{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007508578550994512,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5017157101989023e-05,
      "eval_loss": 6.610052108764648,
      "eval_runtime": 2006.1393,
      "eval_samples_per_second": 13.977,
      "eval_steps_per_second": 6.989,
      "step": 1
    },
    {
      "epoch": 7.508578550994511e-05,
      "grad_norm": 170.0273895263672,
      "learning_rate": 5e-05,
      "loss": 25.587,
      "step": 5
    },
    {
      "epoch": 0.00015017157101989022,
      "grad_norm": 124.8212661743164,
      "learning_rate": 0.0001,
      "loss": 19.484,
      "step": 10
    },
    {
      "epoch": 0.00015017157101989022,
      "eval_loss": 3.6951372623443604,
      "eval_runtime": 1997.7828,
      "eval_samples_per_second": 14.035,
      "eval_steps_per_second": 7.018,
      "step": 10
    },
    {
      "epoch": 0.00022525735652983533,
      "grad_norm": 38.76652908325195,
      "learning_rate": 9.619397662556435e-05,
      "loss": 12.0106,
      "step": 15
    },
    {
      "epoch": 0.00030034314203978044,
      "grad_norm": 34.259403228759766,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.7416,
      "step": 20
    },
    {
      "epoch": 0.00030034314203978044,
      "eval_loss": 1.9584687948226929,
      "eval_runtime": 1992.502,
      "eval_samples_per_second": 14.072,
      "eval_steps_per_second": 7.036,
      "step": 20
    },
    {
      "epoch": 0.0003754289275497256,
      "grad_norm": 29.666738510131836,
      "learning_rate": 6.91341716182545e-05,
      "loss": 7.5972,
      "step": 25
    },
    {
      "epoch": 0.00045051471305967067,
      "grad_norm": 36.94681167602539,
      "learning_rate": 5e-05,
      "loss": 7.1455,
      "step": 30
    },
    {
      "epoch": 0.00045051471305967067,
      "eval_loss": 1.7347800731658936,
      "eval_runtime": 1997.1674,
      "eval_samples_per_second": 14.039,
      "eval_steps_per_second": 7.02,
      "step": 30
    },
    {
      "epoch": 0.0005256004985696158,
      "grad_norm": 25.015377044677734,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.0215,
      "step": 35
    },
    {
      "epoch": 0.0006006862840795609,
      "grad_norm": 18.919721603393555,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 7.0358,
      "step": 40
    },
    {
      "epoch": 0.0006006862840795609,
      "eval_loss": 1.6993168592453003,
      "eval_runtime": 1995.759,
      "eval_samples_per_second": 14.049,
      "eval_steps_per_second": 7.025,
      "step": 40
    },
    {
      "epoch": 0.000675772069589506,
      "grad_norm": 13.560235023498535,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 6.6901,
      "step": 45
    },
    {
      "epoch": 0.0007508578550994512,
      "grad_norm": 19.260150909423828,
      "learning_rate": 0.0,
      "loss": 6.9561,
      "step": 50
    },
    {
      "epoch": 0.0007508578550994512,
      "eval_loss": 1.681768774986267,
      "eval_runtime": 1997.7366,
      "eval_samples_per_second": 14.035,
      "eval_steps_per_second": 7.018,
      "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": 9946583839801344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}