{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.481203007518797,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041483017889551464,
      "grad_norm": 203.76828002929688,
      "learning_rate": 1.4875e-05,
      "loss": 288.5525390625,
      "original_ce_loss": 9.0166,
      "step": 10
    },
    {
      "epoch": 0.08296603577910293,
      "grad_norm": 184.2494659423828,
      "learning_rate": 3.6125000000000004e-05,
      "loss": 287.5813232421875,
      "original_ce_loss": 8.9862,
      "step": 20
    },
    {
      "epoch": 0.1244490536686544,
      "grad_norm": 241.391845703125,
      "learning_rate": 5.7375e-05,
      "loss": 284.6296875,
      "original_ce_loss": 8.894,
      "step": 30
    },
    {
      "epoch": 0.16593207155820586,
      "grad_norm": 327.870361328125,
      "learning_rate": 7.8625e-05,
      "loss": 273.14404296875,
      "original_ce_loss": 8.5351,
      "step": 40
    },
    {
      "epoch": 0.20741508944775733,
      "grad_norm": 80.51351165771484,
      "learning_rate": 9.775e-05,
      "loss": 243.771630859375,
      "original_ce_loss": 7.6172,
      "step": 50
    },
    {
      "epoch": 0.2488981073373088,
      "grad_norm": 61.04130554199219,
      "learning_rate": 0.00011687500000000001,
      "loss": 229.8462646484375,
      "original_ce_loss": 7.182,
      "step": 60
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 60.73427200317383,
      "learning_rate": 0.000129625,
      "loss": 221.95341796875,
      "original_ce_loss": 6.9354,
      "step": 70
    },
    {
      "epoch": 0.3318641431164117,
      "grad_norm": 51.37192916870117,
      "learning_rate": 0.000150875,
      "loss": 214.37080078125,
      "original_ce_loss": 6.6984,
      "step": 80
    },
    {
      "epoch": 0.37334716100596316,
      "grad_norm": 22.531389236450195,
      "learning_rate": 0.000172125,
      "loss": 205.998388671875,
      "original_ce_loss": 6.4368,
      "step": 90
    },
    {
      "epoch": 0.41483017889551466,
      "grad_norm": 16.882768630981445,
      "learning_rate": 0.000193375,
      "loss": 201.5771484375,
      "original_ce_loss": 6.2986,
      "step": 100
    },
    {
      "epoch": 0.4563131967850661,
      "grad_norm": 32.13435363769531,
      "learning_rate": 0.000214625,
      "loss": 199.65380859375,
      "original_ce_loss": 6.2385,
      "step": 110
    },
    {
      "epoch": 0.4977962146746176,
      "grad_norm": 22.2371883392334,
      "learning_rate": 0.000235875,
      "loss": 198.15953369140624,
      "original_ce_loss": 6.1918,
      "step": 120
    },
    {
      "epoch": 0.5392792325641691,
      "grad_norm": 23.51988983154297,
      "learning_rate": 0.000257125,
      "loss": 195.21707763671876,
      "original_ce_loss": 6.0999,
      "step": 130
    },
    {
      "epoch": 0.5807622504537205,
      "grad_norm": 21.056625366210938,
      "learning_rate": 0.000278375,
      "loss": 192.00562744140626,
      "original_ce_loss": 5.9995,
      "step": 140
    },
    {
      "epoch": 0.622245268343272,
      "grad_norm": 27.031875610351562,
      "learning_rate": 0.000299625,
      "loss": 189.01895751953126,
      "original_ce_loss": 5.9062,
      "step": 150
    },
    {
      "epoch": 0.6637282862328234,
      "grad_norm": 18.687732696533203,
      "learning_rate": 0.000320875,
      "loss": 185.54974365234375,
      "original_ce_loss": 5.7978,
      "step": 160
    },
    {
      "epoch": 0.7052113041223749,
      "grad_norm": 34.62672805786133,
      "learning_rate": 0.000342125,
      "loss": 181.4411865234375,
      "original_ce_loss": 5.6694,
      "step": 170
    },
    {
      "epoch": 0.7466943220119263,
      "grad_norm": 22.933151245117188,
      "learning_rate": 0.000363375,
      "loss": 176.920361328125,
      "original_ce_loss": 5.5281,
      "step": 180
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 40.35688018798828,
      "learning_rate": 0.000384625,
      "loss": 171.9557861328125,
      "original_ce_loss": 5.373,
      "step": 190
    },
    {
      "epoch": 0.8296603577910293,
      "grad_norm": 36.39991760253906,
      "learning_rate": 0.000405875,
      "loss": 167.02354736328124,
      "original_ce_loss": 5.2188,
      "step": 200
    },
    {
      "epoch": 0.8711433756805808,
      "grad_norm": 50.5265998840332,
      "learning_rate": 0.00042440580690100075,
      "loss": 162.07708740234375,
      "original_ce_loss": 5.0643,
      "step": 210
    },
    {
      "epoch": 0.9126263935701322,
      "grad_norm": 37.708221435546875,
      "learning_rate": 0.00035703670677632033,
      "loss": 157.2227294921875,
      "original_ce_loss": 4.9126,
      "step": 220
    },
    {
      "epoch": 0.9541094114596836,
      "grad_norm": 35.469329833984375,
      "learning_rate": 0.0002125,
      "loss": 153.1784423828125,
      "original_ce_loss": 4.7862,
      "step": 230
    },
    {
      "epoch": 0.9955924293492352,
      "grad_norm": 16.84328842163086,
      "learning_rate": 6.796329322367959e-05,
      "loss": 149.57703857421876,
      "original_ce_loss": 4.6736,
      "step": 240
    },
    {
      "epoch": 1.0331864143116412,
      "grad_norm": NaN,
      "learning_rate": 0.00040351662824681024,
      "loss": 149.98463439941406,
      "original_ce_loss": 4.6864,
      "step": 250
    },
    {
      "epoch": 1.0746694322011927,
      "grad_norm": 64.90169525146484,
      "learning_rate": 0.00039331657240756313,
      "loss": 145.989599609375,
      "original_ce_loss": 4.5615,
      "step": 260
    },
    {
      "epoch": 1.116152450090744,
      "grad_norm": 42.50829315185547,
      "learning_rate": 0.00037988794433001515,
      "loss": 141.3390625,
      "original_ce_loss": 4.4162,
      "step": 270
    },
    {
      "epoch": 1.1576354679802956,
      "grad_norm": 38.33572769165039,
      "learning_rate": 0.0003644131338923845,
      "loss": 138.03270263671874,
      "original_ce_loss": 4.3129,
      "step": 280
    },
    {
      "epoch": 1.199118485869847,
      "grad_norm": 40.65241241455078,
      "learning_rate": 0.00034708130814771,
      "loss": 135.1212158203125,
      "original_ce_loss": 4.2219,
      "step": 290
    },
    {
      "epoch": 1.2406015037593985,
      "grad_norm": 69.57759857177734,
      "learning_rate": 0.0003281043346605806,
      "loss": 132.01983642578125,
      "original_ce_loss": 4.125,
      "step": 300
    },
    {
      "epoch": 1.28208452164895,
      "grad_norm": 47.51698684692383,
      "learning_rate": 0.00030771419159736043,
      "loss": 128.94189453125,
      "original_ce_loss": 4.0288,
      "step": 310
    },
    {
      "epoch": 1.3235675395385014,
      "grad_norm": 46.686241149902344,
      "learning_rate": 0.0002861601319805566,
      "loss": 126.20169677734376,
      "original_ce_loss": 3.9432,
      "step": 320
    },
    {
      "epoch": 1.365050557428053,
      "grad_norm": 39.812068939208984,
      "learning_rate": 0.00026370563677203054,
      "loss": 123.58370361328124,
      "original_ce_loss": 3.8614,
      "step": 330
    },
    {
      "epoch": 1.4065335753176043,
      "grad_norm": 34.92276382446289,
      "learning_rate": 0.0002406251940311473,
      "loss": 121.514599609375,
      "original_ce_loss": 3.7967,
      "step": 340
    },
    {
      "epoch": 1.4480165932071558,
      "grad_norm": 51.240840911865234,
      "learning_rate": 0.0002172009435200522,
      "loss": 118.99783935546876,
      "original_ce_loss": 3.7181,
      "step": 350
    },
    {
      "epoch": 1.4894996110967074,
      "grad_norm": 42.60438537597656,
      "learning_rate": 0.00019371922777306473,
      "loss": 117.68125,
      "original_ce_loss": 3.6769,
      "step": 360
    },
    {
      "epoch": 1.5309826289862587,
      "grad_norm": 32.416114807128906,
      "learning_rate": 0.00017046709179057757,
      "loss": 115.90443115234375,
      "original_ce_loss": 3.6214,
      "step": 370
    },
    {
      "epoch": 1.5724656468758103,
      "grad_norm": 31.31523895263672,
      "learning_rate": 0.0001477287741458766,
      "loss": 114.24423828125,
      "original_ce_loss": 3.5695,
      "step": 380
    },
    {
      "epoch": 1.6139486647653616,
      "grad_norm": 29.63783836364746,
      "learning_rate": 0.00012578223239826367,
      "loss": 113.076904296875,
      "original_ce_loss": 3.533,
      "step": 390
    },
    {
      "epoch": 1.6554316826549131,
      "grad_norm": 21.96636962890625,
      "learning_rate": 0.0001048957452865007,
      "loss": 111.66766357421875,
      "original_ce_loss": 3.489,
      "step": 400
    },
    {
      "epoch": 1.6969147005444647,
      "grad_norm": 72.03860473632812,
      "learning_rate": 0.00029176382908428956,
      "loss": 111.707080078125,
      "original_ce_loss": 3.4902,
      "step": 410
    },
    {
      "epoch": 1.738397718434016,
      "grad_norm": 56.377784729003906,
      "learning_rate": 0.0002798536820919388,
      "loss": 110.67801513671876,
      "original_ce_loss": 3.4581,
      "step": 420
    },
    {
      "epoch": 1.7798807363235676,
      "grad_norm": 40.06888198852539,
      "learning_rate": 0.0002677033420177621,
      "loss": 108.81322021484375,
      "original_ce_loss": 3.3998,
      "step": 430
    },
    {
      "epoch": 1.821363754213119,
      "grad_norm": 54.35465621948242,
      "learning_rate": 0.0002553561387516336,
      "loss": 107.58404541015625,
      "original_ce_loss": 3.3614,
      "step": 440
    },
    {
      "epoch": 1.8628467721026705,
      "grad_norm": 43.010047912597656,
      "learning_rate": 0.00024285610422636377,
      "loss": 106.3376953125,
      "original_ce_loss": 3.3225,
      "step": 450
    },
    {
      "epoch": 1.904329789992222,
      "grad_norm": 37.77562713623047,
      "learning_rate": 0.00023024781539338732,
      "loss": 105.1876708984375,
      "original_ce_loss": 3.2865,
      "step": 460
    },
    {
      "epoch": 1.9458128078817734,
      "grad_norm": 39.30547332763672,
      "learning_rate": 0.00021757623525483388,
      "loss": 104.48690185546874,
      "original_ce_loss": 3.2646,
      "step": 470
    },
    {
      "epoch": 1.987295825771325,
      "grad_norm": 38.75474548339844,
      "learning_rate": 0.00020615504546354557,
      "loss": 103.30198974609375,
      "original_ce_loss": 3.2276,
      "step": 480
    },
    {
      "epoch": 2.0248898107337308,
      "grad_norm": 68.0500259399414,
      "learning_rate": 0.00019348776342655851,
      "loss": 93.47062377929687,
      "original_ce_loss": 3.2225,
      "step": 490
    },
    {
      "epoch": 2.0663728286232823,
      "grad_norm": 33.5322380065918,
      "learning_rate": 0.00018088828180601698,
      "loss": 102.30059814453125,
      "original_ce_loss": 3.1963,
      "step": 500
    },
    {
      "epoch": 2.107855846512834,
      "grad_norm": 43.00708770751953,
      "learning_rate": 0.00016840153219624304,
      "loss": 101.05491943359375,
      "original_ce_loss": 3.1574,
      "step": 510
    },
    {
      "epoch": 2.1493388644023854,
      "grad_norm": 32.75222396850586,
      "learning_rate": 0.00015607204417271948,
      "loss": 100.06157836914062,
      "original_ce_loss": 3.1263,
      "step": 520
    },
    {
      "epoch": 2.190821882291937,
      "grad_norm": 34.5550537109375,
      "learning_rate": 0.0001439437864931107,
      "loss": 99.03675537109375,
      "original_ce_loss": 3.0943,
      "step": 530
    },
    {
      "epoch": 2.232304900181488,
      "grad_norm": 33.61601257324219,
      "learning_rate": 0.00013206001029824168,
      "loss": 98.9501953125,
      "original_ce_loss": 3.0916,
      "step": 540
    },
    {
      "epoch": 2.2737879180710396,
      "grad_norm": 35.476318359375,
      "learning_rate": 0.00012046309487220386,
      "loss": 98.14458618164062,
      "original_ce_loss": 3.0664,
      "step": 550
    },
    {
      "epoch": 2.315270935960591,
      "grad_norm": 27.919132232666016,
      "learning_rate": 0.00010919439651162934,
      "loss": 97.50660400390625,
      "original_ce_loss": 3.0465,
      "step": 560
    },
    {
      "epoch": 2.3567539538501427,
      "grad_norm": 27.541818618774414,
      "learning_rate": 9.829410104308781e-05,
      "loss": 96.76535034179688,
      "original_ce_loss": 3.0233,
      "step": 570
    },
    {
      "epoch": 2.398236971739694,
      "grad_norm": 25.62722396850586,
      "learning_rate": 8.780108051455205e-05,
      "loss": 96.71749877929688,
      "original_ce_loss": 3.0218,
      "step": 580
    },
    {
      "epoch": 2.4397199896292454,
      "grad_norm": 31.261812210083008,
      "learning_rate": 7.775275457198821e-05,
      "loss": 95.91024169921874,
      "original_ce_loss": 2.9966,
      "step": 590
    },
    {
      "epoch": 2.481203007518797,
      "grad_norm": 25.36027717590332,
      "learning_rate": 6.818495701542595e-05,
      "loss": 95.57075805664063,
      "original_ce_loss": 2.986,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 726,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.867238337530266e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}