{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002372085300187395,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.74417060037479e-05,
      "eval_loss": 1.785589575767517,
      "eval_runtime": 614.2354,
      "eval_samples_per_second": 14.45,
      "eval_steps_per_second": 7.225,
      "step": 1
    },
    {
      "epoch": 0.00023720853001873946,
      "grad_norm": 18.565052032470703,
      "learning_rate": 5e-05,
      "loss": 7.3014,
      "step": 5
    },
    {
      "epoch": 0.00047441706003747893,
      "grad_norm": 11.056122779846191,
      "learning_rate": 0.0001,
      "loss": 6.3042,
      "step": 10
    },
    {
      "epoch": 0.00047441706003747893,
      "eval_loss": 1.4843670129776,
      "eval_runtime": 616.7874,
      "eval_samples_per_second": 14.391,
      "eval_steps_per_second": 7.195,
      "step": 10
    },
    {
      "epoch": 0.0007116255900562184,
      "grad_norm": 12.173872947692871,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.5322,
      "step": 15
    },
    {
      "epoch": 0.0009488341200749579,
      "grad_norm": 10.90223503112793,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.7847,
      "step": 20
    },
    {
      "epoch": 0.0009488341200749579,
      "eval_loss": 1.3738691806793213,
      "eval_runtime": 615.8096,
      "eval_samples_per_second": 14.414,
      "eval_steps_per_second": 7.207,
      "step": 20
    },
    {
      "epoch": 0.0011860426500936974,
      "grad_norm": 8.575257301330566,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.618,
      "step": 25
    },
    {
      "epoch": 0.0014232511801124368,
      "grad_norm": 8.83657169342041,
      "learning_rate": 5e-05,
      "loss": 5.6481,
      "step": 30
    },
    {
      "epoch": 0.0014232511801124368,
      "eval_loss": 1.3377556800842285,
      "eval_runtime": 616.2304,
      "eval_samples_per_second": 14.404,
      "eval_steps_per_second": 7.202,
      "step": 30
    },
    {
      "epoch": 0.0016604597101311763,
      "grad_norm": 9.329240798950195,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.3622,
      "step": 35
    },
    {
      "epoch": 0.0018976682401499157,
      "grad_norm": 7.63873815536499,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.4219,
      "step": 40
    },
    {
      "epoch": 0.0018976682401499157,
      "eval_loss": 1.3230457305908203,
      "eval_runtime": 617.3808,
      "eval_samples_per_second": 14.377,
      "eval_steps_per_second": 7.188,
      "step": 40
    },
    {
      "epoch": 0.0021348767701686554,
      "grad_norm": 6.972021102905273,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.7516,
      "step": 45
    },
    {
      "epoch": 0.002372085300187395,
      "grad_norm": 8.430161476135254,
      "learning_rate": 0.0,
      "loss": 4.741,
      "step": 50
    },
    {
      "epoch": 0.002372085300187395,
      "eval_loss": 1.3194341659545898,
      "eval_runtime": 616.3452,
      "eval_samples_per_second": 14.401,
      "eval_steps_per_second": 7.201,
      "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": 9771313639981056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}