{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 3342,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "grad_norm": 6.054772853851318,
      "learning_rate": 1.9820466786355476e-05,
      "loss": 0.5721,
      "step": 100
    },
    {
      "epoch": 0.36,
      "grad_norm": 9.810357093811035,
      "learning_rate": 1.9640933572710953e-05,
      "loss": 0.3846,
      "step": 200
    },
    {
      "epoch": 0.54,
      "grad_norm": 9.026122093200684,
      "learning_rate": 1.9461400359066428e-05,
      "loss": 0.3019,
      "step": 300
    },
    {
      "epoch": 0.72,
      "grad_norm": 11.95788288116455,
      "learning_rate": 1.9281867145421905e-05,
      "loss": 0.3071,
      "step": 400
    },
    {
      "epoch": 0.9,
      "grad_norm": 15.329608917236328,
      "learning_rate": 1.910233393177738e-05,
      "loss": 0.2907,
      "step": 500
    },
    {
      "epoch": 1.08,
      "grad_norm": 12.364314079284668,
      "learning_rate": 1.8922800718132857e-05,
      "loss": 0.2646,
      "step": 600
    },
    {
      "epoch": 1.26,
      "grad_norm": 14.555986404418945,
      "learning_rate": 1.874326750448833e-05,
      "loss": 0.2097,
      "step": 700
    },
    {
      "epoch": 1.44,
      "grad_norm": 4.199421405792236,
      "learning_rate": 1.8563734290843805e-05,
      "loss": 0.2389,
      "step": 800
    },
    {
      "epoch": 1.62,
      "grad_norm": 22.485984802246094,
      "learning_rate": 1.8384201077199283e-05,
      "loss": 0.2019,
      "step": 900
    },
    {
      "epoch": 1.8,
      "grad_norm": 9.688520431518555,
      "learning_rate": 1.820466786355476e-05,
      "loss": 0.2594,
      "step": 1000
    },
    {
      "epoch": 1.97,
      "grad_norm": 18.052719116210938,
      "learning_rate": 1.8025134649910235e-05,
      "loss": 0.2044,
      "step": 1100
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.7371789216995239,
      "learning_rate": 1.7845601436265712e-05,
      "loss": 0.1551,
      "step": 1200
    },
    {
      "epoch": 2.33,
      "grad_norm": 20.938648223876953,
      "learning_rate": 1.7666068222621186e-05,
      "loss": 0.1463,
      "step": 1300
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.25227147340774536,
      "learning_rate": 1.748653500897666e-05,
      "loss": 0.1493,
      "step": 1400
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.27634137868881226,
      "learning_rate": 1.7307001795332138e-05,
      "loss": 0.1649,
      "step": 1500
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.2588340938091278,
      "learning_rate": 1.7127468581687616e-05,
      "loss": 0.1521,
      "step": 1600
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.05350634083151817,
      "learning_rate": 1.694793536804309e-05,
      "loss": 0.1343,
      "step": 1700
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.02972230687737465,
      "learning_rate": 1.6768402154398564e-05,
      "loss": 0.1068,
      "step": 1800
    },
    {
      "epoch": 3.41,
      "grad_norm": 0.09572970867156982,
      "learning_rate": 1.658886894075404e-05,
      "loss": 0.1151,
      "step": 1900
    },
    {
      "epoch": 3.59,
      "grad_norm": 21.431325912475586,
      "learning_rate": 1.6409335727109516e-05,
      "loss": 0.1073,
      "step": 2000
    },
    {
      "epoch": 3.77,
      "grad_norm": 1.4688669443130493,
      "learning_rate": 1.6229802513464993e-05,
      "loss": 0.1098,
      "step": 2100
    },
    {
      "epoch": 3.95,
      "grad_norm": 19.461355209350586,
      "learning_rate": 1.6050269299820467e-05,
      "loss": 0.1238,
      "step": 2200
    },
    {
      "epoch": 4.13,
      "grad_norm": 6.33543586730957,
      "learning_rate": 1.5870736086175945e-05,
      "loss": 0.0934,
      "step": 2300
    },
    {
      "epoch": 4.31,
      "grad_norm": 10.25698184967041,
      "learning_rate": 1.569120287253142e-05,
      "loss": 0.068,
      "step": 2400
    },
    {
      "epoch": 4.49,
      "grad_norm": 0.05421575903892517,
      "learning_rate": 1.5511669658886893e-05,
      "loss": 0.0767,
      "step": 2500
    },
    {
      "epoch": 4.67,
      "grad_norm": 0.04917303845286369,
      "learning_rate": 1.533213644524237e-05,
      "loss": 0.1053,
      "step": 2600
    },
    {
      "epoch": 4.85,
      "grad_norm": 1.722901463508606,
      "learning_rate": 1.5152603231597847e-05,
      "loss": 0.0513,
      "step": 2700
    },
    {
      "epoch": 5.03,
      "grad_norm": 28.548158645629883,
      "learning_rate": 1.4973070017953321e-05,
      "loss": 0.0611,
      "step": 2800
    },
    {
      "epoch": 5.21,
      "grad_norm": 1.0562294721603394,
      "learning_rate": 1.4793536804308799e-05,
      "loss": 0.0543,
      "step": 2900
    },
    {
      "epoch": 5.39,
      "grad_norm": 0.011326675303280354,
      "learning_rate": 1.4614003590664274e-05,
      "loss": 0.0491,
      "step": 3000
    },
    {
      "epoch": 5.57,
      "grad_norm": 0.009987740777432919,
      "learning_rate": 1.4434470377019749e-05,
      "loss": 0.0567,
      "step": 3100
    },
    {
      "epoch": 5.75,
      "grad_norm": 26.81354331970215,
      "learning_rate": 1.4254937163375226e-05,
      "loss": 0.0641,
      "step": 3200
    },
    {
      "epoch": 5.92,
      "grad_norm": 0.042816389352083206,
      "learning_rate": 1.4075403949730702e-05,
      "loss": 0.0488,
      "step": 3300
    }
  ],
  "logging_steps": 100,
  "max_steps": 11140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 3.4115676633458784e+16,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}