{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016300582745833164,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016300582745833165,
      "grad_norm": 3.6549901962280273,
      "learning_rate": 2e-05,
      "loss": 3.586,
      "step": 1
    },
    {
      "epoch": 0.00016300582745833165,
      "eval_loss": 3.2658746242523193,
      "eval_runtime": 392.7458,
      "eval_samples_per_second": 6.577,
      "eval_steps_per_second": 3.29,
      "step": 1
    },
    {
      "epoch": 0.0003260116549166633,
      "grad_norm": 2.9929354190826416,
      "learning_rate": 4e-05,
      "loss": 2.7839,
      "step": 2
    },
    {
      "epoch": 0.0004890174823749949,
      "grad_norm": 3.852693796157837,
      "learning_rate": 6e-05,
      "loss": 2.8556,
      "step": 3
    },
    {
      "epoch": 0.0004890174823749949,
      "eval_loss": 3.2514045238494873,
      "eval_runtime": 395.9052,
      "eval_samples_per_second": 6.524,
      "eval_steps_per_second": 3.263,
      "step": 3
    },
    {
      "epoch": 0.0006520233098333266,
      "grad_norm": 3.8177576065063477,
      "learning_rate": 8e-05,
      "loss": 3.585,
      "step": 4
    },
    {
      "epoch": 0.0008150291372916582,
      "grad_norm": 3.3665354251861572,
      "learning_rate": 0.0001,
      "loss": 2.9232,
      "step": 5
    },
    {
      "epoch": 0.0009780349647499898,
      "grad_norm": 3.786716938018799,
      "learning_rate": 0.00012,
      "loss": 3.134,
      "step": 6
    },
    {
      "epoch": 0.0009780349647499898,
      "eval_loss": 3.0616915225982666,
      "eval_runtime": 393.6792,
      "eval_samples_per_second": 6.561,
      "eval_steps_per_second": 3.282,
      "step": 6
    },
    {
      "epoch": 0.0011410407922083214,
      "grad_norm": 3.6726279258728027,
      "learning_rate": 0.00014,
      "loss": 2.8369,
      "step": 7
    },
    {
      "epoch": 0.0013040466196666532,
      "grad_norm": 4.7069878578186035,
      "learning_rate": 0.00016,
      "loss": 3.0418,
      "step": 8
    },
    {
      "epoch": 0.0014670524471249848,
      "grad_norm": 3.8643605709075928,
      "learning_rate": 0.00018,
      "loss": 3.2121,
      "step": 9
    },
    {
      "epoch": 0.0014670524471249848,
      "eval_loss": 2.582195520401001,
      "eval_runtime": 393.9473,
      "eval_samples_per_second": 6.557,
      "eval_steps_per_second": 3.28,
      "step": 9
    },
    {
      "epoch": 0.0016300582745833164,
      "grad_norm": 3.746426820755005,
      "learning_rate": 0.0002,
      "loss": 2.2125,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}