{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0122684333210649,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000245368666421298,
      "eval_loss": 11.092495918273926,
      "eval_runtime": 12.3883,
      "eval_samples_per_second": 138.517,
      "eval_steps_per_second": 69.259,
      "step": 1
    },
    {
      "epoch": 0.00122684333210649,
      "grad_norm": 1.5610966682434082,
      "learning_rate": 5e-05,
      "loss": 44.3726,
      "step": 5
    },
    {
      "epoch": 0.00245368666421298,
      "grad_norm": 1.5065815448760986,
      "learning_rate": 0.0001,
      "loss": 44.3545,
      "step": 10
    },
    {
      "epoch": 0.00245368666421298,
      "eval_loss": 11.080097198486328,
      "eval_runtime": 11.7561,
      "eval_samples_per_second": 145.967,
      "eval_steps_per_second": 72.984,
      "step": 10
    },
    {
      "epoch": 0.00368052999631947,
      "grad_norm": 1.7398407459259033,
      "learning_rate": 9.619397662556435e-05,
      "loss": 44.2979,
      "step": 15
    },
    {
      "epoch": 0.00490737332842596,
      "grad_norm": 1.786850094795227,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.2341,
      "step": 20
    },
    {
      "epoch": 0.00490737332842596,
      "eval_loss": 11.046628952026367,
      "eval_runtime": 11.8282,
      "eval_samples_per_second": 145.078,
      "eval_steps_per_second": 72.539,
      "step": 20
    },
    {
      "epoch": 0.00613421666053245,
      "grad_norm": 1.8840152025222778,
      "learning_rate": 6.91341716182545e-05,
      "loss": 44.1891,
      "step": 25
    },
    {
      "epoch": 0.00736105999263894,
      "grad_norm": 1.9868003129959106,
      "learning_rate": 5e-05,
      "loss": 44.0932,
      "step": 30
    },
    {
      "epoch": 0.00736105999263894,
      "eval_loss": 11.0152587890625,
      "eval_runtime": 11.883,
      "eval_samples_per_second": 144.408,
      "eval_steps_per_second": 72.204,
      "step": 30
    },
    {
      "epoch": 0.00858790332474543,
      "grad_norm": 2.558466911315918,
      "learning_rate": 3.086582838174551e-05,
      "loss": 44.0055,
      "step": 35
    },
    {
      "epoch": 0.00981474665685192,
      "grad_norm": 2.319875478744507,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 44.0187,
      "step": 40
    },
    {
      "epoch": 0.00981474665685192,
      "eval_loss": 10.99793529510498,
      "eval_runtime": 11.8249,
      "eval_samples_per_second": 145.117,
      "eval_steps_per_second": 72.559,
      "step": 40
    },
    {
      "epoch": 0.01104158998895841,
      "grad_norm": 2.260441780090332,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 43.9902,
      "step": 45
    },
    {
      "epoch": 0.0122684333210649,
      "grad_norm": 2.374315023422241,
      "learning_rate": 0.0,
      "loss": 43.9643,
      "step": 50
    },
    {
      "epoch": 0.0122684333210649,
      "eval_loss": 10.994427680969238,
      "eval_runtime": 11.7619,
      "eval_samples_per_second": 145.895,
      "eval_steps_per_second": 72.948,
      "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": 882499387392.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}