{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.504424778761062,
  "eval_steps": 500,
  "global_step": 170,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.8676792979240417,
      "learning_rate": 9.91645696388268e-05,
      "loss": 1.6736,
      "step": 10
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 1.35064697265625,
      "learning_rate": 9.665301848904975e-05,
      "loss": 1.1231,
      "step": 20
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 1.436787486076355,
      "learning_rate": 9.255088935784784e-05,
      "loss": 1.0192,
      "step": 30
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.7928199172019958,
      "learning_rate": 8.699803935381485e-05,
      "loss": 0.8938,
      "step": 40
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 1.052542805671692,
      "learning_rate": 8.018378615106108e-05,
      "loss": 0.9706,
      "step": 50
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 1.4108525514602661,
      "learning_rate": 7.23404534331376e-05,
      "loss": 0.8909,
      "step": 60
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 1.1198198795318604,
      "learning_rate": 6.373545009932168e-05,
      "loss": 0.8943,
      "step": 70
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.9904882907867432,
      "learning_rate": 5.466215328310079e-05,
      "loss": 0.873,
      "step": 80
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 1.4658399820327759,
      "learning_rate": 4.542990601526297e-05,
      "loss": 0.8852,
      "step": 90
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 1.0678004026412964,
      "learning_rate": 3.635347054911746e-05,
      "loss": 0.8028,
      "step": 100
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 1.1287755966186523,
      "learning_rate": 2.774229692390805e-05,
      "loss": 0.7924,
      "step": 110
    },
    {
      "epoch": 1.0619469026548674,
      "grad_norm": 0.9173304438591003,
      "learning_rate": 1.9889972641710248e-05,
      "loss": 0.7311,
      "step": 120
    },
    {
      "epoch": 1.1504424778761062,
      "grad_norm": 0.9768574833869934,
      "learning_rate": 1.3064213158260386e-05,
      "loss": 0.7295,
      "step": 130
    },
    {
      "epoch": 1.238938053097345,
      "grad_norm": 1.0783871412277222,
      "learning_rate": 7.497734449769639e-06,
      "loss": 0.7283,
      "step": 140
    },
    {
      "epoch": 1.3274336283185841,
      "grad_norm": 0.9281437993049622,
      "learning_rate": 3.380318844467728e-06,
      "loss": 0.7425,
      "step": 150
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.9174750447273254,
      "learning_rate": 8.523446247096445e-07,
      "loss": 0.7629,
      "step": 160
    },
    {
      "epoch": 1.504424778761062,
      "grad_norm": 1.350212812423706,
      "learning_rate": 0.0,
      "loss": 0.6129,
      "step": 170
    },
    {
      "epoch": 1.504424778761062,
      "step": 170,
      "total_flos": 8891638258335744.0,
      "train_loss": 0.8897645473480225,
      "train_runtime": 144.6489,
      "train_samples_per_second": 9.333,
      "train_steps_per_second": 1.175
    }
  ],
  "logging_steps": 10,
  "max_steps": 170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 8891638258335744.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}