{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999066044029353,
  "eval_steps": 500,
  "global_step": 234,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04269513008672448,
      "grad_norm": 2.6684887191049826,
      "learning_rate": 9.999516923531906e-06,
      "loss": 1.0656,
      "step": 10
    },
    {
      "epoch": 0.08539026017344896,
      "grad_norm": 1.946006163799421,
      "learning_rate": 9.94166060990718e-06,
      "loss": 0.9639,
      "step": 20
    },
    {
      "epoch": 0.12808539026017346,
      "grad_norm": 2.135334096726232,
      "learning_rate": 9.788468426444968e-06,
      "loss": 0.9299,
      "step": 30
    },
    {
      "epoch": 0.17078052034689792,
      "grad_norm": 2.1888584544569722,
      "learning_rate": 9.542895798702702e-06,
      "loss": 0.9412,
      "step": 40
    },
    {
      "epoch": 0.2134756504336224,
      "grad_norm": 1.9868402856495835,
      "learning_rate": 9.209680381068698e-06,
      "loss": 0.9209,
      "step": 50
    },
    {
      "epoch": 0.2561707805203469,
      "grad_norm": 2.102655697602942,
      "learning_rate": 8.795250656636207e-06,
      "loss": 0.9003,
      "step": 60
    },
    {
      "epoch": 0.2988659106070714,
      "grad_norm": 1.9826269424949003,
      "learning_rate": 8.30760191714706e-06,
      "loss": 0.9108,
      "step": 70
    },
    {
      "epoch": 0.34156104069379584,
      "grad_norm": 1.9933280995797364,
      "learning_rate": 7.75614201563372e-06,
      "loss": 0.8927,
      "step": 80
    },
    {
      "epoch": 0.3842561707805203,
      "grad_norm": 1.9585442421548411,
      "learning_rate": 7.1515098675421125e-06,
      "loss": 0.8832,
      "step": 90
    },
    {
      "epoch": 0.4269513008672448,
      "grad_norm": 1.799203130126713,
      "learning_rate": 6.50537020186121e-06,
      "loss": 0.9115,
      "step": 100
    },
    {
      "epoch": 0.4696464309539693,
      "grad_norm": 1.9010281711566903,
      "learning_rate": 5.830188521976794e-06,
      "loss": 0.8754,
      "step": 110
    },
    {
      "epoch": 0.5123415610406938,
      "grad_norm": 1.8562212696724616,
      "learning_rate": 5.1389906177662705e-06,
      "loss": 0.8855,
      "step": 120
    },
    {
      "epoch": 0.5550366911274183,
      "grad_norm": 1.706613487203547,
      "learning_rate": 4.4451112684930424e-06,
      "loss": 0.8842,
      "step": 130
    },
    {
      "epoch": 0.5977318212141428,
      "grad_norm": 1.88229629741251,
      "learning_rate": 3.7619369845930195e-06,
      "loss": 0.8982,
      "step": 140
    },
    {
      "epoch": 0.6404269513008672,
      "grad_norm": 1.6721435452363316,
      "learning_rate": 3.102647751449174e-06,
      "loss": 0.8964,
      "step": 150
    },
    {
      "epoch": 0.6831220813875917,
      "grad_norm": 1.8653475170240106,
      "learning_rate": 2.4799627575040014e-06,
      "loss": 0.8797,
      "step": 160
    },
    {
      "epoch": 0.7258172114743162,
      "grad_norm": 1.722742554654972,
      "learning_rate": 1.90589501219273e-06,
      "loss": 0.8681,
      "step": 170
    },
    {
      "epoch": 0.7685123415610406,
      "grad_norm": 1.791072390996306,
      "learning_rate": 1.3915195876753495e-06,
      "loss": 0.8865,
      "step": 180
    },
    {
      "epoch": 0.8112074716477652,
      "grad_norm": 1.5310513104275707,
      "learning_rate": 9.467599555114137e-07,
      "loss": 0.8728,
      "step": 190
    },
    {
      "epoch": 0.8539026017344896,
      "grad_norm": 1.6358652689401452,
      "learning_rate": 5.801965403290221e-07,
      "loss": 0.8748,
      "step": 200
    },
    {
      "epoch": 0.8965977318212142,
      "grad_norm": 1.5118489110770934,
      "learning_rate": 2.9890118392300493e-07,
      "loss": 0.8737,
      "step": 210
    },
    {
      "epoch": 0.9392928619079386,
      "grad_norm": 1.7168852460490818,
      "learning_rate": 1.0830071334628655e-07,
      "loss": 0.8662,
      "step": 220
    },
    {
      "epoch": 0.9819879919946631,
      "grad_norm": 1.6143069955493654,
      "learning_rate": 1.2072245076156786e-08,
      "loss": 0.8602,
      "step": 230
    }
  ],
  "logging_steps": 10,
  "max_steps": 234,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 25657518981120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}