{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04251700680272109,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": NaN,
      "eval_runtime": 54.6952,
      "eval_samples_per_second": 9.05,
      "eval_steps_per_second": 1.134,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006802721088435374,
      "eval_loss": NaN,
      "eval_runtime": 53.9009,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 1.15,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.013605442176870748,
      "eval_loss": NaN,
      "eval_runtime": 53.8994,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 1.15,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02040816326530612,
      "eval_loss": NaN,
      "eval_runtime": 53.9084,
      "eval_samples_per_second": 9.182,
      "eval_steps_per_second": 1.15,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.027210884353741496,
      "eval_loss": NaN,
      "eval_runtime": 53.9026,
      "eval_samples_per_second": 9.183,
      "eval_steps_per_second": 1.15,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.034013605442176874,
      "eval_loss": NaN,
      "eval_runtime": 53.9007,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 1.15,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04081632653061224,
      "eval_loss": NaN,
      "eval_runtime": 53.9058,
      "eval_samples_per_second": 9.183,
      "eval_steps_per_second": 1.15,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85471820890112e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}