{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026481297583581596,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000264812975835816,
      "grad_norm": 1.0533369779586792,
      "learning_rate": 2e-05,
      "loss": 1.503,
      "step": 1
    },
    {
      "epoch": 0.000264812975835816,
      "eval_loss": 1.7694463729858398,
      "eval_runtime": 53.5621,
      "eval_samples_per_second": 29.685,
      "eval_steps_per_second": 14.843,
      "step": 1
    },
    {
      "epoch": 0.000529625951671632,
      "grad_norm": 1.5920908451080322,
      "learning_rate": 4e-05,
      "loss": 1.8616,
      "step": 2
    },
    {
      "epoch": 0.0007944389275074479,
      "grad_norm": 1.2321345806121826,
      "learning_rate": 6e-05,
      "loss": 1.8369,
      "step": 3
    },
    {
      "epoch": 0.0007944389275074479,
      "eval_loss": 1.7619702816009521,
      "eval_runtime": 53.4509,
      "eval_samples_per_second": 29.747,
      "eval_steps_per_second": 14.873,
      "step": 3
    },
    {
      "epoch": 0.001059251903343264,
      "grad_norm": 1.188199520111084,
      "learning_rate": 8e-05,
      "loss": 1.8216,
      "step": 4
    },
    {
      "epoch": 0.0013240648791790798,
      "grad_norm": 1.0517092943191528,
      "learning_rate": 0.0001,
      "loss": 1.6233,
      "step": 5
    },
    {
      "epoch": 0.0015888778550148957,
      "grad_norm": 1.5111111402511597,
      "learning_rate": 0.00012,
      "loss": 1.6716,
      "step": 6
    },
    {
      "epoch": 0.0015888778550148957,
      "eval_loss": 1.6626200675964355,
      "eval_runtime": 53.5065,
      "eval_samples_per_second": 29.716,
      "eval_steps_per_second": 14.858,
      "step": 6
    },
    {
      "epoch": 0.0018536908308507116,
      "grad_norm": 1.8593997955322266,
      "learning_rate": 0.00014,
      "loss": 1.8786,
      "step": 7
    },
    {
      "epoch": 0.002118503806686528,
      "grad_norm": 1.5864779949188232,
      "learning_rate": 0.00016,
      "loss": 1.4044,
      "step": 8
    },
    {
      "epoch": 0.0023833167825223437,
      "grad_norm": 1.2885961532592773,
      "learning_rate": 0.00018,
      "loss": 1.2005,
      "step": 9
    },
    {
      "epoch": 0.0023833167825223437,
      "eval_loss": 1.2594659328460693,
      "eval_runtime": 53.4821,
      "eval_samples_per_second": 29.73,
      "eval_steps_per_second": 14.865,
      "step": 9
    },
    {
      "epoch": 0.0026481297583581596,
      "grad_norm": 1.5632855892181396,
      "learning_rate": 0.0002,
      "loss": 1.3065,
      "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": 820048664985600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}