{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0038535645472061657,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015414258188824664,
      "grad_norm": 0.6734272241592407,
      "learning_rate": 5e-05,
      "loss": 1.4781,
      "step": 1
    },
    {
      "epoch": 0.00015414258188824664,
      "eval_loss": 1.66375732421875,
      "eval_runtime": 3.2935,
      "eval_samples_per_second": 15.182,
      "eval_steps_per_second": 3.947,
      "step": 1
    },
    {
      "epoch": 0.0003082851637764933,
      "grad_norm": 0.8541533350944519,
      "learning_rate": 0.0001,
      "loss": 1.3495,
      "step": 2
    },
    {
      "epoch": 0.00046242774566473987,
      "grad_norm": 0.6524771451950073,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.315,
      "step": 3
    },
    {
      "epoch": 0.0006165703275529866,
      "grad_norm": 0.5823439955711365,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.3871,
      "step": 4
    },
    {
      "epoch": 0.0007707129094412332,
      "grad_norm": 0.49418699741363525,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.3642,
      "step": 5
    },
    {
      "epoch": 0.0009248554913294797,
      "grad_norm": 0.5664134621620178,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.3952,
      "step": 6
    },
    {
      "epoch": 0.0010789980732177264,
      "grad_norm": 0.4901440739631653,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.5234,
      "step": 7
    },
    {
      "epoch": 0.0012331406551059731,
      "grad_norm": 0.3769587576389313,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.4229,
      "step": 8
    },
    {
      "epoch": 0.0013872832369942196,
      "grad_norm": 0.4188389480113983,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.5131,
      "step": 9
    },
    {
      "epoch": 0.0015414258188824663,
      "grad_norm": 0.5015379190444946,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.5212,
      "step": 10
    },
    {
      "epoch": 0.001695568400770713,
      "grad_norm": 0.5772421956062317,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.572,
      "step": 11
    },
    {
      "epoch": 0.0018497109826589595,
      "grad_norm": 0.6743692755699158,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.5605,
      "step": 12
    },
    {
      "epoch": 0.002003853564547206,
      "grad_norm": 0.2970338761806488,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.4014,
      "step": 13
    },
    {
      "epoch": 0.002157996146435453,
      "grad_norm": 0.2780226469039917,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.155,
      "step": 14
    },
    {
      "epoch": 0.0023121387283236996,
      "grad_norm": 0.2958413362503052,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.273,
      "step": 15
    },
    {
      "epoch": 0.0024662813102119463,
      "grad_norm": 0.3193422853946686,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.2629,
      "step": 16
    },
    {
      "epoch": 0.0026204238921001925,
      "grad_norm": 0.339270681142807,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.3673,
      "step": 17
    },
    {
      "epoch": 0.0027745664739884392,
      "grad_norm": 0.2887856066226959,
      "learning_rate": 7.75e-05,
      "loss": 1.367,
      "step": 18
    },
    {
      "epoch": 0.002928709055876686,
      "grad_norm": 0.3095043897628784,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.3631,
      "step": 19
    },
    {
      "epoch": 0.0030828516377649326,
      "grad_norm": 0.32946938276290894,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.4236,
      "step": 20
    },
    {
      "epoch": 0.0032369942196531793,
      "grad_norm": 0.33055737614631653,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.4734,
      "step": 21
    },
    {
      "epoch": 0.003391136801541426,
      "grad_norm": 0.3694823384284973,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.4547,
      "step": 22
    },
    {
      "epoch": 0.0035452793834296723,
      "grad_norm": 0.4111591875553131,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.5789,
      "step": 23
    },
    {
      "epoch": 0.003699421965317919,
      "grad_norm": 0.48207613825798035,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.5792,
      "step": 24
    },
    {
      "epoch": 0.0038535645472061657,
      "grad_norm": 0.7138695120811462,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.3662,
      "step": 25
    },
    {
      "epoch": 0.0038535645472061657,
      "eval_loss": 1.3446707725524902,
      "eval_runtime": 3.2927,
      "eval_samples_per_second": 15.185,
      "eval_steps_per_second": 3.948,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 2.987771858905989e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}