{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6028636021100227,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024114544084400905,
      "grad_norm": 12.853450775146484,
      "learning_rate": 5e-05,
      "loss": 18.202,
      "step": 1
    },
    {
      "epoch": 0.024114544084400905,
      "eval_loss": 17.88939666748047,
      "eval_runtime": 1.1457,
      "eval_samples_per_second": 43.643,
      "eval_steps_per_second": 11.347,
      "step": 1
    },
    {
      "epoch": 0.04822908816880181,
      "grad_norm": 12.898941993713379,
      "learning_rate": 0.0001,
      "loss": 18.0174,
      "step": 2
    },
    {
      "epoch": 0.07234363225320271,
      "grad_norm": 13.988131523132324,
      "learning_rate": 9.990365154573717e-05,
      "loss": 17.5915,
      "step": 3
    },
    {
      "epoch": 0.09645817633760362,
      "grad_norm": 21.47568130493164,
      "learning_rate": 9.961501876182148e-05,
      "loss": 15.9516,
      "step": 4
    },
    {
      "epoch": 0.12057272042200452,
      "grad_norm": 31.15035629272461,
      "learning_rate": 9.913533761814537e-05,
      "loss": 14.0236,
      "step": 5
    },
    {
      "epoch": 0.14468726450640543,
      "grad_norm": 32.609195709228516,
      "learning_rate": 9.846666218300807e-05,
      "loss": 12.3079,
      "step": 6
    },
    {
      "epoch": 0.16880180859080632,
      "grad_norm": 33.13249588012695,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.6888,
      "step": 7
    },
    {
      "epoch": 0.19291635267520724,
      "grad_norm": 33.3653450012207,
      "learning_rate": 9.657457896300791e-05,
      "loss": 9.2295,
      "step": 8
    },
    {
      "epoch": 0.21703089675960813,
      "grad_norm": 31.56165313720703,
      "learning_rate": 9.535927336897098e-05,
      "loss": 8.028,
      "step": 9
    },
    {
      "epoch": 0.24114544084400905,
      "grad_norm": 26.991592407226562,
      "learning_rate": 9.397114317029975e-05,
      "loss": 6.9241,
      "step": 10
    },
    {
      "epoch": 0.26525998492840996,
      "grad_norm": 31.015859603881836,
      "learning_rate": 9.241613255361455e-05,
      "loss": 5.9948,
      "step": 11
    },
    {
      "epoch": 0.28937452901281085,
      "grad_norm": 42.92523193359375,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.8584,
      "step": 12
    },
    {
      "epoch": 0.31348907309721175,
      "grad_norm": 54.43761444091797,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.4654,
      "step": 13
    },
    {
      "epoch": 0.33760361718161264,
      "grad_norm": 37.214935302734375,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.132,
      "step": 14
    },
    {
      "epoch": 0.3617181612660136,
      "grad_norm": 20.878231048583984,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.3045,
      "step": 15
    },
    {
      "epoch": 0.3858327053504145,
      "grad_norm": 6.039570331573486,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.9199,
      "step": 16
    },
    {
      "epoch": 0.40994724943481536,
      "grad_norm": 2.416555166244507,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.7876,
      "step": 17
    },
    {
      "epoch": 0.43406179351921625,
      "grad_norm": 1.814249873161316,
      "learning_rate": 7.75e-05,
      "loss": 0.7597,
      "step": 18
    },
    {
      "epoch": 0.4581763376036172,
      "grad_norm": 2.3626012802124023,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.7374,
      "step": 19
    },
    {
      "epoch": 0.4822908816880181,
      "grad_norm": 1.6917897462844849,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.7166,
      "step": 20
    },
    {
      "epoch": 0.506405425772419,
      "grad_norm": 0.8339031338691711,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.6961,
      "step": 21
    },
    {
      "epoch": 0.5305199698568199,
      "grad_norm": 1.4751001596450806,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.7014,
      "step": 22
    },
    {
      "epoch": 0.5546345139412208,
      "grad_norm": 2.256863832473755,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.7286,
      "step": 23
    },
    {
      "epoch": 0.5787490580256217,
      "grad_norm": 2.8666281700134277,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.7385,
      "step": 24
    },
    {
      "epoch": 0.6028636021100227,
      "grad_norm": 1.928024411201477,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.7182,
      "step": 25
    },
    {
      "epoch": 0.6028636021100227,
      "eval_loss": 0.7318603992462158,
      "eval_runtime": 1.1476,
      "eval_samples_per_second": 43.57,
      "eval_steps_per_second": 11.328,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.29768176943104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}