{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014316392269148175,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002863278453829635,
      "eval_loss": 3.061569929122925,
      "eval_runtime": 79.8452,
      "eval_samples_per_second": 18.423,
      "eval_steps_per_second": 9.218,
      "step": 1
    },
    {
      "epoch": 0.0014316392269148174,
      "grad_norm": 2.6328675746917725,
      "learning_rate": 5e-05,
      "loss": 2.7243,
      "step": 5
    },
    {
      "epoch": 0.002863278453829635,
      "grad_norm": 1.192201852798462,
      "learning_rate": 0.0001,
      "loss": 2.434,
      "step": 10
    },
    {
      "epoch": 0.002863278453829635,
      "eval_loss": 2.8024604320526123,
      "eval_runtime": 80.0508,
      "eval_samples_per_second": 18.376,
      "eval_steps_per_second": 9.194,
      "step": 10
    },
    {
      "epoch": 0.004294917680744453,
      "grad_norm": 1.666427731513977,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3408,
      "step": 15
    },
    {
      "epoch": 0.00572655690765927,
      "grad_norm": 4.190948009490967,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4434,
      "step": 20
    },
    {
      "epoch": 0.00572655690765927,
      "eval_loss": 2.440873861312866,
      "eval_runtime": 80.1784,
      "eval_samples_per_second": 18.347,
      "eval_steps_per_second": 9.18,
      "step": 20
    },
    {
      "epoch": 0.0071581961345740875,
      "grad_norm": 1.6054500341415405,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1081,
      "step": 25
    },
    {
      "epoch": 0.008589835361488905,
      "grad_norm": 1.9118183851242065,
      "learning_rate": 5e-05,
      "loss": 2.2238,
      "step": 30
    },
    {
      "epoch": 0.008589835361488905,
      "eval_loss": 2.387988805770874,
      "eval_runtime": 80.2029,
      "eval_samples_per_second": 18.341,
      "eval_steps_per_second": 9.177,
      "step": 30
    },
    {
      "epoch": 0.010021474588403722,
      "grad_norm": 1.9751979112625122,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.2428,
      "step": 35
    },
    {
      "epoch": 0.01145311381531854,
      "grad_norm": 1.7656954526901245,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.525,
      "step": 40
    },
    {
      "epoch": 0.01145311381531854,
      "eval_loss": 2.373016834259033,
      "eval_runtime": 80.1916,
      "eval_samples_per_second": 18.344,
      "eval_steps_per_second": 9.178,
      "step": 40
    },
    {
      "epoch": 0.012884753042233358,
      "grad_norm": 1.4309945106506348,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.029,
      "step": 45
    },
    {
      "epoch": 0.014316392269148175,
      "grad_norm": 1.4891185760498047,
      "learning_rate": 0.0,
      "loss": 2.3947,
      "step": 50
    },
    {
      "epoch": 0.014316392269148175,
      "eval_loss": 2.3703513145446777,
      "eval_runtime": 80.6645,
      "eval_samples_per_second": 18.236,
      "eval_steps_per_second": 9.124,
      "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": 2500486653542400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}