{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0326530612244898,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016326530612244899,
      "grad_norm": 3.9275944232940674,
      "learning_rate": 1e-05,
      "loss": 15.4062,
      "step": 1
    },
    {
      "epoch": 0.0016326530612244899,
      "eval_loss": 1.0398951768875122,
      "eval_runtime": 113.6849,
      "eval_samples_per_second": 9.078,
      "eval_steps_per_second": 4.539,
      "step": 1
    },
    {
      "epoch": 0.0032653061224489797,
      "grad_norm": 3.9902234077453613,
      "learning_rate": 2e-05,
      "loss": 16.2773,
      "step": 2
    },
    {
      "epoch": 0.004897959183673469,
      "grad_norm": 4.447629928588867,
      "learning_rate": 3e-05,
      "loss": 16.8359,
      "step": 3
    },
    {
      "epoch": 0.006530612244897959,
      "grad_norm": 3.6420984268188477,
      "learning_rate": 4e-05,
      "loss": 15.5117,
      "step": 4
    },
    {
      "epoch": 0.00816326530612245,
      "grad_norm": 4.099905967712402,
      "learning_rate": 5e-05,
      "loss": 16.7422,
      "step": 5
    },
    {
      "epoch": 0.00816326530612245,
      "eval_loss": 1.0193041563034058,
      "eval_runtime": 36.7376,
      "eval_samples_per_second": 28.091,
      "eval_steps_per_second": 14.046,
      "step": 5
    },
    {
      "epoch": 0.009795918367346938,
      "grad_norm": 4.01804256439209,
      "learning_rate": 6e-05,
      "loss": 15.8086,
      "step": 6
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 4.213345050811768,
      "learning_rate": 7e-05,
      "loss": 16.1016,
      "step": 7
    },
    {
      "epoch": 0.013061224489795919,
      "grad_norm": 4.3585381507873535,
      "learning_rate": 8e-05,
      "loss": 15.5273,
      "step": 8
    },
    {
      "epoch": 0.014693877551020407,
      "grad_norm": 4.254825592041016,
      "learning_rate": 9e-05,
      "loss": 15.5898,
      "step": 9
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 4.836613655090332,
      "learning_rate": 0.0001,
      "loss": 15.2812,
      "step": 10
    },
    {
      "epoch": 0.0163265306122449,
      "eval_loss": 0.9403388500213623,
      "eval_runtime": 37.0488,
      "eval_samples_per_second": 27.855,
      "eval_steps_per_second": 13.928,
      "step": 10
    },
    {
      "epoch": 0.017959183673469388,
      "grad_norm": 3.9569554328918457,
      "learning_rate": 9.755282581475769e-05,
      "loss": 13.3281,
      "step": 11
    },
    {
      "epoch": 0.019591836734693877,
      "grad_norm": 4.2396979331970215,
      "learning_rate": 9.045084971874738e-05,
      "loss": 14.9336,
      "step": 12
    },
    {
      "epoch": 0.02122448979591837,
      "grad_norm": 3.776480197906494,
      "learning_rate": 7.938926261462366e-05,
      "loss": 13.7148,
      "step": 13
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 3.915137767791748,
      "learning_rate": 6.545084971874738e-05,
      "loss": 13.293,
      "step": 14
    },
    {
      "epoch": 0.024489795918367346,
      "grad_norm": 5.005204677581787,
      "learning_rate": 5e-05,
      "loss": 15.0547,
      "step": 15
    },
    {
      "epoch": 0.024489795918367346,
      "eval_loss": 0.8632168769836426,
      "eval_runtime": 36.7318,
      "eval_samples_per_second": 28.096,
      "eval_steps_per_second": 14.048,
      "step": 15
    },
    {
      "epoch": 0.026122448979591838,
      "grad_norm": 4.279781341552734,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 14.0078,
      "step": 16
    },
    {
      "epoch": 0.027755102040816326,
      "grad_norm": 4.18499231338501,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.4355,
      "step": 17
    },
    {
      "epoch": 0.029387755102040815,
      "grad_norm": 4.630531311035156,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.957,
      "step": 18
    },
    {
      "epoch": 0.031020408163265307,
      "grad_norm": 4.716670513153076,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 13.0,
      "step": 19
    },
    {
      "epoch": 0.0326530612244898,
      "grad_norm": 5.805507183074951,
      "learning_rate": 0.0,
      "loss": 14.8984,
      "step": 20
    },
    {
      "epoch": 0.0326530612244898,
      "eval_loss": 0.8439657688140869,
      "eval_runtime": 36.6541,
      "eval_samples_per_second": 28.155,
      "eval_steps_per_second": 14.078,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.802881264615424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}