{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004214696647208817,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.429393294417634e-05,
      "eval_loss": 0.2198059856891632,
      "eval_runtime": 287.611,
      "eval_samples_per_second": 17.367,
      "eval_steps_per_second": 8.685,
      "step": 1
    },
    {
      "epoch": 0.0004214696647208817,
      "grad_norm": 0.35115545988082886,
      "learning_rate": 5e-05,
      "loss": 0.2027,
      "step": 5
    },
    {
      "epoch": 0.0008429393294417634,
      "grad_norm": 0.3351096510887146,
      "learning_rate": 0.0001,
      "loss": 0.1362,
      "step": 10
    },
    {
      "epoch": 0.0008429393294417634,
      "eval_loss": 0.0437222495675087,
      "eval_runtime": 289.151,
      "eval_samples_per_second": 17.275,
      "eval_steps_per_second": 8.639,
      "step": 10
    },
    {
      "epoch": 0.001264408994162645,
      "grad_norm": 0.03451079502701759,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0148,
      "step": 15
    },
    {
      "epoch": 0.0016858786588835268,
      "grad_norm": 0.009307351894676685,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0014,
      "step": 20
    },
    {
      "epoch": 0.0016858786588835268,
      "eval_loss": 0.0004664006410166621,
      "eval_runtime": 290.7743,
      "eval_samples_per_second": 17.178,
      "eval_steps_per_second": 8.591,
      "step": 20
    },
    {
      "epoch": 0.0021073483236044087,
      "grad_norm": 0.014149535447359085,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0003,
      "step": 25
    },
    {
      "epoch": 0.00252881798832529,
      "grad_norm": 0.0014348478289321065,
      "learning_rate": 5e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.00252881798832529,
      "eval_loss": 7.054233719827607e-05,
      "eval_runtime": 290.7879,
      "eval_samples_per_second": 17.177,
      "eval_steps_per_second": 8.59,
      "step": 30
    },
    {
      "epoch": 0.002950287653046172,
      "grad_norm": 0.0006044543697498739,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0001,
      "step": 35
    },
    {
      "epoch": 0.0033717573177670535,
      "grad_norm": 0.0005318066105246544,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0033717573177670535,
      "eval_loss": 5.269195753498934e-05,
      "eval_runtime": 292.3237,
      "eval_samples_per_second": 17.087,
      "eval_steps_per_second": 8.545,
      "step": 40
    },
    {
      "epoch": 0.0037932269824879354,
      "grad_norm": 0.00021961356105748564,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.004214696647208817,
      "grad_norm": 0.00041368522215634584,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 0.004214696647208817,
      "eval_loss": 5.038717790739611e-05,
      "eval_runtime": 292.2613,
      "eval_samples_per_second": 17.091,
      "eval_steps_per_second": 8.547,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8143665679564800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}