", "step": 250, "epoch": 2, "metrics": {"eval/loss": 0.748522541389383, "eval/duration_sec": 27.187080297619104}} {"timestamp": 1774093302.2765276, "event": "train_step", "step": 260, "epoch": 2, "metrics": {"train/step_loss": 0.8724462010643699, "train/step_real_loss": 0.8488068357110023, "train/lr": 3.33379176277258e-05, "train/step_canary_loss": 1.62890625, "perf/step_duration_sec": 8.470736568793654, "perf/samples_per_sec": 7.7915302245551095, "perf/tokens_per_sec": 6277.49423773815, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 53175.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.911073684692383, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093384.391679, "event": "train_step", "step": 270, "epoch": 2, "metrics": {"train/step_loss": 0.8640658855438232, "train/step_real_loss": 0.7926059737801552, "train/lr": 2.962666050951997e-05, "train/step_canary_loss": 5.4375, "perf/step_duration_sec": 7.947357261553407, "perf/samples_per_sec": 8.178819431516908, "perf/tokens_per_sec": 6407.161314659091, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 50920.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093468.0585487, "event": "train_step", "step": 280, "epoch": 2, "metrics": {"train/step_loss": 0.7910019425245431, "train/step_real_loss": 0.8018507286906242, "train/lr": 2.604552384991855e-05, "train/step_canary_loss": 0.0966796875, "perf/step_duration_sec": 8.62639987282455, "perf/samples_per_sec": 7.53500892124967, "perf/tokens_per_sec": 6275.039506402552, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 54131.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093550.7132335, "event": "train_step", "step": 290, "epoch": 2, "metrics": {"train/step_loss": 0.8430270507480159, "train/step_real_loss": 0.8613760396838188, "train/lr": 2.2617379654990623e-05, "train/step_canary_loss": 0.255859375, "perf/step_duration_sec": 8.335046991705894, "perf/samples_per_sec": 7.9183716739300705, "perf/tokens_per_sec": 6261.392413496007, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 52189.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093632.5524132, "event": "train_step", "step": 300, "epoch": 2, "metrics": {"train/step_loss": 0.7691241015087474, "train/step_real_loss": 0.784599058330059, "train/lr": 1.936412279842705e-05, "train/step_canary_loss": 0.27392578125, "perf/step_duration_sec": 8.091827008873224, "perf/samples_per_sec": 8.156378025336753, "perf/tokens_per_sec": 5984.062677922065, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 48422.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.911073684692383, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093659.719083, "event": "eval_step", "step": 300, "epoch": 2, "metrics": {"eval/loss": 0.7462242173737493, "eval/duration_sec": 27.16416385397315}} {"timestamp": 1774093742.5612013, "event": "train_step", "step": 310, "epoch": 2, "metrics": {"train/step_loss": 0.7514625552928809, "train/step_real_loss": 0.7710395082831383, "train/lr": 1.6306531183346385e-05, "train/step_canary_loss": 0.125, "perf/step_duration_sec": 8.240195842459798, "perf/samples_per_sec": 8.009518373327666, "perf/tokens_per_sec": 6369.751520897312, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 52488.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093824.76255, "event": "train_step", "step": 320, "epoch": 2, "metrics": {"train/step_loss": 0.8317307600608239, "train/step_real_loss": 0.8416290208697319, "train/lr": 1.3464133037968912e-05, "train/step_canary_loss": 0.1982421875, "perf/step_duration_sec": 7.953533122316003, "perf/samples_per_sec": 8.172468637569782, "perf/tokens_per_sec": 6226.666720107783, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 49524.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093907.919859, "event": "train_step", "step": 330, "epoch": 2, "metrics": {"train/step_loss": 0.8719267258277306, "train/step_real_loss": 0.8635779246687889, "train/lr": 1.0855082192715294e-05, "train/step_canary_loss": 1.40625, "perf/step_duration_sec": 8.101611092686653, "perf/samples_per_sec": 8.023095561656334, "perf/tokens_per_sec": 5623.572827524039, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 45560.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774093989.7239172, "event": "train_step", "step": 340, "epoch": 2, "metrics": {"train/step_loss": 0.8476224361043988, "train/step_real_loss": 0.8228105828166008, "train/lr": 8.49604213531004e-06, "train/step_canary_loss": 1.6416015625, "perf/step_duration_sec": 8.274557610973716, "perf/samples_per_sec": 7.976257233676254, "perf/tokens_per_sec": 6674.435371234426, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 55228.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094071.9116077, "event": "train_step", "step": 350, "epoch": 2, "metrics": {"train/step_loss": 0.8573094416355741, "train/step_real_loss": 0.816773310303688, "train/lr": 6.402079584406673e-06, "train/step_canary_loss": 1.376171875, "perf/step_duration_sec": 8.637357847765088, "perf/samples_per_sec": 7.988554048140279, "perf/tokens_per_sec": 6212.547974249382, "perf/logical_batch_size": 69.0, "perf/logical_token_count": 53660.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094099.091823, "event": "eval_step", "step": 350, "epoch": 2, "metrics": {"eval/loss": 0.7456388631942629, "eval/duration_sec": 27.17722495831549}} {"timestamp": 1774094181.5654633, "event": "train_step", "step": 360, "epoch": 2, "metrics": {"train/step_loss": 0.8446246770712046, "train/step_real_loss": 0.8453097268939018, "train/lr": 4.586568261458729e-06, "train/step_canary_loss": 0.80078125, "perf/step_duration_sec": 7.976690696552396, "perf/samples_per_sec": 8.148742689508275, "perf/tokens_per_sec": 6948.119478163339, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 55423.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094263.5117958, "event": "train_step", "step": 370, "epoch": 2, "metrics": {"train/step_loss": 0.8721330687403679, "train/step_real_loss": 0.8721330687403679, "train/lr": 3.06110347542643e-06, "perf/step_duration_sec": 8.37641635723412, "perf/samples_per_sec": 7.640498904370688, "perf/tokens_per_sec": 5830.058812420977, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 48835.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094346.1630964, "event": "train_step", "step": 380, "epoch": 2, "metrics": {"train/step_loss": 0.81929341004445, "train/step_real_loss": 0.8280055150389671, "train/lr": 1.8354280658494649e-06, "train/step_canary_loss": 0.26171875, "perf/step_duration_sec": 7.9715049508959055, "perf/samples_per_sec": 8.154043734576712, "perf/tokens_per_sec": 6787.676898315027, "perf/logical_batch_size": 65.0, "perf/logical_token_count": 54108.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094429.2324018, "event": "train_step", "step": 390, "epoch": 2, "metrics": {"train/step_loss": 0.8554338663816452, "train/step_real_loss": 0.8554338663816452, "train/lr": 9.17370177272775e-07, "perf/step_duration_sec": 8.24701151996851, "perf/samples_per_sec": 7.760386880148844, "perf/tokens_per_sec": 6142.34621563781, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 50656.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094512.2904398, "event": "train_step", "step": 400, "epoch": 2, "metrics": {"train/step_loss": 0.7998756021261215, "train/step_real_loss": 0.7998756021261215, "train/lr": 3.127932624475638e-07, "perf/step_duration_sec": 7.943094424903393, "perf/samples_per_sec": 8.0573132555677, "perf/tokens_per_sec": 6869.86671452841, "perf/logical_batch_size": 64.0, "perf/logical_token_count": 54568.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 82.1704511642456}} {"timestamp": 1774094539.4831598, "event": "eval_step", "step": 400, "epoch": 2, "metrics": {"eval/loss": 0.7455017728538349, "eval/duration_sec": 27.190383709967136}} {"timestamp": 1774094621.4459202, "event": "train_step", "step": 410, "epoch": 2, "metrics": {"train/step_loss": 0.854436350591255, "train/step_real_loss": 0.8517185375094414, "train/lr": 2.5558633627303928e-08, "train/step_canary_loss": 0.94140625, "perf/step_duration_sec": 8.378037076443434, "perf/samples_per_sec": 7.877740262760654, "perf/tokens_per_sec": 6647.619184760483, "perf/logical_batch_size": 66.0, "perf/logical_token_count": 55694.0, "perf/gradient_accumulation_steps": 8.0, "system/cuda_memory_allocated_gb": 17.816345691680908, "system/cuda_max_memory_allocated_gb": 88.38552379608154}} {"timestamp": 1774094682.1799755, "event": "train_epoch", "step": 414, "epoch": 2, "metrics": {"train/epoch_loss": 0.840315752633972, "train/epoch_real_loss": 0.8362452851041504, "train/epoch_canary_loss": 1.0832555509625612, "perf/epoch_duration_sec": 1814.1021996028721, "perf/epoch_samples_per_sec": 29.765136722628178, "perf/epoch_tokens_per_sec": 24186.19579955584, "perf/epoch_samples": 53997.0, "perf/epoch_tokens": 43876231.0, "system/cuda_epoch_peak_memory_gb": 88.38552379608154, "eval/loss": 0.7454980848164394, "eval/duration_sec": 27.13153049722314}} {"timestamp": 1774094693.161264, "event": "audit_epoch", "step": 414, "epoch": 2, "metrics": {"audit/delta": 1e-05, "audit/num_canaries": 500.0, "audit/num_members": 250.0, "audit/paper_guess_fraction": 0.2, "audit/paper_guess_steps": 20.0, "audit/loss/auc": 1.0, "audit/loss/empirical_epsilon/0.05": 3.4791953936219215, "audit/loss/empirical_epsilon/0.01": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/loss/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/correct_guesses": 100.0, "audit/embedding/auc": 0.916224, "audit/embedding/empirical_epsilon/0.05": 3.4791953936219215, "audit/embedding/empirical_epsilon/0.01": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/embedding/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/correct_guesses": 100.0, "perf/audit_duration_sec": 6.722778998315334}} {"timestamp": 1774094704.3854914, "event": "audit_final", "step": 414, "epoch": 2, "metrics": {"audit/delta": 1e-05, "audit/num_canaries": 500.0, "audit/num_members": 250.0, "audit/paper_guess_fraction": 0.2, "audit/paper_guess_steps": 20.0, "audit/loss/auc": 1.0, "audit/loss/empirical_epsilon/0.05": 3.4791953936219215, "audit/loss/empirical_epsilon/0.01": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/loss/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/loss/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/loss/empirical_epsilon_details/0.01/correct_guesses": 100.0, "audit/embedding/auc": 0.916224, "audit/embedding/empirical_epsilon/0.05": 3.4791953936219215, "audit/embedding/empirical_epsilon/0.01": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.05/epsilon": 3.4791953936219215, "audit/embedding/empirical_epsilon_details/0.05/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.05/correct_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/epsilon": 3.023197554051876, "audit/embedding/empirical_epsilon_details/0.01/num_guesses": 100.0, "audit/embedding/empirical_epsilon_details/0.01/correct_guesses": 100.0}} {"timestamp": 1774094704.914049, "event": "energy_final", "step": 414, "epoch": null, "metrics": {"energy/codecarbon/duration": 3820.65162669681, "energy/codecarbon/emissions": 0.5568149811716148, "energy/codecarbon/emissions_rate": 0.0001457382236267942, "energy/codecarbon/cpu_power": 179.3439937196561, "energy/codecarbon/gpu_power": 2316.658494927477, "energy/codecarbon/ram_power": 70.0, "energy/codecarbon/cpu_energy": 0.18368298514637418, "energy/codecarbon/gpu_energy": 2.457235179675422, "energy/codecarbon/ram_energy": 0.07169108754482326, "energy/codecarbon/energy_consumed": 2.7126092523666183, "energy/codecarbon/water_consumed": 0.0, "energy/codecarbon/cpu_count": 224.0, "energy/codecarbon/gpu_count": 4.0, "energy/codecarbon/longitude": -121.9552, "energy/codecarbon/latitude": 37.3541, "energy/codecarbon/ram_total_size": 2015.5625190734863, "energy/codecarbon/cpu_utilization_percent": 2.2497114375655825, "energy/codecarbon/gpu_utilization_percent": 96.45330535152151, "energy/codecarbon/ram_utilization_percent": 2.3057974816369358, "energy/codecarbon/ram_used_gb": 46.78091819539025, "energy/codecarbon/pue": 1.0, "energy/codecarbon/wue": 0.0}}