{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17742293191394987,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035484586382789974,
      "eval_loss": 2.0277860164642334,
      "eval_runtime": 55.6569,
      "eval_samples_per_second": 8.534,
      "eval_steps_per_second": 4.276,
      "step": 1
    },
    {
      "epoch": 0.03548458638278998,
      "grad_norm": 2.4754116535186768,
      "learning_rate": 2e-05,
      "loss": 1.8844,
      "step": 10
    },
    {
      "epoch": 0.03548458638278998,
      "eval_loss": 2.014612913131714,
      "eval_runtime": 55.0772,
      "eval_samples_per_second": 8.624,
      "eval_steps_per_second": 4.321,
      "step": 10
    },
    {
      "epoch": 0.07096917276557996,
      "grad_norm": 2.697735071182251,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 1.7786,
      "step": 20
    },
    {
      "epoch": 0.07096917276557996,
      "eval_loss": 1.9640275239944458,
      "eval_runtime": 55.1732,
      "eval_samples_per_second": 8.609,
      "eval_steps_per_second": 4.314,
      "step": 20
    },
    {
      "epoch": 0.10645375914836992,
      "grad_norm": 2.7320609092712402,
      "learning_rate": 1e-05,
      "loss": 1.7021,
      "step": 30
    },
    {
      "epoch": 0.10645375914836992,
      "eval_loss": 1.9071805477142334,
      "eval_runtime": 55.0911,
      "eval_samples_per_second": 8.622,
      "eval_steps_per_second": 4.32,
      "step": 30
    },
    {
      "epoch": 0.14193834553115992,
      "grad_norm": 3.545992612838745,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 1.7116,
      "step": 40
    },
    {
      "epoch": 0.14193834553115992,
      "eval_loss": 1.87216055393219,
      "eval_runtime": 54.5241,
      "eval_samples_per_second": 8.712,
      "eval_steps_per_second": 4.365,
      "step": 40
    },
    {
      "epoch": 0.17742293191394987,
      "grad_norm": 4.46636962890625,
      "learning_rate": 0.0,
      "loss": 1.7662,
      "step": 50
    },
    {
      "epoch": 0.17742293191394987,
      "eval_loss": 1.8663088083267212,
      "eval_runtime": 54.7312,
      "eval_samples_per_second": 8.679,
      "eval_steps_per_second": 4.349,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3076438974464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}