{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003713330857779428,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003713330857779428,
      "grad_norm": 0.9048739671707153,
      "learning_rate": 2e-05,
      "loss": 1.6929,
      "step": 1
    },
    {
      "epoch": 0.0003713330857779428,
      "eval_loss": 0.41446250677108765,
      "eval_runtime": 84.0088,
      "eval_samples_per_second": 13.499,
      "eval_steps_per_second": 6.749,
      "step": 1
    },
    {
      "epoch": 0.0007426661715558856,
      "grad_norm": 1.0262705087661743,
      "learning_rate": 4e-05,
      "loss": 1.5191,
      "step": 2
    },
    {
      "epoch": 0.0011139992573338284,
      "grad_norm": 1.5031936168670654,
      "learning_rate": 6e-05,
      "loss": 2.5841,
      "step": 3
    },
    {
      "epoch": 0.0011139992573338284,
      "eval_loss": 0.4126916229724884,
      "eval_runtime": 83.9214,
      "eval_samples_per_second": 13.513,
      "eval_steps_per_second": 6.756,
      "step": 3
    },
    {
      "epoch": 0.0014853323431117712,
      "grad_norm": 0.9208312630653381,
      "learning_rate": 8e-05,
      "loss": 1.4263,
      "step": 4
    },
    {
      "epoch": 0.001856665428889714,
      "grad_norm": 1.0679188966751099,
      "learning_rate": 0.0001,
      "loss": 1.3681,
      "step": 5
    },
    {
      "epoch": 0.0022279985146676567,
      "grad_norm": 1.2294297218322754,
      "learning_rate": 0.00012,
      "loss": 1.537,
      "step": 6
    },
    {
      "epoch": 0.0022279985146676567,
      "eval_loss": 0.3838834762573242,
      "eval_runtime": 84.289,
      "eval_samples_per_second": 13.454,
      "eval_steps_per_second": 6.727,
      "step": 6
    },
    {
      "epoch": 0.0025993316004456,
      "grad_norm": 1.6782110929489136,
      "learning_rate": 0.00014,
      "loss": 1.617,
      "step": 7
    },
    {
      "epoch": 0.0029706646862235424,
      "grad_norm": 1.534745693206787,
      "learning_rate": 0.00016,
      "loss": 1.1142,
      "step": 8
    },
    {
      "epoch": 0.0033419977720014855,
      "grad_norm": 1.9831204414367676,
      "learning_rate": 0.00018,
      "loss": 1.2442,
      "step": 9
    },
    {
      "epoch": 0.0033419977720014855,
      "eval_loss": 0.2274419665336609,
      "eval_runtime": 84.2778,
      "eval_samples_per_second": 13.455,
      "eval_steps_per_second": 6.728,
      "step": 9
    },
    {
      "epoch": 0.003713330857779428,
      "grad_norm": 2.1001076698303223,
      "learning_rate": 0.0002,
      "loss": 0.968,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1628749242040320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}