{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0034132605171089685,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.826521034217937e-05,
      "eval_loss": 3.115783452987671,
      "eval_runtime": 186.1759,
      "eval_samples_per_second": 33.13,
      "eval_steps_per_second": 16.565,
      "step": 1
    },
    {
      "epoch": 0.0003413260517108968,
      "grad_norm": 2.2947301864624023,
      "learning_rate": 5e-05,
      "loss": 2.9986,
      "step": 5
    },
    {
      "epoch": 0.0006826521034217937,
      "grad_norm": 2.5597593784332275,
      "learning_rate": 0.0001,
      "loss": 3.0651,
      "step": 10
    },
    {
      "epoch": 0.0006826521034217937,
      "eval_loss": 3.018254518508911,
      "eval_runtime": 186.6409,
      "eval_samples_per_second": 33.047,
      "eval_steps_per_second": 16.524,
      "step": 10
    },
    {
      "epoch": 0.0010239781551326906,
      "grad_norm": 2.3084704875946045,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.8458,
      "step": 15
    },
    {
      "epoch": 0.0013653042068435873,
      "grad_norm": 2.918429136276245,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5002,
      "step": 20
    },
    {
      "epoch": 0.0013653042068435873,
      "eval_loss": 2.5421009063720703,
      "eval_runtime": 186.4994,
      "eval_samples_per_second": 33.073,
      "eval_steps_per_second": 16.536,
      "step": 20
    },
    {
      "epoch": 0.0017066302585544842,
      "grad_norm": 2.7874643802642822,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.5545,
      "step": 25
    },
    {
      "epoch": 0.002047956310265381,
      "grad_norm": 2.591674327850342,
      "learning_rate": 5e-05,
      "loss": 2.2392,
      "step": 30
    },
    {
      "epoch": 0.002047956310265381,
      "eval_loss": 2.4233028888702393,
      "eval_runtime": 186.4659,
      "eval_samples_per_second": 33.078,
      "eval_steps_per_second": 16.539,
      "step": 30
    },
    {
      "epoch": 0.002389282361976278,
      "grad_norm": 2.8810315132141113,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0842,
      "step": 35
    },
    {
      "epoch": 0.0027306084136871746,
      "grad_norm": 3.684279441833496,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.4791,
      "step": 40
    },
    {
      "epoch": 0.0027306084136871746,
      "eval_loss": 2.390902280807495,
      "eval_runtime": 186.2961,
      "eval_samples_per_second": 33.109,
      "eval_steps_per_second": 16.554,
      "step": 40
    },
    {
      "epoch": 0.0030719344653980713,
      "grad_norm": 3.342024087905884,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.3955,
      "step": 45
    },
    {
      "epoch": 0.0034132605171089685,
      "grad_norm": 3.112165927886963,
      "learning_rate": 0.0,
      "loss": 2.4418,
      "step": 50
    },
    {
      "epoch": 0.0034132605171089685,
      "eval_loss": 2.384955406188965,
      "eval_runtime": 186.5009,
      "eval_samples_per_second": 33.072,
      "eval_steps_per_second": 16.536,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}