{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00810142990237777,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001620285980475554,
      "eval_loss": 2.3156306743621826,
      "eval_runtime": 316.9863,
      "eval_samples_per_second": 8.199,
      "eval_steps_per_second": 4.101,
      "step": 1
    },
    {
      "epoch": 0.000810142990237777,
      "grad_norm": 1.3373298645019531,
      "learning_rate": 5e-05,
      "loss": 2.1229,
      "step": 5
    },
    {
      "epoch": 0.001620285980475554,
      "grad_norm": 1.4930287599563599,
      "learning_rate": 0.0001,
      "loss": 2.2211,
      "step": 10
    },
    {
      "epoch": 0.001620285980475554,
      "eval_loss": 2.0873374938964844,
      "eval_runtime": 319.8042,
      "eval_samples_per_second": 8.127,
      "eval_steps_per_second": 4.065,
      "step": 10
    },
    {
      "epoch": 0.002430428970713331,
      "grad_norm": 2.017960786819458,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9019,
      "step": 15
    },
    {
      "epoch": 0.003240571960951108,
      "grad_norm": 2.592176675796509,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.84,
      "step": 20
    },
    {
      "epoch": 0.003240571960951108,
      "eval_loss": 1.7282837629318237,
      "eval_runtime": 318.4369,
      "eval_samples_per_second": 8.162,
      "eval_steps_per_second": 4.082,
      "step": 20
    },
    {
      "epoch": 0.004050714951188885,
      "grad_norm": 2.8930394649505615,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6837,
      "step": 25
    },
    {
      "epoch": 0.004860857941426662,
      "grad_norm": 2.3434412479400635,
      "learning_rate": 5e-05,
      "loss": 1.3884,
      "step": 30
    },
    {
      "epoch": 0.004860857941426662,
      "eval_loss": 1.6404736042022705,
      "eval_runtime": 319.3128,
      "eval_samples_per_second": 8.139,
      "eval_steps_per_second": 4.071,
      "step": 30
    },
    {
      "epoch": 0.005671000931664439,
      "grad_norm": 1.746314525604248,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6467,
      "step": 35
    },
    {
      "epoch": 0.006481143921902216,
      "grad_norm": 3.41062593460083,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8136,
      "step": 40
    },
    {
      "epoch": 0.006481143921902216,
      "eval_loss": 1.6066102981567383,
      "eval_runtime": 319.9679,
      "eval_samples_per_second": 8.123,
      "eval_steps_per_second": 4.063,
      "step": 40
    },
    {
      "epoch": 0.007291286912139993,
      "grad_norm": 2.4135866165161133,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5883,
      "step": 45
    },
    {
      "epoch": 0.00810142990237777,
      "grad_norm": 2.768815040588379,
      "learning_rate": 0.0,
      "loss": 1.542,
      "step": 50
    },
    {
      "epoch": 0.00810142990237777,
      "eval_loss": 1.595735788345337,
      "eval_runtime": 320.2184,
      "eval_samples_per_second": 8.116,
      "eval_steps_per_second": 4.06,
      "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": 1.8356925162848256e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}