{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.986666666666667,
  "eval_steps": 500,
  "global_step": 168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 7.053971290588379,
      "learning_rate": 4.97273712672844e-06,
      "loss": 0.5704,
      "step": 10
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 5.397775650024414,
      "learning_rate": 4.861084470200228e-06,
      "loss": 0.2394,
      "step": 20
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.6659767627716064,
      "learning_rate": 4.667009949002349e-06,
      "loss": 0.1046,
      "step": 30
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 3.866196870803833,
      "learning_rate": 4.397288409237892e-06,
      "loss": 0.0639,
      "step": 40
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 3.2750980854034424,
      "learning_rate": 4.061335419273658e-06,
      "loss": 0.0841,
      "step": 50
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 2.892080783843994,
      "learning_rate": 3.6708785865814186e-06,
      "loss": 0.1054,
      "step": 60
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 3.0646233558654785,
      "learning_rate": 3.239548164813544e-06,
      "loss": 0.0709,
      "step": 70
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 3.744271755218506,
      "learning_rate": 2.782401242396799e-06,
      "loss": 0.0684,
      "step": 80
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.9203922748565674,
      "learning_rate": 2.3153961224961665e-06,
      "loss": 0.082,
      "step": 90
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 2.8430514335632324,
      "learning_rate": 1.854835242944048e-06,
      "loss": 0.0505,
      "step": 100
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 1.6261467933654785,
      "learning_rate": 1.4167960829520933e-06,
      "loss": 0.0843,
      "step": 110
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 2.9942877292633057,
      "learning_rate": 1.0165699227860215e-06,
      "loss": 0.0642,
      "step": 120
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 1.675881266593933,
      "learning_rate": 6.681280484488576e-07,
      "loss": 0.0684,
      "step": 130
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 5.115616321563721,
      "learning_rate": 3.8363403535449846e-07,
      "loss": 0.0837,
      "step": 140
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 2.429882287979126,
      "learning_rate": 1.7301913642614382e-07,
      "loss": 0.0603,
      "step": 150
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 3.372321128845215,
      "learning_rate": 4.3635597174694347e-08,
      "loss": 0.06,
      "step": 160
    },
    {
      "epoch": 2.986666666666667,
      "step": 168,
      "total_flos": 1.5795369631678464e+16,
      "train_loss": 0.11316087664592833,
      "train_runtime": 355.6972,
      "train_samples_per_second": 7.591,
      "train_steps_per_second": 0.472
    }
  ],
  "logging_steps": 10,
  "max_steps": 168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.5795369631678464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}