{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02588661661920787,
  "eval_steps": 6,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005177323323841574,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0005177323323841574,
      "eval_loss": NaN,
      "eval_runtime": 153.8808,
      "eval_samples_per_second": 15.856,
      "eval_steps_per_second": 3.964,
      "step": 1
    },
    {
      "epoch": 0.0010354646647683149,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001553196997152472,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0020709293295366298,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0025886616619207868,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003106393994304944,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003106393994304944,
      "eval_loss": NaN,
      "eval_runtime": 153.9633,
      "eval_samples_per_second": 15.848,
      "eval_steps_per_second": 3.962,
      "step": 6
    },
    {
      "epoch": 0.0036241263266891016,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0041418586590732595,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.004659590991457417,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0051773233238415735,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005695055656225731,
      "grad_norm": NaN,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.006212787988609888,
      "grad_norm": NaN,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.006212787988609888,
      "eval_loss": NaN,
      "eval_runtime": 153.9656,
      "eval_samples_per_second": 15.848,
      "eval_steps_per_second": 3.962,
      "step": 12
    },
    {
      "epoch": 0.006730520320994046,
      "grad_norm": NaN,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007248252653378203,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.007765984985762361,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.008283717318146519,
      "grad_norm": NaN,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.008801449650530676,
      "grad_norm": NaN,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.009319181982914834,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009319181982914834,
      "eval_loss": NaN,
      "eval_runtime": 154.0206,
      "eval_samples_per_second": 15.842,
      "eval_steps_per_second": 3.961,
      "step": 18
    },
    {
      "epoch": 0.00983691431529899,
      "grad_norm": NaN,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.010354646647683147,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.010872378980067305,
      "grad_norm": NaN,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.011390111312451462,
      "grad_norm": NaN,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.01190784364483562,
      "grad_norm": NaN,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.012425575977219777,
      "grad_norm": NaN,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.012425575977219777,
      "eval_loss": NaN,
      "eval_runtime": 154.0687,
      "eval_samples_per_second": 15.837,
      "eval_steps_per_second": 3.959,
      "step": 24
    },
    {
      "epoch": 0.012943308309603935,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.013461040641988092,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.01397877297437225,
      "grad_norm": NaN,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.014496505306756407,
      "grad_norm": NaN,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.015014237639140565,
      "grad_norm": NaN,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.015531969971524721,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.015531969971524721,
      "eval_loss": NaN,
      "eval_runtime": 154.0713,
      "eval_samples_per_second": 15.837,
      "eval_steps_per_second": 3.959,
      "step": 30
    },
    {
      "epoch": 0.01604970230390888,
      "grad_norm": NaN,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.016567434636293038,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.017085166968677193,
      "grad_norm": NaN,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.01760289930106135,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.01812063163344551,
      "grad_norm": NaN,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.018638363965829668,
      "grad_norm": NaN,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.018638363965829668,
      "eval_loss": NaN,
      "eval_runtime": 154.0698,
      "eval_samples_per_second": 15.837,
      "eval_steps_per_second": 3.959,
      "step": 36
    },
    {
      "epoch": 0.019156096298213823,
      "grad_norm": NaN,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.01967382863059798,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.02019156096298214,
      "grad_norm": NaN,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.020709293295366294,
      "grad_norm": NaN,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.021227025627750452,
      "grad_norm": NaN,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.02174475796013461,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.02174475796013461,
      "eval_loss": NaN,
      "eval_runtime": 154.0369,
      "eval_samples_per_second": 15.84,
      "eval_steps_per_second": 3.96,
      "step": 42
    },
    {
      "epoch": 0.02226249029251877,
      "grad_norm": NaN,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.022780222624902924,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.023297954957287082,
      "grad_norm": NaN,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.02381568728967124,
      "grad_norm": NaN,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0243334196220554,
      "grad_norm": NaN,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.024851151954439554,
      "grad_norm": NaN,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.024851151954439554,
      "eval_loss": NaN,
      "eval_runtime": 153.9609,
      "eval_samples_per_second": 15.848,
      "eval_steps_per_second": 3.962,
      "step": 48
    },
    {
      "epoch": 0.025368884286823712,
      "grad_norm": NaN,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.02588661661920787,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 1.54405315805184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}