{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 10.0,
  "global_step": 1462,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0004999422837239569,
      "loss": 0.841,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000499769161545176,
      "loss": 0.5851,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004994807133993966,
      "loss": 0.582,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004990770724718415,
      "loss": 0.5389,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004985584251357201,
      "loss": 0.5349,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000497925010866175,
      "loss": 0.5181,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004971771221297088,
      "loss": 0.5041,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004963151042491437,
      "loss": 0.5311,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004953393552441752,
      "loss": 0.4979,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004942503256475948,
      "loss": 0.5101,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000493048518297265,
      "loss": 0.5458,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0004917344881039438,
      "loss": 0.5137,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0004903088417950664,
      "loss": 0.4865,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004887722376345999,
      "loss": 0.5004,
      "step": 140
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00048712538511910353,
      "loss": 0.4931,
      "step": 150
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0004853690446501323,
      "loss": 0.4855,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00048350402718313703,
      "loss": 0.5288,
      "step": 170
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00048153119385302114,
      "loss": 0.4931,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00047945145557652923,
      "loss": 0.5064,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000477265772631649,
      "loss": 0.5217,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00047497515421422205,
      "loss": 0.4952,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00047258065797196744,
      "loss": 0.5501,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00047008338951613397,
      "loss": 0.5033,
      "step": 230
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000467484501911006,
      "loss": 0.5217,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000464785195141499,
      "loss": 0.5051,
      "step": 250
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00046198671555909,
      "loss": 0.5066,
      "step": 260
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0004590903553063396,
      "loss": 0.4972,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0004560974517202708,
      "loss": 0.5008,
      "step": 280
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00045300938671487994,
      "loss": 0.5091,
      "step": 290
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0004498275861430654,
      "loss": 0.4764,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00044655351913826794,
      "loss": 0.506,
      "step": 310
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00044318869743612796,
      "loss": 0.521,
      "step": 320
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000439734674676471,
      "loss": 0.4923,
      "step": 330
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00043619304568594545,
      "loss": 0.5319,
      "step": 340
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0004325654457416431,
      "loss": 0.4804,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00042922848418325,
      "loss": 0.5062,
      "step": 360
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0004254421861612533,
      "loss": 0.4685,
      "step": 370
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000421574881182088,
      "loss": 0.502,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0004176283548972877,
      "loss": 0.5225,
      "step": 390
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0004136044295372563,
      "loss": 0.5375,
      "step": 400
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00040950496306988853,
      "loss": 0.5128,
      "step": 410
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00040533184834269057,
      "loss": 0.5079,
      "step": 420
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0004010870122087948,
      "loss": 0.5297,
      "step": 430
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003967724146372738,
      "loss": 0.5069,
      "step": 440
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003923900478081629,
      "loss": 0.5238,
      "step": 450
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003879419351926115,
      "loss": 0.5052,
      "step": 460
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003834301306185841,
      "loss": 0.5068,
      "step": 470
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003788567173225469,
      "loss": 0.497,
      "step": 480
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003742238069875736,
      "loss": 0.5203,
      "step": 490
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00036953353876831866,
      "loss": 0.4843,
      "step": 500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000364788078303304,
      "loss": 0.4976,
      "step": 510
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000359989616714979,
      "loss": 0.5101,
      "step": 520
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003551403695980124,
      "loss": 0.485,
      "step": 530
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003502425759962859,
      "loss": 0.5139,
      "step": 540
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003452984973690597,
      "loss": 0.507,
      "step": 550
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003403104165467883,
      "loss": 0.4868,
      "step": 560
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000335280636677069,
      "loss": 0.5278,
      "step": 570
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00033021148016120915,
      "loss": 0.4709,
      "step": 580
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003251052875819029,
      "loss": 0.5023,
      "step": 590
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003199644166225136,
      "loss": 0.499,
      "step": 600
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00031479124097846047,
      "loss": 0.5014,
      "step": 610
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003095881492612115,
      "loss": 0.5224,
      "step": 620
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003043575438953893,
      "loss": 0.5063,
      "step": 630
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00029910184000949916,
      "loss": 0.5092,
      "step": 640
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002938234643207913,
      "loss": 0.498,
      "step": 650
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002885248540147722,
      "loss": 0.4861,
      "step": 660
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00028320845561988255,
      "loss": 0.5027,
      "step": 670
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002778767238778607,
      "loss": 0.5162,
      "step": 680
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002725321206103147,
      "loss": 0.495,
      "step": 690
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002671771135820249,
      "loss": 0.4804,
      "step": 700
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002618141753615021,
      "loss": 0.4684,
      "step": 710
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002564457821793282,
      "loss": 0.4736,
      "step": 720
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00025107441278480563,
      "loss": 0.4928,
      "step": 730
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00024570254730144417,
      "loss": 0.5076,
      "step": 740
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00024033266608181257,
      "loss": 0.4936,
      "step": 750
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00023496724856228514,
      "loss": 0.5076,
      "step": 760
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00022960877211821102,
      "loss": 0.4881,
      "step": 770
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002242597109200352,
      "loss": 0.5276,
      "step": 780
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021892253479089907,
      "loss": 0.4963,
      "step": 790
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00021359970806624883,
      "loss": 0.4923,
      "step": 800
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00020829368845597693,
      "loss": 0.5217,
      "step": 810
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002030069259096234,
      "loss": 0.4848,
      "step": 820
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001977418614851605,
      "loss": 0.4759,
      "step": 830
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001925009262218818,
      "loss": 0.5065,
      "step": 840
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001872865400179182,
      "loss": 0.4642,
      "step": 850
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00018210111051289815,
      "loss": 0.4869,
      "step": 860
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017694703197626734,
      "loss": 0.4859,
      "step": 870
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001718266842017823,
      "loss": 0.4529,
      "step": 880
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00016674243140868777,
      "loss": 0.5037,
      "step": 890
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001616966211500851,
      "loss": 0.475,
      "step": 900
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001566915832289964,
      "loss": 0.4951,
      "step": 910
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00015172962862262362,
      "loss": 0.4845,
      "step": 920
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00014681304841530107,
      "loss": 0.4528,
      "step": 930
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00014194411274063212,
      "loss": 0.4856,
      "step": 940
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00013712506973330036,
      "loss": 0.4764,
      "step": 950
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00013235814449103736,
      "loss": 0.4775,
      "step": 960
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012764553804722867,
      "loss": 0.4961,
      "step": 970
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012298942635462923,
      "loss": 0.4862,
      "step": 980
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011839195928066102,
      "loss": 0.485,
      "step": 990
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011385525961475404,
      "loss": 0.4862,
      "step": 1000
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010938142208819007,
      "loss": 0.4768,
      "step": 1010
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010497251240690254,
      "loss": 0.4885,
      "step": 1020
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010063056629767691,
      "loss": 0.4758,
      "step": 1030
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.635758856819508e-05,
      "loss": 0.4676,
      "step": 1040
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.215555218135416e-05,
      "loss": 0.4858,
      "step": 1050
    },
    {
      "epoch": 1.45,
      "learning_rate": 8.802639734429043e-05,
      "loss": 0.456,
      "step": 1060
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.39720306125274e-05,
      "loss": 0.4776,
      "step": 1070
    },
    {
      "epoch": 1.48,
      "learning_rate": 7.999432400966063e-05,
      "loss": 0.461,
      "step": 1080
    },
    {
      "epoch": 1.49,
      "learning_rate": 7.609511416298859e-05,
      "loss": 0.4893,
      "step": 1090
    },
    {
      "epoch": 1.5,
      "learning_rate": 7.227620145548624e-05,
      "loss": 0.4917,
      "step": 1100
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.853934919451357e-05,
      "loss": 0.5223,
      "step": 1110
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.488628279764369e-05,
      "loss": 0.4687,
      "step": 1120
    },
    {
      "epoch": 1.55,
      "learning_rate": 6.131868899598503e-05,
      "loss": 0.4788,
      "step": 1130
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.783821505536696e-05,
      "loss": 0.472,
      "step": 1140
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.444646801574729e-05,
      "loss": 0.4664,
      "step": 1150
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.114501394919316e-05,
      "loss": 0.4547,
      "step": 1160
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.7935377236778654e-05,
      "loss": 0.4927,
      "step": 1170
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.4819039864731625e-05,
      "loss": 0.4814,
      "step": 1180
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.1797440740156204e-05,
      "loss": 0.4681,
      "step": 1190
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.887197502664572e-05,
      "loss": 0.4979,
      "step": 1200
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.6043993500093466e-05,
      "loss": 0.4743,
      "step": 1210
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.3314801924998973e-05,
      "loss": 0.4792,
      "step": 1220
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.068566045155682e-05,
      "loss": 0.4791,
      "step": 1230
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.8157783033807365e-05,
      "loss": 0.4846,
      "step": 1240
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.57323368691173e-05,
      "loss": 0.4684,
      "step": 1250
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.3410441859249538e-05,
      "loss": 0.4645,
      "step": 1260
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.1193170093270847e-05,
      "loss": 0.51,
      "step": 1270
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.908154535253559e-05,
      "loss": 0.4606,
      "step": 1280
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.707654263797534e-05,
      "loss": 0.4711,
      "step": 1290
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.5179087719911138e-05,
      "loss": 0.4523,
      "step": 1300
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.3390056710597648e-05,
      "loss": 0.4997,
      "step": 1310
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.1710275659695596e-05,
      "loss": 0.4838,
      "step": 1320
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.0140520172859518e-05,
      "loss": 0.4573,
      "step": 1330
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.681515053617473e-06,
      "loss": 0.4858,
      "step": 1340
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.333933968707046e-06,
      "loss": 0.4855,
      "step": 1350
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.098399137023425e-06,
      "loss": 0.462,
      "step": 1360
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.975481042321816e-06,
      "loss": 0.4766,
      "step": 1370
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.965698169808018e-06,
      "loss": 0.5164,
      "step": 1380
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.069516766738195e-06,
      "loss": 0.472,
      "step": 1390
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.2873506271382515e-06,
      "loss": 0.4915,
      "step": 1400
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.6195609007428057e-06,
      "loss": 0.4754,
      "step": 1410
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.066455926241383e-06,
      "loss": 0.4655,
      "step": 1420
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.282910889090499e-07,
      "loss": 0.4948,
      "step": 1430
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.052687026874612e-07,
      "loss": 0.501,
      "step": 1440
    },
    {
      "epoch": 1.98,
      "learning_rate": 9.753791677027945e-08,
      "loss": 0.473,
      "step": 1450
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.194646736622621e-09,
      "loss": 0.4731,
      "step": 1460
    },
    {
      "epoch": 2.0,
      "step": 1462,
      "total_flos": 3.404194232389337e+18,
      "train_loss": 0.49735359360353076,
      "train_runtime": 25276.0399,
      "train_samples_per_second": 3.7,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 10,
  "max_steps": 1462,
  "num_train_epochs": 2,
  "save_steps": 150,
  "total_flos": 3.404194232389337e+18,
  "trial_name": null,
  "trial_params": null
}