{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014044450686422527,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8088901372845056e-05,
      "eval_loss": 10.3773832321167,
      "eval_runtime": 88.7404,
      "eval_samples_per_second": 168.92,
      "eval_steps_per_second": 84.46,
      "step": 1
    },
    {
      "epoch": 0.00014044450686422527,
      "grad_norm": 0.1895916610956192,
      "learning_rate": 5e-05,
      "loss": 41.5126,
      "step": 5
    },
    {
      "epoch": 0.00028088901372845055,
      "grad_norm": 0.19288326799869537,
      "learning_rate": 0.0001,
      "loss": 41.5087,
      "step": 10
    },
    {
      "epoch": 0.00028088901372845055,
      "eval_loss": 10.376968383789062,
      "eval_runtime": 88.129,
      "eval_samples_per_second": 170.092,
      "eval_steps_per_second": 85.046,
      "step": 10
    },
    {
      "epoch": 0.0004213335205926758,
      "grad_norm": 0.288252592086792,
      "learning_rate": 9.619397662556435e-05,
      "loss": 41.5117,
      "step": 15
    },
    {
      "epoch": 0.0005617780274569011,
      "grad_norm": 0.18418413400650024,
      "learning_rate": 8.535533905932738e-05,
      "loss": 41.5029,
      "step": 20
    },
    {
      "epoch": 0.0005617780274569011,
      "eval_loss": 10.376041412353516,
      "eval_runtime": 89.2859,
      "eval_samples_per_second": 167.888,
      "eval_steps_per_second": 83.944,
      "step": 20
    },
    {
      "epoch": 0.0007022225343211264,
      "grad_norm": 0.22784556448459625,
      "learning_rate": 6.91341716182545e-05,
      "loss": 41.5063,
      "step": 25
    },
    {
      "epoch": 0.0008426670411853516,
      "grad_norm": 0.27184101939201355,
      "learning_rate": 5e-05,
      "loss": 41.5015,
      "step": 30
    },
    {
      "epoch": 0.0008426670411853516,
      "eval_loss": 10.375298500061035,
      "eval_runtime": 89.91,
      "eval_samples_per_second": 166.722,
      "eval_steps_per_second": 83.361,
      "step": 30
    },
    {
      "epoch": 0.000983111548049577,
      "grad_norm": 0.3025659918785095,
      "learning_rate": 3.086582838174551e-05,
      "loss": 41.5005,
      "step": 35
    },
    {
      "epoch": 0.0011235560549138022,
      "grad_norm": 0.2809828221797943,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 41.4964,
      "step": 40
    },
    {
      "epoch": 0.0011235560549138022,
      "eval_loss": 10.374896049499512,
      "eval_runtime": 89.844,
      "eval_samples_per_second": 166.845,
      "eval_steps_per_second": 83.422,
      "step": 40
    },
    {
      "epoch": 0.0012640005617780275,
      "grad_norm": 0.2692044675350189,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 41.4948,
      "step": 45
    },
    {
      "epoch": 0.0014044450686422527,
      "grad_norm": 0.3889637589454651,
      "learning_rate": 0.0,
      "loss": 41.507,
      "step": 50
    },
    {
      "epoch": 0.0014044450686422527,
      "eval_loss": 10.374822616577148,
      "eval_runtime": 87.3375,
      "eval_samples_per_second": 171.633,
      "eval_steps_per_second": 85.817,
      "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": 2220006506496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}