{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 4,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 1.869510531425476,
      "learning_rate": 0.0,
      "loss": 1.6582717895507812,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.4465402364730835,
      "learning_rate": 1e-05,
      "loss": 1.39208984375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.276446580886841,
      "learning_rate": 9.94459753267812e-06,
      "loss": 1.953125,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 2.215484380722046,
      "learning_rate": 9.779754323328192e-06,
      "loss": 1.899658203125,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.9182502031326294,
      "learning_rate": 9.509529358847655e-06,
      "loss": 1.667724609375,
      "step": 5
    },
    {
      "epoch": 0.23809523809523808,
      "eval_loss": 2.453125,
      "eval_runtime": 10.6216,
      "eval_samples_per_second": 0.094,
      "eval_steps_per_second": 0.094,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.0919392108917236,
      "learning_rate": 9.140576474687263e-06,
      "loss": 1.90869140625,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.093019962310791,
      "learning_rate": 8.681980515339464e-06,
      "loss": 1.7752685546875,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.9170184135437012,
      "learning_rate": 8.14503363531613e-06,
      "loss": 1.70947265625,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.925852656364441,
      "learning_rate": 7.5429572488279615e-06,
      "loss": 1.809814453125,
      "step": 9
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 2.390625,
      "eval_runtime": 0.829,
      "eval_samples_per_second": 1.206,
      "eval_steps_per_second": 1.206,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.0689780712127686,
      "learning_rate": 6.890576474687264e-06,
      "loss": 1.87548828125,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 2.0856761932373047,
      "learning_rate": 6.20395509268104e-06,
      "loss": 1.931640625,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.7902768850326538,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.6474609375,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.6947816610336304,
      "learning_rate": 4.796044907318961e-06,
      "loss": 1.75390625,
      "step": 13
    },
    {
      "epoch": 0.6190476190476191,
      "eval_loss": 2.328125,
      "eval_runtime": 0.8257,
      "eval_samples_per_second": 1.211,
      "eval_steps_per_second": 1.211,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.8652945756912231,
      "learning_rate": 4.109423525312738e-06,
      "loss": 1.800048828125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.87651526927948,
      "learning_rate": 3.45704275117204e-06,
      "loss": 1.70166015625,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.8096357583999634,
      "learning_rate": 2.854966364683872e-06,
      "loss": 1.751953125,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.9394772052764893,
      "learning_rate": 2.3180194846605367e-06,
      "loss": 1.868896484375,
      "step": 17
    },
    {
      "epoch": 0.8095238095238095,
      "eval_loss": 2.296875,
      "eval_runtime": 0.8266,
      "eval_samples_per_second": 1.21,
      "eval_steps_per_second": 1.21,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.7789219617843628,
      "learning_rate": 1.8594235253127373e-06,
      "loss": 1.80322265625,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 1.8745474815368652,
      "learning_rate": 1.490470641152345e-06,
      "loss": 1.703369140625,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.7236051559448242,
      "learning_rate": 1.2202456766718092e-06,
      "loss": 1.692138671875,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.77152681350708,
      "learning_rate": 1.0554024673218808e-06,
      "loss": 1.63671875,
      "step": 21
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.28125,
      "eval_runtime": 0.8292,
      "eval_samples_per_second": 1.206,
      "eval_steps_per_second": 1.206,
      "step": 21
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7489904145596416.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}