{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013066024253807521,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 0.47401177883148193,
      "learning_rate": 1e-05,
      "loss": 1.7067,
      "step": 1
    },
    {
      "epoch": 0.0006533012126903761,
      "eval_loss": 1.999820590019226,
      "eval_runtime": 112.5729,
      "eval_samples_per_second": 22.901,
      "eval_steps_per_second": 11.45,
      "step": 1
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 0.505779504776001,
      "learning_rate": 2e-05,
      "loss": 1.9039,
      "step": 2
    },
    {
      "epoch": 0.0019599036380711283,
      "grad_norm": 0.5579796433448792,
      "learning_rate": 3e-05,
      "loss": 1.8283,
      "step": 3
    },
    {
      "epoch": 0.0026132048507615043,
      "grad_norm": 0.5206772089004517,
      "learning_rate": 4e-05,
      "loss": 1.8651,
      "step": 4
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 0.5004145503044128,
      "learning_rate": 5e-05,
      "loss": 1.9099,
      "step": 5
    },
    {
      "epoch": 0.0032665060634518802,
      "eval_loss": 1.9857652187347412,
      "eval_runtime": 43.7424,
      "eval_samples_per_second": 58.936,
      "eval_steps_per_second": 29.468,
      "step": 5
    },
    {
      "epoch": 0.003919807276142257,
      "grad_norm": 0.5522999167442322,
      "learning_rate": 6e-05,
      "loss": 1.9055,
      "step": 6
    },
    {
      "epoch": 0.0045731084888326326,
      "grad_norm": 0.4944389760494232,
      "learning_rate": 7e-05,
      "loss": 1.8609,
      "step": 7
    },
    {
      "epoch": 0.0052264097015230085,
      "grad_norm": 0.5072996020317078,
      "learning_rate": 8e-05,
      "loss": 1.9091,
      "step": 8
    },
    {
      "epoch": 0.0058797109142133845,
      "grad_norm": 0.5102063417434692,
      "learning_rate": 9e-05,
      "loss": 1.821,
      "step": 9
    },
    {
      "epoch": 0.0065330121269037604,
      "grad_norm": 0.4876532256603241,
      "learning_rate": 0.0001,
      "loss": 1.7781,
      "step": 10
    },
    {
      "epoch": 0.0065330121269037604,
      "eval_loss": 1.9432145357131958,
      "eval_runtime": 45.4678,
      "eval_samples_per_second": 56.699,
      "eval_steps_per_second": 28.35,
      "step": 10
    },
    {
      "epoch": 0.007186313339594136,
      "grad_norm": 0.5278764367103577,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8105,
      "step": 11
    },
    {
      "epoch": 0.007839614552284513,
      "grad_norm": 0.46804916858673096,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9332,
      "step": 12
    },
    {
      "epoch": 0.00849291576497489,
      "grad_norm": 0.5591187477111816,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.9395,
      "step": 13
    },
    {
      "epoch": 0.009146216977665265,
      "grad_norm": 0.43466073274612427,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7936,
      "step": 14
    },
    {
      "epoch": 0.009799518190355641,
      "grad_norm": 0.5184069871902466,
      "learning_rate": 5e-05,
      "loss": 1.812,
      "step": 15
    },
    {
      "epoch": 0.009799518190355641,
      "eval_loss": 1.9075682163238525,
      "eval_runtime": 56.4883,
      "eval_samples_per_second": 45.638,
      "eval_steps_per_second": 22.819,
      "step": 15
    },
    {
      "epoch": 0.010452819403046017,
      "grad_norm": 0.5313090682029724,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.8681,
      "step": 16
    },
    {
      "epoch": 0.011106120615736393,
      "grad_norm": 0.4654507339000702,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8468,
      "step": 17
    },
    {
      "epoch": 0.011759421828426769,
      "grad_norm": 0.5464712977409363,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8831,
      "step": 18
    },
    {
      "epoch": 0.012412723041117145,
      "grad_norm": 0.5164174437522888,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9027,
      "step": 19
    },
    {
      "epoch": 0.013066024253807521,
      "grad_norm": 0.4609745442867279,
      "learning_rate": 0.0,
      "loss": 1.8915,
      "step": 20
    },
    {
      "epoch": 0.013066024253807521,
      "eval_loss": 1.8998370170593262,
      "eval_runtime": 45.7387,
      "eval_samples_per_second": 56.364,
      "eval_steps_per_second": 28.182,
      "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": 897059500326912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}