{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002,
      "grad_norm": 0.7236698865890503,
      "learning_rate": 0.000396,
      "loss": 8.129180297851562,
      "step": 100
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.6699316501617432,
      "learning_rate": 0.0005999985696164921,
      "loss": 6.683881225585938,
      "step": 200
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.4809923470020294,
      "learning_rate": 0.0005999867739541219,
      "loss": 6.335140991210937,
      "step": 300
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.6197829246520996,
      "learning_rate": 0.0005999630639489827,
      "loss": 6.119940185546875,
      "step": 400
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.5310641527175903,
      "learning_rate": 0.0005999274405427468,
      "loss": 5.908866577148437,
      "step": 500
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.4188089668750763,
      "learning_rate": 0.0005998799051502414,
      "loss": 5.712981567382813,
      "step": 600
    },
    {
      "epoch": 0.014,
      "grad_norm": 0.43575364351272583,
      "learning_rate": 0.0005998204596593927,
      "loss": 5.54151123046875,
      "step": 700
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.3631345331668854,
      "learning_rate": 0.0005997491064311517,
      "loss": 5.377118530273438,
      "step": 800
    },
    {
      "epoch": 0.018,
      "grad_norm": 0.4753637909889221,
      "learning_rate": 0.000599665848299399,
      "loss": 5.2575732421875,
      "step": 900
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.3885057270526886,
      "learning_rate": 0.0005995706885708337,
      "loss": 5.168424072265625,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.21422370900467913,
      "eval_loss": 5.0658464431762695,
      "eval_runtime": 5.7327,
      "eval_samples_per_second": 338.583,
      "eval_steps_per_second": 21.281,
      "step": 1000
    },
    {
      "epoch": 0.022,
      "grad_norm": 0.35898318886756897,
      "learning_rate": 0.0005994636310248412,
      "loss": 5.058907165527343,
      "step": 1100
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.36867955327033997,
      "learning_rate": 0.000599344679913343,
      "loss": 4.899845275878906,
      "step": 1200
    },
    {
      "epoch": 0.026,
      "grad_norm": 0.3753994405269623,
      "learning_rate": 0.0005992138399606286,
      "loss": 4.828855285644531,
      "step": 1300
    },
    {
      "epoch": 0.028,
      "grad_norm": 0.3426174521446228,
      "learning_rate": 0.0005990711163631674,
      "loss": 4.73110595703125,
      "step": 1400
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.34207016229629517,
      "learning_rate": 0.000598916514789402,
      "loss": 4.640643005371094,
      "step": 1500
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.40568745136260986,
      "learning_rate": 0.0005987500413795236,
      "loss": 4.591531677246094,
      "step": 1600
    },
    {
      "epoch": 0.034,
      "grad_norm": 0.31946808099746704,
      "learning_rate": 0.0005985717027452278,
      "loss": 4.533291015625,
      "step": 1700
    },
    {
      "epoch": 0.036,
      "grad_norm": 0.30501991510391235,
      "learning_rate": 0.0005983815059694525,
      "loss": 4.492686157226562,
      "step": 1800
    },
    {
      "epoch": 0.038,
      "grad_norm": 0.33989349007606506,
      "learning_rate": 0.0005981794586060958,
      "loss": 4.41447509765625,
      "step": 1900
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.3303995430469513,
      "learning_rate": 0.0005979655686797167,
      "loss": 4.396521911621094,
      "step": 2000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.2874403514237522,
      "eval_loss": 4.30245304107666,
      "eval_runtime": 5.7068,
      "eval_samples_per_second": 340.121,
      "eval_steps_per_second": 21.378,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 50000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.271008768e+16,
  "train_batch_size": 120,
  "trial_name": null,
  "trial_params": null
}