{
  "best_global_step": 1500,
  "best_metric": 3.755718469619751,
  "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-1500",
  "epoch": 0.2090920179122162,
  "eval_steps": 25,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034848669652036033,
      "grad_norm": 0.2964903712272644,
      "learning_rate": 8.000000000000001e-06,
      "loss": 37.88656494140625,
      "step": 25
    },
    {
      "epoch": 0.0034848669652036033,
      "eval_loss": 4.6062092781066895,
      "eval_runtime": 134.4005,
      "eval_samples_per_second": 94.895,
      "eval_steps_per_second": 47.448,
      "step": 25
    },
    {
      "epoch": 0.006969733930407207,
      "grad_norm": 0.34245482087135315,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 37.61192138671875,
      "step": 50
    },
    {
      "epoch": 0.006969733930407207,
      "eval_loss": 4.552639007568359,
      "eval_runtime": 131.7871,
      "eval_samples_per_second": 96.777,
      "eval_steps_per_second": 48.389,
      "step": 50
    },
    {
      "epoch": 0.01045460089561081,
      "grad_norm": 0.3815608024597168,
      "learning_rate": 2.466666666666667e-05,
      "loss": 37.09659912109375,
      "step": 75
    },
    {
      "epoch": 0.01045460089561081,
      "eval_loss": 4.443544864654541,
      "eval_runtime": 154.9254,
      "eval_samples_per_second": 82.323,
      "eval_steps_per_second": 41.162,
      "step": 75
    },
    {
      "epoch": 0.013939467860814413,
      "grad_norm": 0.3647356331348419,
      "learning_rate": 2.498250672211728e-05,
      "loss": 36.29866943359375,
      "step": 100
    },
    {
      "epoch": 0.013939467860814413,
      "eval_loss": 4.3369669914245605,
      "eval_runtime": 138.8908,
      "eval_samples_per_second": 91.828,
      "eval_steps_per_second": 45.914,
      "step": 100
    },
    {
      "epoch": 0.017424334826018018,
      "grad_norm": 0.3683606684207916,
      "learning_rate": 2.4927134858925575e-05,
      "loss": 35.8759912109375,
      "step": 125
    },
    {
      "epoch": 0.017424334826018018,
      "eval_loss": 4.242681980133057,
      "eval_runtime": 125.8059,
      "eval_samples_per_second": 101.378,
      "eval_steps_per_second": 50.689,
      "step": 125
    },
    {
      "epoch": 0.02090920179122162,
      "grad_norm": 0.41745099425315857,
      "learning_rate": 2.4834022195605383e-05,
      "loss": 34.71609375,
      "step": 150
    },
    {
      "epoch": 0.02090920179122162,
      "eval_loss": 4.15211820602417,
      "eval_runtime": 144.0648,
      "eval_samples_per_second": 88.53,
      "eval_steps_per_second": 44.265,
      "step": 150
    },
    {
      "epoch": 0.024394068756425222,
      "grad_norm": 0.5502339601516724,
      "learning_rate": 2.470345151225491e-05,
      "loss": 34.4389111328125,
      "step": 175
    },
    {
      "epoch": 0.024394068756425222,
      "eval_loss": 4.065174579620361,
      "eval_runtime": 164.1963,
      "eval_samples_per_second": 77.675,
      "eval_steps_per_second": 38.838,
      "step": 175
    },
    {
      "epoch": 0.027878935721628827,
      "grad_norm": 0.5007655024528503,
      "learning_rate": 2.4535819347748074e-05,
      "loss": 33.89746337890625,
      "step": 200
    },
    {
      "epoch": 0.027878935721628827,
      "eval_loss": 3.987807035446167,
      "eval_runtime": 141.6182,
      "eval_samples_per_second": 90.059,
      "eval_steps_per_second": 45.03,
      "step": 200
    },
    {
      "epoch": 0.03136380268683243,
      "grad_norm": 0.48552975058555603,
      "learning_rate": 2.433163479545898e-05,
      "loss": 34.3608935546875,
      "step": 225
    },
    {
      "epoch": 0.03136380268683243,
      "eval_loss": 3.951249361038208,
      "eval_runtime": 178.1207,
      "eval_samples_per_second": 71.603,
      "eval_steps_per_second": 35.802,
      "step": 225
    },
    {
      "epoch": 0.034848669652036035,
      "grad_norm": 0.4646497964859009,
      "learning_rate": 2.4091517957162068e-05,
      "loss": 33.36589599609375,
      "step": 250
    },
    {
      "epoch": 0.034848669652036035,
      "eval_loss": 3.9345061779022217,
      "eval_runtime": 191.2882,
      "eval_samples_per_second": 66.674,
      "eval_steps_per_second": 33.337,
      "step": 250
    },
    {
      "epoch": 0.038333536617239636,
      "grad_norm": 0.5384636521339417,
      "learning_rate": 2.3816198059803415e-05,
      "loss": 32.43830810546875,
      "step": 275
    },
    {
      "epoch": 0.038333536617239636,
      "eval_loss": 3.919111967086792,
      "eval_runtime": 157.7724,
      "eval_samples_per_second": 80.838,
      "eval_steps_per_second": 40.419,
      "step": 275
    },
    {
      "epoch": 0.04181840358244324,
      "grad_norm": 0.5843191742897034,
      "learning_rate": 2.350651124086246e-05,
      "loss": 33.16199462890625,
      "step": 300
    },
    {
      "epoch": 0.04181840358244324,
      "eval_loss": 3.907341957092285,
      "eval_runtime": 137.2039,
      "eval_samples_per_second": 92.957,
      "eval_steps_per_second": 46.478,
      "step": 300
    },
    {
      "epoch": 0.045303270547646844,
      "grad_norm": 0.6355782151222229,
      "learning_rate": 2.316339800902997e-05,
      "loss": 31.9848095703125,
      "step": 325
    },
    {
      "epoch": 0.045303270547646844,
      "eval_loss": 3.904228925704956,
      "eval_runtime": 142.1459,
      "eval_samples_per_second": 89.725,
      "eval_steps_per_second": 44.862,
      "step": 325
    },
    {
      "epoch": 0.048788137512850445,
      "grad_norm": 0.6354503035545349,
      "learning_rate": 2.2787900387914035e-05,
      "loss": 32.89923095703125,
      "step": 350
    },
    {
      "epoch": 0.048788137512850445,
      "eval_loss": 3.889650344848633,
      "eval_runtime": 135.6805,
      "eval_samples_per_second": 94.0,
      "eval_steps_per_second": 47.0,
      "step": 350
    },
    {
      "epoch": 0.05227300447805405,
      "grad_norm": 0.4500903785228729,
      "learning_rate": 2.238115875144865e-05,
      "loss": 31.9859375,
      "step": 375
    },
    {
      "epoch": 0.05227300447805405,
      "eval_loss": 3.881140947341919,
      "eval_runtime": 137.1013,
      "eval_samples_per_second": 93.026,
      "eval_steps_per_second": 46.513,
      "step": 375
    },
    {
      "epoch": 0.05575787144325765,
      "grad_norm": 0.7105244994163513,
      "learning_rate": 2.1944408360615527e-05,
      "loss": 31.830234375,
      "step": 400
    },
    {
      "epoch": 0.05575787144325765,
      "eval_loss": 3.876532554626465,
      "eval_runtime": 138.0891,
      "eval_samples_per_second": 92.361,
      "eval_steps_per_second": 46.18,
      "step": 400
    },
    {
      "epoch": 0.059242738408461254,
      "grad_norm": 0.5426522493362427,
      "learning_rate": 2.147897561199711e-05,
      "loss": 32.8569921875,
      "step": 425
    },
    {
      "epoch": 0.059242738408461254,
      "eval_loss": 3.869863510131836,
      "eval_runtime": 137.3068,
      "eval_samples_per_second": 92.887,
      "eval_steps_per_second": 46.443,
      "step": 425
    },
    {
      "epoch": 0.06272760537366485,
      "grad_norm": 0.6868773698806763,
      "learning_rate": 2.0986274009553747e-05,
      "loss": 33.1663525390625,
      "step": 450
    },
    {
      "epoch": 0.06272760537366485,
      "eval_loss": 3.858783483505249,
      "eval_runtime": 136.4747,
      "eval_samples_per_second": 93.453,
      "eval_steps_per_second": 46.727,
      "step": 450
    },
    {
      "epoch": 0.06621247233886847,
      "grad_norm": 0.6488957405090332,
      "learning_rate": 2.0467799871858624e-05,
      "loss": 32.170732421875,
      "step": 475
    },
    {
      "epoch": 0.06621247233886847,
      "eval_loss": 3.857388496398926,
      "eval_runtime": 138.5464,
      "eval_samples_per_second": 92.056,
      "eval_steps_per_second": 46.028,
      "step": 475
    },
    {
      "epoch": 0.06969733930407207,
      "grad_norm": 0.5700647830963135,
      "learning_rate": 1.9925127787827415e-05,
      "loss": 32.3882470703125,
      "step": 500
    },
    {
      "epoch": 0.06969733930407207,
      "eval_loss": 3.852177619934082,
      "eval_runtime": 137.7764,
      "eval_samples_per_second": 92.57,
      "eval_steps_per_second": 46.285,
      "step": 500
    },
    {
      "epoch": 0.07318220626927567,
      "grad_norm": 0.6471461653709412,
      "learning_rate": 1.9359905834743513e-05,
      "loss": 32.83000244140625,
      "step": 525
    },
    {
      "epoch": 0.07318220626927567,
      "eval_loss": 3.8465960025787354,
      "eval_runtime": 137.4128,
      "eval_samples_per_second": 92.815,
      "eval_steps_per_second": 46.408,
      "step": 525
    },
    {
      "epoch": 0.07666707323447927,
      "grad_norm": 0.6369190812110901,
      "learning_rate": 1.8773850573101503e-05,
      "loss": 32.35257080078125,
      "step": 550
    },
    {
      "epoch": 0.07666707323447927,
      "eval_loss": 3.842385768890381,
      "eval_runtime": 140.2355,
      "eval_samples_per_second": 90.947,
      "eval_steps_per_second": 45.474,
      "step": 550
    },
    {
      "epoch": 0.08015194019968287,
      "grad_norm": 0.5800191164016724,
      "learning_rate": 1.8168741833469327e-05,
      "loss": 31.9875244140625,
      "step": 575
    },
    {
      "epoch": 0.08015194019968287,
      "eval_loss": 3.8325023651123047,
      "eval_runtime": 137.4074,
      "eval_samples_per_second": 92.819,
      "eval_steps_per_second": 46.409,
      "step": 575
    },
    {
      "epoch": 0.08363680716488649,
      "grad_norm": 0.655426025390625,
      "learning_rate": 1.7546417311201357e-05,
      "loss": 31.470654296875,
      "step": 600
    },
    {
      "epoch": 0.08363680716488649,
      "eval_loss": 3.82979416847229,
      "eval_runtime": 136.3318,
      "eval_samples_per_second": 93.551,
      "eval_steps_per_second": 46.776,
      "step": 600
    },
    {
      "epoch": 0.08712167413009009,
      "grad_norm": 0.5678662657737732,
      "learning_rate": 1.690876698541802e-05,
      "loss": 32.25173828125,
      "step": 625
    },
    {
      "epoch": 0.08712167413009009,
      "eval_loss": 3.828555107116699,
      "eval_runtime": 142.3008,
      "eval_samples_per_second": 89.627,
      "eval_steps_per_second": 44.814,
      "step": 625
    },
    {
      "epoch": 0.09060654109529369,
      "grad_norm": 0.6696360111236572,
      "learning_rate": 1.625772737920128e-05,
      "loss": 32.847529296875,
      "step": 650
    },
    {
      "epoch": 0.09060654109529369,
      "eval_loss": 3.8212130069732666,
      "eval_runtime": 145.4915,
      "eval_samples_per_second": 87.661,
      "eval_steps_per_second": 43.831,
      "step": 650
    },
    {
      "epoch": 0.09409140806049729,
      "grad_norm": 0.6813345551490784,
      "learning_rate": 1.5595275678437756e-05,
      "loss": 32.22562744140625,
      "step": 675
    },
    {
      "epoch": 0.09409140806049729,
      "eval_loss": 3.8163504600524902,
      "eval_runtime": 135.9053,
      "eval_samples_per_second": 93.845,
      "eval_steps_per_second": 46.922,
      "step": 675
    },
    {
      "epoch": 0.09757627502570089,
      "grad_norm": 0.6201620101928711,
      "learning_rate": 1.4923423727170106e-05,
      "loss": 32.73896240234375,
      "step": 700
    },
    {
      "epoch": 0.09757627502570089,
      "eval_loss": 3.8148138523101807,
      "eval_runtime": 140.771,
      "eval_samples_per_second": 90.601,
      "eval_steps_per_second": 45.301,
      "step": 700
    },
    {
      "epoch": 0.10106114199090449,
      "grad_norm": 0.6953298449516296,
      "learning_rate": 1.4244211917692812e-05,
      "loss": 32.32746826171875,
      "step": 725
    },
    {
      "epoch": 0.10106114199090449,
      "eval_loss": 3.8123884201049805,
      "eval_runtime": 141.0245,
      "eval_samples_per_second": 90.438,
      "eval_steps_per_second": 45.219,
      "step": 725
    },
    {
      "epoch": 0.1045460089561081,
      "grad_norm": 0.7098183035850525,
      "learning_rate": 1.355970299394786e-05,
      "loss": 32.90800048828125,
      "step": 750
    },
    {
      "epoch": 0.1045460089561081,
      "eval_loss": 3.810453414916992,
      "eval_runtime": 138.6332,
      "eval_samples_per_second": 91.998,
      "eval_steps_per_second": 45.999,
      "step": 750
    },
    {
      "epoch": 0.1080308759213117,
      "grad_norm": 0.7382436990737915,
      "learning_rate": 1.2871975787039157e-05,
      "loss": 32.9301318359375,
      "step": 775
    },
    {
      "epoch": 0.1080308759213117,
      "eval_loss": 3.806396007537842,
      "eval_runtime": 141.0631,
      "eval_samples_per_second": 90.413,
      "eval_steps_per_second": 45.207,
      "step": 775
    },
    {
      "epoch": 0.1115157428865153,
      "grad_norm": 0.702569842338562,
      "learning_rate": 1.218311890189081e-05,
      "loss": 31.67234619140625,
      "step": 800
    },
    {
      "epoch": 0.1115157428865153,
      "eval_loss": 3.803560495376587,
      "eval_runtime": 138.1294,
      "eval_samples_per_second": 92.334,
      "eval_steps_per_second": 46.167,
      "step": 800
    },
    {
      "epoch": 0.11500060985171891,
      "grad_norm": 0.7312149405479431,
      "learning_rate": 1.1495224374222602e-05,
      "loss": 32.169111328125,
      "step": 825
    },
    {
      "epoch": 0.11500060985171891,
      "eval_loss": 3.7968807220458984,
      "eval_runtime": 140.9117,
      "eval_samples_per_second": 90.511,
      "eval_steps_per_second": 45.255,
      "step": 825
    },
    {
      "epoch": 0.11848547681692251,
      "grad_norm": 0.8160529732704163,
      "learning_rate": 1.0810381317106293e-05,
      "loss": 32.00342529296875,
      "step": 850
    },
    {
      "epoch": 0.11848547681692251,
      "eval_loss": 3.791039228439331,
      "eval_runtime": 129.2785,
      "eval_samples_per_second": 98.655,
      "eval_steps_per_second": 49.328,
      "step": 850
    },
    {
      "epoch": 0.12197034378212612,
      "grad_norm": 0.7061131000518799,
      "learning_rate": 1.013066957639785e-05,
      "loss": 31.30172607421875,
      "step": 875
    },
    {
      "epoch": 0.12197034378212612,
      "eval_loss": 3.791710615158081,
      "eval_runtime": 125.3783,
      "eval_samples_per_second": 101.724,
      "eval_steps_per_second": 50.862,
      "step": 875
    },
    {
      "epoch": 0.1254552107473297,
      "grad_norm": 0.8358163237571716,
      "learning_rate": 9.45815341431398e-06,
      "loss": 31.78281982421875,
      "step": 900
    },
    {
      "epoch": 0.1254552107473297,
      "eval_loss": 3.7942440509796143,
      "eval_runtime": 135.2641,
      "eval_samples_per_second": 94.29,
      "eval_steps_per_second": 47.145,
      "step": 900
    },
    {
      "epoch": 0.12894007771253332,
      "grad_norm": 0.7387733459472656,
      "learning_rate": 8.79487524033558e-06,
      "loss": 30.677724609375,
      "step": 925
    },
    {
      "epoch": 0.12894007771253332,
      "eval_loss": 3.790346384048462,
      "eval_runtime": 126.5812,
      "eval_samples_per_second": 100.757,
      "eval_steps_per_second": 50.379,
      "step": 925
    },
    {
      "epoch": 0.13242494467773694,
      "grad_norm": 0.6606021523475647,
      "learning_rate": 8.142849408477312e-06,
      "loss": 32.30339111328125,
      "step": 950
    },
    {
      "epoch": 0.13242494467773694,
      "eval_loss": 3.7845609188079834,
      "eval_runtime": 126.5895,
      "eval_samples_per_second": 100.751,
      "eval_steps_per_second": 50.375,
      "step": 950
    },
    {
      "epoch": 0.13590981164294053,
      "grad_norm": 0.7597334980964661,
      "learning_rate": 7.504056099760629e-06,
      "loss": 31.49365966796875,
      "step": 975
    },
    {
      "epoch": 0.13590981164294053,
      "eval_loss": 3.783795118331909,
      "eval_runtime": 128.5471,
      "eval_samples_per_second": 99.217,
      "eval_steps_per_second": 49.608,
      "step": 975
    },
    {
      "epoch": 0.13939467860814414,
      "grad_norm": 0.8744051456451416,
      "learning_rate": 6.880435308469124e-06,
      "loss": 32.4120263671875,
      "step": 1000
    },
    {
      "epoch": 0.13939467860814414,
      "eval_loss": 3.78021240234375,
      "eval_runtime": 126.8291,
      "eval_samples_per_second": 100.561,
      "eval_steps_per_second": 50.28,
      "step": 1000
    },
    {
      "epoch": 0.14287954557334773,
      "grad_norm": 0.8689478039741516,
      "learning_rate": 6.273880950449624e-06,
      "loss": 32.66720458984375,
      "step": 1025
    },
    {
      "epoch": 0.14287954557334773,
      "eval_loss": 3.7732369899749756,
      "eval_runtime": 124.3195,
      "eval_samples_per_second": 102.59,
      "eval_steps_per_second": 51.295,
      "step": 1025
    },
    {
      "epoch": 0.14636441253855134,
      "grad_norm": 0.8830795288085938,
      "learning_rate": 5.6862351113520505e-06,
      "loss": 32.37453125,
      "step": 1050
    },
    {
      "epoch": 0.14636441253855134,
      "eval_loss": 3.7737340927124023,
      "eval_runtime": 124.7043,
      "eval_samples_per_second": 102.274,
      "eval_steps_per_second": 51.137,
      "step": 1050
    },
    {
      "epoch": 0.14984927950375496,
      "grad_norm": 0.8162481188774109,
      "learning_rate": 5.119282452275787e-06,
      "loss": 31.86205078125,
      "step": 1075
    },
    {
      "epoch": 0.14984927950375496,
      "eval_loss": 3.7654809951782227,
      "eval_runtime": 123.5389,
      "eval_samples_per_second": 103.239,
      "eval_steps_per_second": 51.619,
      "step": 1075
    },
    {
      "epoch": 0.15333414646895854,
      "grad_norm": 0.8534089922904968,
      "learning_rate": 4.574744789812638e-06,
      "loss": 32.600322265625,
      "step": 1100
    },
    {
      "epoch": 0.15333414646895854,
      "eval_loss": 3.764484405517578,
      "eval_runtime": 133.2209,
      "eval_samples_per_second": 95.736,
      "eval_steps_per_second": 47.868,
      "step": 1100
    },
    {
      "epoch": 0.15681901343416216,
      "grad_norm": 0.7590998411178589,
      "learning_rate": 4.054275866946371e-06,
      "loss": 32.25859375,
      "step": 1125
    },
    {
      "epoch": 0.15681901343416216,
      "eval_loss": 3.763986349105835,
      "eval_runtime": 125.3471,
      "eval_samples_per_second": 101.749,
      "eval_steps_per_second": 50.875,
      "step": 1125
    },
    {
      "epoch": 0.16030388039936574,
      "grad_norm": 0.7258529663085938,
      "learning_rate": 3.559456330689684e-06,
      "loss": 32.69231201171875,
      "step": 1150
    },
    {
      "epoch": 0.16030388039936574,
      "eval_loss": 3.7613186836242676,
      "eval_runtime": 125.2043,
      "eval_samples_per_second": 101.865,
      "eval_steps_per_second": 50.933,
      "step": 1150
    },
    {
      "epoch": 0.16378874736456936,
      "grad_norm": 0.7329394817352295,
      "learning_rate": 3.091788931711123e-06,
      "loss": 31.1957958984375,
      "step": 1175
    },
    {
      "epoch": 0.16378874736456936,
      "eval_loss": 3.7616991996765137,
      "eval_runtime": 125.2233,
      "eval_samples_per_second": 101.85,
      "eval_steps_per_second": 50.925,
      "step": 1175
    },
    {
      "epoch": 0.16727361432977297,
      "grad_norm": 0.7856114506721497,
      "learning_rate": 2.652693960530743e-06,
      "loss": 32.34443359375,
      "step": 1200
    },
    {
      "epoch": 0.16727361432977297,
      "eval_loss": 3.762284755706787,
      "eval_runtime": 133.7621,
      "eval_samples_per_second": 95.348,
      "eval_steps_per_second": 47.674,
      "step": 1200
    },
    {
      "epoch": 0.17075848129497656,
      "grad_norm": 0.8546104431152344,
      "learning_rate": 2.243504934144444e-06,
      "loss": 31.9795556640625,
      "step": 1225
    },
    {
      "epoch": 0.17075848129497656,
      "eval_loss": 3.761392593383789,
      "eval_runtime": 135.3874,
      "eval_samples_per_second": 94.204,
      "eval_steps_per_second": 47.102,
      "step": 1225
    },
    {
      "epoch": 0.17424334826018018,
      "grad_norm": 0.7697765231132507,
      "learning_rate": 1.8654645461766941e-06,
      "loss": 32.6721044921875,
      "step": 1250
    },
    {
      "epoch": 0.17424334826018018,
      "eval_loss": 3.7579221725463867,
      "eval_runtime": 126.4138,
      "eval_samples_per_second": 100.891,
      "eval_steps_per_second": 50.445,
      "step": 1250
    },
    {
      "epoch": 0.17772821522538376,
      "grad_norm": 0.8027380108833313,
      "learning_rate": 1.5197208928608375e-06,
      "loss": 31.33625,
      "step": 1275
    },
    {
      "epoch": 0.17772821522538376,
      "eval_loss": 3.7570292949676514,
      "eval_runtime": 126.0065,
      "eval_samples_per_second": 101.217,
      "eval_steps_per_second": 50.608,
      "step": 1275
    },
    {
      "epoch": 0.18121308219058738,
      "grad_norm": 0.9305113554000854,
      "learning_rate": 1.2073239863085644e-06,
      "loss": 31.53912353515625,
      "step": 1300
    },
    {
      "epoch": 0.18121308219058738,
      "eval_loss": 3.757063627243042,
      "eval_runtime": 129.7946,
      "eval_samples_per_second": 98.263,
      "eval_steps_per_second": 49.131,
      "step": 1300
    },
    {
      "epoch": 0.184697949155791,
      "grad_norm": 0.7605619430541992,
      "learning_rate": 9.292225656576406e-07,
      "loss": 31.6432275390625,
      "step": 1325
    },
    {
      "epoch": 0.184697949155791,
      "eval_loss": 3.7579827308654785,
      "eval_runtime": 134.7529,
      "eval_samples_per_second": 94.647,
      "eval_steps_per_second": 47.324,
      "step": 1325
    },
    {
      "epoch": 0.18818281612099458,
      "grad_norm": 1.0467506647109985,
      "learning_rate": 6.862612157823259e-07,
      "loss": 31.46984619140625,
      "step": 1350
    },
    {
      "epoch": 0.18818281612099458,
      "eval_loss": 3.7580692768096924,
      "eval_runtime": 137.7265,
      "eval_samples_per_second": 92.604,
      "eval_steps_per_second": 46.302,
      "step": 1350
    },
    {
      "epoch": 0.1916676830861982,
      "grad_norm": 0.9806191921234131,
      "learning_rate": 4.7917780231687e-07,
      "loss": 31.9260205078125,
      "step": 1375
    },
    {
      "epoch": 0.1916676830861982,
      "eval_loss": 3.756873369216919,
      "eval_runtime": 137.2747,
      "eval_samples_per_second": 92.909,
      "eval_steps_per_second": 46.454,
      "step": 1375
    },
    {
      "epoch": 0.19515255005140178,
      "grad_norm": 0.8240782022476196,
      "learning_rate": 3.0860123078183255e-07,
      "loss": 31.5154150390625,
      "step": 1400
    },
    {
      "epoch": 0.19515255005140178,
      "eval_loss": 3.7562670707702637,
      "eval_runtime": 135.5843,
      "eval_samples_per_second": 94.067,
      "eval_steps_per_second": 47.033,
      "step": 1400
    },
    {
      "epoch": 0.1986374170166054,
      "grad_norm": 0.7925982475280762,
      "learning_rate": 1.7504953661868912e-07,
      "loss": 31.911298828125,
      "step": 1425
    },
    {
      "epoch": 0.1986374170166054,
      "eval_loss": 3.755851984024048,
      "eval_runtime": 138.0145,
      "eval_samples_per_second": 92.411,
      "eval_steps_per_second": 46.205,
      "step": 1425
    },
    {
      "epoch": 0.20212228398180898,
      "grad_norm": 0.7086665034294128,
      "learning_rate": 7.89283119332157e-08,
      "loss": 32.10687255859375,
      "step": 1450
    },
    {
      "epoch": 0.20212228398180898,
      "eval_loss": 3.7557601928710938,
      "eval_runtime": 136.786,
      "eval_samples_per_second": 93.241,
      "eval_steps_per_second": 46.62,
      "step": 1450
    },
    {
      "epoch": 0.2056071509470126,
      "grad_norm": 0.7362121343612671,
      "learning_rate": 2.0529473725605652e-08,
      "loss": 32.00110595703125,
      "step": 1475
    },
    {
      "epoch": 0.2056071509470126,
      "eval_loss": 3.755723714828491,
      "eval_runtime": 133.1205,
      "eval_samples_per_second": 95.808,
      "eval_steps_per_second": 47.904,
      "step": 1475
    },
    {
      "epoch": 0.2090920179122162,
      "grad_norm": 0.749195396900177,
      "learning_rate": 3.0377348117505145e-11,
      "loss": 31.84532470703125,
      "step": 1500
    },
    {
      "epoch": 0.2090920179122162,
      "eval_loss": 3.755718469619751,
      "eval_runtime": 128.4402,
      "eval_samples_per_second": 99.299,
      "eval_steps_per_second": 49.65,
      "step": 1500
    }
  ],
  "logging_steps": 25,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 750,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1149555179520000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}