{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.4188497066497803,
      "learning_rate": 0.0,
      "loss": 2.4874,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6966615915298462,
      "learning_rate": 4e-05,
      "loss": 2.6618,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8571358919143677,
      "learning_rate": 8e-05,
      "loss": 2.8953,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.701550841331482,
      "learning_rate": 0.00012,
      "loss": 2.5134,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.3071422576904297,
      "learning_rate": 0.00016,
      "loss": 2.8063,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.2974326610565186,
      "learning_rate": 0.0002,
      "loss": 2.1778,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 3.3090689182281494,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.1984,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5245072841644287,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5319,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8647416234016418,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.6248,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.0439573526382446,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1487,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.1243475675582886,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.0713,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6728630661964417,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2753,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.4465005397796631,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0032,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6374929547309875,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9887,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5495445132255554,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.2954,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5156247019767761,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1906,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4463346004486084,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9256,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4280051290988922,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1569,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.43795275688171387,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9857,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3561479449272156,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.2937,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4115261137485504,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0066,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3871329128742218,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1393,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.33028116822242737,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1698,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2790043354034424,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8708,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3371724486351013,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8378,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.34898409247398376,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.1172,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.33062544465065,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9484,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3693927824497223,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0166,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3819218575954437,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0723,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.36232468485832214,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0513,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4624798396956672.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}