{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023502867349816676,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.401146939926671e-05,
      "grad_norm": 1.0696098804473877,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3106,
      "step": 1
    },
    {
      "epoch": 9.401146939926671e-05,
      "eval_loss": 3.1381921768188477,
      "eval_runtime": 306.7613,
      "eval_samples_per_second": 29.202,
      "eval_steps_per_second": 14.601,
      "step": 1
    },
    {
      "epoch": 0.00018802293879853342,
      "grad_norm": 1.1547324657440186,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.3901,
      "step": 2
    },
    {
      "epoch": 0.0002820344081978001,
      "grad_norm": 1.1568049192428589,
      "learning_rate": 0.0001,
      "loss": 2.4531,
      "step": 3
    },
    {
      "epoch": 0.00037604587759706683,
      "grad_norm": 1.295903205871582,
      "learning_rate": 9.99524110790929e-05,
      "loss": 2.5252,
      "step": 4
    },
    {
      "epoch": 0.00047005734699633354,
      "grad_norm": 1.3080066442489624,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.5252,
      "step": 5
    },
    {
      "epoch": 0.0005640688163956002,
      "grad_norm": 1.4140979051589966,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.2832,
      "step": 6
    },
    {
      "epoch": 0.000658080285794867,
      "grad_norm": 1.2049480676651,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.1834,
      "step": 7
    },
    {
      "epoch": 0.0007520917551941337,
      "grad_norm": 1.691810131072998,
      "learning_rate": 9.881480035599667e-05,
      "loss": 2.1438,
      "step": 8
    },
    {
      "epoch": 0.0008461032245934004,
      "grad_norm": 1.4161789417266846,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9656,
      "step": 9
    },
    {
      "epoch": 0.0009401146939926671,
      "grad_norm": 1.1197580099105835,
      "learning_rate": 9.768584753741134e-05,
      "loss": 1.8062,
      "step": 10
    },
    {
      "epoch": 0.001034126163391934,
      "grad_norm": 1.2883065938949585,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8325,
      "step": 11
    },
    {
      "epoch": 0.0011281376327912005,
      "grad_norm": 1.2502721548080444,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7662,
      "step": 12
    },
    {
      "epoch": 0.0012221491021904673,
      "grad_norm": 1.160671353340149,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.6167,
      "step": 13
    },
    {
      "epoch": 0.001316160571589734,
      "grad_norm": 1.2814849615097046,
      "learning_rate": 9.435054165891109e-05,
      "loss": 1.5443,
      "step": 14
    },
    {
      "epoch": 0.0014101720409890007,
      "grad_norm": 1.3020795583724976,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4767,
      "step": 15
    },
    {
      "epoch": 0.0015041835103882673,
      "grad_norm": 1.122304081916809,
      "learning_rate": 9.21695722906443e-05,
      "loss": 1.3664,
      "step": 16
    },
    {
      "epoch": 0.0015981949797875341,
      "grad_norm": 1.0071494579315186,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.2036,
      "step": 17
    },
    {
      "epoch": 0.0016922064491868007,
      "grad_norm": 1.019412875175476,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.2946,
      "step": 18
    },
    {
      "epoch": 0.0017862179185860676,
      "grad_norm": 1.3061738014221191,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2691,
      "step": 19
    },
    {
      "epoch": 0.0018802293879853342,
      "grad_norm": 1.2895138263702393,
      "learning_rate": 8.68638668405062e-05,
      "loss": 1.2012,
      "step": 20
    },
    {
      "epoch": 0.0019742408573846008,
      "grad_norm": 1.0393970012664795,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9289,
      "step": 21
    },
    {
      "epoch": 0.002068252326783868,
      "grad_norm": 1.161494255065918,
      "learning_rate": 8.377951038078302e-05,
      "loss": 1.0573,
      "step": 22
    },
    {
      "epoch": 0.0021622637961831344,
      "grad_norm": 1.2825669050216675,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0959,
      "step": 23
    },
    {
      "epoch": 0.002256275265582401,
      "grad_norm": 1.2384896278381348,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.9377,
      "step": 24
    },
    {
      "epoch": 0.0023502867349816676,
      "grad_norm": 1.1488481760025024,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.9027,
      "step": 25
    },
    {
      "epoch": 0.0023502867349816676,
      "eval_loss": 0.9509760737419128,
      "eval_runtime": 306.6139,
      "eval_samples_per_second": 29.216,
      "eval_steps_per_second": 14.608,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5208852450508800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}