{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005034929825665555,
  "eval_steps": 25,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012587324564163887,
      "grad_norm": 4.972455978393555,
      "learning_rate": 2e-05,
      "loss": 11.8587,
      "step": 1
    },
    {
      "epoch": 0.00012587324564163887,
      "eval_loss": NaN,
      "eval_runtime": 3606.4326,
      "eval_samples_per_second": 0.928,
      "eval_steps_per_second": 0.464,
      "step": 1
    },
    {
      "epoch": 0.00025174649128327774,
      "grad_norm": 12.494519233703613,
      "learning_rate": 4e-05,
      "loss": 5.71,
      "step": 2
    },
    {
      "epoch": 0.0003776197369249166,
      "grad_norm": 18.601806640625,
      "learning_rate": 6e-05,
      "loss": 11.1117,
      "step": 3
    },
    {
      "epoch": 0.0005034929825665555,
      "grad_norm": 8.032801628112793,
      "learning_rate": 8e-05,
      "loss": 3.9358,
      "step": 4
    },
    {
      "epoch": 0.0006293662282081943,
      "grad_norm": 12.177727699279785,
      "learning_rate": 0.0001,
      "loss": 16.7821,
      "step": 5
    },
    {
      "epoch": 0.0007552394738498332,
      "grad_norm": 6.706995964050293,
      "learning_rate": 0.00012,
      "loss": 10.3418,
      "step": 6
    },
    {
      "epoch": 0.0008811127194914721,
      "grad_norm": 6.680157661437988,
      "learning_rate": 0.00014,
      "loss": 4.845,
      "step": 7
    },
    {
      "epoch": 0.001006985965133111,
      "grad_norm": 9.944180488586426,
      "learning_rate": 0.00016,
      "loss": 2.6742,
      "step": 8
    },
    {
      "epoch": 0.0011328592107747498,
      "grad_norm": 14.13370418548584,
      "learning_rate": 0.00018,
      "loss": 3.8844,
      "step": 9
    },
    {
      "epoch": 0.0012587324564163887,
      "grad_norm": 17.886985778808594,
      "learning_rate": 0.0002,
      "loss": 3.3169,
      "step": 10
    },
    {
      "epoch": 0.0013846057020580275,
      "grad_norm": 21.377635955810547,
      "learning_rate": 0.0001999390827019096,
      "loss": 1.0058,
      "step": 11
    },
    {
      "epoch": 0.0015104789476996663,
      "grad_norm": 11.985687255859375,
      "learning_rate": 0.00019975640502598244,
      "loss": 0.8173,
      "step": 12
    },
    {
      "epoch": 0.0016363521933413054,
      "grad_norm": 17.24648666381836,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.3288,
      "step": 13
    },
    {
      "epoch": 0.0017622254389829443,
      "grad_norm": 38.9212532043457,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.7752,
      "step": 14
    },
    {
      "epoch": 0.001888098684624583,
      "grad_norm": 12.58133316040039,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.7308,
      "step": 15
    },
    {
      "epoch": 0.002013971930266222,
      "grad_norm": 5.521592617034912,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.1023,
      "step": 16
    },
    {
      "epoch": 0.002139845175907861,
      "grad_norm": 1.7692532539367676,
      "learning_rate": 0.00019702957262759965,
      "loss": 0.0166,
      "step": 17
    },
    {
      "epoch": 0.0022657184215494996,
      "grad_norm": 9.756790161132812,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.1932,
      "step": 18
    },
    {
      "epoch": 0.0023915916671911385,
      "grad_norm": 8.156234741210938,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.3879,
      "step": 19
    },
    {
      "epoch": 0.0025174649128327773,
      "grad_norm": 6.355808258056641,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.4888,
      "step": 20
    },
    {
      "epoch": 0.002643338158474416,
      "grad_norm": 6.595178127288818,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.6385,
      "step": 21
    },
    {
      "epoch": 0.002769211404116055,
      "grad_norm": 3.2132580280303955,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.518,
      "step": 22
    },
    {
      "epoch": 0.002895084649757694,
      "grad_norm": 16.919002532958984,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.3769,
      "step": 23
    },
    {
      "epoch": 0.0030209578953993327,
      "grad_norm": 0.020209377631545067,
      "learning_rate": 0.00018829475928589271,
      "loss": 0.0002,
      "step": 24
    },
    {
      "epoch": 0.0031468311410409715,
      "grad_norm": 0.8074254989624023,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0241,
      "step": 25
    },
    {
      "epoch": 0.0031468311410409715,
      "eval_loss": NaN,
      "eval_runtime": 3493.5914,
      "eval_samples_per_second": 0.957,
      "eval_steps_per_second": 0.479,
      "step": 25
    },
    {
      "epoch": 0.003272704386682611,
      "grad_norm": 19.329341888427734,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.7896,
      "step": 26
    },
    {
      "epoch": 0.0033985776323242497,
      "grad_norm": 8.426005363464355,
      "learning_rate": 0.00018290375725550417,
      "loss": 0.4921,
      "step": 27
    },
    {
      "epoch": 0.0035244508779658885,
      "grad_norm": 6.269211292266846,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.5567,
      "step": 28
    },
    {
      "epoch": 0.0036503241236075274,
      "grad_norm": 4.1337480545043945,
      "learning_rate": 0.00017880107536067218,
      "loss": 0.0482,
      "step": 29
    },
    {
      "epoch": 0.003776197369249166,
      "grad_norm": 0.4672463834285736,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.0424,
      "step": 30
    },
    {
      "epoch": 0.003902070614890805,
      "grad_norm": 0.22993697226047516,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.0041,
      "step": 31
    },
    {
      "epoch": 0.004027943860532444,
      "grad_norm": 1.7465827465057373,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.0228,
      "step": 32
    },
    {
      "epoch": 0.004153817106174082,
      "grad_norm": 0.28992122411727905,
      "learning_rate": 0.00016946583704589973,
      "loss": 0.0067,
      "step": 33
    },
    {
      "epoch": 0.004279690351815722,
      "grad_norm": 0.9798206090927124,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0262,
      "step": 34
    },
    {
      "epoch": 0.004405563597457361,
      "grad_norm": 0.009784302674233913,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.0007,
      "step": 35
    },
    {
      "epoch": 0.004531436843098999,
      "grad_norm": 2.536167860031128,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.0487,
      "step": 36
    },
    {
      "epoch": 0.0046573100887406385,
      "grad_norm": 0.8000788688659668,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0149,
      "step": 37
    },
    {
      "epoch": 0.004783183334382277,
      "grad_norm": 0.0,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.004909056580023916,
      "grad_norm": 0.015558776445686817,
      "learning_rate": 0.0001529919264233205,
      "loss": 0.0014,
      "step": 39
    },
    {
      "epoch": 0.005034929825665555,
      "grad_norm": 3.2701315879821777,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2162,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.63415360651264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}