{
  "best_global_step": 1750,
  "best_metric": 0.21951219512195122,
  "best_model_checkpoint": "out_qwen_4b_sft_augmented/checkpoint-1750",
  "epoch": 2.9185243637798384,
  "eval_steps": 50,
  "global_step": 1850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015782205563227462,
      "grad_norm": 324.9078480271927,
      "learning_rate": 2.3560209424083772e-07,
      "loss": 36.8443,
      "step": 10,
      "true_loss": 4.5233
    },
    {
      "epoch": 0.031564411126454923,
      "grad_norm": 168.6194251999255,
      "learning_rate": 4.973821989528796e-07,
      "loss": 36.0645,
      "step": 20,
      "true_loss": 4.3899
    },
    {
      "epoch": 0.04734661668968238,
      "grad_norm": 192.6442003874084,
      "learning_rate": 7.591623036649215e-07,
      "loss": 37.1343,
      "step": 30,
      "true_loss": 4.7917
    },
    {
      "epoch": 0.06312882225290985,
      "grad_norm": 169.69405108448686,
      "learning_rate": 1.0209424083769635e-06,
      "loss": 35.8286,
      "step": 40,
      "true_loss": 4.5888
    },
    {
      "epoch": 0.0789110278161373,
      "grad_norm": 177.6752080525516,
      "learning_rate": 1.2827225130890052e-06,
      "loss": 35.1516,
      "step": 50,
      "true_loss": 4.1833
    },
    {
      "epoch": 0.0789110278161373,
      "eval_accuracy": 0.02328159645232816,
      "eval_loss": 4.40457820892334,
      "eval_runtime": 23.7263,
      "eval_samples_per_second": 38.017,
      "eval_steps_per_second": 4.763,
      "step": 50
    },
    {
      "epoch": 0.09469323337936476,
      "grad_norm": 175.29116271759068,
      "learning_rate": 1.5445026178010472e-06,
      "loss": 34.7314,
      "step": 60,
      "true_loss": 4.224
    },
    {
      "epoch": 0.11047543894259222,
      "grad_norm": 753.0264561952334,
      "learning_rate": 1.8062827225130891e-06,
      "loss": 33.9206,
      "step": 70,
      "true_loss": 4.0565
    },
    {
      "epoch": 0.1262576445058197,
      "grad_norm": 200.47588314223879,
      "learning_rate": 2.068062827225131e-06,
      "loss": 34.0037,
      "step": 80,
      "true_loss": 4.3621
    },
    {
      "epoch": 0.14203985006904715,
      "grad_norm": 164.18077066091436,
      "learning_rate": 2.329842931937173e-06,
      "loss": 33.3705,
      "step": 90,
      "true_loss": 4.1432
    },
    {
      "epoch": 0.1578220556322746,
      "grad_norm": 144.60587833889255,
      "learning_rate": 2.591623036649215e-06,
      "loss": 33.3276,
      "step": 100,
      "true_loss": 4.1424
    },
    {
      "epoch": 0.1578220556322746,
      "eval_accuracy": 0.043237250554323724,
      "eval_loss": 4.096348285675049,
      "eval_runtime": 23.3422,
      "eval_samples_per_second": 38.643,
      "eval_steps_per_second": 4.841,
      "step": 100
    },
    {
      "epoch": 0.17360426119550207,
      "grad_norm": 270.635578631285,
      "learning_rate": 2.853403141361257e-06,
      "loss": 32.6581,
      "step": 110,
      "true_loss": 4.1497
    },
    {
      "epoch": 0.18938646675872953,
      "grad_norm": 100.33088317059614,
      "learning_rate": 3.115183246073299e-06,
      "loss": 32.8629,
      "step": 120,
      "true_loss": 4.1273
    },
    {
      "epoch": 0.20516867232195699,
      "grad_norm": 108.96506382691295,
      "learning_rate": 3.3769633507853404e-06,
      "loss": 33.0279,
      "step": 130,
      "true_loss": 4.1729
    },
    {
      "epoch": 0.22095087788518444,
      "grad_norm": 101.57985399798042,
      "learning_rate": 3.6387434554973826e-06,
      "loss": 33.3713,
      "step": 140,
      "true_loss": 4.2379
    },
    {
      "epoch": 0.2367330834484119,
      "grad_norm": 109.81214136700734,
      "learning_rate": 3.900523560209425e-06,
      "loss": 33.2539,
      "step": 150,
      "true_loss": 4.388
    },
    {
      "epoch": 0.2367330834484119,
      "eval_accuracy": 0.04434589800443459,
      "eval_loss": 4.049750328063965,
      "eval_runtime": 23.5037,
      "eval_samples_per_second": 38.377,
      "eval_steps_per_second": 4.808,
      "step": 150
    },
    {
      "epoch": 0.2525152890116394,
      "grad_norm": 131.31761293379333,
      "learning_rate": 4.1623036649214665e-06,
      "loss": 32.8656,
      "step": 160,
      "true_loss": 4.1088
    },
    {
      "epoch": 0.26829749457486685,
      "grad_norm": 93.21133961816744,
      "learning_rate": 4.424083769633508e-06,
      "loss": 32.7579,
      "step": 170,
      "true_loss": 4.092
    },
    {
      "epoch": 0.2840797001380943,
      "grad_norm": 99.10049214777489,
      "learning_rate": 4.68586387434555e-06,
      "loss": 32.777,
      "step": 180,
      "true_loss": 4.1288
    },
    {
      "epoch": 0.29986190570132176,
      "grad_norm": 103.48370344024212,
      "learning_rate": 4.947643979057592e-06,
      "loss": 32.983,
      "step": 190,
      "true_loss": 3.9901
    },
    {
      "epoch": 0.3156441112645492,
      "grad_norm": 101.42410788589872,
      "learning_rate": 4.976621858562245e-06,
      "loss": 32.8281,
      "step": 200,
      "true_loss": 4.1047
    },
    {
      "epoch": 0.3156441112645492,
      "eval_accuracy": 0.06873614190687362,
      "eval_loss": 4.009181022644043,
      "eval_runtime": 23.3653,
      "eval_samples_per_second": 38.604,
      "eval_steps_per_second": 4.836,
      "step": 200
    },
    {
      "epoch": 0.3314263168277767,
      "grad_norm": 83.2901468921201,
      "learning_rate": 4.94739918176505e-06,
      "loss": 33.1028,
      "step": 210,
      "true_loss": 4.0052
    },
    {
      "epoch": 0.34720852239100414,
      "grad_norm": 170.23336077552057,
      "learning_rate": 4.9181765049678555e-06,
      "loss": 32.644,
      "step": 220,
      "true_loss": 4.1984
    },
    {
      "epoch": 0.3629907279542316,
      "grad_norm": 73.10967930914595,
      "learning_rate": 4.888953828170661e-06,
      "loss": 32.9998,
      "step": 230,
      "true_loss": 4.1035
    },
    {
      "epoch": 0.37877293351745905,
      "grad_norm": 75.66187004852954,
      "learning_rate": 4.859731151373466e-06,
      "loss": 32.6017,
      "step": 240,
      "true_loss": 3.9774
    },
    {
      "epoch": 0.3945551390806865,
      "grad_norm": 101.5303291876841,
      "learning_rate": 4.830508474576272e-06,
      "loss": 32.5215,
      "step": 250,
      "true_loss": 4.107
    },
    {
      "epoch": 0.3945551390806865,
      "eval_accuracy": 0.07095343680709534,
      "eval_loss": 3.933732271194458,
      "eval_runtime": 23.3822,
      "eval_samples_per_second": 38.576,
      "eval_steps_per_second": 4.833,
      "step": 250
    },
    {
      "epoch": 0.41033734464391397,
      "grad_norm": 87.68390524050062,
      "learning_rate": 4.801285797779077e-06,
      "loss": 32.8537,
      "step": 260,
      "true_loss": 4.0852
    },
    {
      "epoch": 0.42611955020714143,
      "grad_norm": 83.56798040873913,
      "learning_rate": 4.772063120981883e-06,
      "loss": 32.452,
      "step": 270,
      "true_loss": 4.1138
    },
    {
      "epoch": 0.4419017557703689,
      "grad_norm": 76.69106361052454,
      "learning_rate": 4.742840444184687e-06,
      "loss": 31.8737,
      "step": 280,
      "true_loss": 3.8671
    },
    {
      "epoch": 0.45768396133359635,
      "grad_norm": 79.70560950668154,
      "learning_rate": 4.713617767387494e-06,
      "loss": 32.1678,
      "step": 290,
      "true_loss": 3.9949
    },
    {
      "epoch": 0.4734661668968238,
      "grad_norm": 77.14726547694464,
      "learning_rate": 4.684395090590298e-06,
      "loss": 32.2324,
      "step": 300,
      "true_loss": 4.1541
    },
    {
      "epoch": 0.4734661668968238,
      "eval_accuracy": 0.07206208425720621,
      "eval_loss": 3.944307804107666,
      "eval_runtime": 24.0666,
      "eval_samples_per_second": 37.479,
      "eval_steps_per_second": 4.695,
      "step": 300
    },
    {
      "epoch": 0.4892483724600513,
      "grad_norm": 74.39357075334843,
      "learning_rate": 4.655172413793104e-06,
      "loss": 32.7538,
      "step": 310,
      "true_loss": 3.9691
    },
    {
      "epoch": 0.5050305780232788,
      "grad_norm": 69.2140729496397,
      "learning_rate": 4.625949736995909e-06,
      "loss": 32.241,
      "step": 320,
      "true_loss": 4.1026
    },
    {
      "epoch": 0.5208127835865062,
      "grad_norm": 76.34039893901215,
      "learning_rate": 4.596727060198715e-06,
      "loss": 32.7047,
      "step": 330,
      "true_loss": 4.2664
    },
    {
      "epoch": 0.5365949891497337,
      "grad_norm": 76.48584051124504,
      "learning_rate": 4.56750438340152e-06,
      "loss": 32.2899,
      "step": 340,
      "true_loss": 4.1581
    },
    {
      "epoch": 0.5523771947129611,
      "grad_norm": 75.38836139042635,
      "learning_rate": 4.5382817066043256e-06,
      "loss": 32.8474,
      "step": 350,
      "true_loss": 4.0243
    },
    {
      "epoch": 0.5523771947129611,
      "eval_accuracy": 0.07317073170731707,
      "eval_loss": 3.8937127590179443,
      "eval_runtime": 23.6141,
      "eval_samples_per_second": 38.198,
      "eval_steps_per_second": 4.785,
      "step": 350
    },
    {
      "epoch": 0.5681594002761886,
      "grad_norm": 85.00115390444991,
      "learning_rate": 4.509059029807131e-06,
      "loss": 31.7532,
      "step": 360,
      "true_loss": 3.988
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 76.08205167618928,
      "learning_rate": 4.479836353009936e-06,
      "loss": 31.7753,
      "step": 370,
      "true_loss": 3.9777
    },
    {
      "epoch": 0.5997238114026435,
      "grad_norm": 68.74246027512453,
      "learning_rate": 4.450613676212742e-06,
      "loss": 31.4578,
      "step": 380,
      "true_loss": 3.9916
    },
    {
      "epoch": 0.6155060169658709,
      "grad_norm": 71.81332443942438,
      "learning_rate": 4.4213909994155465e-06,
      "loss": 32.0656,
      "step": 390,
      "true_loss": 4.1254
    },
    {
      "epoch": 0.6312882225290984,
      "grad_norm": 71.77472037885094,
      "learning_rate": 4.392168322618352e-06,
      "loss": 32.2929,
      "step": 400,
      "true_loss": 3.8869
    },
    {
      "epoch": 0.6312882225290984,
      "eval_accuracy": 0.1130820399113082,
      "eval_loss": 3.7887723445892334,
      "eval_runtime": 23.904,
      "eval_samples_per_second": 37.734,
      "eval_steps_per_second": 4.727,
      "step": 400
    },
    {
      "epoch": 0.647070428092326,
      "grad_norm": 71.4147738866297,
      "learning_rate": 4.3629456458211574e-06,
      "loss": 31.9759,
      "step": 410,
      "true_loss": 3.9893
    },
    {
      "epoch": 0.6628526336555534,
      "grad_norm": 73.99693807240743,
      "learning_rate": 4.333722969023963e-06,
      "loss": 31.8449,
      "step": 420,
      "true_loss": 3.9648
    },
    {
      "epoch": 0.6786348392187809,
      "grad_norm": 74.124412349921,
      "learning_rate": 4.304500292226768e-06,
      "loss": 31.9984,
      "step": 430,
      "true_loss": 3.8608
    },
    {
      "epoch": 0.6944170447820083,
      "grad_norm": 80.24673254296576,
      "learning_rate": 4.275277615429574e-06,
      "loss": 31.8185,
      "step": 440,
      "true_loss": 4.033
    },
    {
      "epoch": 0.7101992503452358,
      "grad_norm": 83.65131551190922,
      "learning_rate": 4.246054938632379e-06,
      "loss": 31.7604,
      "step": 450,
      "true_loss": 3.9851
    },
    {
      "epoch": 0.7101992503452358,
      "eval_accuracy": 0.11862527716186252,
      "eval_loss": 3.731326103210449,
      "eval_runtime": 23.8861,
      "eval_samples_per_second": 37.762,
      "eval_steps_per_second": 4.731,
      "step": 450
    },
    {
      "epoch": 0.7259814559084632,
      "grad_norm": 82.91785549569512,
      "learning_rate": 4.216832261835184e-06,
      "loss": 31.9212,
      "step": 460,
      "true_loss": 4.0262
    },
    {
      "epoch": 0.7417636614716907,
      "grad_norm": 77.3700837190592,
      "learning_rate": 4.18760958503799e-06,
      "loss": 31.558,
      "step": 470,
      "true_loss": 3.9037
    },
    {
      "epoch": 0.7575458670349181,
      "grad_norm": 79.2567711758356,
      "learning_rate": 4.158386908240795e-06,
      "loss": 31.9821,
      "step": 480,
      "true_loss": 3.9674
    },
    {
      "epoch": 0.7733280725981456,
      "grad_norm": 79.15209026205977,
      "learning_rate": 4.1291642314436e-06,
      "loss": 31.6287,
      "step": 490,
      "true_loss": 4.0236
    },
    {
      "epoch": 0.789110278161373,
      "grad_norm": 82.91621808879624,
      "learning_rate": 4.0999415546464065e-06,
      "loss": 31.1936,
      "step": 500,
      "true_loss": 3.8798
    },
    {
      "epoch": 0.789110278161373,
      "eval_accuracy": 0.1419068736141907,
      "eval_loss": 3.6688694953918457,
      "eval_runtime": 23.5535,
      "eval_samples_per_second": 38.296,
      "eval_steps_per_second": 4.798,
      "step": 500
    },
    {
      "epoch": 0.8048924837246005,
      "grad_norm": 81.33416413304444,
      "learning_rate": 4.070718877849211e-06,
      "loss": 31.9352,
      "step": 510,
      "true_loss": 3.9601
    },
    {
      "epoch": 0.8206746892878279,
      "grad_norm": 84.38809367146038,
      "learning_rate": 4.0414962010520166e-06,
      "loss": 31.4177,
      "step": 520,
      "true_loss": 4.0845
    },
    {
      "epoch": 0.8364568948510555,
      "grad_norm": 71.30053276240011,
      "learning_rate": 4.012273524254822e-06,
      "loss": 31.7603,
      "step": 530,
      "true_loss": 3.997
    },
    {
      "epoch": 0.8522391004142829,
      "grad_norm": 80.60566610130194,
      "learning_rate": 3.9830508474576275e-06,
      "loss": 31.2764,
      "step": 540,
      "true_loss": 3.8168
    },
    {
      "epoch": 0.8680213059775104,
      "grad_norm": 91.53898913592603,
      "learning_rate": 3.953828170660433e-06,
      "loss": 31.4915,
      "step": 550,
      "true_loss": 3.9316
    },
    {
      "epoch": 0.8680213059775104,
      "eval_accuracy": 0.1419068736141907,
      "eval_loss": 3.6105031967163086,
      "eval_runtime": 23.4993,
      "eval_samples_per_second": 38.384,
      "eval_steps_per_second": 4.809,
      "step": 550
    },
    {
      "epoch": 0.8838035115407378,
      "grad_norm": 80.87596019476308,
      "learning_rate": 3.924605493863238e-06,
      "loss": 31.1347,
      "step": 560,
      "true_loss": 3.7968
    },
    {
      "epoch": 0.8995857171039653,
      "grad_norm": 80.68070986181071,
      "learning_rate": 3.895382817066044e-06,
      "loss": 31.7808,
      "step": 570,
      "true_loss": 3.9588
    },
    {
      "epoch": 0.9153679226671927,
      "grad_norm": 82.14608732630818,
      "learning_rate": 3.8661601402688484e-06,
      "loss": 31.0608,
      "step": 580,
      "true_loss": 3.9779
    },
    {
      "epoch": 0.9311501282304202,
      "grad_norm": 79.11284293573352,
      "learning_rate": 3.836937463471655e-06,
      "loss": 30.9633,
      "step": 590,
      "true_loss": 4.0027
    },
    {
      "epoch": 0.9469323337936476,
      "grad_norm": 74.83038134855214,
      "learning_rate": 3.8077147866744598e-06,
      "loss": 31.2218,
      "step": 600,
      "true_loss": 3.8863
    },
    {
      "epoch": 0.9469323337936476,
      "eval_accuracy": 0.1419068736141907,
      "eval_loss": 3.6132075786590576,
      "eval_runtime": 24.0285,
      "eval_samples_per_second": 37.539,
      "eval_steps_per_second": 4.703,
      "step": 600
    },
    {
      "epoch": 0.9627145393568751,
      "grad_norm": 77.6288128447819,
      "learning_rate": 3.7784921098772652e-06,
      "loss": 31.104,
      "step": 610,
      "true_loss": 3.8553
    },
    {
      "epoch": 0.9784967449201026,
      "grad_norm": 78.73674435660126,
      "learning_rate": 3.7492694330800707e-06,
      "loss": 31.4592,
      "step": 620,
      "true_loss": 3.8146
    },
    {
      "epoch": 0.99427895048333,
      "grad_norm": 84.19142784542193,
      "learning_rate": 3.7200467562828757e-06,
      "loss": 31.4694,
      "step": 630,
      "true_loss": 3.8633
    },
    {
      "epoch": 1.0094693233379364,
      "grad_norm": 83.97120538549059,
      "learning_rate": 3.6908240794856816e-06,
      "loss": 29.9569,
      "step": 640,
      "true_loss": 3.9506
    },
    {
      "epoch": 1.0252515289011639,
      "grad_norm": 78.03329090311782,
      "learning_rate": 3.6616014026884866e-06,
      "loss": 30.6145,
      "step": 650,
      "true_loss": 3.8972
    },
    {
      "epoch": 1.0252515289011639,
      "eval_accuracy": 0.13303769401330376,
      "eval_loss": 3.5806682109832764,
      "eval_runtime": 23.4297,
      "eval_samples_per_second": 38.498,
      "eval_steps_per_second": 4.823,
      "step": 650
    },
    {
      "epoch": 1.0410337344643914,
      "grad_norm": 90.48371602841107,
      "learning_rate": 3.6323787258912916e-06,
      "loss": 30.3281,
      "step": 660,
      "true_loss": 4.0951
    },
    {
      "epoch": 1.056815940027619,
      "grad_norm": 80.37129983569977,
      "learning_rate": 3.6031560490940975e-06,
      "loss": 30.4516,
      "step": 670,
      "true_loss": 4.0298
    },
    {
      "epoch": 1.0725981455908462,
      "grad_norm": 89.0421974632656,
      "learning_rate": 3.5739333722969025e-06,
      "loss": 30.5053,
      "step": 680,
      "true_loss": 3.838
    },
    {
      "epoch": 1.0883803511540737,
      "grad_norm": 87.6238382263665,
      "learning_rate": 3.544710695499708e-06,
      "loss": 30.1458,
      "step": 690,
      "true_loss": 3.4672
    },
    {
      "epoch": 1.1041625567173012,
      "grad_norm": 93.33199336725635,
      "learning_rate": 3.5154880187025135e-06,
      "loss": 29.9857,
      "step": 700,
      "true_loss": 3.8479
    },
    {
      "epoch": 1.1041625567173012,
      "eval_accuracy": 0.1574279379157428,
      "eval_loss": 3.5641186237335205,
      "eval_runtime": 23.6052,
      "eval_samples_per_second": 38.212,
      "eval_steps_per_second": 4.787,
      "step": 700
    },
    {
      "epoch": 1.1199447622805287,
      "grad_norm": 92.22724838108498,
      "learning_rate": 3.486265341905319e-06,
      "loss": 29.8985,
      "step": 710,
      "true_loss": 3.6761
    },
    {
      "epoch": 1.1357269678437563,
      "grad_norm": 84.13971221580583,
      "learning_rate": 3.457042665108124e-06,
      "loss": 30.7157,
      "step": 720,
      "true_loss": 3.6518
    },
    {
      "epoch": 1.1515091734069836,
      "grad_norm": 85.8960190061776,
      "learning_rate": 3.42781998831093e-06,
      "loss": 30.2104,
      "step": 730,
      "true_loss": 3.7526
    },
    {
      "epoch": 1.167291378970211,
      "grad_norm": 86.69215126012148,
      "learning_rate": 3.398597311513735e-06,
      "loss": 29.405,
      "step": 740,
      "true_loss": 4.0226
    },
    {
      "epoch": 1.1830735845334386,
      "grad_norm": 87.86033437742292,
      "learning_rate": 3.3693746347165403e-06,
      "loss": 30.511,
      "step": 750,
      "true_loss": 3.7897
    },
    {
      "epoch": 1.1830735845334386,
      "eval_accuracy": 0.14523281596452328,
      "eval_loss": 3.493298292160034,
      "eval_runtime": 23.8274,
      "eval_samples_per_second": 37.856,
      "eval_steps_per_second": 4.742,
      "step": 750
    },
    {
      "epoch": 1.198855790096666,
      "grad_norm": 111.93866332819323,
      "learning_rate": 3.3401519579193458e-06,
      "loss": 29.8573,
      "step": 760,
      "true_loss": 3.7307
    },
    {
      "epoch": 1.2146379956598934,
      "grad_norm": 78.19039410059621,
      "learning_rate": 3.310929281122151e-06,
      "loss": 30.2595,
      "step": 770,
      "true_loss": 3.7585
    },
    {
      "epoch": 1.230420201223121,
      "grad_norm": 136.24794475282891,
      "learning_rate": 3.2817066043249562e-06,
      "loss": 30.1392,
      "step": 780,
      "true_loss": 3.6031
    },
    {
      "epoch": 1.2462024067863484,
      "grad_norm": 83.26617285476617,
      "learning_rate": 3.252483927527762e-06,
      "loss": 29.7774,
      "step": 790,
      "true_loss": 3.8831
    },
    {
      "epoch": 1.261984612349576,
      "grad_norm": 82.12832696286748,
      "learning_rate": 3.223261250730567e-06,
      "loss": 30.2729,
      "step": 800,
      "true_loss": 3.7239
    },
    {
      "epoch": 1.261984612349576,
      "eval_accuracy": 0.15964523281596452,
      "eval_loss": 3.5300114154815674,
      "eval_runtime": 23.4485,
      "eval_samples_per_second": 38.467,
      "eval_steps_per_second": 4.819,
      "step": 800
    },
    {
      "epoch": 1.2777668179128034,
      "grad_norm": 90.3512257461839,
      "learning_rate": 3.194038573933372e-06,
      "loss": 30.1961,
      "step": 810,
      "true_loss": 3.784
    },
    {
      "epoch": 1.2935490234760307,
      "grad_norm": 84.55475078707286,
      "learning_rate": 3.164815897136178e-06,
      "loss": 29.3181,
      "step": 820,
      "true_loss": 3.5114
    },
    {
      "epoch": 1.3093312290392582,
      "grad_norm": 89.4992221052368,
      "learning_rate": 3.135593220338983e-06,
      "loss": 30.2988,
      "step": 830,
      "true_loss": 3.7831
    },
    {
      "epoch": 1.3251134346024858,
      "grad_norm": 92.43123125189919,
      "learning_rate": 3.1063705435417885e-06,
      "loss": 30.0873,
      "step": 840,
      "true_loss": 3.8634
    },
    {
      "epoch": 1.340895640165713,
      "grad_norm": 89.04832868320074,
      "learning_rate": 3.0771478667445944e-06,
      "loss": 30.2665,
      "step": 850,
      "true_loss": 3.8983
    },
    {
      "epoch": 1.340895640165713,
      "eval_accuracy": 0.16851441241685144,
      "eval_loss": 3.462191343307495,
      "eval_runtime": 23.8924,
      "eval_samples_per_second": 37.753,
      "eval_steps_per_second": 4.73,
      "step": 850
    },
    {
      "epoch": 1.3566778457289406,
      "grad_norm": 92.16494941680725,
      "learning_rate": 3.0479251899473994e-06,
      "loss": 29.7738,
      "step": 860,
      "true_loss": 4.0234
    },
    {
      "epoch": 1.372460051292168,
      "grad_norm": 85.57074344764075,
      "learning_rate": 3.0187025131502045e-06,
      "loss": 30.0651,
      "step": 870,
      "true_loss": 3.7162
    },
    {
      "epoch": 1.3882422568553956,
      "grad_norm": 97.12213474754635,
      "learning_rate": 2.9894798363530103e-06,
      "loss": 30.0534,
      "step": 880,
      "true_loss": 3.969
    },
    {
      "epoch": 1.404024462418623,
      "grad_norm": 85.14532114581857,
      "learning_rate": 2.9602571595558154e-06,
      "loss": 30.1717,
      "step": 890,
      "true_loss": 3.8654
    },
    {
      "epoch": 1.4198066679818504,
      "grad_norm": 89.01307343902022,
      "learning_rate": 2.931034482758621e-06,
      "loss": 30.2877,
      "step": 900,
      "true_loss": 3.6224
    },
    {
      "epoch": 1.4198066679818504,
      "eval_accuracy": 0.16186252771618626,
      "eval_loss": 3.4574382305145264,
      "eval_runtime": 23.3454,
      "eval_samples_per_second": 38.637,
      "eval_steps_per_second": 4.84,
      "step": 900
    },
    {
      "epoch": 1.435588873545078,
      "grad_norm": 87.24388793474637,
      "learning_rate": 2.9018118059614263e-06,
      "loss": 30.8903,
      "step": 910,
      "true_loss": 3.8262
    },
    {
      "epoch": 1.4513710791083054,
      "grad_norm": 84.04918766102597,
      "learning_rate": 2.8725891291642317e-06,
      "loss": 29.8196,
      "step": 920,
      "true_loss": 3.918
    },
    {
      "epoch": 1.4671532846715327,
      "grad_norm": 83.16951966482195,
      "learning_rate": 2.8433664523670368e-06,
      "loss": 29.6097,
      "step": 930,
      "true_loss": 3.4664
    },
    {
      "epoch": 1.4829354902347602,
      "grad_norm": 96.29394268139959,
      "learning_rate": 2.8141437755698426e-06,
      "loss": 29.7147,
      "step": 940,
      "true_loss": 3.6577
    },
    {
      "epoch": 1.4987176957979877,
      "grad_norm": 101.35324066409235,
      "learning_rate": 2.7849210987726477e-06,
      "loss": 29.4593,
      "step": 950,
      "true_loss": 3.6391
    },
    {
      "epoch": 1.4987176957979877,
      "eval_accuracy": 0.15188470066518847,
      "eval_loss": 3.448209762573242,
      "eval_runtime": 23.74,
      "eval_samples_per_second": 37.995,
      "eval_steps_per_second": 4.76,
      "step": 950
    },
    {
      "epoch": 1.5144999013612153,
      "grad_norm": 91.01958083657513,
      "learning_rate": 2.7556984219754535e-06,
      "loss": 29.4563,
      "step": 960,
      "true_loss": 3.5778
    },
    {
      "epoch": 1.5302821069244428,
      "grad_norm": 94.87158519297142,
      "learning_rate": 2.7264757451782586e-06,
      "loss": 29.8641,
      "step": 970,
      "true_loss": 3.9124
    },
    {
      "epoch": 1.5460643124876703,
      "grad_norm": 84.01959219280997,
      "learning_rate": 2.697253068381064e-06,
      "loss": 29.8265,
      "step": 980,
      "true_loss": 3.5047
    },
    {
      "epoch": 1.5618465180508976,
      "grad_norm": 91.64799353240991,
      "learning_rate": 2.6680303915838695e-06,
      "loss": 29.858,
      "step": 990,
      "true_loss": 3.701
    },
    {
      "epoch": 1.577628723614125,
      "grad_norm": 88.05009850532113,
      "learning_rate": 2.638807714786675e-06,
      "loss": 29.9069,
      "step": 1000,
      "true_loss": 3.6317
    },
    {
      "epoch": 1.577628723614125,
      "eval_accuracy": 0.14412416851441243,
      "eval_loss": 3.4386119842529297,
      "eval_runtime": 24.0921,
      "eval_samples_per_second": 37.44,
      "eval_steps_per_second": 4.69,
      "step": 1000
    },
    {
      "epoch": 1.5934109291773524,
      "grad_norm": 88.61468815912133,
      "learning_rate": 2.60958503798948e-06,
      "loss": 29.7709,
      "step": 1010,
      "true_loss": 3.6406
    },
    {
      "epoch": 1.60919313474058,
      "grad_norm": 85.25549864190619,
      "learning_rate": 2.580362361192286e-06,
      "loss": 29.8656,
      "step": 1020,
      "true_loss": 4.0205
    },
    {
      "epoch": 1.6249753403038074,
      "grad_norm": 95.17123739206981,
      "learning_rate": 2.551139684395091e-06,
      "loss": 29.3146,
      "step": 1030,
      "true_loss": 3.7517
    },
    {
      "epoch": 1.640757545867035,
      "grad_norm": 94.05266971651754,
      "learning_rate": 2.521917007597896e-06,
      "loss": 29.5985,
      "step": 1040,
      "true_loss": 3.8767
    },
    {
      "epoch": 1.6565397514302624,
      "grad_norm": 84.23330948930467,
      "learning_rate": 2.4926943308007014e-06,
      "loss": 29.6116,
      "step": 1050,
      "true_loss": 3.6806
    },
    {
      "epoch": 1.6565397514302624,
      "eval_accuracy": 0.1574279379157428,
      "eval_loss": 3.4331889152526855,
      "eval_runtime": 24.0418,
      "eval_samples_per_second": 37.518,
      "eval_steps_per_second": 4.7,
      "step": 1050
    },
    {
      "epoch": 1.67232195699349,
      "grad_norm": 95.80967931580453,
      "learning_rate": 2.463471654003507e-06,
      "loss": 29.4546,
      "step": 1060,
      "true_loss": 3.5296
    },
    {
      "epoch": 1.6881041625567172,
      "grad_norm": 89.21975858244956,
      "learning_rate": 2.4342489772063123e-06,
      "loss": 29.4728,
      "step": 1070,
      "true_loss": 3.8411
    },
    {
      "epoch": 1.7038863681199448,
      "grad_norm": 93.36233191510571,
      "learning_rate": 2.4050263004091177e-06,
      "loss": 29.5254,
      "step": 1080,
      "true_loss": 3.7742
    },
    {
      "epoch": 1.7196685736831723,
      "grad_norm": 107.3636400374849,
      "learning_rate": 2.375803623611923e-06,
      "loss": 29.5684,
      "step": 1090,
      "true_loss": 3.6389
    },
    {
      "epoch": 1.7354507792463996,
      "grad_norm": 1304.6259656582167,
      "learning_rate": 2.3465809468147286e-06,
      "loss": 29.638,
      "step": 1100,
      "true_loss": 3.7105
    },
    {
      "epoch": 1.7354507792463996,
      "eval_accuracy": 0.16518847006651885,
      "eval_loss": 3.4311046600341797,
      "eval_runtime": 23.6704,
      "eval_samples_per_second": 38.107,
      "eval_steps_per_second": 4.774,
      "step": 1100
    },
    {
      "epoch": 1.751232984809627,
      "grad_norm": 96.2130469861494,
      "learning_rate": 2.3173582700175337e-06,
      "loss": 29.3766,
      "step": 1110,
      "true_loss": 3.67
    },
    {
      "epoch": 1.7670151903728546,
      "grad_norm": 95.92673596052384,
      "learning_rate": 2.288135593220339e-06,
      "loss": 29.3919,
      "step": 1120,
      "true_loss": 3.8554
    },
    {
      "epoch": 1.782797395936082,
      "grad_norm": 88.05948564467495,
      "learning_rate": 2.2589129164231446e-06,
      "loss": 29.2821,
      "step": 1130,
      "true_loss": 3.7715
    },
    {
      "epoch": 1.7985796014993096,
      "grad_norm": 90.55869365935298,
      "learning_rate": 2.22969023962595e-06,
      "loss": 29.7986,
      "step": 1140,
      "true_loss": 3.6651
    },
    {
      "epoch": 1.8143618070625371,
      "grad_norm": 94.20405819159555,
      "learning_rate": 2.2004675628287555e-06,
      "loss": 29.8496,
      "step": 1150,
      "true_loss": 3.7782
    },
    {
      "epoch": 1.8143618070625371,
      "eval_accuracy": 0.16186252771618626,
      "eval_loss": 3.4140689373016357,
      "eval_runtime": 24.0501,
      "eval_samples_per_second": 37.505,
      "eval_steps_per_second": 4.699,
      "step": 1150
    },
    {
      "epoch": 1.8301440126257644,
      "grad_norm": 87.96745013401917,
      "learning_rate": 2.171244886031561e-06,
      "loss": 29.5695,
      "step": 1160,
      "true_loss": 3.8398
    },
    {
      "epoch": 1.845926218188992,
      "grad_norm": 92.10246815773178,
      "learning_rate": 2.142022209234366e-06,
      "loss": 29.8099,
      "step": 1170,
      "true_loss": 3.9006
    },
    {
      "epoch": 1.8617084237522192,
      "grad_norm": 83.12415816117908,
      "learning_rate": 2.1127995324371714e-06,
      "loss": 30.2325,
      "step": 1180,
      "true_loss": 3.623
    },
    {
      "epoch": 1.8774906293154467,
      "grad_norm": 107.24249122552868,
      "learning_rate": 2.083576855639977e-06,
      "loss": 29.8222,
      "step": 1190,
      "true_loss": 3.5215
    },
    {
      "epoch": 1.8932728348786743,
      "grad_norm": 91.4088303372265,
      "learning_rate": 2.054354178842782e-06,
      "loss": 29.498,
      "step": 1200,
      "true_loss": 3.653
    },
    {
      "epoch": 1.8932728348786743,
      "eval_accuracy": 0.16851441241685144,
      "eval_loss": 3.4037177562713623,
      "eval_runtime": 23.8616,
      "eval_samples_per_second": 37.801,
      "eval_steps_per_second": 4.736,
      "step": 1200
    },
    {
      "epoch": 1.9090550404419018,
      "grad_norm": 100.69059595068175,
      "learning_rate": 2.0251315020455873e-06,
      "loss": 29.1097,
      "step": 1210,
      "true_loss": 3.5445
    },
    {
      "epoch": 1.9248372460051293,
      "grad_norm": 96.05062058766768,
      "learning_rate": 1.995908825248393e-06,
      "loss": 29.5919,
      "step": 1220,
      "true_loss": 3.6302
    },
    {
      "epoch": 1.9406194515683568,
      "grad_norm": 89.1551204065743,
      "learning_rate": 1.9666861484511982e-06,
      "loss": 29.0917,
      "step": 1230,
      "true_loss": 3.5472
    },
    {
      "epoch": 1.956401657131584,
      "grad_norm": 101.09204426369772,
      "learning_rate": 1.9374634716540037e-06,
      "loss": 28.8413,
      "step": 1240,
      "true_loss": 3.8083
    },
    {
      "epoch": 1.9721838626948116,
      "grad_norm": 105.57133293543227,
      "learning_rate": 1.908240794856809e-06,
      "loss": 29.533,
      "step": 1250,
      "true_loss": 3.7014
    },
    {
      "epoch": 1.9721838626948116,
      "eval_accuracy": 0.17516629711751663,
      "eval_loss": 3.385300397872925,
      "eval_runtime": 23.5478,
      "eval_samples_per_second": 38.305,
      "eval_steps_per_second": 4.799,
      "step": 1250
    },
    {
      "epoch": 1.987966068258039,
      "grad_norm": 96.01274952042326,
      "learning_rate": 1.8790181180596146e-06,
      "loss": 29.2844,
      "step": 1260,
      "true_loss": 3.8112
    },
    {
      "epoch": 2.0031564411126457,
      "grad_norm": 94.04158733000145,
      "learning_rate": 1.8497954412624196e-06,
      "loss": 27.161,
      "step": 1270,
      "true_loss": 3.399
    },
    {
      "epoch": 2.0189386466758728,
      "grad_norm": 113.00306213639786,
      "learning_rate": 1.820572764465225e-06,
      "loss": 27.5121,
      "step": 1280,
      "true_loss": 3.5377
    },
    {
      "epoch": 2.0347208522391003,
      "grad_norm": 128.85739550143202,
      "learning_rate": 1.7913500876680305e-06,
      "loss": 27.3831,
      "step": 1290,
      "true_loss": 3.3378
    },
    {
      "epoch": 2.0505030578023278,
      "grad_norm": 135.357215369742,
      "learning_rate": 1.7621274108708358e-06,
      "loss": 28.0219,
      "step": 1300,
      "true_loss": 3.6161
    },
    {
      "epoch": 2.0505030578023278,
      "eval_accuracy": 0.17849223946784923,
      "eval_loss": 3.400832414627075,
      "eval_runtime": 24.2954,
      "eval_samples_per_second": 37.126,
      "eval_steps_per_second": 4.651,
      "step": 1300
    },
    {
      "epoch": 2.0662852633655553,
      "grad_norm": 133.18820676570508,
      "learning_rate": 1.7329047340736412e-06,
      "loss": 27.7807,
      "step": 1310,
      "true_loss": 3.5333
    },
    {
      "epoch": 2.082067468928783,
      "grad_norm": 132.12454176042834,
      "learning_rate": 1.7036820572764467e-06,
      "loss": 27.6285,
      "step": 1320,
      "true_loss": 3.122
    },
    {
      "epoch": 2.0978496744920103,
      "grad_norm": 121.63901914437486,
      "learning_rate": 1.674459380479252e-06,
      "loss": 27.2663,
      "step": 1330,
      "true_loss": 3.2256
    },
    {
      "epoch": 2.113631880055238,
      "grad_norm": 137.06803144579217,
      "learning_rate": 1.6452367036820574e-06,
      "loss": 27.6847,
      "step": 1340,
      "true_loss": 3.3579
    },
    {
      "epoch": 2.1294140856184653,
      "grad_norm": 127.41062741726843,
      "learning_rate": 1.6160140268848628e-06,
      "loss": 27.7085,
      "step": 1350,
      "true_loss": 3.45
    },
    {
      "epoch": 2.1294140856184653,
      "eval_accuracy": 0.18070953436807094,
      "eval_loss": 3.376422643661499,
      "eval_runtime": 23.8791,
      "eval_samples_per_second": 37.774,
      "eval_steps_per_second": 4.732,
      "step": 1350
    },
    {
      "epoch": 2.1451962911816924,
      "grad_norm": 121.2757103113971,
      "learning_rate": 1.586791350087668e-06,
      "loss": 27.6917,
      "step": 1360,
      "true_loss": 3.3579
    },
    {
      "epoch": 2.16097849674492,
      "grad_norm": 128.57906764071424,
      "learning_rate": 1.5575686732904735e-06,
      "loss": 26.6196,
      "step": 1370,
      "true_loss": 3.2661
    },
    {
      "epoch": 2.1767607023081474,
      "grad_norm": 144.7381021633525,
      "learning_rate": 1.528345996493279e-06,
      "loss": 28.1214,
      "step": 1380,
      "true_loss": 3.5539
    },
    {
      "epoch": 2.192542907871375,
      "grad_norm": 145.5114518133331,
      "learning_rate": 1.4991233196960842e-06,
      "loss": 27.5329,
      "step": 1390,
      "true_loss": 3.5611
    },
    {
      "epoch": 2.2083251134346025,
      "grad_norm": 137.75864220522647,
      "learning_rate": 1.4699006428988897e-06,
      "loss": 27.6466,
      "step": 1400,
      "true_loss": 3.4073
    },
    {
      "epoch": 2.2083251134346025,
      "eval_accuracy": 0.18514412416851442,
      "eval_loss": 3.3832011222839355,
      "eval_runtime": 23.5091,
      "eval_samples_per_second": 38.368,
      "eval_steps_per_second": 4.807,
      "step": 1400
    },
    {
      "epoch": 2.22410731899783,
      "grad_norm": 132.61505430150723,
      "learning_rate": 1.4406779661016951e-06,
      "loss": 27.1518,
      "step": 1410,
      "true_loss": 3.4681
    },
    {
      "epoch": 2.2398895245610575,
      "grad_norm": 140.85574741341603,
      "learning_rate": 1.4114552893045006e-06,
      "loss": 27.7041,
      "step": 1420,
      "true_loss": 3.6406
    },
    {
      "epoch": 2.255671730124285,
      "grad_norm": 245.85007563586552,
      "learning_rate": 1.3822326125073058e-06,
      "loss": 27.6303,
      "step": 1430,
      "true_loss": 3.5352
    },
    {
      "epoch": 2.2714539356875125,
      "grad_norm": 577.1875021093457,
      "learning_rate": 1.3530099357101113e-06,
      "loss": 28.509,
      "step": 1440,
      "true_loss": 3.5396
    },
    {
      "epoch": 2.28723614125074,
      "grad_norm": 147.03022521178113,
      "learning_rate": 1.3237872589129167e-06,
      "loss": 27.6055,
      "step": 1450,
      "true_loss": 3.4989
    },
    {
      "epoch": 2.28723614125074,
      "eval_accuracy": 0.18514412416851442,
      "eval_loss": 3.4081857204437256,
      "eval_runtime": 24.0487,
      "eval_samples_per_second": 37.507,
      "eval_steps_per_second": 4.699,
      "step": 1450
    },
    {
      "epoch": 2.303018346813967,
      "grad_norm": 158.25616293531198,
      "learning_rate": 1.2945645821157218e-06,
      "loss": 27.6877,
      "step": 1460,
      "true_loss": 3.6034
    },
    {
      "epoch": 2.3188005523771946,
      "grad_norm": 155.95509000199831,
      "learning_rate": 1.2653419053185272e-06,
      "loss": 27.8664,
      "step": 1470,
      "true_loss": 3.5089
    },
    {
      "epoch": 2.334582757940422,
      "grad_norm": 146.83540699519045,
      "learning_rate": 1.2361192285213327e-06,
      "loss": 27.413,
      "step": 1480,
      "true_loss": 3.5116
    },
    {
      "epoch": 2.3503649635036497,
      "grad_norm": 141.1565994249431,
      "learning_rate": 1.2068965517241381e-06,
      "loss": 27.1606,
      "step": 1490,
      "true_loss": 3.426
    },
    {
      "epoch": 2.366147169066877,
      "grad_norm": 159.8393327569506,
      "learning_rate": 1.1776738749269434e-06,
      "loss": 27.7131,
      "step": 1500,
      "true_loss": 3.3148
    },
    {
      "epoch": 2.366147169066877,
      "eval_accuracy": 0.19623059866962306,
      "eval_loss": 3.372471332550049,
      "eval_runtime": 23.4809,
      "eval_samples_per_second": 38.414,
      "eval_steps_per_second": 4.812,
      "step": 1500
    },
    {
      "epoch": 2.3819293746301047,
      "grad_norm": 168.70353622158657,
      "learning_rate": 1.1484511981297488e-06,
      "loss": 26.9731,
      "step": 1510,
      "true_loss": 3.3077
    },
    {
      "epoch": 2.397711580193332,
      "grad_norm": 163.63685602929394,
      "learning_rate": 1.1192285213325543e-06,
      "loss": 27.206,
      "step": 1520,
      "true_loss": 3.2603
    },
    {
      "epoch": 2.4134937857565593,
      "grad_norm": 171.43412737818744,
      "learning_rate": 1.0900058445353595e-06,
      "loss": 26.3347,
      "step": 1530,
      "true_loss": 3.2123
    },
    {
      "epoch": 2.4292759913197868,
      "grad_norm": 167.19508362270676,
      "learning_rate": 1.0607831677381648e-06,
      "loss": 27.482,
      "step": 1540,
      "true_loss": 3.4389
    },
    {
      "epoch": 2.4450581968830143,
      "grad_norm": 165.6072657994525,
      "learning_rate": 1.0315604909409702e-06,
      "loss": 26.6002,
      "step": 1550,
      "true_loss": 3.4554
    },
    {
      "epoch": 2.4450581968830143,
      "eval_accuracy": 0.1984478935698448,
      "eval_loss": 3.3719024658203125,
      "eval_runtime": 23.4592,
      "eval_samples_per_second": 38.45,
      "eval_steps_per_second": 4.817,
      "step": 1550
    },
    {
      "epoch": 2.460840402446242,
      "grad_norm": 173.48714728794272,
      "learning_rate": 1.0023378141437757e-06,
      "loss": 27.0777,
      "step": 1560,
      "true_loss": 3.4451
    },
    {
      "epoch": 2.4766226080094693,
      "grad_norm": 169.41551174748028,
      "learning_rate": 9.731151373465811e-07,
      "loss": 27.1345,
      "step": 1570,
      "true_loss": 3.3625
    },
    {
      "epoch": 2.492404813572697,
      "grad_norm": 179.8847072240023,
      "learning_rate": 9.438924605493864e-07,
      "loss": 27.0216,
      "step": 1580,
      "true_loss": 3.2843
    },
    {
      "epoch": 2.5081870191359243,
      "grad_norm": 166.02108936347767,
      "learning_rate": 9.146697837521917e-07,
      "loss": 26.7401,
      "step": 1590,
      "true_loss": 3.2657
    },
    {
      "epoch": 2.523969224699152,
      "grad_norm": 454.3584387218693,
      "learning_rate": 8.854471069549972e-07,
      "loss": 26.1234,
      "step": 1600,
      "true_loss": 3.3808
    },
    {
      "epoch": 2.523969224699152,
      "eval_accuracy": 0.20288248337028825,
      "eval_loss": 3.380685567855835,
      "eval_runtime": 24.1535,
      "eval_samples_per_second": 37.344,
      "eval_steps_per_second": 4.678,
      "step": 1600
    },
    {
      "epoch": 2.5397514302623794,
      "grad_norm": 164.3488500545829,
      "learning_rate": 8.562244301578025e-07,
      "loss": 26.6329,
      "step": 1610,
      "true_loss": 3.4502
    },
    {
      "epoch": 2.555533635825607,
      "grad_norm": 224.71536684248224,
      "learning_rate": 8.270017533606079e-07,
      "loss": 27.4489,
      "step": 1620,
      "true_loss": 3.4381
    },
    {
      "epoch": 2.571315841388834,
      "grad_norm": 189.92117872676408,
      "learning_rate": 7.977790765634133e-07,
      "loss": 27.2729,
      "step": 1630,
      "true_loss": 3.3647
    },
    {
      "epoch": 2.5870980469520615,
      "grad_norm": 172.51933992524627,
      "learning_rate": 7.685563997662187e-07,
      "loss": 27.1534,
      "step": 1640,
      "true_loss": 3.5251
    },
    {
      "epoch": 2.602880252515289,
      "grad_norm": 166.6926362336406,
      "learning_rate": 7.393337229690241e-07,
      "loss": 26.9745,
      "step": 1650,
      "true_loss": 3.3921
    },
    {
      "epoch": 2.602880252515289,
      "eval_accuracy": 0.2006651884700665,
      "eval_loss": 3.3468966484069824,
      "eval_runtime": 23.7179,
      "eval_samples_per_second": 38.03,
      "eval_steps_per_second": 4.764,
      "step": 1650
    },
    {
      "epoch": 2.6186624580785165,
      "grad_norm": 160.91931691807488,
      "learning_rate": 7.101110461718295e-07,
      "loss": 26.7737,
      "step": 1660,
      "true_loss": 3.4577
    },
    {
      "epoch": 2.634444663641744,
      "grad_norm": 181.67048483012417,
      "learning_rate": 6.808883693746347e-07,
      "loss": 26.7581,
      "step": 1670,
      "true_loss": 3.2471
    },
    {
      "epoch": 2.6502268692049715,
      "grad_norm": 217.44579386829224,
      "learning_rate": 6.516656925774401e-07,
      "loss": 26.4481,
      "step": 1680,
      "true_loss": 3.0002
    },
    {
      "epoch": 2.6660090747681986,
      "grad_norm": 195.64586609651414,
      "learning_rate": 6.224430157802455e-07,
      "loss": 26.7862,
      "step": 1690,
      "true_loss": 3.1025
    },
    {
      "epoch": 2.681791280331426,
      "grad_norm": 179.8032160582305,
      "learning_rate": 5.93220338983051e-07,
      "loss": 27.108,
      "step": 1700,
      "true_loss": 3.1252
    },
    {
      "epoch": 2.681791280331426,
      "eval_accuracy": 0.2017738359201774,
      "eval_loss": 3.3589749336242676,
      "eval_runtime": 23.6074,
      "eval_samples_per_second": 38.208,
      "eval_steps_per_second": 4.787,
      "step": 1700
    },
    {
      "epoch": 2.6975734858946536,
      "grad_norm": 189.69952810255015,
      "learning_rate": 5.639976621858563e-07,
      "loss": 26.6985,
      "step": 1710,
      "true_loss": 3.3933
    },
    {
      "epoch": 2.713355691457881,
      "grad_norm": 242.2858845486621,
      "learning_rate": 5.347749853886616e-07,
      "loss": 26.7437,
      "step": 1720,
      "true_loss": 3.1209
    },
    {
      "epoch": 2.7291378970211086,
      "grad_norm": 185.37642956971033,
      "learning_rate": 5.05552308591467e-07,
      "loss": 26.7456,
      "step": 1730,
      "true_loss": 3.1121
    },
    {
      "epoch": 2.744920102584336,
      "grad_norm": 201.70311652816994,
      "learning_rate": 4.763296317942724e-07,
      "loss": 26.8516,
      "step": 1740,
      "true_loss": 3.397
    },
    {
      "epoch": 2.7607023081475637,
      "grad_norm": 181.35331376149924,
      "learning_rate": 4.4710695499707774e-07,
      "loss": 27.6208,
      "step": 1750,
      "true_loss": 3.6422
    },
    {
      "epoch": 2.7607023081475637,
      "eval_accuracy": 0.21951219512195122,
      "eval_loss": 3.3623762130737305,
      "eval_runtime": 23.6173,
      "eval_samples_per_second": 38.192,
      "eval_steps_per_second": 4.785,
      "step": 1750
    },
    {
      "epoch": 2.776484513710791,
      "grad_norm": 207.9779142213798,
      "learning_rate": 4.1788427819988314e-07,
      "loss": 26.674,
      "step": 1760,
      "true_loss": 3.221
    },
    {
      "epoch": 2.7922667192740187,
      "grad_norm": 203.7549680190773,
      "learning_rate": 3.8866160140268854e-07,
      "loss": 26.5723,
      "step": 1770,
      "true_loss": 3.2956
    },
    {
      "epoch": 2.808048924837246,
      "grad_norm": 196.13189611302036,
      "learning_rate": 3.594389246054939e-07,
      "loss": 26.4406,
      "step": 1780,
      "true_loss": 3.4648
    },
    {
      "epoch": 2.8238311304004737,
      "grad_norm": 198.30227589105047,
      "learning_rate": 3.3021624780829924e-07,
      "loss": 26.1588,
      "step": 1790,
      "true_loss": 3.2933
    },
    {
      "epoch": 2.839613335963701,
      "grad_norm": 199.85226446602726,
      "learning_rate": 3.0099357101110464e-07,
      "loss": 26.2669,
      "step": 1800,
      "true_loss": 3.2296
    },
    {
      "epoch": 2.839613335963701,
      "eval_accuracy": 0.2073170731707317,
      "eval_loss": 3.3512346744537354,
      "eval_runtime": 23.6919,
      "eval_samples_per_second": 38.072,
      "eval_steps_per_second": 4.77,
      "step": 1800
    },
    {
      "epoch": 2.8553955415269283,
      "grad_norm": 217.9595424207247,
      "learning_rate": 2.7177089421391004e-07,
      "loss": 26.0995,
      "step": 1810,
      "true_loss": 3.0267
    },
    {
      "epoch": 2.871177747090156,
      "grad_norm": 222.64507007990645,
      "learning_rate": 2.425482174167154e-07,
      "loss": 25.9481,
      "step": 1820,
      "true_loss": 3.4288
    },
    {
      "epoch": 2.8869599526533833,
      "grad_norm": 201.21510324225665,
      "learning_rate": 2.1332554061952078e-07,
      "loss": 25.9752,
      "step": 1830,
      "true_loss": 3.1737
    },
    {
      "epoch": 2.902742158216611,
      "grad_norm": 192.09070144987018,
      "learning_rate": 1.8410286382232613e-07,
      "loss": 26.059,
      "step": 1840,
      "true_loss": 3.024
    },
    {
      "epoch": 2.9185243637798384,
      "grad_norm": 940.254161469039,
      "learning_rate": 1.5488018702513153e-07,
      "loss": 25.8304,
      "step": 1850,
      "true_loss": 2.8998
    },
    {
      "epoch": 2.9185243637798384,
      "eval_accuracy": 0.21840354767184036,
      "eval_loss": 3.3478667736053467,
      "eval_runtime": 23.6868,
      "eval_samples_per_second": 38.08,
      "eval_steps_per_second": 4.771,
      "step": 1850
    }
  ],
  "logging_steps": 10,
  "max_steps": 1902,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}