{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4708097928436911,
  "eval_steps": 63,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018832391713747645,
      "eval_loss": 0.7905556559562683,
      "eval_runtime": 6.9905,
      "eval_samples_per_second": 16.022,
      "eval_steps_per_second": 8.011,
      "step": 1
    },
    {
      "epoch": 0.018832391713747645,
      "grad_norm": 0.7901492118835449,
      "learning_rate": 0.00019979453927503364,
      "loss": 0.6816,
      "step": 10
    },
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 0.40178900957107544,
      "learning_rate": 0.00019815591569910654,
      "loss": 0.4805,
      "step": 20
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 0.5106184482574463,
      "learning_rate": 0.00019490557470106686,
      "loss": 0.4685,
      "step": 30
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 0.49268558621406555,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.4709,
      "step": 40
    },
    {
      "epoch": 0.09416195856873823,
      "grad_norm": 0.4141705632209778,
      "learning_rate": 0.00018380881048918405,
      "loss": 0.4638,
      "step": 50
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.410208135843277,
      "learning_rate": 0.00017614459583691346,
      "loss": 0.3985,
      "step": 60
    },
    {
      "epoch": 0.11864406779661017,
      "eval_loss": 0.4390982985496521,
      "eval_runtime": 6.0034,
      "eval_samples_per_second": 18.656,
      "eval_steps_per_second": 9.328,
      "step": 63
    },
    {
      "epoch": 0.1318267419962335,
      "grad_norm": 0.7335411310195923,
      "learning_rate": 0.0001672300890261317,
      "loss": 0.4612,
      "step": 70
    },
    {
      "epoch": 0.15065913370998116,
      "grad_norm": 0.48060673475265503,
      "learning_rate": 0.00015721166601221698,
      "loss": 0.4036,
      "step": 80
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.3535134196281433,
      "learning_rate": 0.00014625382902408356,
      "loss": 0.4005,
      "step": 90
    },
    {
      "epoch": 0.18832391713747645,
      "grad_norm": 0.3984243869781494,
      "learning_rate": 0.00013453650544213076,
      "loss": 0.4554,
      "step": 100
    },
    {
      "epoch": 0.2071563088512241,
      "grad_norm": 0.4779428541660309,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.4137,
      "step": 110
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.4857834577560425,
      "learning_rate": 0.00010960230259076818,
      "loss": 0.4406,
      "step": 120
    },
    {
      "epoch": 0.23728813559322035,
      "eval_loss": 0.4128398299217224,
      "eval_runtime": 5.9848,
      "eval_samples_per_second": 18.714,
      "eval_steps_per_second": 9.357,
      "step": 126
    },
    {
      "epoch": 0.2448210922787194,
      "grad_norm": 0.40318259596824646,
      "learning_rate": 9.679484224283449e-05,
      "loss": 0.4051,
      "step": 130
    },
    {
      "epoch": 0.263653483992467,
      "grad_norm": 0.37790176272392273,
      "learning_rate": 8.404001049666211e-05,
      "loss": 0.4071,
      "step": 140
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 0.5717161893844604,
      "learning_rate": 7.154724133689677e-05,
      "loss": 0.4225,
      "step": 150
    },
    {
      "epoch": 0.3013182674199623,
      "grad_norm": 0.4312959313392639,
      "learning_rate": 5.952166568776062e-05,
      "loss": 0.3938,
      "step": 160
    },
    {
      "epoch": 0.32015065913371,
      "grad_norm": 0.44728565216064453,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 0.3668,
      "step": 170
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.36283445358276367,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.4178,
      "step": 180
    },
    {
      "epoch": 0.3559322033898305,
      "eval_loss": 0.3976288139820099,
      "eval_runtime": 5.9895,
      "eval_samples_per_second": 18.7,
      "eval_steps_per_second": 9.35,
      "step": 189
    },
    {
      "epoch": 0.3578154425612053,
      "grad_norm": 0.40222638845443726,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 0.3894,
      "step": 190
    },
    {
      "epoch": 0.3766478342749529,
      "grad_norm": 0.3540307283401489,
      "learning_rate": 1.985863781320435e-05,
      "loss": 0.4443,
      "step": 200
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 0.4166598320007324,
      "learning_rate": 1.286812958766106e-05,
      "loss": 0.3663,
      "step": 210
    },
    {
      "epoch": 0.4143126177024482,
      "grad_norm": 0.5152053236961365,
      "learning_rate": 7.308324265397836e-06,
      "loss": 0.3393,
      "step": 220
    },
    {
      "epoch": 0.4331450094161959,
      "grad_norm": 0.3762021064758301,
      "learning_rate": 3.270513696097055e-06,
      "loss": 0.3951,
      "step": 230
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.39529839158058167,
      "learning_rate": 8.209986176753948e-07,
      "loss": 0.3999,
      "step": 240
    },
    {
      "epoch": 0.4708097928436911,
      "grad_norm": 0.5087373852729797,
      "learning_rate": 0.0,
      "loss": 0.4061,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8219503632384e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}