{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9767729182110205,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.2311009168624878,
      "learning_rate": 5.6012058970266934e-05,
      "loss": 1.6789,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 10,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.4872009754180908,
      "learning_rate": 7.287336883921704e-05,
      "loss": 1.3884,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 20,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.7868104577064514,
      "learning_rate": 8.273660282559241e-05,
      "loss": 1.2404,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 30,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.35713163018226624,
      "learning_rate": 8.973467870816715e-05,
      "loss": 1.2036,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 40,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.3057297468185425,
      "learning_rate": 9.516280807158375e-05,
      "loss": 1.1788,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 50,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.3608625531196594,
      "learning_rate": 9.959791269454252e-05,
      "loss": 1.1525,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 60,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.3684042990207672,
      "learning_rate": 9.959204487506375e-05,
      "loss": 1.1261,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 70,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4175470471382141,
      "learning_rate": 9.908210096889343e-05,
      "loss": 1.1214,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 80,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.4869045317173004,
      "learning_rate": 9.85721570627231e-05,
      "loss": 1.1043,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 90,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6399329900741577,
      "learning_rate": 9.806221315655279e-05,
      "loss": 1.1059,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5639649033546448,
      "learning_rate": 9.755226925038246e-05,
      "loss": 1.0711,
      "max_memory_allocated (GB)": 91.91,
      "memory_allocated (GB)": 14.99,
      "step": 110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.44946518540382385,
      "learning_rate": 9.704232534421214e-05,
      "loss": 1.0644,
      "max_memory_allocated (GB)": 91.91,
      "memory_allocated (GB)": 14.99,
      "step": 120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.5573060512542725,
      "learning_rate": 9.653238143804181e-05,
      "loss": 1.0634,
      "max_memory_allocated (GB)": 91.92,
      "memory_allocated (GB)": 14.99,
      "step": 130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6105266213417053,
      "learning_rate": 9.60224375318715e-05,
      "loss": 1.0597,
      "max_memory_allocated (GB)": 91.92,
      "memory_allocated (GB)": 14.99,
      "step": 140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.6286391615867615,
      "learning_rate": 9.551249362570118e-05,
      "loss": 1.0528,
      "max_memory_allocated (GB)": 91.92,
      "memory_allocated (GB)": 14.99,
      "step": 150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8733624815940857,
      "learning_rate": 9.500254971953085e-05,
      "loss": 1.0524,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.6268635392189026,
      "learning_rate": 9.449260581336054e-05,
      "loss": 1.0345,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5832647681236267,
      "learning_rate": 9.398266190719021e-05,
      "loss": 1.0262,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.6518144011497498,
      "learning_rate": 9.347271800101989e-05,
      "loss": 1.0318,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.49274373054504395,
      "learning_rate": 9.296277409484956e-05,
      "loss": 1.0298,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5237769484519958,
      "learning_rate": 9.245283018867925e-05,
      "loss": 1.0176,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.564319372177124,
      "learning_rate": 9.194288628250894e-05,
      "loss": 1.0172,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.4697343111038208,
      "learning_rate": 9.14329423763386e-05,
      "loss": 1.0262,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 230,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5207454562187195,
      "learning_rate": 9.092299847016829e-05,
      "loss": 1.024,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 240,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.4637609124183655,
      "learning_rate": 9.041305456399796e-05,
      "loss": 1.0069,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 250,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.47436627745628357,
      "learning_rate": 8.990311065782764e-05,
      "loss": 1.0119,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 260,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.5096576809883118,
      "learning_rate": 8.939316675165733e-05,
      "loss": 1.0092,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 270,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5780492424964905,
      "learning_rate": 8.8883222845487e-05,
      "loss": 1.0082,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 280,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.4528846740722656,
      "learning_rate": 8.837327893931669e-05,
      "loss": 1.0057,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 290,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5259899497032166,
      "learning_rate": 8.786333503314635e-05,
      "loss": 0.9989,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 300,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5007658004760742,
      "learning_rate": 8.735339112697604e-05,
      "loss": 0.9997,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 310,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4527484178543091,
      "learning_rate": 8.684344722080571e-05,
      "loss": 0.9949,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 320,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.4365575611591339,
      "learning_rate": 8.633350331463539e-05,
      "loss": 0.9943,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 330,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.49428853392601013,
      "learning_rate": 8.582355940846507e-05,
      "loss": 1.0005,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 340,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.4611368775367737,
      "learning_rate": 8.531361550229475e-05,
      "loss": 0.9972,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 350,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.43548157811164856,
      "learning_rate": 8.480367159612444e-05,
      "loss": 0.9833,
      "max_memory_allocated (GB)": 91.93,
      "memory_allocated (GB)": 14.99,
      "step": 360,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.4797479808330536,
      "learning_rate": 8.42937276899541e-05,
      "loss": 0.981,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 370,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.44958415627479553,
      "learning_rate": 8.378378378378379e-05,
      "loss": 0.9969,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 380,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.4499351680278778,
      "learning_rate": 8.327383987761347e-05,
      "loss": 0.9847,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 390,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.45021358132362366,
      "learning_rate": 8.276389597144315e-05,
      "loss": 0.9874,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 400,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.4754478335380554,
      "learning_rate": 8.225395206527282e-05,
      "loss": 0.9955,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 410,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.44393980503082275,
      "learning_rate": 8.17440081591025e-05,
      "loss": 0.9898,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 420,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.43429532647132874,
      "learning_rate": 8.123406425293219e-05,
      "loss": 0.9905,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 430,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.4695710837841034,
      "learning_rate": 8.072412034676186e-05,
      "loss": 0.9702,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 440,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.40997833013534546,
      "learning_rate": 8.021417644059154e-05,
      "loss": 0.9825,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 450,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4330343008041382,
      "learning_rate": 7.970423253442122e-05,
      "loss": 0.9777,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 460,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.42674386501312256,
      "learning_rate": 7.91942886282509e-05,
      "loss": 0.9794,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 470,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.4461188316345215,
      "learning_rate": 7.868434472208057e-05,
      "loss": 0.979,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 480,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4532679617404938,
      "learning_rate": 7.817440081591025e-05,
      "loss": 0.9764,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 490,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.42160096764564514,
      "learning_rate": 7.766445690973994e-05,
      "loss": 0.967,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 500,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.45428088307380676,
      "learning_rate": 7.715451300356961e-05,
      "loss": 0.975,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 510,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.3874836564064026,
      "learning_rate": 7.664456909739929e-05,
      "loss": 0.9707,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 520,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4256057143211365,
      "learning_rate": 7.613462519122897e-05,
      "loss": 0.9775,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 530,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.3986164331436157,
      "learning_rate": 7.562468128505865e-05,
      "loss": 0.972,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 540,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4044497311115265,
      "learning_rate": 7.511473737888832e-05,
      "loss": 0.9725,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 550,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.439773291349411,
      "learning_rate": 7.460479347271801e-05,
      "loss": 0.9667,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 560,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.42315754294395447,
      "learning_rate": 7.409484956654769e-05,
      "loss": 0.9714,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 570,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.38059332966804504,
      "learning_rate": 7.358490566037736e-05,
      "loss": 0.979,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 580,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.4393787086009979,
      "learning_rate": 7.307496175420703e-05,
      "loss": 0.9663,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 590,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.4336337447166443,
      "learning_rate": 7.256501784803672e-05,
      "loss": 0.9661,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 600,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.41273126006126404,
      "learning_rate": 7.20550739418664e-05,
      "loss": 0.9672,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 610,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.45420095324516296,
      "learning_rate": 7.154513003569607e-05,
      "loss": 0.9668,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 620,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.4193101227283478,
      "learning_rate": 7.103518612952576e-05,
      "loss": 0.9684,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 630,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.4247801601886749,
      "learning_rate": 7.052524222335543e-05,
      "loss": 0.9652,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 640,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5118327140808105,
      "learning_rate": 7.001529831718512e-05,
      "loss": 0.9777,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 650,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.42659929394721985,
      "learning_rate": 6.950535441101478e-05,
      "loss": 0.9624,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 660,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.45405977964401245,
      "learning_rate": 6.899541050484447e-05,
      "loss": 0.9585,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 670,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.40387892723083496,
      "learning_rate": 6.848546659867415e-05,
      "loss": 0.9633,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 680,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.39345934987068176,
      "learning_rate": 6.797552269250382e-05,
      "loss": 0.9788,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 690,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.4187304675579071,
      "learning_rate": 6.746557878633351e-05,
      "loss": 0.9651,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 700,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4518466293811798,
      "learning_rate": 6.695563488016318e-05,
      "loss": 0.965,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 710,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.4474211037158966,
      "learning_rate": 6.644569097399287e-05,
      "loss": 0.9714,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 720,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.38997548818588257,
      "learning_rate": 6.593574706782255e-05,
      "loss": 0.9528,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 730,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.42444851994514465,
      "learning_rate": 6.542580316165222e-05,
      "loss": 0.9638,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 740,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.4098523259162903,
      "learning_rate": 6.491585925548191e-05,
      "loss": 0.9534,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 750,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.42875897884368896,
      "learning_rate": 6.440591534931157e-05,
      "loss": 0.9631,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 760,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.4514971077442169,
      "learning_rate": 6.389597144314126e-05,
      "loss": 0.9623,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 770,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.43437400460243225,
      "learning_rate": 6.338602753697093e-05,
      "loss": 0.9657,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 780,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.40089166164398193,
      "learning_rate": 6.287608363080062e-05,
      "loss": 0.9607,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 790,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.3970320224761963,
      "learning_rate": 6.23661397246303e-05,
      "loss": 0.9623,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 800,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5439819693565369,
      "learning_rate": 6.185619581845997e-05,
      "loss": 0.9585,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 810,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.37487202882766724,
      "learning_rate": 6.134625191228966e-05,
      "loss": 0.9509,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 820,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.42697498202323914,
      "learning_rate": 6.0836308006119326e-05,
      "loss": 0.9525,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 830,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.38735342025756836,
      "learning_rate": 6.032636409994901e-05,
      "loss": 0.954,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 840,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.4077759087085724,
      "learning_rate": 5.981642019377869e-05,
      "loss": 0.9528,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 850,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.38065391778945923,
      "learning_rate": 5.930647628760837e-05,
      "loss": 0.9589,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 860,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.3892410695552826,
      "learning_rate": 5.879653238143804e-05,
      "loss": 0.9538,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 870,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.3951966166496277,
      "learning_rate": 5.8286588475267726e-05,
      "loss": 0.9518,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 880,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.5943160057067871,
      "learning_rate": 5.777664456909741e-05,
      "loss": 0.9437,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 890,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.440020889043808,
      "learning_rate": 5.7266700662927075e-05,
      "loss": 0.9635,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 900,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.44286438822746277,
      "learning_rate": 5.6756756756756757e-05,
      "loss": 0.9511,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 910,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4247153699398041,
      "learning_rate": 5.624681285058644e-05,
      "loss": 0.9475,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 920,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.42017248272895813,
      "learning_rate": 5.573686894441612e-05,
      "loss": 0.9436,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 930,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.4182833731174469,
      "learning_rate": 5.5226925038245794e-05,
      "loss": 0.9557,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 940,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.41079315543174744,
      "learning_rate": 5.4716981132075475e-05,
      "loss": 0.9585,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 950,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.3954004943370819,
      "learning_rate": 5.4207037225905157e-05,
      "loss": 0.9478,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 960,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.39996138215065,
      "learning_rate": 5.369709331973484e-05,
      "loss": 0.947,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 970,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.39325571060180664,
      "learning_rate": 5.3187149413564506e-05,
      "loss": 0.9473,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 980,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.43744412064552307,
      "learning_rate": 5.267720550739419e-05,
      "loss": 0.9437,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 990,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.36840781569480896,
      "learning_rate": 5.216726160122387e-05,
      "loss": 0.9441,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1000,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4539542496204376,
      "learning_rate": 5.165731769505354e-05,
      "loss": 0.9518,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1010,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.4364802837371826,
      "learning_rate": 5.1147373788883224e-05,
      "loss": 0.9423,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1020,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.42135128378868103,
      "learning_rate": 5.0637429882712906e-05,
      "loss": 0.9519,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1030,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.3595232367515564,
      "learning_rate": 5.012748597654259e-05,
      "loss": 0.9494,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1040,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.38723716139793396,
      "learning_rate": 4.961754207037226e-05,
      "loss": 0.9459,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1050,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.39567115902900696,
      "learning_rate": 4.910759816420194e-05,
      "loss": 0.9457,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1060,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.3695621192455292,
      "learning_rate": 4.859765425803162e-05,
      "loss": 0.9423,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1070,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.37855803966522217,
      "learning_rate": 4.80877103518613e-05,
      "loss": 0.9484,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1080,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.3890206515789032,
      "learning_rate": 4.7577766445690974e-05,
      "loss": 0.9452,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1090,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.38612017035484314,
      "learning_rate": 4.7067822539520655e-05,
      "loss": 0.9351,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.36654138565063477,
      "learning_rate": 4.655787863335033e-05,
      "loss": 0.9513,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.41428259015083313,
      "learning_rate": 4.604793472718002e-05,
      "loss": 0.9469,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.42189493775367737,
      "learning_rate": 4.553799082100969e-05,
      "loss": 0.9367,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.4327576160430908,
      "learning_rate": 4.5028046914839374e-05,
      "loss": 0.9333,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.4243718981742859,
      "learning_rate": 4.451810300866905e-05,
      "loss": 0.9354,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.3888280391693115,
      "learning_rate": 4.400815910249872e-05,
      "loss": 0.9381,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.36528488993644714,
      "learning_rate": 4.3498215196328404e-05,
      "loss": 0.953,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.410566121339798,
      "learning_rate": 4.2988271290158086e-05,
      "loss": 0.9491,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.39953145384788513,
      "learning_rate": 4.247832738398777e-05,
      "loss": 0.9342,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.37041422724723816,
      "learning_rate": 4.196838347781744e-05,
      "loss": 0.9485,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.41900932788848877,
      "learning_rate": 4.145843957164712e-05,
      "loss": 0.9463,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.39692798256874084,
      "learning_rate": 4.09484956654768e-05,
      "loss": 0.9425,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.4093817472457886,
      "learning_rate": 4.043855175930648e-05,
      "loss": 0.9439,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1230,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.3851373493671417,
      "learning_rate": 3.992860785313616e-05,
      "loss": 0.9478,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1240,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.39068475365638733,
      "learning_rate": 3.9418663946965835e-05,
      "loss": 0.9425,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1250,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.4238007068634033,
      "learning_rate": 3.8908720040795516e-05,
      "loss": 0.9387,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1260,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.3815898299217224,
      "learning_rate": 3.839877613462519e-05,
      "loss": 0.9367,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1270,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.3882830739021301,
      "learning_rate": 3.788883222845487e-05,
      "loss": 0.9529,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1280,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.5217743515968323,
      "learning_rate": 3.737888832228455e-05,
      "loss": 0.9372,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1290,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.381600022315979,
      "learning_rate": 3.6868944416114235e-05,
      "loss": 0.9344,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1300,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.3727063238620758,
      "learning_rate": 3.635900050994391e-05,
      "loss": 0.9505,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1310,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.35615187883377075,
      "learning_rate": 3.5849056603773584e-05,
      "loss": 0.9329,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1320,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.3927929103374481,
      "learning_rate": 3.5339112697603265e-05,
      "loss": 0.9425,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1330,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.42496153712272644,
      "learning_rate": 3.482916879143294e-05,
      "loss": 0.9354,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1340,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.38419976830482483,
      "learning_rate": 3.431922488526262e-05,
      "loss": 0.9402,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1350,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.4346012771129608,
      "learning_rate": 3.38092809790923e-05,
      "loss": 0.9444,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1360,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.4262070655822754,
      "learning_rate": 3.3299337072921984e-05,
      "loss": 0.9456,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1370,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.3871968984603882,
      "learning_rate": 3.278939316675166e-05,
      "loss": 0.946,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1380,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.36344829201698303,
      "learning_rate": 3.227944926058134e-05,
      "loss": 0.9354,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1390,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.38965150713920593,
      "learning_rate": 3.1769505354411015e-05,
      "loss": 0.9268,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1400,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.39498674869537354,
      "learning_rate": 3.1259561448240696e-05,
      "loss": 0.9187,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1410,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.3658037781715393,
      "learning_rate": 3.074961754207038e-05,
      "loss": 0.9335,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1420,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.37881678342819214,
      "learning_rate": 3.0239673635900052e-05,
      "loss": 0.942,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1430,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.37767714262008667,
      "learning_rate": 2.9729729729729733e-05,
      "loss": 0.9308,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1440,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.3596402108669281,
      "learning_rate": 2.9219785823559408e-05,
      "loss": 0.9217,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1450,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.3982533812522888,
      "learning_rate": 2.8709841917389093e-05,
      "loss": 0.9321,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1460,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.37246957421302795,
      "learning_rate": 2.8199898011218767e-05,
      "loss": 0.9333,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1470,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.3782934844493866,
      "learning_rate": 2.7689954105048445e-05,
      "loss": 0.9413,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1480,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.3564135432243347,
      "learning_rate": 2.7180010198878126e-05,
      "loss": 0.9224,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1490,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.3907375633716583,
      "learning_rate": 2.66700662927078e-05,
      "loss": 0.9316,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1500,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.37077468633651733,
      "learning_rate": 2.6160122386537482e-05,
      "loss": 0.9439,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1510,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.3694670498371124,
      "learning_rate": 2.565017848036716e-05,
      "loss": 0.9366,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1520,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.4076436758041382,
      "learning_rate": 2.5140234574196842e-05,
      "loss": 0.934,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1530,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.37471699714660645,
      "learning_rate": 2.4630290668026516e-05,
      "loss": 0.9269,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1540,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.3876965641975403,
      "learning_rate": 2.4120346761856198e-05,
      "loss": 0.9302,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1550,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.3646378815174103,
      "learning_rate": 2.3610402855685876e-05,
      "loss": 0.9487,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1560,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.35151660442352295,
      "learning_rate": 2.3100458949515554e-05,
      "loss": 0.9327,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1570,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.3730565011501312,
      "learning_rate": 2.2590515043345235e-05,
      "loss": 0.9375,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1580,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.39022204279899597,
      "learning_rate": 2.2080571137174913e-05,
      "loss": 0.9241,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1590,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.37705516815185547,
      "learning_rate": 2.157062723100459e-05,
      "loss": 0.9347,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1600,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.37316569685935974,
      "learning_rate": 2.106068332483427e-05,
      "loss": 0.9288,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1610,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.38276973366737366,
      "learning_rate": 2.0550739418663947e-05,
      "loss": 0.9456,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1620,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.3851768672466278,
      "learning_rate": 2.0040795512493625e-05,
      "loss": 0.9322,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1630,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.39158496260643005,
      "learning_rate": 1.9530851606323306e-05,
      "loss": 0.9243,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1640,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.36135101318359375,
      "learning_rate": 1.9020907700152984e-05,
      "loss": 0.9304,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1650,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.35885167121887207,
      "learning_rate": 1.8510963793982662e-05,
      "loss": 0.9366,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1660,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.3604848086833954,
      "learning_rate": 1.8001019887812343e-05,
      "loss": 0.9352,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1670,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.3818376362323761,
      "learning_rate": 1.7491075981642018e-05,
      "loss": 0.9249,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1680,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.37588033080101013,
      "learning_rate": 1.69811320754717e-05,
      "loss": 0.9435,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1690,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.39090296626091003,
      "learning_rate": 1.6471188169301377e-05,
      "loss": 0.9369,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1700,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.36099740862846375,
      "learning_rate": 1.5961244263131055e-05,
      "loss": 0.9336,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1710,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.38522326946258545,
      "learning_rate": 1.5451300356960737e-05,
      "loss": 0.9345,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1720,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.3819480836391449,
      "learning_rate": 1.4941356450790415e-05,
      "loss": 0.9378,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1730,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.3639472424983978,
      "learning_rate": 1.4431412544620093e-05,
      "loss": 0.9199,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1740,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.37957242131233215,
      "learning_rate": 1.3921468638449772e-05,
      "loss": 0.9309,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1750,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.3529975712299347,
      "learning_rate": 1.3411524732279452e-05,
      "loss": 0.9365,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1760,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.36888596415519714,
      "learning_rate": 1.2901580826109128e-05,
      "loss": 0.929,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1770,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.3920755684375763,
      "learning_rate": 1.2391636919938808e-05,
      "loss": 0.9368,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1780,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.3655153810977936,
      "learning_rate": 1.1881693013768486e-05,
      "loss": 0.9224,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1790,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.3592711389064789,
      "learning_rate": 1.1371749107598164e-05,
      "loss": 0.9243,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1800,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.3836236596107483,
      "learning_rate": 1.0861805201427844e-05,
      "loss": 0.9338,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1810,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.3464523255825043,
      "learning_rate": 1.0351861295257523e-05,
      "loss": 0.9263,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1820,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.3582245409488678,
      "learning_rate": 9.841917389087201e-06,
      "loss": 0.9381,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1830,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.3634730279445648,
      "learning_rate": 9.33197348291688e-06,
      "loss": 0.9334,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1840,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.35473546385765076,
      "learning_rate": 8.822029576746559e-06,
      "loss": 0.9309,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1850,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.34900808334350586,
      "learning_rate": 8.312085670576237e-06,
      "loss": 0.9332,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1860,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.34784045815467834,
      "learning_rate": 7.802141764405915e-06,
      "loss": 0.9256,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1870,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.3699551224708557,
      "learning_rate": 7.2921978582355945e-06,
      "loss": 0.9193,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1880,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.3443852961063385,
      "learning_rate": 6.782253952065273e-06,
      "loss": 0.9336,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1890,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.34538397192955017,
      "learning_rate": 6.272310045894952e-06,
      "loss": 0.9324,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1900,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.3482609987258911,
      "learning_rate": 5.762366139724631e-06,
      "loss": 0.9366,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1910,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.36807572841644287,
      "learning_rate": 5.252422233554309e-06,
      "loss": 0.9354,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1920,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.34861066937446594,
      "learning_rate": 4.742478327383989e-06,
      "loss": 0.9329,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1930,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.35355910658836365,
      "learning_rate": 4.2325344212136666e-06,
      "loss": 0.9296,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1940,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.3384307324886322,
      "learning_rate": 3.7225905150433454e-06,
      "loss": 0.9317,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1950,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.33987560868263245,
      "learning_rate": 3.2126466088730238e-06,
      "loss": 0.9382,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1960,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.3600024878978729,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.9278,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1970,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.362325519323349,
      "learning_rate": 2.192758796532382e-06,
      "loss": 0.9207,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1980,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.33737602829933167,
      "learning_rate": 1.6828148903620604e-06,
      "loss": 0.9348,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 1990,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.37504151463508606,
      "learning_rate": 1.1728709841917388e-06,
      "loss": 0.9265,
      "max_memory_allocated (GB)": 91.98,
      "memory_allocated (GB)": 14.99,
      "step": 2000,
      "total_memory_available (GB)": 94.62
    }
  ],
  "logging_steps": 10,
  "max_steps": 2022,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.238964389820498e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}