{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.86046511627907,
  "eval_steps": 500,
  "global_step": 530,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 2.80859375,
      "learning_rate": 0.00019982437317643217,
      "loss": 0.7797,
      "step": 10
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 3.423828125,
      "learning_rate": 0.00019929810960135172,
      "loss": 0.7869,
      "step": 20
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 3.751953125,
      "learning_rate": 0.00019842305779475968,
      "loss": 0.7876,
      "step": 30
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 5.54296875,
      "learning_rate": 0.0001972022914080411,
      "loss": 0.8025,
      "step": 40
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 5.96875,
      "learning_rate": 0.00019564009842765225,
      "loss": 0.7775,
      "step": 50
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": 7.3984375,
      "learning_rate": 0.0001937419661134121,
      "loss": 0.7599,
      "step": 60
    },
    {
      "epoch": 1.302325581395349,
      "grad_norm": 6.05078125,
      "learning_rate": 0.00019151456172430183,
      "loss": 0.7773,
      "step": 70
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 5.4375,
      "learning_rate": 0.00018896570909947475,
      "loss": 0.7747,
      "step": 80
    },
    {
      "epoch": 1.6744186046511627,
      "grad_norm": 5.05078125,
      "learning_rate": 0.00018610436117673555,
      "loss": 0.7561,
      "step": 90
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 5.4765625,
      "learning_rate": 0.0001829405685450202,
      "loss": 0.7699,
      "step": 100
    },
    {
      "epoch": 2.046511627906977,
      "grad_norm": 4.58203125,
      "learning_rate": 0.00017948544414133534,
      "loss": 0.7668,
      "step": 110
    },
    {
      "epoch": 2.2325581395348837,
      "grad_norm": 5.43359375,
      "learning_rate": 0.00017575112421616202,
      "loss": 0.763,
      "step": 120
    },
    {
      "epoch": 2.4186046511627906,
      "grad_norm": 4.69140625,
      "learning_rate": 0.00017175072570443312,
      "loss": 0.7538,
      "step": 130
    },
    {
      "epoch": 2.604651162790698,
      "grad_norm": 4.97265625,
      "learning_rate": 0.00016749830015182107,
      "loss": 0.773,
      "step": 140
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 7.2109375,
      "learning_rate": 0.00016300878435817113,
      "loss": 0.7781,
      "step": 150
    },
    {
      "epoch": 2.9767441860465116,
      "grad_norm": 5.51171875,
      "learning_rate": 0.0001582979479114472,
      "loss": 0.7505,
      "step": 160
    },
    {
      "epoch": 3.1627906976744184,
      "grad_norm": 5.9375,
      "learning_rate": 0.0001533823377964791,
      "loss": 0.7353,
      "step": 170
    },
    {
      "epoch": 3.3488372093023258,
      "grad_norm": 5.92578125,
      "learning_rate": 0.00014827922027307451,
      "loss": 0.7321,
      "step": 180
    },
    {
      "epoch": 3.5348837209302326,
      "grad_norm": 10.3828125,
      "learning_rate": 0.00014300652022765207,
      "loss": 0.7498,
      "step": 190
    },
    {
      "epoch": 3.7209302325581395,
      "grad_norm": 10.515625,
      "learning_rate": 0.00013758275821142382,
      "loss": 0.7595,
      "step": 200
    },
    {
      "epoch": 3.9069767441860463,
      "grad_norm": 7.015625,
      "learning_rate": 0.00013202698538628376,
      "loss": 0.7685,
      "step": 210
    },
    {
      "epoch": 4.093023255813954,
      "grad_norm": 5.71484375,
      "learning_rate": 0.00012635871660690676,
      "loss": 0.7613,
      "step": 220
    },
    {
      "epoch": 4.27906976744186,
      "grad_norm": 5.6171875,
      "learning_rate": 0.00012059786187410984,
      "loss": 0.7483,
      "step": 230
    },
    {
      "epoch": 4.465116279069767,
      "grad_norm": 6.875,
      "learning_rate": 0.00011476465640024814,
      "loss": 0.7515,
      "step": 240
    },
    {
      "epoch": 4.651162790697675,
      "grad_norm": 5.3125,
      "learning_rate": 0.00010887958953229349,
      "loss": 0.7514,
      "step": 250
    },
    {
      "epoch": 4.837209302325581,
      "grad_norm": 6.1875,
      "learning_rate": 0.00010296333278225599,
      "loss": 0.7544,
      "step": 260
    },
    {
      "epoch": 5.023255813953488,
      "grad_norm": 7.9609375,
      "learning_rate": 9.703666721774402e-05,
      "loss": 0.7221,
      "step": 270
    },
    {
      "epoch": 5.209302325581396,
      "grad_norm": 6.609375,
      "learning_rate": 9.112041046770653e-05,
      "loss": 0.7334,
      "step": 280
    },
    {
      "epoch": 5.395348837209302,
      "grad_norm": 4.640625,
      "learning_rate": 8.523534359975189e-05,
      "loss": 0.7175,
      "step": 290
    },
    {
      "epoch": 5.5813953488372094,
      "grad_norm": 4.47265625,
      "learning_rate": 7.940213812589018e-05,
      "loss": 0.7294,
      "step": 300
    },
    {
      "epoch": 5.767441860465116,
      "grad_norm": 6.55859375,
      "learning_rate": 7.364128339309326e-05,
      "loss": 0.75,
      "step": 310
    },
    {
      "epoch": 5.953488372093023,
      "grad_norm": 7.55859375,
      "learning_rate": 6.797301461371625e-05,
      "loss": 0.7479,
      "step": 320
    },
    {
      "epoch": 6.1395348837209305,
      "grad_norm": 7.60546875,
      "learning_rate": 6.24172417885762e-05,
      "loss": 0.7285,
      "step": 330
    },
    {
      "epoch": 6.325581395348837,
      "grad_norm": 7.0078125,
      "learning_rate": 5.699347977234799e-05,
      "loss": 0.7402,
      "step": 340
    },
    {
      "epoch": 6.511627906976744,
      "grad_norm": 5.78515625,
      "learning_rate": 5.172077972692553e-05,
      "loss": 0.7532,
      "step": 350
    },
    {
      "epoch": 6.6976744186046515,
      "grad_norm": 8.921875,
      "learning_rate": 4.661766220352097e-05,
      "loss": 0.714,
      "step": 360
    },
    {
      "epoch": 6.883720930232558,
      "grad_norm": 8.34375,
      "learning_rate": 4.170205208855281e-05,
      "loss": 0.736,
      "step": 370
    },
    {
      "epoch": 7.069767441860465,
      "grad_norm": 5.9921875,
      "learning_rate": 3.69912156418289e-05,
      "loss": 0.7404,
      "step": 380
    },
    {
      "epoch": 7.2558139534883725,
      "grad_norm": 8.7890625,
      "learning_rate": 3.250169984817897e-05,
      "loss": 0.7355,
      "step": 390
    },
    {
      "epoch": 7.441860465116279,
      "grad_norm": 6.76953125,
      "learning_rate": 2.8249274295566864e-05,
      "loss": 0.73,
      "step": 400
    },
    {
      "epoch": 7.627906976744186,
      "grad_norm": 6.28125,
      "learning_rate": 2.4248875783837987e-05,
      "loss": 0.7192,
      "step": 410
    },
    {
      "epoch": 7.813953488372093,
      "grad_norm": 5.9140625,
      "learning_rate": 2.0514555858664663e-05,
      "loss": 0.7425,
      "step": 420
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.7265625,
      "learning_rate": 1.7059431454979824e-05,
      "loss": 0.7263,
      "step": 430
    },
    {
      "epoch": 8.186046511627907,
      "grad_norm": 6.07421875,
      "learning_rate": 1.3895638823264446e-05,
      "loss": 0.7217,
      "step": 440
    },
    {
      "epoch": 8.372093023255815,
      "grad_norm": 6.421875,
      "learning_rate": 1.103429090052528e-05,
      "loss": 0.7507,
      "step": 450
    },
    {
      "epoch": 8.55813953488372,
      "grad_norm": 9.28125,
      "learning_rate": 8.485438275698154e-06,
      "loss": 0.7174,
      "step": 460
    },
    {
      "epoch": 8.744186046511627,
      "grad_norm": 7.484375,
      "learning_rate": 6.258033886587911e-06,
      "loss": 0.7317,
      "step": 470
    },
    {
      "epoch": 8.930232558139535,
      "grad_norm": 5.91015625,
      "learning_rate": 4.359901572347758e-06,
      "loss": 0.7517,
      "step": 480
    },
    {
      "epoch": 9.116279069767442,
      "grad_norm": 5.78125,
      "learning_rate": 2.7977085919589254e-06,
      "loss": 0.7121,
      "step": 490
    },
    {
      "epoch": 9.30232558139535,
      "grad_norm": 6.01171875,
      "learning_rate": 1.576942205240317e-06,
      "loss": 0.7469,
      "step": 500
    },
    {
      "epoch": 9.488372093023255,
      "grad_norm": 5.47265625,
      "learning_rate": 7.018903986483083e-07,
      "loss": 0.7216,
      "step": 510
    },
    {
      "epoch": 9.674418604651162,
      "grad_norm": 7.90625,
      "learning_rate": 1.7562682356786487e-07,
      "loss": 0.7351,
      "step": 520
    },
    {
      "epoch": 9.86046511627907,
      "grad_norm": 6.05078125,
      "learning_rate": 0.0,
      "loss": 0.7443,
      "step": 530
    },
    {
      "epoch": 9.86046511627907,
      "step": 530,
      "total_flos": 3.46013457973248e+16,
      "train_loss": 0.7484581434501791,
      "train_runtime": 447.8277,
      "train_samples_per_second": 4.801,
      "train_steps_per_second": 1.183
    }
  ],
  "logging_steps": 10,
  "max_steps": 530,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3.46013457973248e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}