{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12562814070351758,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005025125628140704,
      "grad_norm": 31.318880081176758,
      "learning_rate": 5e-05,
      "loss": 9.9457,
      "step": 1
    },
    {
      "epoch": 0.005025125628140704,
      "eval_loss": 10.103697776794434,
      "eval_runtime": 3.4546,
      "eval_samples_per_second": 14.473,
      "eval_steps_per_second": 3.763,
      "step": 1
    },
    {
      "epoch": 0.010050251256281407,
      "grad_norm": 29.720123291015625,
      "learning_rate": 0.0001,
      "loss": 9.878,
      "step": 2
    },
    {
      "epoch": 0.01507537688442211,
      "grad_norm": 22.948766708374023,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.3223,
      "step": 3
    },
    {
      "epoch": 0.020100502512562814,
      "grad_norm": 17.66668128967285,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.5395,
      "step": 4
    },
    {
      "epoch": 0.02512562814070352,
      "grad_norm": 15.968902587890625,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.1588,
      "step": 5
    },
    {
      "epoch": 0.03015075376884422,
      "grad_norm": 8.603658676147461,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.5038,
      "step": 6
    },
    {
      "epoch": 0.035175879396984924,
      "grad_norm": 1.9850454330444336,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0695,
      "step": 7
    },
    {
      "epoch": 0.04020100502512563,
      "grad_norm": 0.10290369391441345,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0027,
      "step": 8
    },
    {
      "epoch": 0.04522613065326633,
      "grad_norm": 0.012726015411317348,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0003,
      "step": 9
    },
    {
      "epoch": 0.05025125628140704,
      "grad_norm": 0.0040101478807628155,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0001,
      "step": 10
    },
    {
      "epoch": 0.05527638190954774,
      "grad_norm": 0.002046189270913601,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.06030150753768844,
      "grad_norm": 0.0013901140773668885,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.06532663316582915,
      "grad_norm": 0.0014676337596029043,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.07035175879396985,
      "grad_norm": 0.0016537312185391784,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.07537688442211055,
      "grad_norm": 0.0017593232914805412,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.08040201005025126,
      "grad_norm": 0.001999079715460539,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.08542713567839195,
      "grad_norm": 0.0017273002304136753,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.09045226130653267,
      "grad_norm": 0.0015520518645644188,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09547738693467336,
      "grad_norm": 0.0019633998163044453,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.10050251256281408,
      "grad_norm": 0.0010238109389320016,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.10552763819095477,
      "grad_norm": 0.0008244161726906896,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.11055276381909548,
      "grad_norm": 0.0008459144737571478,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.11557788944723618,
      "grad_norm": 0.0006594207370653749,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.12060301507537688,
      "grad_norm": 0.0006014013197273016,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.12562814070351758,
      "grad_norm": 0.00041312165558338165,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.12562814070351758,
      "eval_loss": 4.0785057535686065e-06,
      "eval_runtime": 3.5133,
      "eval_samples_per_second": 14.232,
      "eval_steps_per_second": 3.7,
      "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": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}