{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4825796886582654,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.339092493057251,
      "learning_rate": 5.6012058970266934e-05,
      "loss": 1.6822,
      "max_memory_allocated (GB)": 91.88,
      "memory_allocated (GB)": 14.99,
      "step": 10,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.4976561069488525,
      "learning_rate": 7.287336883921704e-05,
      "loss": 1.3895,
      "max_memory_allocated (GB)": 91.9,
      "memory_allocated (GB)": 14.99,
      "step": 20,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5813677310943604,
      "learning_rate": 8.273660282559241e-05,
      "loss": 1.2399,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 30,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.3463669717311859,
      "learning_rate": 8.973467870816715e-05,
      "loss": 1.2044,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 40,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.3429594039916992,
      "learning_rate": 9.516280807158375e-05,
      "loss": 1.1798,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 50,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.3272635042667389,
      "learning_rate": 9.959791269454252e-05,
      "loss": 1.153,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 60,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.37938210368156433,
      "learning_rate": 9.959204487506375e-05,
      "loss": 1.1266,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 70,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4513859152793884,
      "learning_rate": 9.908210096889343e-05,
      "loss": 1.1218,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 80,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5865214467048645,
      "learning_rate": 9.85721570627231e-05,
      "loss": 1.1048,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 90,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6466606855392456,
      "learning_rate": 9.806221315655279e-05,
      "loss": 1.1064,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5907604098320007,
      "learning_rate": 9.755226925038246e-05,
      "loss": 1.0716,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7884001135826111,
      "learning_rate": 9.704232534421214e-05,
      "loss": 1.0656,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.7752586007118225,
      "learning_rate": 9.653238143804181e-05,
      "loss": 1.065,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.5188919901847839,
      "learning_rate": 9.60224375318715e-05,
      "loss": 1.0606,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5289068818092346,
      "learning_rate": 9.551249362570118e-05,
      "loss": 1.0537,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.0006146430969238,
      "learning_rate": 9.500254971953085e-05,
      "loss": 1.0528,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5318694710731506,
      "learning_rate": 9.449260581336054e-05,
      "loss": 1.0357,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5409672260284424,
      "learning_rate": 9.398266190719021e-05,
      "loss": 1.0264,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.5338054299354553,
      "learning_rate": 9.347271800101989e-05,
      "loss": 1.0319,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5304291844367981,
      "learning_rate": 9.296277409484956e-05,
      "loss": 1.0301,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5799819231033325,
      "learning_rate": 9.245283018867925e-05,
      "loss": 1.0179,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.4919432997703552,
      "learning_rate": 9.194288628250894e-05,
      "loss": 1.0174,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.5090098977088928,
      "learning_rate": 9.14329423763386e-05,
      "loss": 1.0261,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 230,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5532674193382263,
      "learning_rate": 9.092299847016829e-05,
      "loss": 1.0239,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 240,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5546780824661255,
      "learning_rate": 9.041305456399796e-05,
      "loss": 1.0072,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 250,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.5483475923538208,
      "learning_rate": 8.990311065782764e-05,
      "loss": 1.0121,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 260,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.4962722063064575,
      "learning_rate": 8.939316675165733e-05,
      "loss": 1.0097,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 270,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5032678842544556,
      "learning_rate": 8.8883222845487e-05,
      "loss": 1.0085,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 280,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.48048779368400574,
      "learning_rate": 8.837327893931669e-05,
      "loss": 1.006,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 290,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.493956595659256,
      "learning_rate": 8.786333503314635e-05,
      "loss": 0.9991,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 300,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.4832962155342102,
      "learning_rate": 8.735339112697604e-05,
      "loss": 0.9994,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 310,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.44359833002090454,
      "learning_rate": 8.684344722080571e-05,
      "loss": 0.9949,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 320,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.432824045419693,
      "learning_rate": 8.633350331463539e-05,
      "loss": 0.9945,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 330,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.5194958448410034,
      "learning_rate": 8.582355940846507e-05,
      "loss": 1.0005,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 340,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.4381203353404999,
      "learning_rate": 8.531361550229475e-05,
      "loss": 0.9971,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 350,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.4479101300239563,
      "learning_rate": 8.480367159612444e-05,
      "loss": 0.9834,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 360,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.44543156027793884,
      "learning_rate": 8.42937276899541e-05,
      "loss": 0.9811,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 370,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.46895870566368103,
      "learning_rate": 8.378378378378379e-05,
      "loss": 0.9969,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 380,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.42161303758621216,
      "learning_rate": 8.327383987761347e-05,
      "loss": 0.9852,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 390,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4941897690296173,
      "learning_rate": 8.276389597144315e-05,
      "loss": 0.9878,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 400,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.4448719918727875,
      "learning_rate": 8.225395206527282e-05,
      "loss": 0.9956,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 410,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.4166922867298126,
      "learning_rate": 8.17440081591025e-05,
      "loss": 0.9899,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 420,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.40304499864578247,
      "learning_rate": 8.123406425293219e-05,
      "loss": 0.9908,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 430,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.43452388048171997,
      "learning_rate": 8.072412034676186e-05,
      "loss": 0.9705,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 440,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4060077965259552,
      "learning_rate": 8.021417644059154e-05,
      "loss": 0.9825,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 450,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4520680904388428,
      "learning_rate": 7.970423253442122e-05,
      "loss": 0.9782,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 460,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.4969607889652252,
      "learning_rate": 7.91942886282509e-05,
      "loss": 0.9798,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 470,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.48629072308540344,
      "learning_rate": 7.868434472208057e-05,
      "loss": 0.9795,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 480,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4386264979839325,
      "learning_rate": 7.817440081591025e-05,
      "loss": 0.9767,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 490,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.44945308566093445,
      "learning_rate": 7.766445690973994e-05,
      "loss": 0.9673,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 500,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4677426218986511,
      "learning_rate": 7.715451300356961e-05,
      "loss": 0.9752,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 510,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.4450967013835907,
      "learning_rate": 7.664456909739929e-05,
      "loss": 0.9708,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 520,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.425359308719635,
      "learning_rate": 7.613462519122897e-05,
      "loss": 0.9777,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 530,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.427310049533844,
      "learning_rate": 7.562468128505865e-05,
      "loss": 0.9721,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 540,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4417431056499481,
      "learning_rate": 7.511473737888832e-05,
      "loss": 0.9728,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 550,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.4482574164867401,
      "learning_rate": 7.460479347271801e-05,
      "loss": 0.967,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 560,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.434935063123703,
      "learning_rate": 7.409484956654769e-05,
      "loss": 0.9715,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 570,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.39001864194869995,
      "learning_rate": 7.358490566037736e-05,
      "loss": 0.9793,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 580,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.45607784390449524,
      "learning_rate": 7.307496175420703e-05,
      "loss": 0.9665,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 590,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.539667010307312,
      "learning_rate": 7.256501784803672e-05,
      "loss": 0.9664,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 600,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4229834973812103,
      "learning_rate": 7.20550739418664e-05,
      "loss": 0.9674,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 610,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.4525637626647949,
      "learning_rate": 7.154513003569607e-05,
      "loss": 0.9671,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 620,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.3813334107398987,
      "learning_rate": 7.103518612952576e-05,
      "loss": 0.9683,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 630,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.41690248250961304,
      "learning_rate": 7.052524222335543e-05,
      "loss": 0.9652,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 640,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4197711944580078,
      "learning_rate": 7.001529831718512e-05,
      "loss": 0.9776,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 650,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.4112277925014496,
      "learning_rate": 6.950535441101478e-05,
      "loss": 0.9627,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 660,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4737640917301178,
      "learning_rate": 6.899541050484447e-05,
      "loss": 0.9586,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 670,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4623068869113922,
      "learning_rate": 6.848546659867415e-05,
      "loss": 0.9637,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 680,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.47191059589385986,
      "learning_rate": 6.797552269250382e-05,
      "loss": 0.9791,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 690,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.4488503336906433,
      "learning_rate": 6.746557878633351e-05,
      "loss": 0.9654,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 700,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4537357985973358,
      "learning_rate": 6.695563488016318e-05,
      "loss": 0.9652,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 710,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.4568102955818176,
      "learning_rate": 6.644569097399287e-05,
      "loss": 0.972,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 720,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.37428340315818787,
      "learning_rate": 6.593574706782255e-05,
      "loss": 0.9531,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 730,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.40930184721946716,
      "learning_rate": 6.542580316165222e-05,
      "loss": 0.964,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 740,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.419447124004364,
      "learning_rate": 6.491585925548191e-05,
      "loss": 0.9535,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 750,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.4166411757469177,
      "learning_rate": 6.440591534931157e-05,
      "loss": 0.9632,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 760,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.43183305859565735,
      "learning_rate": 6.389597144314126e-05,
      "loss": 0.9623,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 770,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.4423561692237854,
      "learning_rate": 6.338602753697093e-05,
      "loss": 0.9662,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 780,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4051528871059418,
      "learning_rate": 6.287608363080062e-05,
      "loss": 0.9606,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 790,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.41725561022758484,
      "learning_rate": 6.23661397246303e-05,
      "loss": 0.9626,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 800,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4825494587421417,
      "learning_rate": 6.185619581845997e-05,
      "loss": 0.9586,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 810,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.3946501612663269,
      "learning_rate": 6.134625191228966e-05,
      "loss": 0.9511,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 820,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.4180380702018738,
      "learning_rate": 6.0836308006119326e-05,
      "loss": 0.9525,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 830,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.4118707478046417,
      "learning_rate": 6.032636409994901e-05,
      "loss": 0.9545,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 840,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.4261344075202942,
      "learning_rate": 5.981642019377869e-05,
      "loss": 0.9533,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 850,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.39828041195869446,
      "learning_rate": 5.930647628760837e-05,
      "loss": 0.9591,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 860,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.40321114659309387,
      "learning_rate": 5.879653238143804e-05,
      "loss": 0.9541,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 870,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.39925679564476013,
      "learning_rate": 5.8286588475267726e-05,
      "loss": 0.9518,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 880,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4243835210800171,
      "learning_rate": 5.777664456909741e-05,
      "loss": 0.9438,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 890,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.41923442482948303,
      "learning_rate": 5.7266700662927075e-05,
      "loss": 0.9637,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 900,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.3989606499671936,
      "learning_rate": 5.6756756756756757e-05,
      "loss": 0.9513,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 910,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4022904634475708,
      "learning_rate": 5.624681285058644e-05,
      "loss": 0.9475,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 920,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4124114513397217,
      "learning_rate": 5.573686894441612e-05,
      "loss": 0.9436,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 930,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.4305116832256317,
      "learning_rate": 5.5226925038245794e-05,
      "loss": 0.956,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 940,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.37347981333732605,
      "learning_rate": 5.4716981132075475e-05,
      "loss": 0.9589,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 950,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.43223634362220764,
      "learning_rate": 5.4207037225905157e-05,
      "loss": 0.948,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 960,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.38680389523506165,
      "learning_rate": 5.369709331973484e-05,
      "loss": 0.9474,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 970,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.42318058013916016,
      "learning_rate": 5.3187149413564506e-05,
      "loss": 0.9474,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 980,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.39201366901397705,
      "learning_rate": 5.267720550739419e-05,
      "loss": 0.9438,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 990,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.37628376483917236,
      "learning_rate": 5.216726160122387e-05,
      "loss": 0.9441,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1000,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.43160149455070496,
      "learning_rate": 5.165731769505354e-05,
      "loss": 0.9521,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1010,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.4002411663532257,
      "learning_rate": 5.1147373788883224e-05,
      "loss": 0.9425,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1020,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.4099406599998474,
      "learning_rate": 5.0637429882712906e-05,
      "loss": 0.9522,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1030,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.366636723279953,
      "learning_rate": 5.012748597654259e-05,
      "loss": 0.9493,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1040,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.39663130044937134,
      "learning_rate": 4.961754207037226e-05,
      "loss": 0.9458,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1050,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.36909976601600647,
      "learning_rate": 4.910759816420194e-05,
      "loss": 0.9455,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1060,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.3812944293022156,
      "learning_rate": 4.859765425803162e-05,
      "loss": 0.9423,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1070,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.38268741965293884,
      "learning_rate": 4.80877103518613e-05,
      "loss": 0.9487,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1080,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.3832300007343292,
      "learning_rate": 4.7577766445690974e-05,
      "loss": 0.9455,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1090,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.4103021025657654,
      "learning_rate": 4.7067822539520655e-05,
      "loss": 0.9353,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.3691622316837311,
      "learning_rate": 4.655787863335033e-05,
      "loss": 0.9514,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.42021074891090393,
      "learning_rate": 4.604793472718002e-05,
      "loss": 0.9469,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.4154146909713745,
      "learning_rate": 4.553799082100969e-05,
      "loss": 0.9367,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.41266191005706787,
      "learning_rate": 4.5028046914839374e-05,
      "loss": 0.9333,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.4136646091938019,
      "learning_rate": 4.451810300866905e-05,
      "loss": 0.9357,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.3877258002758026,
      "learning_rate": 4.400815910249872e-05,
      "loss": 0.9386,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.3618062734603882,
      "learning_rate": 4.3498215196328404e-05,
      "loss": 0.953,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.41884803771972656,
      "learning_rate": 4.2988271290158086e-05,
      "loss": 0.9491,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.4496184289455414,
      "learning_rate": 4.247832738398777e-05,
      "loss": 0.9343,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.39843064546585083,
      "learning_rate": 4.196838347781744e-05,
      "loss": 0.9486,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.3992258608341217,
      "learning_rate": 4.145843957164712e-05,
      "loss": 0.9461,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.4257832169532776,
      "learning_rate": 4.09484956654768e-05,
      "loss": 0.9427,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.4028872847557068,
      "learning_rate": 4.043855175930648e-05,
      "loss": 0.9443,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1230,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.3647397458553314,
      "learning_rate": 3.992860785313616e-05,
      "loss": 0.9482,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1240,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.4042160212993622,
      "learning_rate": 3.9418663946965835e-05,
      "loss": 0.9424,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1250,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.4318855404853821,
      "learning_rate": 3.8908720040795516e-05,
      "loss": 0.9392,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1260,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.3970791697502136,
      "learning_rate": 3.839877613462519e-05,
      "loss": 0.9369,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1270,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.40742847323417664,
      "learning_rate": 3.788883222845487e-05,
      "loss": 0.953,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1280,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.47150084376335144,
      "learning_rate": 3.737888832228455e-05,
      "loss": 0.9375,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1290,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.3862932324409485,
      "learning_rate": 3.6868944416114235e-05,
      "loss": 0.9347,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1300,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.3804072141647339,
      "learning_rate": 3.635900050994391e-05,
      "loss": 0.9504,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1310,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.3536450266838074,
      "learning_rate": 3.5849056603773584e-05,
      "loss": 0.9334,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1320,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.4137759506702423,
      "learning_rate": 3.5339112697603265e-05,
      "loss": 0.9424,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1330,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.37751680612564087,
      "learning_rate": 3.482916879143294e-05,
      "loss": 0.9355,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1340,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.3878466784954071,
      "learning_rate": 3.431922488526262e-05,
      "loss": 0.9404,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1350,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.3671165406703949,
      "learning_rate": 3.38092809790923e-05,
      "loss": 0.9448,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1360,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.3908054828643799,
      "learning_rate": 3.3299337072921984e-05,
      "loss": 0.9456,
      "max_memory_allocated (GB)": 91.96,
      "memory_allocated (GB)": 14.99,
      "step": 1370,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.3817441463470459,
      "learning_rate": 3.278939316675166e-05,
      "loss": 0.9457,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1380,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.3505423069000244,
      "learning_rate": 3.227944926058134e-05,
      "loss": 0.9355,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1390,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.37634551525115967,
      "learning_rate": 3.1769505354411015e-05,
      "loss": 0.9271,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1400,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.3707720935344696,
      "learning_rate": 3.1259561448240696e-05,
      "loss": 0.9189,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1410,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.36191660165786743,
      "learning_rate": 3.074961754207038e-05,
      "loss": 0.9334,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1420,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.3946132957935333,
      "learning_rate": 3.0239673635900052e-05,
      "loss": 0.9423,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1430,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.38084161281585693,
      "learning_rate": 2.9729729729729733e-05,
      "loss": 0.9311,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1440,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.3604285717010498,
      "learning_rate": 2.9219785823559408e-05,
      "loss": 0.9219,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1450,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.3744727373123169,
      "learning_rate": 2.8709841917389093e-05,
      "loss": 0.9326,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1460,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.38844382762908936,
      "learning_rate": 2.8199898011218767e-05,
      "loss": 0.9332,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1470,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.39416611194610596,
      "learning_rate": 2.7689954105048445e-05,
      "loss": 0.9415,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1480,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.35142263770103455,
      "learning_rate": 2.7180010198878126e-05,
      "loss": 0.9227,
      "max_memory_allocated (GB)": 91.97,
      "memory_allocated (GB)": 14.99,
      "step": 1490,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.3765707314014435,
      "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
    }
  ],
  "logging_steps": 10,
  "max_steps": 2022,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.6792232923653734e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}