{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 3251,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03076804738279297,
      "grad_norm": 0.4551459848880768,
      "learning_rate": 4.75e-05,
      "loss": 1.0461,
      "step": 100
    },
    {
      "epoch": 0.06153609476558594,
      "grad_norm": 0.398708701133728,
      "learning_rate": 4.849254205014281e-05,
      "loss": 0.5103,
      "step": 200
    },
    {
      "epoch": 0.09230414214837891,
      "grad_norm": 0.5458264946937561,
      "learning_rate": 4.690574420818788e-05,
      "loss": 0.5164,
      "step": 300
    },
    {
      "epoch": 0.12307218953117188,
      "grad_norm": 0.4311501085758209,
      "learning_rate": 4.5318946366232947e-05,
      "loss": 0.5276,
      "step": 400
    },
    {
      "epoch": 0.15384023691396484,
      "grad_norm": 0.38870149850845337,
      "learning_rate": 4.373214852427801e-05,
      "loss": 0.5037,
      "step": 500
    },
    {
      "epoch": 0.18460828429675782,
      "grad_norm": 0.5005269050598145,
      "learning_rate": 4.2145350682323075e-05,
      "loss": 0.53,
      "step": 600
    },
    {
      "epoch": 0.21537633167955078,
      "grad_norm": 0.389077365398407,
      "learning_rate": 4.055855284036814e-05,
      "loss": 0.5078,
      "step": 700
    },
    {
      "epoch": 0.24614437906234377,
      "grad_norm": 0.44048070907592773,
      "learning_rate": 3.8971754998413204e-05,
      "loss": 0.522,
      "step": 800
    },
    {
      "epoch": 0.27691242644513675,
      "grad_norm": 0.34244316816329956,
      "learning_rate": 3.7384957156458266e-05,
      "loss": 0.4913,
      "step": 900
    },
    {
      "epoch": 0.3076804738279297,
      "grad_norm": 0.46572574973106384,
      "learning_rate": 3.5798159314503333e-05,
      "loss": 0.4939,
      "step": 1000
    },
    {
      "epoch": 0.3076804738279297,
      "eval_loss": 0.3825926184654236,
      "eval_runtime": 4.7315,
      "eval_samples_per_second": 42.27,
      "eval_steps_per_second": 21.135,
      "step": 1000
    },
    {
      "epoch": 0.33844852121072266,
      "grad_norm": 0.4824311435222626,
      "learning_rate": 3.4211361472548394e-05,
      "loss": 0.5102,
      "step": 1100
    },
    {
      "epoch": 0.36921656859351565,
      "grad_norm": 0.41817840933799744,
      "learning_rate": 3.262456363059346e-05,
      "loss": 0.519,
      "step": 1200
    },
    {
      "epoch": 0.3999846159763086,
      "grad_norm": 0.33424732089042664,
      "learning_rate": 3.103776578863853e-05,
      "loss": 0.5107,
      "step": 1300
    },
    {
      "epoch": 0.43075266335910156,
      "grad_norm": 0.5414207577705383,
      "learning_rate": 2.9450967946683595e-05,
      "loss": 0.5178,
      "step": 1400
    },
    {
      "epoch": 0.46152071074189455,
      "grad_norm": 0.49227190017700195,
      "learning_rate": 2.786417010472866e-05,
      "loss": 0.5162,
      "step": 1500
    },
    {
      "epoch": 0.49228875812468753,
      "grad_norm": 0.3693729043006897,
      "learning_rate": 2.6277372262773724e-05,
      "loss": 0.501,
      "step": 1600
    },
    {
      "epoch": 0.5230568055074805,
      "grad_norm": 0.6255485415458679,
      "learning_rate": 2.4690574420818788e-05,
      "loss": 0.5097,
      "step": 1700
    },
    {
      "epoch": 0.5538248528902735,
      "grad_norm": 0.4786062240600586,
      "learning_rate": 2.3103776578863853e-05,
      "loss": 0.5122,
      "step": 1800
    },
    {
      "epoch": 0.5845929002730664,
      "grad_norm": 0.44093266129493713,
      "learning_rate": 2.1516978736908917e-05,
      "loss": 0.518,
      "step": 1900
    },
    {
      "epoch": 0.6153609476558594,
      "grad_norm": 0.5277242064476013,
      "learning_rate": 1.9930180894953985e-05,
      "loss": 0.5087,
      "step": 2000
    },
    {
      "epoch": 0.6153609476558594,
      "eval_loss": 0.37586718797683716,
      "eval_runtime": 4.7269,
      "eval_samples_per_second": 42.311,
      "eval_steps_per_second": 21.155,
      "step": 2000
    },
    {
      "epoch": 0.6461289950386524,
      "grad_norm": 0.3952804207801819,
      "learning_rate": 1.834338305299905e-05,
      "loss": 0.4978,
      "step": 2100
    },
    {
      "epoch": 0.6768970424214453,
      "grad_norm": 0.49758800864219666,
      "learning_rate": 1.6756585211044114e-05,
      "loss": 0.524,
      "step": 2200
    },
    {
      "epoch": 0.7076650898042383,
      "grad_norm": 0.3507545292377472,
      "learning_rate": 1.5169787369089178e-05,
      "loss": 0.5127,
      "step": 2300
    },
    {
      "epoch": 0.7384331371870313,
      "grad_norm": 0.4394129514694214,
      "learning_rate": 1.3582989527134243e-05,
      "loss": 0.506,
      "step": 2400
    },
    {
      "epoch": 0.7692011845698242,
      "grad_norm": 0.5479759573936462,
      "learning_rate": 1.1996191685179309e-05,
      "loss": 0.5175,
      "step": 2500
    },
    {
      "epoch": 0.7999692319526172,
      "grad_norm": 0.3974688947200775,
      "learning_rate": 1.0409393843224374e-05,
      "loss": 0.544,
      "step": 2600
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 0.4838125705718994,
      "learning_rate": 8.822596001269438e-06,
      "loss": 0.5323,
      "step": 2700
    },
    {
      "epoch": 0.8615053267182031,
      "grad_norm": 0.3339136838912964,
      "learning_rate": 7.235798159314504e-06,
      "loss": 0.5321,
      "step": 2800
    },
    {
      "epoch": 0.8922733741009962,
      "grad_norm": 0.3484480679035187,
      "learning_rate": 5.649000317359569e-06,
      "loss": 0.4897,
      "step": 2900
    },
    {
      "epoch": 0.9230414214837891,
      "grad_norm": 0.377142995595932,
      "learning_rate": 4.062202475404633e-06,
      "loss": 0.5001,
      "step": 3000
    },
    {
      "epoch": 0.9230414214837891,
      "eval_loss": 0.3712926208972931,
      "eval_runtime": 4.7886,
      "eval_samples_per_second": 41.766,
      "eval_steps_per_second": 20.883,
      "step": 3000
    },
    {
      "epoch": 0.953809468866582,
      "grad_norm": 0.4788321554660797,
      "learning_rate": 2.4754046334496985e-06,
      "loss": 0.5155,
      "step": 3100
    },
    {
      "epoch": 0.9845775162493751,
      "grad_norm": 0.38534921407699585,
      "learning_rate": 8.886067914947636e-07,
      "loss": 0.5219,
      "step": 3200
    }
  ],
  "logging_steps": 100,
  "max_steps": 3251,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3587708248064e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}