{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2121212121212122,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024242424242424242,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.024242424242424242,
      "eval_loss": NaN,
      "eval_runtime": 1.9116,
      "eval_samples_per_second": 9.416,
      "eval_steps_per_second": 4.708,
      "step": 1
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.12121212121212122,
      "eval_loss": NaN,
      "eval_runtime": 1.3761,
      "eval_samples_per_second": 13.081,
      "eval_steps_per_second": 6.54,
      "step": 5
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.24242424242424243,
      "eval_loss": NaN,
      "eval_runtime": 1.3772,
      "eval_samples_per_second": 13.07,
      "eval_steps_per_second": 6.535,
      "step": 10
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": NaN,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": NaN,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": NaN,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": NaN,
      "eval_runtime": 1.3789,
      "eval_samples_per_second": 13.054,
      "eval_steps_per_second": 6.527,
      "step": 15
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": NaN,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": NaN,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": NaN,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.48484848484848486,
      "eval_loss": NaN,
      "eval_runtime": 1.3845,
      "eval_samples_per_second": 13.001,
      "eval_steps_per_second": 6.501,
      "step": 20
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": NaN,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": NaN,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": NaN,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": NaN,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.6060606060606061,
      "eval_loss": NaN,
      "eval_runtime": 1.3851,
      "eval_samples_per_second": 12.996,
      "eval_steps_per_second": 6.498,
      "step": 25
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": NaN,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": NaN,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": NaN,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": NaN,
      "eval_runtime": 1.3892,
      "eval_samples_per_second": 12.958,
      "eval_steps_per_second": 6.479,
      "step": 30
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": NaN,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.8,
      "grad_norm": NaN,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": NaN,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.8484848484848485,
      "eval_loss": NaN,
      "eval_runtime": 1.39,
      "eval_samples_per_second": 12.95,
      "eval_steps_per_second": 6.475,
      "step": 35
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": NaN,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.896969696969697,
      "grad_norm": NaN,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": NaN,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": NaN,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.9696969696969697,
      "eval_loss": NaN,
      "eval_runtime": 1.3919,
      "eval_samples_per_second": 12.932,
      "eval_steps_per_second": 6.466,
      "step": 40
    },
    {
      "epoch": 0.9939393939393939,
      "grad_norm": NaN,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 1.0424242424242425,
      "grad_norm": NaN,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": NaN,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 1.0909090909090908,
      "eval_loss": NaN,
      "eval_runtime": 1.3954,
      "eval_samples_per_second": 12.899,
      "eval_steps_per_second": 6.45,
      "step": 45
    },
    {
      "epoch": 1.1151515151515152,
      "grad_norm": NaN,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 1.1393939393939394,
      "grad_norm": NaN,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": NaN,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 1.187878787878788,
      "grad_norm": NaN,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 1.2121212121212122,
      "eval_loss": NaN,
      "eval_runtime": 1.3945,
      "eval_samples_per_second": 12.908,
      "eval_steps_per_second": 6.454,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.64316422602752e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}