{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010552085092014182,
  "eval_steps": 63,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.220834036805673e-05,
      "eval_loss": NaN,
      "eval_runtime": 852.9585,
      "eval_samples_per_second": 11.696,
      "eval_steps_per_second": 5.848,
      "step": 1
    },
    {
      "epoch": 0.0004220834036805673,
      "grad_norm": NaN,
      "learning_rate": 0.00019979453927503364,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008441668073611346,
      "grad_norm": NaN,
      "learning_rate": 0.00019815591569910654,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.001266250211041702,
      "grad_norm": NaN,
      "learning_rate": 0.00019490557470106686,
      "loss": 12.0083,
      "step": 30
    },
    {
      "epoch": 0.0016883336147222692,
      "grad_norm": NaN,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.0508,
      "step": 40
    },
    {
      "epoch": 0.0021104170184028364,
      "grad_norm": NaN,
      "learning_rate": 0.00018380881048918405,
      "loss": 3.6852,
      "step": 50
    },
    {
      "epoch": 0.002532500422083404,
      "grad_norm": NaN,
      "learning_rate": 0.00017614459583691346,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.002659125443187574,
      "eval_loss": NaN,
      "eval_runtime": 853.023,
      "eval_samples_per_second": 11.695,
      "eval_steps_per_second": 5.847,
      "step": 63
    },
    {
      "epoch": 0.002954583825763971,
      "grad_norm": NaN,
      "learning_rate": 0.0001672300890261317,
      "loss": 4.186,
      "step": 70
    },
    {
      "epoch": 0.0033766672294445383,
      "grad_norm": NaN,
      "learning_rate": 0.00015721166601221698,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.0037987506331251053,
      "grad_norm": NaN,
      "learning_rate": 0.00014625382902408356,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.004220834036805673,
      "grad_norm": NaN,
      "learning_rate": 0.00013453650544213076,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.00464291744048624,
      "grad_norm": NaN,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.005065000844166808,
      "grad_norm": NaN,
      "learning_rate": 0.00010960230259076818,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.005318250886375148,
      "eval_loss": NaN,
      "eval_runtime": 852.0498,
      "eval_samples_per_second": 11.708,
      "eval_steps_per_second": 5.854,
      "step": 126
    },
    {
      "epoch": 0.005487084247847374,
      "grad_norm": NaN,
      "learning_rate": 9.679484224283449e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.005909167651527942,
      "grad_norm": NaN,
      "learning_rate": 8.404001049666211e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.006331251055208509,
      "grad_norm": NaN,
      "learning_rate": 7.154724133689677e-05,
      "loss": 0.8831,
      "step": 150
    },
    {
      "epoch": 0.006753334458889077,
      "grad_norm": NaN,
      "learning_rate": 5.952166568776062e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.007175417862569644,
      "grad_norm": NaN,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 0.0689,
      "step": 170
    },
    {
      "epoch": 0.007597501266250211,
      "grad_norm": NaN,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.0793,
      "step": 180
    },
    {
      "epoch": 0.007977376329562722,
      "eval_loss": NaN,
      "eval_runtime": 853.2017,
      "eval_samples_per_second": 11.692,
      "eval_steps_per_second": 5.846,
      "step": 189
    },
    {
      "epoch": 0.008019584669930779,
      "grad_norm": NaN,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.008441668073611346,
      "grad_norm": NaN,
      "learning_rate": 1.985863781320435e-05,
      "loss": 0.5067,
      "step": 200
    },
    {
      "epoch": 0.008863751477291912,
      "grad_norm": NaN,
      "learning_rate": 1.286812958766106e-05,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.00928583488097248,
      "grad_norm": NaN,
      "learning_rate": 7.308324265397836e-06,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.009707918284653047,
      "grad_norm": NaN,
      "learning_rate": 3.270513696097055e-06,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.010130001688333615,
      "grad_norm": NaN,
      "learning_rate": 8.209986176753948e-07,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.010552085092014182,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.509693130801152e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}