{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9747899159663865,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 4.469196166173266,
      "learning_rate": 0.0,
      "loss": 0.889,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 4.365192499514651,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9117,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 3.965699785576992,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.878,
      "step": 3
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 2.2523927807625044,
      "learning_rate": 1e-05,
      "loss": 0.7814,
      "step": 4
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 4.003900590954268,
      "learning_rate": 9.96354437049027e-06,
      "loss": 0.859,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 3.9172213327695036,
      "learning_rate": 9.854709087130261e-06,
      "loss": 0.7727,
      "step": 6
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 3.3484290901238447,
      "learning_rate": 9.675081213427076e-06,
      "loss": 0.6556,
      "step": 7
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 3.0412731911621695,
      "learning_rate": 9.427280128266049e-06,
      "loss": 0.7545,
      "step": 8
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": 1.824318016038074,
      "learning_rate": 9.114919329468283e-06,
      "loss": 0.6364,
      "step": 9
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 1.4055884613148466,
      "learning_rate": 8.742553740855507e-06,
      "loss": 0.6121,
      "step": 10
    },
    {
      "epoch": 0.3697478991596639,
      "grad_norm": 1.6529134782337978,
      "learning_rate": 8.315613291203977e-06,
      "loss": 0.6341,
      "step": 11
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 1.410865474352178,
      "learning_rate": 7.84032373365578e-06,
      "loss": 0.6073,
      "step": 12
    },
    {
      "epoch": 0.4369747899159664,
      "grad_norm": 1.3475768201990301,
      "learning_rate": 7.323615860218844e-06,
      "loss": 0.5754,
      "step": 13
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.231638918744367,
      "learning_rate": 6.773024435212678e-06,
      "loss": 0.6227,
      "step": 14
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 1.3031603882175071,
      "learning_rate": 6.1965783214377895e-06,
      "loss": 0.7014,
      "step": 15
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 1.289342432305298,
      "learning_rate": 5.6026834012766155e-06,
      "loss": 0.5801,
      "step": 16
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.297660868574315,
      "learning_rate": 5e-06,
      "loss": 0.5476,
      "step": 17
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 1.155602860047339,
      "learning_rate": 4.397316598723385e-06,
      "loss": 0.6054,
      "step": 18
    },
    {
      "epoch": 0.6386554621848739,
      "grad_norm": 1.1265443534540045,
      "learning_rate": 3.803421678562213e-06,
      "loss": 0.575,
      "step": 19
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 1.1202857464472886,
      "learning_rate": 3.226975564787322e-06,
      "loss": 0.5674,
      "step": 20
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.2002904858114178,
      "learning_rate": 2.6763841397811576e-06,
      "loss": 0.6012,
      "step": 21
    },
    {
      "epoch": 0.7394957983193278,
      "grad_norm": 1.0836740860048584,
      "learning_rate": 2.159676266344222e-06,
      "loss": 0.5655,
      "step": 22
    },
    {
      "epoch": 0.773109243697479,
      "grad_norm": 1.0370486449910274,
      "learning_rate": 1.6843867087960252e-06,
      "loss": 0.5576,
      "step": 23
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 0.972526640027234,
      "learning_rate": 1.257446259144494e-06,
      "loss": 0.5328,
      "step": 24
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 1.047736836683075,
      "learning_rate": 8.850806705317183e-07,
      "loss": 0.5591,
      "step": 25
    },
    {
      "epoch": 0.8739495798319328,
      "grad_norm": 1.0682305380809587,
      "learning_rate": 5.727198717339511e-07,
      "loss": 0.5739,
      "step": 26
    },
    {
      "epoch": 0.907563025210084,
      "grad_norm": 1.0211661595553563,
      "learning_rate": 3.2491878657292643e-07,
      "loss": 0.5883,
      "step": 27
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.8985589898304817,
      "learning_rate": 1.4529091286973994e-07,
      "loss": 0.5539,
      "step": 28
    },
    {
      "epoch": 0.9747899159663865,
      "grad_norm": 0.97842043850681,
      "learning_rate": 3.645562950973014e-08,
      "loss": 0.6418,
      "step": 29
    },
    {
      "epoch": 0.9747899159663865,
      "step": 29,
      "total_flos": 3973377679360.0,
      "train_loss": 0.6531299044345987,
      "train_runtime": 453.7926,
      "train_samples_per_second": 2.098,
      "train_steps_per_second": 0.064
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3973377679360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}