{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 285,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 6.817053318023682,
      "learning_rate": 3.103448275862069e-06,
      "loss": 1.7184,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 3.1392080783843994,
      "learning_rate": 6.551724137931035e-06,
      "loss": 1.3182,
      "step": 20
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.015719175338745,
      "learning_rate": 1e-05,
      "loss": 1.1251,
      "step": 30
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.9676525592803955,
      "learning_rate": 9.962397672993552e-06,
      "loss": 1.0058,
      "step": 40
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.8632580041885376,
      "learning_rate": 9.850156265972722e-06,
      "loss": 0.9239,
      "step": 50
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.8993644714355469,
      "learning_rate": 9.664963994173695e-06,
      "loss": 0.8924,
      "step": 60
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.7902690172195435,
      "learning_rate": 9.409606321741776e-06,
      "loss": 0.8465,
      "step": 70
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.7192617654800415,
      "learning_rate": 9.08792406575792e-06,
      "loss": 0.8273,
      "step": 80
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.8437436819076538,
      "learning_rate": 8.704755626774796e-06,
      "loss": 0.8021,
      "step": 90
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.7052956819534302,
      "learning_rate": 8.265864214768883e-06,
      "loss": 0.7917,
      "step": 100
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 1.7855916023254395,
      "learning_rate": 7.777851165098012e-06,
      "loss": 0.7887,
      "step": 110
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.0044033527374268,
      "learning_rate": 7.248056648273034e-06,
      "loss": 0.763,
      "step": 120
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 1.8151040077209473,
      "learning_rate": 6.684449266961101e-06,
      "loss": 0.7469,
      "step": 130
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 1.8096654415130615,
      "learning_rate": 6.095506200784349e-06,
      "loss": 0.7253,
      "step": 140
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.7122279405593872,
      "learning_rate": 5.490085701647805e-06,
      "loss": 0.72,
      "step": 150
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 1.7539193630218506,
      "learning_rate": 4.87729385738544e-06,
      "loss": 0.7192,
      "step": 160
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 1.7335082292556763,
      "learning_rate": 4.266347627723192e-06,
      "loss": 0.6983,
      "step": 170
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.573112964630127,
      "learning_rate": 3.6664362126255087e-06,
      "loss": 0.71,
      "step": 180
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.6635979413986206,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.6856,
      "step": 190
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 1.7431310415267944,
      "learning_rate": 2.5355090388510806e-06,
      "loss": 0.6967,
      "step": 200
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.7996807098388672,
      "learning_rate": 2.0215034775378336e-06,
      "loss": 0.6816,
      "step": 210
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 1.960167407989502,
      "learning_rate": 1.5522972763146653e-06,
      "loss": 0.6715,
      "step": 220
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 1.6907997131347656,
      "learning_rate": 1.134947733186315e-06,
      "loss": 0.6711,
      "step": 230
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.6383390426635742,
      "learning_rate": 7.757321737514645e-07,
      "loss": 0.6826,
      "step": 240
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 1.712764859199524,
      "learning_rate": 4.800535343827834e-07,
      "loss": 0.6665,
      "step": 250
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 1.6468104124069214,
      "learning_rate": 2.523590970348166e-07,
      "loss": 0.6751,
      "step": 260
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.5951693058013916,
      "learning_rate": 9.607359798384785e-08,
      "loss": 0.6582,
      "step": 270
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 1.599989891052246,
      "learning_rate": 1.3547716606548967e-08,
      "loss": 0.6676,
      "step": 280
    },
    {
      "epoch": 1.0,
      "step": 285,
      "total_flos": 2.5900842583955866e+17,
      "train_loss": 0.8155809151498895,
      "train_runtime": 632.1431,
      "train_samples_per_second": 57.644,
      "train_steps_per_second": 0.451
    }
  ],
  "logging_steps": 10,
  "max_steps": 285,
  "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": 2.5900842583955866e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}