{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2705444707473791,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005410889414947582,
      "eval_loss": 12.122608184814453,
      "eval_runtime": 46.8513,
      "eval_samples_per_second": 26.573,
      "eval_steps_per_second": 3.33,
      "step": 1
    },
    {
      "epoch": 0.05410889414947582,
      "grad_norm": 12.570738792419434,
      "learning_rate": 9.330127018922194e-05,
      "loss": 9.2419,
      "step": 10
    },
    {
      "epoch": 0.05410889414947582,
      "eval_loss": 3.6160972118377686,
      "eval_runtime": 46.8308,
      "eval_samples_per_second": 26.585,
      "eval_steps_per_second": 3.331,
      "step": 10
    },
    {
      "epoch": 0.10821778829895164,
      "grad_norm": 4.354996681213379,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.276,
      "step": 20
    },
    {
      "epoch": 0.10821778829895164,
      "eval_loss": 0.3355282247066498,
      "eval_runtime": 46.6907,
      "eval_samples_per_second": 26.665,
      "eval_steps_per_second": 3.341,
      "step": 20
    },
    {
      "epoch": 0.16232668244842746,
      "grad_norm": 1.7737544775009155,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2268,
      "step": 30
    },
    {
      "epoch": 0.16232668244842746,
      "eval_loss": 0.17853505909442902,
      "eval_runtime": 46.8298,
      "eval_samples_per_second": 26.586,
      "eval_steps_per_second": 3.331,
      "step": 30
    },
    {
      "epoch": 0.21643557659790327,
      "grad_norm": 0.8568832278251648,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1519,
      "step": 40
    },
    {
      "epoch": 0.21643557659790327,
      "eval_loss": 0.15219616889953613,
      "eval_runtime": 46.7461,
      "eval_samples_per_second": 26.633,
      "eval_steps_per_second": 3.337,
      "step": 40
    },
    {
      "epoch": 0.2705444707473791,
      "grad_norm": 1.276870846748352,
      "learning_rate": 0.0,
      "loss": 0.1551,
      "step": 50
    },
    {
      "epoch": 0.2705444707473791,
      "eval_loss": 0.15099486708641052,
      "eval_runtime": 46.8903,
      "eval_samples_per_second": 26.551,
      "eval_steps_per_second": 3.327,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": 6.57458278170624e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}