{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04024144869215292,
      "grad_norm": 128.68338012695312,
      "learning_rate": 6.34920634920635e-07,
      "loss": 5.7142,
      "step": 5
    },
    {
      "epoch": 0.08048289738430583,
      "grad_norm": 124.65970611572266,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 5.8126,
      "step": 10
    },
    {
      "epoch": 0.12072434607645875,
      "grad_norm": 63.15693664550781,
      "learning_rate": 2.222222222222222e-06,
      "loss": 4.9144,
      "step": 15
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 26.409881591796875,
      "learning_rate": 3.015873015873016e-06,
      "loss": 4.1026,
      "step": 20
    },
    {
      "epoch": 0.2012072434607646,
      "grad_norm": 18.272987365722656,
      "learning_rate": 3.80952380952381e-06,
      "loss": 3.8405,
      "step": 25
    },
    {
      "epoch": 0.2414486921529175,
      "grad_norm": 13.232375144958496,
      "learning_rate": 4.603174603174604e-06,
      "loss": 3.5374,
      "step": 30
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 50.732887268066406,
      "learning_rate": 5.396825396825397e-06,
      "loss": 3.3776,
      "step": 35
    },
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 11.886248588562012,
      "learning_rate": 6.1904761904761914e-06,
      "loss": 3.2729,
      "step": 40
    },
    {
      "epoch": 0.36217303822937624,
      "grad_norm": 12.157098770141602,
      "learning_rate": 6.984126984126984e-06,
      "loss": 3.0134,
      "step": 45
    },
    {
      "epoch": 0.4024144869215292,
      "grad_norm": 11.598234176635742,
      "learning_rate": 7.77777777777778e-06,
      "loss": 2.9235,
      "step": 50
    },
    {
      "epoch": 0.4426559356136821,
      "grad_norm": 11.506558418273926,
      "learning_rate": 8.571428571428571e-06,
      "loss": 2.584,
      "step": 55
    },
    {
      "epoch": 0.482897384305835,
      "grad_norm": 14.368203163146973,
      "learning_rate": 9.365079365079366e-06,
      "loss": 2.4279,
      "step": 60
    },
    {
      "epoch": 0.5231388329979879,
      "grad_norm": 12.335148811340332,
      "learning_rate": 9.999921879324127e-06,
      "loss": 2.244,
      "step": 65
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 17.981578826904297,
      "learning_rate": 9.997187911979252e-06,
      "loss": 2.0648,
      "step": 70
    },
    {
      "epoch": 0.6036217303822937,
      "grad_norm": 12.924208641052246,
      "learning_rate": 9.990550351633784e-06,
      "loss": 2.0333,
      "step": 75
    },
    {
      "epoch": 0.6438631790744467,
      "grad_norm": 36.98970031738281,
      "learning_rate": 9.980014383270668e-06,
      "loss": 1.7114,
      "step": 80
    },
    {
      "epoch": 0.6841046277665996,
      "grad_norm": 11.499068260192871,
      "learning_rate": 9.965588237145219e-06,
      "loss": 1.725,
      "step": 85
    },
    {
      "epoch": 0.7243460764587525,
      "grad_norm": 13.697612762451172,
      "learning_rate": 9.947283182355982e-06,
      "loss": 1.7076,
      "step": 90
    },
    {
      "epoch": 0.7645875251509054,
      "grad_norm": 11.36514663696289,
      "learning_rate": 9.925113518041796e-06,
      "loss": 1.4663,
      "step": 95
    },
    {
      "epoch": 0.8048289738430584,
      "grad_norm": 11.20559024810791,
      "learning_rate": 9.899096562211902e-06,
      "loss": 1.1067,
      "step": 100
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 10.782366752624512,
      "learning_rate": 9.869252638217846e-06,
      "loss": 1.2299,
      "step": 105
    },
    {
      "epoch": 0.8853118712273642,
      "grad_norm": 12.094294548034668,
      "learning_rate": 9.83560505887773e-06,
      "loss": 0.9908,
      "step": 110
    },
    {
      "epoch": 0.9255533199195171,
      "grad_norm": 10.271987915039062,
      "learning_rate": 9.798180108265218e-06,
      "loss": 0.8628,
      "step": 115
    },
    {
      "epoch": 0.96579476861167,
      "grad_norm": 13.298333168029785,
      "learning_rate": 9.757007021177529e-06,
      "loss": 0.7913,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.651159286499023,
      "learning_rate": 9.712117960298433e-06,
      "loss": 0.6121,
      "step": 125
    }
  ],
  "logging_steps": 5,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.553888784102195e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}