{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09775171065493646,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019550342130987292,
      "eval_loss": 2.0243232250213623,
      "eval_runtime": 13.8701,
      "eval_samples_per_second": 15.573,
      "eval_steps_per_second": 7.787,
      "step": 1
    },
    {
      "epoch": 0.009775171065493646,
      "grad_norm": 1.1785598993301392,
      "learning_rate": 5e-05,
      "loss": 1.6526,
      "step": 5
    },
    {
      "epoch": 0.019550342130987292,
      "grad_norm": 1.4754868745803833,
      "learning_rate": 0.0001,
      "loss": 1.735,
      "step": 10
    },
    {
      "epoch": 0.019550342130987292,
      "eval_loss": 1.6014662981033325,
      "eval_runtime": 13.4717,
      "eval_samples_per_second": 16.034,
      "eval_steps_per_second": 8.017,
      "step": 10
    },
    {
      "epoch": 0.02932551319648094,
      "grad_norm": 0.9464597105979919,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0844,
      "step": 15
    },
    {
      "epoch": 0.039100684261974585,
      "grad_norm": 0.9503406286239624,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7427,
      "step": 20
    },
    {
      "epoch": 0.039100684261974585,
      "eval_loss": 0.7665548920631409,
      "eval_runtime": 13.6189,
      "eval_samples_per_second": 15.86,
      "eval_steps_per_second": 7.93,
      "step": 20
    },
    {
      "epoch": 0.04887585532746823,
      "grad_norm": 1.5756646394729614,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7232,
      "step": 25
    },
    {
      "epoch": 0.05865102639296188,
      "grad_norm": 1.3072627782821655,
      "learning_rate": 5e-05,
      "loss": 0.5132,
      "step": 30
    },
    {
      "epoch": 0.05865102639296188,
      "eval_loss": 0.6312705278396606,
      "eval_runtime": 13.6659,
      "eval_samples_per_second": 15.806,
      "eval_steps_per_second": 7.903,
      "step": 30
    },
    {
      "epoch": 0.06842619745845552,
      "grad_norm": 1.5003061294555664,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6253,
      "step": 35
    },
    {
      "epoch": 0.07820136852394917,
      "grad_norm": 1.320988416671753,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5696,
      "step": 40
    },
    {
      "epoch": 0.07820136852394917,
      "eval_loss": 0.574241578578949,
      "eval_runtime": 13.724,
      "eval_samples_per_second": 15.739,
      "eval_steps_per_second": 7.869,
      "step": 40
    },
    {
      "epoch": 0.08797653958944282,
      "grad_norm": 0.8891041874885559,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5825,
      "step": 45
    },
    {
      "epoch": 0.09775171065493646,
      "grad_norm": 1.9904056787490845,
      "learning_rate": 0.0,
      "loss": 0.5554,
      "step": 50
    },
    {
      "epoch": 0.09775171065493646,
      "eval_loss": 0.5622581839561462,
      "eval_runtime": 13.654,
      "eval_samples_per_second": 15.82,
      "eval_steps_per_second": 7.91,
      "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": 8713180230451200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}