{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.099601593625498,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00199203187250996,
      "eval_loss": 1.1114661693572998,
      "eval_runtime": 14.9557,
      "eval_samples_per_second": 14.175,
      "eval_steps_per_second": 7.088,
      "step": 1
    },
    {
      "epoch": 0.0099601593625498,
      "grad_norm": 0.4821946322917938,
      "learning_rate": 5e-05,
      "loss": 1.1065,
      "step": 5
    },
    {
      "epoch": 0.0199203187250996,
      "grad_norm": 0.5409933924674988,
      "learning_rate": 0.0001,
      "loss": 1.1812,
      "step": 10
    },
    {
      "epoch": 0.0199203187250996,
      "eval_loss": 1.0850259065628052,
      "eval_runtime": 14.8907,
      "eval_samples_per_second": 14.237,
      "eval_steps_per_second": 7.119,
      "step": 10
    },
    {
      "epoch": 0.029880478087649404,
      "grad_norm": 0.6434897780418396,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0113,
      "step": 15
    },
    {
      "epoch": 0.0398406374501992,
      "grad_norm": 0.9250468611717224,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1422,
      "step": 20
    },
    {
      "epoch": 0.0398406374501992,
      "eval_loss": 1.044611930847168,
      "eval_runtime": 14.8938,
      "eval_samples_per_second": 14.234,
      "eval_steps_per_second": 7.117,
      "step": 20
    },
    {
      "epoch": 0.049800796812749,
      "grad_norm": 0.5784384608268738,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9165,
      "step": 25
    },
    {
      "epoch": 0.05976095617529881,
      "grad_norm": 0.6139729619026184,
      "learning_rate": 5e-05,
      "loss": 1.1056,
      "step": 30
    },
    {
      "epoch": 0.05976095617529881,
      "eval_loss": 1.0264966487884521,
      "eval_runtime": 14.9046,
      "eval_samples_per_second": 14.224,
      "eval_steps_per_second": 7.112,
      "step": 30
    },
    {
      "epoch": 0.0697211155378486,
      "grad_norm": 0.5393847227096558,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9776,
      "step": 35
    },
    {
      "epoch": 0.0796812749003984,
      "grad_norm": 0.5789812803268433,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9913,
      "step": 40
    },
    {
      "epoch": 0.0796812749003984,
      "eval_loss": 1.020814299583435,
      "eval_runtime": 14.9615,
      "eval_samples_per_second": 14.17,
      "eval_steps_per_second": 7.085,
      "step": 40
    },
    {
      "epoch": 0.08964143426294821,
      "grad_norm": 0.5929783582687378,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9709,
      "step": 45
    },
    {
      "epoch": 0.099601593625498,
      "grad_norm": 0.6848423480987549,
      "learning_rate": 0.0,
      "loss": 1.0246,
      "step": 50
    },
    {
      "epoch": 0.099601593625498,
      "eval_loss": 1.0198479890823364,
      "eval_runtime": 14.9231,
      "eval_samples_per_second": 14.206,
      "eval_steps_per_second": 7.103,
      "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": 4163310278148096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}