{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.24,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 3366.383771014986,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 50.181,
      "step": 5
    },
    {
      "epoch": 0.8,
      "grad_norm": 138.84039031345438,
      "learning_rate": 7.500000000000001e-06,
      "loss": 9.0003,
      "step": 10
    },
    {
      "epoch": 1.16,
      "grad_norm": 31.069992807592296,
      "learning_rate": 9.814814814814815e-06,
      "loss": 2.0675,
      "step": 15
    },
    {
      "epoch": 1.56,
      "grad_norm": 38.6699521302523,
      "learning_rate": 9.351851851851854e-06,
      "loss": 2.348,
      "step": 20
    },
    {
      "epoch": 1.96,
      "grad_norm": 31.534923460458895,
      "learning_rate": 8.888888888888888e-06,
      "loss": 2.7579,
      "step": 25
    },
    {
      "epoch": 2.32,
      "grad_norm": 35.62793738569212,
      "learning_rate": 8.425925925925926e-06,
      "loss": 2.6538,
      "step": 30
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 43.09111169943847,
      "learning_rate": 7.962962962962963e-06,
      "loss": 3.0774,
      "step": 35
    },
    {
      "epoch": 3.08,
      "grad_norm": 31.55815735622089,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.5569,
      "step": 40
    },
    {
      "epoch": 3.48,
      "grad_norm": 32.987381074140224,
      "learning_rate": 7.0370370370370375e-06,
      "loss": 2.691,
      "step": 45
    },
    {
      "epoch": 3.88,
      "grad_norm": 30.799908902389816,
      "learning_rate": 6.574074074074075e-06,
      "loss": 2.725,
      "step": 50
    },
    {
      "epoch": 4.24,
      "grad_norm": 30.428695432735317,
      "learning_rate": 6.111111111111112e-06,
      "loss": 2.1202,
      "step": 55
    },
    {
      "epoch": 4.64,
      "grad_norm": 29.827204683187425,
      "learning_rate": 5.6481481481481485e-06,
      "loss": 2.3278,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 33.33785124405715,
      "learning_rate": 5.185185185185185e-06,
      "loss": 2.1507,
      "step": 65
    },
    {
      "epoch": 5.4,
      "grad_norm": 25.114796048971975,
      "learning_rate": 4.722222222222222e-06,
      "loss": 2.0327,
      "step": 70
    },
    {
      "epoch": 5.8,
      "grad_norm": 22.363021156501855,
      "learning_rate": 4.2592592592592596e-06,
      "loss": 2.0363,
      "step": 75
    },
    {
      "epoch": 6.16,
      "grad_norm": 27.92963131520657,
      "learning_rate": 3.796296296296297e-06,
      "loss": 1.7444,
      "step": 80
    },
    {
      "epoch": 6.5600000000000005,
      "grad_norm": 24.85153444942929,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.9417,
      "step": 85
    },
    {
      "epoch": 6.96,
      "grad_norm": 24.5998271042858,
      "learning_rate": 2.8703703703703706e-06,
      "loss": 1.9907,
      "step": 90
    },
    {
      "epoch": 7.32,
      "grad_norm": 19.476935749731375,
      "learning_rate": 2.4074074074074075e-06,
      "loss": 1.6776,
      "step": 95
    },
    {
      "epoch": 7.72,
      "grad_norm": 32.61686883093416,
      "learning_rate": 1.944444444444445e-06,
      "loss": 2.0266,
      "step": 100
    },
    {
      "epoch": 8.08,
      "grad_norm": 22.893625227037738,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 1.7539,
      "step": 105
    },
    {
      "epoch": 8.48,
      "grad_norm": 29.10691686568226,
      "learning_rate": 1.0185185185185185e-06,
      "loss": 2.2201,
      "step": 110
    },
    {
      "epoch": 8.88,
      "grad_norm": 25.9922847192214,
      "learning_rate": 5.555555555555555e-07,
      "loss": 1.9925,
      "step": 115
    },
    {
      "epoch": 9.24,
      "grad_norm": 25.22158299607113,
      "learning_rate": 9.259259259259259e-08,
      "loss": 1.8082,
      "step": 120
    },
    {
      "epoch": 9.24,
      "step": 120,
      "total_flos": 0.0,
      "train_loss": 4.495095912615458,
      "train_runtime": 3832.3964,
      "train_samples_per_second": 1.044,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 5,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}