{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02620407735443635,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002620407735443635,
      "grad_norm": 1.2820378541946411,
      "learning_rate": 4.999563265377426e-05,
      "loss": 0.6609,
      "step": 10
    },
    {
      "epoch": 0.000524081547088727,
      "grad_norm": 1.3106062412261963,
      "learning_rate": 4.999126530754852e-05,
      "loss": 0.8066,
      "step": 20
    },
    {
      "epoch": 0.0007861223206330905,
      "grad_norm": 1.6985974311828613,
      "learning_rate": 4.9986897961322784e-05,
      "loss": 0.6863,
      "step": 30
    },
    {
      "epoch": 0.001048163094177454,
      "grad_norm": 1.2552741765975952,
      "learning_rate": 4.9982530615097044e-05,
      "loss": 0.5674,
      "step": 40
    },
    {
      "epoch": 0.0013102038677218176,
      "grad_norm": 1.3928155899047852,
      "learning_rate": 4.9978163268871304e-05,
      "loss": 0.5992,
      "step": 50
    },
    {
      "epoch": 0.001572244641266181,
      "grad_norm": 1.5794411897659302,
      "learning_rate": 4.9973795922645565e-05,
      "loss": 0.7939,
      "step": 60
    },
    {
      "epoch": 0.0018342854148105446,
      "grad_norm": 1.4024512767791748,
      "learning_rate": 4.9969428576419825e-05,
      "loss": 0.6178,
      "step": 70
    },
    {
      "epoch": 0.002096326188354908,
      "grad_norm": 1.2232664823532104,
      "learning_rate": 4.9965061230194085e-05,
      "loss": 0.7544,
      "step": 80
    },
    {
      "epoch": 0.0023583669618992714,
      "grad_norm": 1.5368870496749878,
      "learning_rate": 4.9960693883968346e-05,
      "loss": 0.6645,
      "step": 90
    },
    {
      "epoch": 0.002620407735443635,
      "grad_norm": 1.6177372932434082,
      "learning_rate": 4.9956326537742606e-05,
      "loss": 0.6329,
      "step": 100
    },
    {
      "epoch": 0.0028824485089879986,
      "grad_norm": 1.3803173303604126,
      "learning_rate": 4.995195919151687e-05,
      "loss": 0.7114,
      "step": 110
    },
    {
      "epoch": 0.003144489282532362,
      "grad_norm": 1.5191670656204224,
      "learning_rate": 4.9947591845291134e-05,
      "loss": 0.8717,
      "step": 120
    },
    {
      "epoch": 0.0034065300560767254,
      "grad_norm": 1.2967548370361328,
      "learning_rate": 4.994322449906539e-05,
      "loss": 0.7618,
      "step": 130
    },
    {
      "epoch": 0.003668570829621089,
      "grad_norm": 1.8742738962173462,
      "learning_rate": 4.9938857152839655e-05,
      "loss": 0.5896,
      "step": 140
    },
    {
      "epoch": 0.003930611603165452,
      "grad_norm": 1.697966456413269,
      "learning_rate": 4.993448980661391e-05,
      "loss": 0.7493,
      "step": 150
    },
    {
      "epoch": 0.004192652376709816,
      "grad_norm": 1.5282775163650513,
      "learning_rate": 4.9930122460388175e-05,
      "loss": 0.6359,
      "step": 160
    },
    {
      "epoch": 0.00445469315025418,
      "grad_norm": 1.2776225805282593,
      "learning_rate": 4.992575511416243e-05,
      "loss": 0.7677,
      "step": 170
    },
    {
      "epoch": 0.004716733923798543,
      "grad_norm": 1.2036848068237305,
      "learning_rate": 4.9921387767936696e-05,
      "loss": 0.6234,
      "step": 180
    },
    {
      "epoch": 0.0049787746973429066,
      "grad_norm": 1.1325912475585938,
      "learning_rate": 4.991702042171095e-05,
      "loss": 0.624,
      "step": 190
    },
    {
      "epoch": 0.00524081547088727,
      "grad_norm": 1.3846409320831299,
      "learning_rate": 4.991265307548522e-05,
      "loss": 0.5979,
      "step": 200
    },
    {
      "epoch": 0.005502856244431633,
      "grad_norm": 1.9792439937591553,
      "learning_rate": 4.990828572925948e-05,
      "loss": 0.7897,
      "step": 210
    },
    {
      "epoch": 0.005764897017975997,
      "grad_norm": 1.8546253442764282,
      "learning_rate": 4.990391838303374e-05,
      "loss": 0.7035,
      "step": 220
    },
    {
      "epoch": 0.006026937791520361,
      "grad_norm": 1.5434975624084473,
      "learning_rate": 4.9899551036808e-05,
      "loss": 0.7092,
      "step": 230
    },
    {
      "epoch": 0.006288978565064724,
      "grad_norm": 1.0328209400177002,
      "learning_rate": 4.989518369058226e-05,
      "loss": 0.6239,
      "step": 240
    },
    {
      "epoch": 0.006551019338609088,
      "grad_norm": 0.9389006495475769,
      "learning_rate": 4.989081634435652e-05,
      "loss": 0.6957,
      "step": 250
    },
    {
      "epoch": 0.006813060112153451,
      "grad_norm": 1.0274962186813354,
      "learning_rate": 4.988644899813078e-05,
      "loss": 0.5302,
      "step": 260
    },
    {
      "epoch": 0.0070751008856978145,
      "grad_norm": 1.2626285552978516,
      "learning_rate": 4.988208165190504e-05,
      "loss": 0.6541,
      "step": 270
    },
    {
      "epoch": 0.007337141659242178,
      "grad_norm": 1.4558316469192505,
      "learning_rate": 4.98777143056793e-05,
      "loss": 0.7284,
      "step": 280
    },
    {
      "epoch": 0.007599182432786541,
      "grad_norm": 1.3997328281402588,
      "learning_rate": 4.987334695945356e-05,
      "loss": 0.6888,
      "step": 290
    },
    {
      "epoch": 0.007861223206330904,
      "grad_norm": 1.7742432355880737,
      "learning_rate": 4.986897961322782e-05,
      "loss": 0.6869,
      "step": 300
    },
    {
      "epoch": 0.008123263979875268,
      "grad_norm": 1.4925923347473145,
      "learning_rate": 4.986461226700208e-05,
      "loss": 0.731,
      "step": 310
    },
    {
      "epoch": 0.008385304753419632,
      "grad_norm": 1.5941082239151,
      "learning_rate": 4.986024492077634e-05,
      "loss": 0.7149,
      "step": 320
    },
    {
      "epoch": 0.008647345526963996,
      "grad_norm": 1.507450819015503,
      "learning_rate": 4.98558775745506e-05,
      "loss": 0.6443,
      "step": 330
    },
    {
      "epoch": 0.00890938630050836,
      "grad_norm": 0.9866214990615845,
      "learning_rate": 4.985151022832487e-05,
      "loss": 0.6003,
      "step": 340
    },
    {
      "epoch": 0.009171427074052723,
      "grad_norm": 0.9682250022888184,
      "learning_rate": 4.984714288209912e-05,
      "loss": 0.6602,
      "step": 350
    },
    {
      "epoch": 0.009433467847597085,
      "grad_norm": 1.7567181587219238,
      "learning_rate": 4.984277553587338e-05,
      "loss": 0.5647,
      "step": 360
    },
    {
      "epoch": 0.00969550862114145,
      "grad_norm": 1.4297257661819458,
      "learning_rate": 4.9838408189647643e-05,
      "loss": 0.6628,
      "step": 370
    },
    {
      "epoch": 0.009957549394685813,
      "grad_norm": 1.515763521194458,
      "learning_rate": 4.9834040843421904e-05,
      "loss": 0.568,
      "step": 380
    },
    {
      "epoch": 0.010219590168230177,
      "grad_norm": 1.1806342601776123,
      "learning_rate": 4.9829673497196164e-05,
      "loss": 0.6729,
      "step": 390
    },
    {
      "epoch": 0.01048163094177454,
      "grad_norm": 1.1328020095825195,
      "learning_rate": 4.9825306150970425e-05,
      "loss": 0.6963,
      "step": 400
    },
    {
      "epoch": 0.010743671715318903,
      "grad_norm": 0.7740004658699036,
      "learning_rate": 4.9820938804744685e-05,
      "loss": 0.6654,
      "step": 410
    },
    {
      "epoch": 0.011005712488863267,
      "grad_norm": 0.9519413113594055,
      "learning_rate": 4.9816571458518945e-05,
      "loss": 0.6487,
      "step": 420
    },
    {
      "epoch": 0.01126775326240763,
      "grad_norm": 0.8964847922325134,
      "learning_rate": 4.981220411229321e-05,
      "loss": 0.5667,
      "step": 430
    },
    {
      "epoch": 0.011529794035951994,
      "grad_norm": 1.428072452545166,
      "learning_rate": 4.9807836766067466e-05,
      "loss": 0.8164,
      "step": 440
    },
    {
      "epoch": 0.011791834809496358,
      "grad_norm": 1.4375147819519043,
      "learning_rate": 4.980346941984173e-05,
      "loss": 0.5476,
      "step": 450
    },
    {
      "epoch": 0.012053875583040722,
      "grad_norm": 1.1702146530151367,
      "learning_rate": 4.979910207361599e-05,
      "loss": 0.7342,
      "step": 460
    },
    {
      "epoch": 0.012315916356585084,
      "grad_norm": 1.2703320980072021,
      "learning_rate": 4.9794734727390254e-05,
      "loss": 0.5767,
      "step": 470
    },
    {
      "epoch": 0.012577957130129448,
      "grad_norm": 1.2520267963409424,
      "learning_rate": 4.979036738116451e-05,
      "loss": 0.5969,
      "step": 480
    },
    {
      "epoch": 0.012839997903673812,
      "grad_norm": 1.413979172706604,
      "learning_rate": 4.9786000034938775e-05,
      "loss": 0.7011,
      "step": 490
    },
    {
      "epoch": 0.013102038677218176,
      "grad_norm": 1.3918565511703491,
      "learning_rate": 4.978163268871303e-05,
      "loss": 0.6041,
      "step": 500
    },
    {
      "epoch": 0.01336407945076254,
      "grad_norm": 0.9175894260406494,
      "learning_rate": 4.9777265342487296e-05,
      "loss": 0.5052,
      "step": 510
    },
    {
      "epoch": 0.013626120224306901,
      "grad_norm": 1.296505331993103,
      "learning_rate": 4.9772897996261556e-05,
      "loss": 0.6076,
      "step": 520
    },
    {
      "epoch": 0.013888160997851265,
      "grad_norm": 1.2490183115005493,
      "learning_rate": 4.9768530650035816e-05,
      "loss": 0.6287,
      "step": 530
    },
    {
      "epoch": 0.014150201771395629,
      "grad_norm": 1.398285984992981,
      "learning_rate": 4.976416330381008e-05,
      "loss": 0.7905,
      "step": 540
    },
    {
      "epoch": 0.014412242544939993,
      "grad_norm": 1.3094829320907593,
      "learning_rate": 4.975979595758434e-05,
      "loss": 0.5133,
      "step": 550
    },
    {
      "epoch": 0.014674283318484357,
      "grad_norm": 1.7128199338912964,
      "learning_rate": 4.97554286113586e-05,
      "loss": 0.824,
      "step": 560
    },
    {
      "epoch": 0.014936324092028719,
      "grad_norm": 1.1319103240966797,
      "learning_rate": 4.975106126513286e-05,
      "loss": 0.5893,
      "step": 570
    },
    {
      "epoch": 0.015198364865573083,
      "grad_norm": 1.6176029443740845,
      "learning_rate": 4.974669391890712e-05,
      "loss": 0.581,
      "step": 580
    },
    {
      "epoch": 0.015460405639117446,
      "grad_norm": 1.590836524963379,
      "learning_rate": 4.974232657268138e-05,
      "loss": 0.5814,
      "step": 590
    },
    {
      "epoch": 0.01572244641266181,
      "grad_norm": 1.6922227144241333,
      "learning_rate": 4.973795922645564e-05,
      "loss": 0.5917,
      "step": 600
    },
    {
      "epoch": 0.015984487186206174,
      "grad_norm": 1.3479337692260742,
      "learning_rate": 4.97335918802299e-05,
      "loss": 0.7356,
      "step": 610
    },
    {
      "epoch": 0.016246527959750536,
      "grad_norm": 2.2019124031066895,
      "learning_rate": 4.972922453400416e-05,
      "loss": 0.6197,
      "step": 620
    },
    {
      "epoch": 0.016508568733294902,
      "grad_norm": 1.6211423873901367,
      "learning_rate": 4.972485718777842e-05,
      "loss": 0.6299,
      "step": 630
    },
    {
      "epoch": 0.016770609506839264,
      "grad_norm": 1.157416582107544,
      "learning_rate": 4.972048984155268e-05,
      "loss": 0.6343,
      "step": 640
    },
    {
      "epoch": 0.01703265028038363,
      "grad_norm": 1.2576712369918823,
      "learning_rate": 4.971612249532695e-05,
      "loss": 0.6126,
      "step": 650
    },
    {
      "epoch": 0.01729469105392799,
      "grad_norm": 1.3852715492248535,
      "learning_rate": 4.97117551491012e-05,
      "loss": 0.6352,
      "step": 660
    },
    {
      "epoch": 0.017556731827472354,
      "grad_norm": 1.0178048610687256,
      "learning_rate": 4.970738780287547e-05,
      "loss": 0.5923,
      "step": 670
    },
    {
      "epoch": 0.01781877260101672,
      "grad_norm": 0.8760583996772766,
      "learning_rate": 4.970302045664972e-05,
      "loss": 0.6158,
      "step": 680
    },
    {
      "epoch": 0.01808081337456108,
      "grad_norm": 0.8956984281539917,
      "learning_rate": 4.969865311042398e-05,
      "loss": 0.5746,
      "step": 690
    },
    {
      "epoch": 0.018342854148105447,
      "grad_norm": 1.1126501560211182,
      "learning_rate": 4.969428576419824e-05,
      "loss": 0.6254,
      "step": 700
    },
    {
      "epoch": 0.01860489492164981,
      "grad_norm": 1.168455958366394,
      "learning_rate": 4.96899184179725e-05,
      "loss": 0.652,
      "step": 710
    },
    {
      "epoch": 0.01886693569519417,
      "grad_norm": 1.3628567457199097,
      "learning_rate": 4.9685551071746764e-05,
      "loss": 0.5789,
      "step": 720
    },
    {
      "epoch": 0.019128976468738536,
      "grad_norm": 1.1971865892410278,
      "learning_rate": 4.9681183725521024e-05,
      "loss": 0.6408,
      "step": 730
    },
    {
      "epoch": 0.0193910172422829,
      "grad_norm": 1.1916868686676025,
      "learning_rate": 4.9676816379295285e-05,
      "loss": 0.6461,
      "step": 740
    },
    {
      "epoch": 0.019653058015827264,
      "grad_norm": 1.1797837018966675,
      "learning_rate": 4.9672449033069545e-05,
      "loss": 0.5843,
      "step": 750
    },
    {
      "epoch": 0.019915098789371626,
      "grad_norm": 0.7941935658454895,
      "learning_rate": 4.966808168684381e-05,
      "loss": 0.6165,
      "step": 760
    },
    {
      "epoch": 0.02017713956291599,
      "grad_norm": 1.4876329898834229,
      "learning_rate": 4.9663714340618066e-05,
      "loss": 0.6347,
      "step": 770
    },
    {
      "epoch": 0.020439180336460354,
      "grad_norm": 1.1482038497924805,
      "learning_rate": 4.965934699439233e-05,
      "loss": 0.5662,
      "step": 780
    },
    {
      "epoch": 0.020701221110004716,
      "grad_norm": 1.3942419290542603,
      "learning_rate": 4.9654979648166586e-05,
      "loss": 0.6189,
      "step": 790
    },
    {
      "epoch": 0.02096326188354908,
      "grad_norm": 0.8826277256011963,
      "learning_rate": 4.9650612301940854e-05,
      "loss": 0.6801,
      "step": 800
    },
    {
      "epoch": 0.021225302657093444,
      "grad_norm": 1.3729712963104248,
      "learning_rate": 4.964624495571511e-05,
      "loss": 0.5789,
      "step": 810
    },
    {
      "epoch": 0.021487343430637806,
      "grad_norm": 0.747199296951294,
      "learning_rate": 4.9641877609489374e-05,
      "loss": 0.651,
      "step": 820
    },
    {
      "epoch": 0.02174938420418217,
      "grad_norm": 0.7911145091056824,
      "learning_rate": 4.963751026326363e-05,
      "loss": 0.6834,
      "step": 830
    },
    {
      "epoch": 0.022011424977726533,
      "grad_norm": 1.1725844144821167,
      "learning_rate": 4.9633142917037895e-05,
      "loss": 0.6687,
      "step": 840
    },
    {
      "epoch": 0.0222734657512709,
      "grad_norm": 1.2759829759597778,
      "learning_rate": 4.9628775570812156e-05,
      "loss": 0.6612,
      "step": 850
    },
    {
      "epoch": 0.02253550652481526,
      "grad_norm": 1.497684359550476,
      "learning_rate": 4.9624408224586416e-05,
      "loss": 0.686,
      "step": 860
    },
    {
      "epoch": 0.022797547298359623,
      "grad_norm": 1.4431102275848389,
      "learning_rate": 4.9620040878360676e-05,
      "loss": 0.5838,
      "step": 870
    },
    {
      "epoch": 0.02305958807190399,
      "grad_norm": 0.8864196538925171,
      "learning_rate": 4.961567353213494e-05,
      "loss": 0.6076,
      "step": 880
    },
    {
      "epoch": 0.02332162884544835,
      "grad_norm": 1.4421597719192505,
      "learning_rate": 4.96113061859092e-05,
      "loss": 0.6669,
      "step": 890
    },
    {
      "epoch": 0.023583669618992716,
      "grad_norm": 1.541601300239563,
      "learning_rate": 4.960693883968346e-05,
      "loss": 0.477,
      "step": 900
    },
    {
      "epoch": 0.02384571039253708,
      "grad_norm": 1.0725853443145752,
      "learning_rate": 4.960257149345772e-05,
      "loss": 0.5399,
      "step": 910
    },
    {
      "epoch": 0.024107751166081444,
      "grad_norm": 1.4579834938049316,
      "learning_rate": 4.959820414723198e-05,
      "loss": 0.636,
      "step": 920
    },
    {
      "epoch": 0.024369791939625806,
      "grad_norm": 1.1018449068069458,
      "learning_rate": 4.959383680100624e-05,
      "loss": 0.7731,
      "step": 930
    },
    {
      "epoch": 0.024631832713170168,
      "grad_norm": 1.3531861305236816,
      "learning_rate": 4.95894694547805e-05,
      "loss": 0.7017,
      "step": 940
    },
    {
      "epoch": 0.024893873486714534,
      "grad_norm": 1.1225773096084595,
      "learning_rate": 4.958510210855476e-05,
      "loss": 0.7228,
      "step": 950
    },
    {
      "epoch": 0.025155914260258896,
      "grad_norm": 0.6442508697509766,
      "learning_rate": 4.958073476232902e-05,
      "loss": 0.4421,
      "step": 960
    },
    {
      "epoch": 0.02541795503380326,
      "grad_norm": 1.1338638067245483,
      "learning_rate": 4.957636741610328e-05,
      "loss": 0.6533,
      "step": 970
    },
    {
      "epoch": 0.025679995807347623,
      "grad_norm": 1.0796573162078857,
      "learning_rate": 4.957200006987755e-05,
      "loss": 0.6407,
      "step": 980
    },
    {
      "epoch": 0.025942036580891985,
      "grad_norm": 1.001578450202942,
      "learning_rate": 4.95676327236518e-05,
      "loss": 0.652,
      "step": 990
    },
    {
      "epoch": 0.02620407735443635,
      "grad_norm": 1.521545648574829,
      "learning_rate": 4.956326537742607e-05,
      "loss": 0.4812,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 114486,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3739037466624000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}