{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.945914738349268,
  "eval_steps": 4096,
  "global_step": 20480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011823934229365849,
      "grad_norm": 2.4639666080474854,
      "learning_rate": 0.000498046875,
      "loss": 0.1339670717716217,
      "step": 256
    },
    {
      "epoch": 0.023647868458731697,
      "grad_norm": 1.5375629663467407,
      "learning_rate": 0.000998046875,
      "loss": 0.1467132717370987,
      "step": 512
    },
    {
      "epoch": 0.03547180268809755,
      "grad_norm": 1.506445288658142,
      "learning_rate": 0.000999640996023194,
      "loss": 0.15337222814559937,
      "step": 768
    },
    {
      "epoch": 0.047295736917463395,
      "grad_norm": 1.641593098640442,
      "learning_rate": 0.0009985588674043958,
      "loss": 0.15139617025852203,
      "step": 1024
    },
    {
      "epoch": 0.05911967114682925,
      "grad_norm": 1.3137743473052979,
      "learning_rate": 0.0009967551747861387,
      "loss": 0.14983117580413818,
      "step": 1280
    },
    {
      "epoch": 0.0709436053761951,
      "grad_norm": 1.3725732564926147,
      "learning_rate": 0.000994232528651847,
      "loss": 0.14979030191898346,
      "step": 1536
    },
    {
      "epoch": 0.08276753960556095,
      "grad_norm": 2.0527191162109375,
      "learning_rate": 0.0009909945800260092,
      "loss": 0.14714637398719788,
      "step": 1792
    },
    {
      "epoch": 0.09459147383492679,
      "grad_norm": 1.8648000955581665,
      "learning_rate": 0.0009870460151900522,
      "loss": 0.1472843438386917,
      "step": 2048
    },
    {
      "epoch": 0.10641540806429264,
      "grad_norm": 1.025286078453064,
      "learning_rate": 0.0009823925488998885,
      "loss": 0.1452621966600418,
      "step": 2304
    },
    {
      "epoch": 0.1182393422936585,
      "grad_norm": 0.9860194325447083,
      "learning_rate": 0.0009770409161149525,
      "loss": 0.1464366316795349,
      "step": 2560
    },
    {
      "epoch": 0.13006327652302435,
      "grad_norm": 1.4449650049209595,
      "learning_rate": 0.0009709988622506973,
      "loss": 0.1476413458585739,
      "step": 2816
    },
    {
      "epoch": 0.1418872107523902,
      "grad_norm": 1.548802375793457,
      "learning_rate": 0.000964275131968659,
      "loss": 0.14479056000709534,
      "step": 3072
    },
    {
      "epoch": 0.15371114498175603,
      "grad_norm": 0.9572728872299194,
      "learning_rate": 0.0009568794565203123,
      "loss": 0.14605838060379028,
      "step": 3328
    },
    {
      "epoch": 0.1655350792111219,
      "grad_norm": 1.05500066280365,
      "learning_rate": 0.0009488225396630347,
      "loss": 0.14362677931785583,
      "step": 3584
    },
    {
      "epoch": 0.17735901344048774,
      "grad_norm": 0.7869608402252197,
      "learning_rate": 0.0009401160421685646,
      "loss": 0.14176346361637115,
      "step": 3840
    },
    {
      "epoch": 0.18918294766985358,
      "grad_norm": 0.8075957298278809,
      "learning_rate": 0.0009307725649463714,
      "loss": 0.14215654134750366,
      "step": 4096
    },
    {
      "epoch": 0.18918294766985358,
      "eval_bleu": 0.0007156187561984728,
      "eval_loss": 0.1407095858291404,
      "eval_mse_loss": 0.1407095858291404,
      "step": 4096
    },
    {
      "epoch": 0.18918294766985358,
      "eval_bleu": 0.0007156187561984728,
      "eval_loss": 0.1407095858291404,
      "eval_mse_loss": 0.1407095858291404,
      "eval_runtime": 172.648,
      "eval_samples_per_second": 162.139,
      "eval_steps_per_second": 2.537,
      "step": 4096
    },
    {
      "epoch": 0.20100688189921945,
      "grad_norm": 1.2594881057739258,
      "learning_rate": 0.0009208056308063659,
      "loss": 0.1409526914358139,
      "step": 4352
    },
    {
      "epoch": 0.2128308161285853,
      "grad_norm": 1.2300289869308472,
      "learning_rate": 0.0009102296648873445,
      "loss": 0.14084666967391968,
      "step": 4608
    },
    {
      "epoch": 0.22465475035795113,
      "grad_norm": 1.4511398077011108,
      "learning_rate": 0.0008990599737794927,
      "loss": 0.13930904865264893,
      "step": 4864
    },
    {
      "epoch": 0.236478684587317,
      "grad_norm": 1.1964119672775269,
      "learning_rate": 0.0008873127233711644,
      "loss": 0.13842026889324188,
      "step": 5120
    },
    {
      "epoch": 0.24830261881668284,
      "grad_norm": 0.9578610062599182,
      "learning_rate": 0.0008750049154520011,
      "loss": 0.1392611265182495,
      "step": 5376
    },
    {
      "epoch": 0.2601265530460487,
      "grad_norm": 0.9959284067153931,
      "learning_rate": 0.0008621543631062487,
      "loss": 0.1368764489889145,
      "step": 5632
    },
    {
      "epoch": 0.27195048727541454,
      "grad_norm": 1.342193603515625,
      "learning_rate": 0.0008487796649318904,
      "loss": 0.13701793551445007,
      "step": 5888
    },
    {
      "epoch": 0.2837744215047804,
      "grad_norm": 0.5825753211975098,
      "learning_rate": 0.0008349001781229053,
      "loss": 0.13572891056537628,
      "step": 6144
    },
    {
      "epoch": 0.2955983557341462,
      "grad_norm": 1.275922417640686,
      "learning_rate": 0.0008205359904536107,
      "loss": 0.134858176112175,
      "step": 6400
    },
    {
      "epoch": 0.30742228996351206,
      "grad_norm": 1.0904085636138916,
      "learning_rate": 0.0008057078912056363,
      "loss": 0.13740675151348114,
      "step": 6656
    },
    {
      "epoch": 0.3192462241928779,
      "grad_norm": 0.7365452647209167,
      "learning_rate": 0.0007904373410796086,
      "loss": 0.13476549088954926,
      "step": 6912
    },
    {
      "epoch": 0.3310701584222438,
      "grad_norm": 0.9742300510406494,
      "learning_rate": 0.0007747464411350876,
      "loss": 0.1339239925146103,
      "step": 7168
    },
    {
      "epoch": 0.34289409265160964,
      "grad_norm": 1.1681714057922363,
      "learning_rate": 0.000758657900803716,
      "loss": 0.1327570527791977,
      "step": 7424
    },
    {
      "epoch": 0.3547180268809755,
      "grad_norm": 1.0932402610778809,
      "learning_rate": 0.000742195005021869,
      "loss": 0.13453976809978485,
      "step": 7680
    },
    {
      "epoch": 0.3665419611103413,
      "grad_norm": 1.7933037281036377,
      "learning_rate": 0.0007253815805303786,
      "loss": 0.1339324563741684,
      "step": 7936
    },
    {
      "epoch": 0.37836589533970716,
      "grad_norm": 1.258001446723938,
      "learning_rate": 0.0007082419613901028,
      "loss": 0.13321880996227264,
      "step": 8192
    },
    {
      "epoch": 0.37836589533970716,
      "eval_bleu": 0.0009159004592492724,
      "eval_loss": 0.13241331889953242,
      "eval_mse_loss": 0.13241331889953242,
      "step": 8192
    },
    {
      "epoch": 0.37836589533970716,
      "eval_bleu": 0.0009159004592492724,
      "eval_loss": 0.13241331889953242,
      "eval_mse_loss": 0.13241331889953242,
      "eval_runtime": 171.6296,
      "eval_samples_per_second": 163.101,
      "eval_steps_per_second": 2.552,
      "step": 8192
    },
    {
      "epoch": 0.390189829569073,
      "grad_norm": 2.0500435829162598,
      "learning_rate": 0.0006908009537632514,
      "loss": 0.13275721669197083,
      "step": 8448
    },
    {
      "epoch": 0.4020137637984389,
      "grad_norm": 1.0164549350738525,
      "learning_rate": 0.0006730838000114403,
      "loss": 0.13082970678806305,
      "step": 8704
    },
    {
      "epoch": 0.41383769802780473,
      "grad_norm": 0.9163410663604736,
      "learning_rate": 0.0006551161421624341,
      "loss": 0.1323855221271515,
      "step": 8960
    },
    {
      "epoch": 0.4256616322571706,
      "grad_norm": 0.8464987874031067,
      "learning_rate": 0.0006369239847984517,
      "loss": 0.12907665967941284,
      "step": 9216
    },
    {
      "epoch": 0.4374855664865364,
      "grad_norm": 0.790055513381958,
      "learning_rate": 0.0006185336574197479,
      "loss": 0.13018614053726196,
      "step": 9472
    },
    {
      "epoch": 0.44930950071590225,
      "grad_norm": 1.4321770668029785,
      "learning_rate": 0.0005999717763379407,
      "loss": 0.13014769554138184,
      "step": 9728
    },
    {
      "epoch": 0.4611334349452681,
      "grad_norm": 1.1316198110580444,
      "learning_rate": 0.0005812652061542363,
      "loss": 0.13009950518608093,
      "step": 9984
    },
    {
      "epoch": 0.472957369174634,
      "grad_norm": 2.499011516571045,
      "learning_rate": 0.0005624410208783071,
      "loss": 0.13046522438526154,
      "step": 10240
    },
    {
      "epoch": 0.48478130340399983,
      "grad_norm": 1.3082486391067505,
      "learning_rate": 0.0005435264647440881,
      "loss": 0.12951838970184326,
      "step": 10496
    },
    {
      "epoch": 0.49660523763336567,
      "grad_norm": 0.8309692144393921,
      "learning_rate": 0.000524548912779213,
      "loss": 0.1311841756105423,
      "step": 10752
    },
    {
      "epoch": 0.5084291718627315,
      "grad_norm": 2.236577272415161,
      "learning_rate": 0.0005055358311851499,
      "loss": 0.1328016221523285,
      "step": 11008
    },
    {
      "epoch": 0.5202531060920974,
      "grad_norm": 1.8365247249603271,
      "learning_rate": 0.0004865147375853812,
      "loss": 0.13411875069141388,
      "step": 11264
    },
    {
      "epoch": 0.5320770403214632,
      "grad_norm": 1.6082954406738281,
      "learning_rate": 0.0004675131611991607,
      "loss": 0.13458885252475739,
      "step": 11520
    },
    {
      "epoch": 0.5439009745508291,
      "grad_norm": 1.031647801399231,
      "learning_rate": 0.0004485586029984899,
      "loss": 0.13649903237819672,
      "step": 11776
    },
    {
      "epoch": 0.5557249087801949,
      "grad_norm": 1.5296710729599,
      "learning_rate": 0.00042967849590597266,
      "loss": 0.1377032846212387,
      "step": 12032
    },
    {
      "epoch": 0.5675488430095608,
      "grad_norm": 1.8958959579467773,
      "learning_rate": 0.0004109001650911621,
      "loss": 0.13875064253807068,
      "step": 12288
    },
    {
      "epoch": 0.5675488430095608,
      "eval_bleu": 0.0008588915725993688,
      "eval_loss": 0.13989224594477648,
      "eval_mse_loss": 0.13989224594477648,
      "step": 12288
    },
    {
      "epoch": 0.5675488430095608,
      "eval_bleu": 0.0008588915725993688,
      "eval_loss": 0.13989224594477648,
      "eval_mse_loss": 0.13989224594477648,
      "eval_runtime": 173.5527,
      "eval_samples_per_second": 161.294,
      "eval_steps_per_second": 2.524,
      "step": 12288
    },
    {
      "epoch": 0.5793727772389267,
      "grad_norm": 2.3443777561187744,
      "learning_rate": 0.0003922507884228551,
      "loss": 0.1418546885251999,
      "step": 12544
    },
    {
      "epoch": 0.5911967114682924,
      "grad_norm": 1.1060763597488403,
      "learning_rate": 0.00037375735713457723,
      "loss": 0.1433623880147934,
      "step": 12800
    },
    {
      "epoch": 0.6030206456976583,
      "grad_norm": 1.806127905845642,
      "learning_rate": 0.00035544663676018276,
      "loss": 0.14775635302066803,
      "step": 13056
    },
    {
      "epoch": 0.6148445799270241,
      "grad_norm": 1.7125252485275269,
      "learning_rate": 0.00033734512839611255,
      "loss": 0.14960132539272308,
      "step": 13312
    },
    {
      "epoch": 0.62666851415639,
      "grad_norm": 2.017378091812134,
      "learning_rate": 0.0003194790303463687,
      "loss": 0.15272539854049683,
      "step": 13568
    },
    {
      "epoch": 0.6384924483857558,
      "grad_norm": 2.1264116764068604,
      "learning_rate": 0.00030187420020572406,
      "loss": 0.15218184888362885,
      "step": 13824
    },
    {
      "epoch": 0.6503163826151217,
      "grad_norm": 1.8446365594863892,
      "learning_rate": 0.00028455611743603626,
      "loss": 0.1529884785413742,
      "step": 14080
    },
    {
      "epoch": 0.6621403168444876,
      "grad_norm": 2.2964935302734375,
      "learning_rate": 0.0002675498464898373,
      "loss": 0.15051132440567017,
      "step": 14336
    },
    {
      "epoch": 0.6739642510738534,
      "grad_norm": 2.4945242404937744,
      "learning_rate": 0.0002508800005345623,
      "loss": 0.14853885769844055,
      "step": 14592
    },
    {
      "epoch": 0.6857881853032193,
      "grad_norm": 1.3437820672988892,
      "learning_rate": 0.00023457070582992562,
      "loss": 0.14716462790966034,
      "step": 14848
    },
    {
      "epoch": 0.6976121195325851,
      "grad_norm": 1.631665587425232,
      "learning_rate": 0.00021864556680999692,
      "loss": 0.14523349702358246,
      "step": 15104
    },
    {
      "epoch": 0.709436053761951,
      "grad_norm": 1.9889062643051147,
      "learning_rate": 0.0002031276319205152,
      "loss": 0.14392541348934174,
      "step": 15360
    },
    {
      "epoch": 0.7212599879913169,
      "grad_norm": 2.4409310817718506,
      "learning_rate": 0.00018803936026088542,
      "loss": 0.14354340732097626,
      "step": 15616
    },
    {
      "epoch": 0.7330839222206826,
      "grad_norm": 2.1943178176879883,
      "learning_rate": 0.00017340258907913464,
      "loss": 0.14236165583133698,
      "step": 15872
    },
    {
      "epoch": 0.7449078564500485,
      "grad_norm": 7.1248555183410645,
      "learning_rate": 0.0001592385021668743,
      "loss": 0.14313820004463196,
      "step": 16128
    },
    {
      "epoch": 0.7567317906794143,
      "grad_norm": 1.3160756826400757,
      "learning_rate": 0.0001455675992000087,
      "loss": 0.1404125690460205,
      "step": 16384
    },
    {
      "epoch": 0.7567317906794143,
      "eval_bleu": 0.000725950642943874,
      "eval_loss": 0.1416369776101145,
      "eval_mse_loss": 0.1416369776101145,
      "step": 16384
    },
    {
      "epoch": 0.7567317906794143,
      "eval_bleu": 0.000725950642943874,
      "eval_loss": 0.1416369776101145,
      "eval_mse_loss": 0.1416369776101145,
      "eval_runtime": 172.4801,
      "eval_samples_per_second": 162.297,
      "eval_steps_per_second": 2.539,
      "step": 16384
    },
    {
      "epoch": 0.7685557249087802,
      "grad_norm": 2.9946746826171875,
      "learning_rate": 0.000132409666069565,
      "loss": 0.13992173969745636,
      "step": 16640
    },
    {
      "epoch": 0.780379659138146,
      "grad_norm": 1.9437847137451172,
      "learning_rate": 0.0001197837462455823,
      "loss": 0.1393483430147171,
      "step": 16896
    },
    {
      "epoch": 0.7922035933675119,
      "grad_norm": 1.5408047437667847,
      "learning_rate": 0.00010770811321550749,
      "loss": 0.139127716422081,
      "step": 17152
    },
    {
      "epoch": 0.8040275275968778,
      "grad_norm": 4.208256721496582,
      "learning_rate": 9.620024403698591e-05,
      "loss": 0.1388680338859558,
      "step": 17408
    },
    {
      "epoch": 0.8158514618262436,
      "grad_norm": 1.5926990509033203,
      "learning_rate": 8.527679404332429e-05,
      "loss": 0.13790729641914368,
      "step": 17664
    },
    {
      "epoch": 0.8276753960556095,
      "grad_norm": 1.5863239765167236,
      "learning_rate": 7.495357273823544e-05,
      "loss": 0.13762786984443665,
      "step": 17920
    },
    {
      "epoch": 0.8394993302849753,
      "grad_norm": 0.7356535792350769,
      "learning_rate": 6.524552091475183e-05,
      "loss": 0.13656531274318695,
      "step": 18176
    },
    {
      "epoch": 0.8513232645143411,
      "grad_norm": 1.0298752784729004,
      "learning_rate": 5.6166689031422024e-05,
      "loss": 0.13603614270687103,
      "step": 18432
    },
    {
      "epoch": 0.8631471987437069,
      "grad_norm": 0.8704520463943481,
      "learning_rate": 4.773021687709067e-05,
      "loss": 0.13718988001346588,
      "step": 18688
    },
    {
      "epoch": 0.8749711329730728,
      "grad_norm": 1.7993870973587036,
      "learning_rate": 3.994831455368719e-05,
      "loss": 0.13554991781711578,
      "step": 18944
    },
    {
      "epoch": 0.8867950672024387,
      "grad_norm": 1.9661895036697388,
      "learning_rate": 3.283224480455282e-05,
      "loss": 0.13669779896736145,
      "step": 19200
    },
    {
      "epoch": 0.8986190014318045,
      "grad_norm": 2.396397113800049,
      "learning_rate": 2.639230671387627e-05,
      "loss": 0.13444113731384277,
      "step": 19456
    },
    {
      "epoch": 0.9104429356611704,
      "grad_norm": 5.158544063568115,
      "learning_rate": 2.063782080083576e-05,
      "loss": 0.13486656546592712,
      "step": 19712
    },
    {
      "epoch": 0.9222668698905362,
      "grad_norm": 2.635748863220215,
      "learning_rate": 1.557711553001523e-05,
      "loss": 0.13480573892593384,
      "step": 19968
    },
    {
      "epoch": 0.9340908041199021,
      "grad_norm": 1.383921504020691,
      "learning_rate": 1.1217515257622269e-05,
      "loss": 0.13407942652702332,
      "step": 20224
    },
    {
      "epoch": 0.945914738349268,
      "grad_norm": 1.3553746938705444,
      "learning_rate": 7.565329630950746e-06,
      "loss": 0.13326187431812286,
      "step": 20480
    },
    {
      "epoch": 0.945914738349268,
      "eval_bleu": 0.0007028356585600878,
      "eval_loss": 0.13298223137039028,
      "eval_mse_loss": 0.13298223137039028,
      "step": 20480
    },
    {
      "epoch": 0.945914738349268,
      "eval_bleu": 0.0007028356585600878,
      "eval_loss": 0.13298223137039028,
      "eval_mse_loss": 0.13298223137039028,
      "eval_runtime": 172.3836,
      "eval_samples_per_second": 162.388,
      "eval_steps_per_second": 2.541,
      "step": 20480
    }
  ],
  "logging_steps": 256,
  "max_steps": 21651,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4096,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}