{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10552975939214859,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005276487969607429,
      "grad_norm": 0.6827425360679626,
      "learning_rate": 2.9947235120303926e-05,
      "loss": 2.207,
      "step": 50
    },
    {
      "epoch": 0.010552975939214858,
      "grad_norm": 0.5957860350608826,
      "learning_rate": 2.989447024060785e-05,
      "loss": 0.2398,
      "step": 100
    },
    {
      "epoch": 0.015829463908822287,
      "grad_norm": 0.46854081749916077,
      "learning_rate": 2.9841705360911777e-05,
      "loss": 0.0525,
      "step": 150
    },
    {
      "epoch": 0.021105951878429716,
      "grad_norm": 0.10302311927080154,
      "learning_rate": 2.9788940481215702e-05,
      "loss": 0.0037,
      "step": 200
    },
    {
      "epoch": 0.026382439848037148,
      "grad_norm": 0.01405419036746025,
      "learning_rate": 2.9736175601519628e-05,
      "loss": 0.001,
      "step": 250
    },
    {
      "epoch": 0.031658927817644573,
      "grad_norm": 0.12790632247924805,
      "learning_rate": 2.9683410721823553e-05,
      "loss": 0.0007,
      "step": 300
    },
    {
      "epoch": 0.036935415787252006,
      "grad_norm": 0.0026043676771223545,
      "learning_rate": 2.9630645842127478e-05,
      "loss": 0.0004,
      "step": 350
    },
    {
      "epoch": 0.04221190375685943,
      "grad_norm": 0.030596332624554634,
      "learning_rate": 2.9577880962431404e-05,
      "loss": 0.0016,
      "step": 400
    },
    {
      "epoch": 0.047488391726466864,
      "grad_norm": 0.04252925142645836,
      "learning_rate": 2.952511608273533e-05,
      "loss": 0.0008,
      "step": 450
    },
    {
      "epoch": 0.052764879696074296,
      "grad_norm": 0.03828505799174309,
      "learning_rate": 2.947235120303926e-05,
      "loss": 0.0003,
      "step": 500
    },
    {
      "epoch": 0.05804136766568172,
      "grad_norm": 0.006123501807451248,
      "learning_rate": 2.9419586323343186e-05,
      "loss": 0.0004,
      "step": 550
    },
    {
      "epoch": 0.06331785563528915,
      "grad_norm": 0.0026047523133456707,
      "learning_rate": 2.9366821443647112e-05,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 0.06859434360489658,
      "grad_norm": 0.0018419412663206458,
      "learning_rate": 2.9314056563951037e-05,
      "loss": 0.0002,
      "step": 650
    },
    {
      "epoch": 0.07387083157450401,
      "grad_norm": 0.03250932693481445,
      "learning_rate": 2.9261291684254962e-05,
      "loss": 0.0009,
      "step": 700
    },
    {
      "epoch": 0.07914731954411144,
      "grad_norm": 0.001018165610730648,
      "learning_rate": 2.9208526804558888e-05,
      "loss": 0.0003,
      "step": 750
    },
    {
      "epoch": 0.08442380751371886,
      "grad_norm": 0.0010480296332389116,
      "learning_rate": 2.9155761924862813e-05,
      "loss": 0.0002,
      "step": 800
    },
    {
      "epoch": 0.0897002954833263,
      "grad_norm": 0.000887015659827739,
      "learning_rate": 2.910299704516674e-05,
      "loss": 0.0001,
      "step": 850
    },
    {
      "epoch": 0.09497678345293373,
      "grad_norm": 0.02170419879257679,
      "learning_rate": 2.9050232165470664e-05,
      "loss": 0.0001,
      "step": 900
    },
    {
      "epoch": 0.10025327142254116,
      "grad_norm": 0.02256314642727375,
      "learning_rate": 2.899746728577459e-05,
      "loss": 0.0002,
      "step": 950
    },
    {
      "epoch": 0.10552975939214859,
      "grad_norm": 0.007039123214781284,
      "learning_rate": 2.8944702406078515e-05,
      "loss": 0.0001,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 28428,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}