{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1172,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 2.1641297340393066,
      "eval_runtime": 2.1264,
      "eval_samples_per_second": 9.405,
      "eval_steps_per_second": 0.941,
      "step": 0
    },
    {
      "epoch": 0.0008535154166222128,
      "grad_norm": 4.247310161590576,
      "learning_rate": 5.681818181818182e-08,
      "loss": 1.0032,
      "step": 1
    },
    {
      "epoch": 0.008535154166222128,
      "grad_norm": 4.285112380981445,
      "learning_rate": 5.681818181818182e-07,
      "loss": 0.9823,
      "step": 10
    },
    {
      "epoch": 0.017070308332444255,
      "grad_norm": 3.0184619426727295,
      "learning_rate": 1.1363636363636364e-06,
      "loss": 0.9382,
      "step": 20
    },
    {
      "epoch": 0.02560546249866638,
      "grad_norm": 2.0186476707458496,
      "learning_rate": 1.7045454545454546e-06,
      "loss": 0.8583,
      "step": 30
    },
    {
      "epoch": 0.03414061666488851,
      "grad_norm": 1.175138235092163,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.764,
      "step": 40
    },
    {
      "epoch": 0.04267577083111064,
      "grad_norm": 0.9045423269271851,
      "learning_rate": 2.8409090909090916e-06,
      "loss": 0.714,
      "step": 50
    },
    {
      "epoch": 0.05121092499733276,
      "grad_norm": 0.8305149078369141,
      "learning_rate": 3.409090909090909e-06,
      "loss": 0.6835,
      "step": 60
    },
    {
      "epoch": 0.05974607916355489,
      "grad_norm": 0.7908885478973389,
      "learning_rate": 3.9772727272727275e-06,
      "loss": 0.6549,
      "step": 70
    },
    {
      "epoch": 0.06828123332977702,
      "grad_norm": 0.8054904341697693,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6368,
      "step": 80
    },
    {
      "epoch": 0.07681638749599914,
      "grad_norm": 0.7891983985900879,
      "learning_rate": 5.113636363636364e-06,
      "loss": 0.631,
      "step": 90
    },
    {
      "epoch": 0.08535154166222128,
      "grad_norm": 0.7775433659553528,
      "learning_rate": 5.681818181818183e-06,
      "loss": 0.6186,
      "step": 100
    },
    {
      "epoch": 0.0938866958284434,
      "grad_norm": 0.8340434432029724,
      "learning_rate": 6.25e-06,
      "loss": 0.6028,
      "step": 110
    },
    {
      "epoch": 0.10242184999466553,
      "grad_norm": 0.7749195098876953,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.5965,
      "step": 120
    },
    {
      "epoch": 0.11095700416088766,
      "grad_norm": 0.7949061393737793,
      "learning_rate": 7.386363636363637e-06,
      "loss": 0.5837,
      "step": 130
    },
    {
      "epoch": 0.11949215832710978,
      "grad_norm": 0.8714171051979065,
      "learning_rate": 7.954545454545455e-06,
      "loss": 0.5865,
      "step": 140
    },
    {
      "epoch": 0.1280273124933319,
      "grad_norm": 0.7890238761901855,
      "learning_rate": 8.522727272727273e-06,
      "loss": 0.5712,
      "step": 150
    },
    {
      "epoch": 0.13656246665955404,
      "grad_norm": 0.8195155262947083,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.5774,
      "step": 160
    },
    {
      "epoch": 0.14509762082577615,
      "grad_norm": 0.8219712972640991,
      "learning_rate": 9.65909090909091e-06,
      "loss": 0.5767,
      "step": 170
    },
    {
      "epoch": 0.1536327749919983,
      "grad_norm": 0.8124852776527405,
      "learning_rate": 1.0227272727272729e-05,
      "loss": 0.5643,
      "step": 180
    },
    {
      "epoch": 0.16216792915822043,
      "grad_norm": 0.8383850455284119,
      "learning_rate": 1.0795454545454547e-05,
      "loss": 0.5734,
      "step": 190
    },
    {
      "epoch": 0.17070308332444256,
      "grad_norm": 0.7605228424072266,
      "learning_rate": 1.1363636363636366e-05,
      "loss": 0.5661,
      "step": 200
    },
    {
      "epoch": 0.17923823749066467,
      "grad_norm": 0.8585752844810486,
      "learning_rate": 1.1931818181818183e-05,
      "loss": 0.5534,
      "step": 210
    },
    {
      "epoch": 0.1877733916568868,
      "grad_norm": 0.8643070459365845,
      "learning_rate": 1.25e-05,
      "loss": 0.5549,
      "step": 220
    },
    {
      "epoch": 0.19630854582310894,
      "grad_norm": 0.9826616644859314,
      "learning_rate": 1.306818181818182e-05,
      "loss": 0.5531,
      "step": 230
    },
    {
      "epoch": 0.20484369998933105,
      "grad_norm": 0.8799106478691101,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.5371,
      "step": 240
    },
    {
      "epoch": 0.2133788541555532,
      "grad_norm": 0.757698118686676,
      "learning_rate": 1.4204545454545455e-05,
      "loss": 0.5459,
      "step": 250
    },
    {
      "epoch": 0.22191400832177532,
      "grad_norm": 0.8704412579536438,
      "learning_rate": 1.4772727272727274e-05,
      "loss": 0.5369,
      "step": 260
    },
    {
      "epoch": 0.23044916248799743,
      "grad_norm": 0.7941352725028992,
      "learning_rate": 1.5340909090909094e-05,
      "loss": 0.5359,
      "step": 270
    },
    {
      "epoch": 0.23898431665421957,
      "grad_norm": 0.7990615367889404,
      "learning_rate": 1.590909090909091e-05,
      "loss": 0.5285,
      "step": 280
    },
    {
      "epoch": 0.2475194708204417,
      "grad_norm": 0.7938647270202637,
      "learning_rate": 1.647727272727273e-05,
      "loss": 0.5391,
      "step": 290
    },
    {
      "epoch": 0.2560546249866638,
      "grad_norm": 0.7677845358848572,
      "learning_rate": 1.7045454545454546e-05,
      "loss": 0.5195,
      "step": 300
    },
    {
      "epoch": 0.26458977915288595,
      "grad_norm": 0.7977807521820068,
      "learning_rate": 1.7613636363636366e-05,
      "loss": 0.5246,
      "step": 310
    },
    {
      "epoch": 0.2731249333191081,
      "grad_norm": 0.819622814655304,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.5176,
      "step": 320
    },
    {
      "epoch": 0.2816600874853302,
      "grad_norm": 0.8428648114204407,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.513,
      "step": 330
    },
    {
      "epoch": 0.2901952416515523,
      "grad_norm": 0.7542017102241516,
      "learning_rate": 1.931818181818182e-05,
      "loss": 0.5196,
      "step": 340
    },
    {
      "epoch": 0.29873039581777444,
      "grad_norm": 0.8601102232933044,
      "learning_rate": 1.9886363636363638e-05,
      "loss": 0.5206,
      "step": 350
    },
    {
      "epoch": 0.3072655499839966,
      "grad_norm": 0.7532691955566406,
      "learning_rate": 1.9999683918961086e-05,
      "loss": 0.5162,
      "step": 360
    },
    {
      "epoch": 0.3158007041502187,
      "grad_norm": 0.7489638924598694,
      "learning_rate": 1.999839987398595e-05,
      "loss": 0.5122,
      "step": 370
    },
    {
      "epoch": 0.32433585831644085,
      "grad_norm": 0.7671491503715515,
      "learning_rate": 1.9996128236743682e-05,
      "loss": 0.5161,
      "step": 380
    },
    {
      "epoch": 0.332871012482663,
      "grad_norm": 0.7274801731109619,
      "learning_rate": 1.9992869231615323e-05,
      "loss": 0.5167,
      "step": 390
    },
    {
      "epoch": 0.3414061666488851,
      "grad_norm": 0.7289360165596008,
      "learning_rate": 1.9988623180509206e-05,
      "loss": 0.5127,
      "step": 400
    },
    {
      "epoch": 0.3499413208151072,
      "grad_norm": 0.7416843175888062,
      "learning_rate": 1.9983390502829168e-05,
      "loss": 0.5208,
      "step": 410
    },
    {
      "epoch": 0.35847647498132934,
      "grad_norm": 0.7530054450035095,
      "learning_rate": 1.997717171543311e-05,
      "loss": 0.5011,
      "step": 420
    },
    {
      "epoch": 0.3670116291475515,
      "grad_norm": 0.7372049689292908,
      "learning_rate": 1.9969967432581962e-05,
      "loss": 0.5091,
      "step": 430
    },
    {
      "epoch": 0.3755467833137736,
      "grad_norm": 0.8357003927230835,
      "learning_rate": 1.996177836587899e-05,
      "loss": 0.5114,
      "step": 440
    },
    {
      "epoch": 0.38408193747999575,
      "grad_norm": 0.8466181755065918,
      "learning_rate": 1.9952605324199516e-05,
      "loss": 0.5009,
      "step": 450
    },
    {
      "epoch": 0.3926170916462179,
      "grad_norm": 0.7260451316833496,
      "learning_rate": 1.9942449213611028e-05,
      "loss": 0.5087,
      "step": 460
    },
    {
      "epoch": 0.40115224581243997,
      "grad_norm": 0.6815033555030823,
      "learning_rate": 1.9931311037283673e-05,
      "loss": 0.5033,
      "step": 470
    },
    {
      "epoch": 0.4096873999786621,
      "grad_norm": 0.706380307674408,
      "learning_rate": 1.9919191895391176e-05,
      "loss": 0.4974,
      "step": 480
    },
    {
      "epoch": 0.41822255414488424,
      "grad_norm": 0.736223042011261,
      "learning_rate": 1.9906092985002163e-05,
      "loss": 0.4981,
      "step": 490
    },
    {
      "epoch": 0.4267577083111064,
      "grad_norm": 0.9467535614967346,
      "learning_rate": 1.9892015599961927e-05,
      "loss": 0.5017,
      "step": 500
    },
    {
      "epoch": 0.4352928624773285,
      "grad_norm": 0.7372705936431885,
      "learning_rate": 1.9876961130764624e-05,
      "loss": 0.5047,
      "step": 510
    },
    {
      "epoch": 0.44382801664355065,
      "grad_norm": 0.7471463680267334,
      "learning_rate": 1.9860931064415934e-05,
      "loss": 0.5009,
      "step": 520
    },
    {
      "epoch": 0.45236317080977273,
      "grad_norm": 0.6775240898132324,
      "learning_rate": 1.9843926984286165e-05,
      "loss": 0.5045,
      "step": 530
    },
    {
      "epoch": 0.46089832497599487,
      "grad_norm": 0.6793776750564575,
      "learning_rate": 1.9825950569953884e-05,
      "loss": 0.4978,
      "step": 540
    },
    {
      "epoch": 0.469433479142217,
      "grad_norm": 0.6851901412010193,
      "learning_rate": 1.980700359703999e-05,
      "loss": 0.494,
      "step": 550
    },
    {
      "epoch": 0.47796863330843914,
      "grad_norm": 0.6855452060699463,
      "learning_rate": 1.9787087937032333e-05,
      "loss": 0.4952,
      "step": 560
    },
    {
      "epoch": 0.4865037874746613,
      "grad_norm": 0.707453727722168,
      "learning_rate": 1.976620555710087e-05,
      "loss": 0.4949,
      "step": 570
    },
    {
      "epoch": 0.4950389416408834,
      "grad_norm": 0.6674401760101318,
      "learning_rate": 1.9744358519903343e-05,
      "loss": 0.4863,
      "step": 580
    },
    {
      "epoch": 0.5035740958071055,
      "grad_norm": 0.7680632472038269,
      "learning_rate": 1.9721548983381554e-05,
      "loss": 0.4882,
      "step": 590
    },
    {
      "epoch": 0.5121092499733276,
      "grad_norm": 0.6789171099662781,
      "learning_rate": 1.9697779200548202e-05,
      "loss": 0.4848,
      "step": 600
    },
    {
      "epoch": 0.5206444041395498,
      "grad_norm": 0.6551903486251831,
      "learning_rate": 1.9673051519264342e-05,
      "loss": 0.4951,
      "step": 610
    },
    {
      "epoch": 0.5291795583057719,
      "grad_norm": 0.7067411541938782,
      "learning_rate": 1.964736838200749e-05,
      "loss": 0.493,
      "step": 620
    },
    {
      "epoch": 0.537714712471994,
      "grad_norm": 0.6695910692214966,
      "learning_rate": 1.9620732325630342e-05,
      "loss": 0.4938,
      "step": 630
    },
    {
      "epoch": 0.5462498666382162,
      "grad_norm": 0.6625940203666687,
      "learning_rate": 1.9593145981110223e-05,
      "loss": 0.4873,
      "step": 640
    },
    {
      "epoch": 0.5547850208044383,
      "grad_norm": 0.7263137102127075,
      "learning_rate": 1.9564612073289192e-05,
      "loss": 0.4964,
      "step": 650
    },
    {
      "epoch": 0.5633201749706604,
      "grad_norm": 0.7034249901771545,
      "learning_rate": 1.9535133420604905e-05,
      "loss": 0.4952,
      "step": 660
    },
    {
      "epoch": 0.5718553291368825,
      "grad_norm": 0.633065402507782,
      "learning_rate": 1.9504712934812228e-05,
      "loss": 0.4982,
      "step": 670
    },
    {
      "epoch": 0.5803904833031046,
      "grad_norm": 0.7597299814224243,
      "learning_rate": 1.9473353620695614e-05,
      "loss": 0.4839,
      "step": 680
    },
    {
      "epoch": 0.5889256374693268,
      "grad_norm": 0.6461811065673828,
      "learning_rate": 1.9441058575772317e-05,
      "loss": 0.4853,
      "step": 690
    },
    {
      "epoch": 0.5974607916355489,
      "grad_norm": 0.6678339242935181,
      "learning_rate": 1.940783098998643e-05,
      "loss": 0.4814,
      "step": 700
    },
    {
      "epoch": 0.6059959458017711,
      "grad_norm": 0.6317865252494812,
      "learning_rate": 1.9373674145393804e-05,
      "loss": 0.4896,
      "step": 710
    },
    {
      "epoch": 0.6145310999679932,
      "grad_norm": 0.6536778211593628,
      "learning_rate": 1.9338591415837856e-05,
      "loss": 0.4795,
      "step": 720
    },
    {
      "epoch": 0.6230662541342153,
      "grad_norm": 0.653390645980835,
      "learning_rate": 1.9302586266616318e-05,
      "loss": 0.4862,
      "step": 730
    },
    {
      "epoch": 0.6316014083004374,
      "grad_norm": 0.6988620758056641,
      "learning_rate": 1.9265662254138958e-05,
      "loss": 0.4913,
      "step": 740
    },
    {
      "epoch": 0.6401365624666595,
      "grad_norm": 0.6603461503982544,
      "learning_rate": 1.922782302557628e-05,
      "loss": 0.4813,
      "step": 750
    },
    {
      "epoch": 0.6486717166328817,
      "grad_norm": 0.7291558980941772,
      "learning_rate": 1.918907231849931e-05,
      "loss": 0.4843,
      "step": 760
    },
    {
      "epoch": 0.6572068707991038,
      "grad_norm": 0.678535521030426,
      "learning_rate": 1.914941396051036e-05,
      "loss": 0.4819,
      "step": 770
    },
    {
      "epoch": 0.665742024965326,
      "grad_norm": 0.7419494390487671,
      "learning_rate": 1.910885186886502e-05,
      "loss": 0.4759,
      "step": 780
    },
    {
      "epoch": 0.674277179131548,
      "grad_norm": 0.7254301309585571,
      "learning_rate": 1.9067390050085183e-05,
      "loss": 0.4754,
      "step": 790
    },
    {
      "epoch": 0.6828123332977702,
      "grad_norm": 0.6892661452293396,
      "learning_rate": 1.902503259956333e-05,
      "loss": 0.4759,
      "step": 800
    },
    {
      "epoch": 0.6913474874639923,
      "grad_norm": 0.6353612542152405,
      "learning_rate": 1.8981783701157985e-05,
      "loss": 0.4787,
      "step": 810
    },
    {
      "epoch": 0.6998826416302144,
      "grad_norm": 0.578580915927887,
      "learning_rate": 1.8937647626780473e-05,
      "loss": 0.4748,
      "step": 820
    },
    {
      "epoch": 0.7084177957964366,
      "grad_norm": 0.6349884867668152,
      "learning_rate": 1.889262873597295e-05,
      "loss": 0.4817,
      "step": 830
    },
    {
      "epoch": 0.7169529499626587,
      "grad_norm": 0.6372865438461304,
      "learning_rate": 1.8846731475477796e-05,
      "loss": 0.4811,
      "step": 840
    },
    {
      "epoch": 0.7254881041288809,
      "grad_norm": 0.70332932472229,
      "learning_rate": 1.8799960378798382e-05,
      "loss": 0.4854,
      "step": 850
    },
    {
      "epoch": 0.734023258295103,
      "grad_norm": 0.6345937252044678,
      "learning_rate": 1.8752320065751276e-05,
      "loss": 0.4804,
      "step": 860
    },
    {
      "epoch": 0.742558412461325,
      "grad_norm": 0.7001857757568359,
      "learning_rate": 1.8703815242009927e-05,
      "loss": 0.4823,
      "step": 870
    },
    {
      "epoch": 0.7510935666275472,
      "grad_norm": 0.6997294425964355,
      "learning_rate": 1.8654450698639845e-05,
      "loss": 0.4772,
      "step": 880
    },
    {
      "epoch": 0.7596287207937693,
      "grad_norm": 0.6218723058700562,
      "learning_rate": 1.860423131162538e-05,
      "loss": 0.4741,
      "step": 890
    },
    {
      "epoch": 0.7681638749599915,
      "grad_norm": 0.6111359000205994,
      "learning_rate": 1.8553162041388096e-05,
      "loss": 0.4724,
      "step": 900
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.6032017469406128,
      "learning_rate": 1.8501247932296785e-05,
      "loss": 0.4769,
      "step": 910
    },
    {
      "epoch": 0.7852341832924358,
      "grad_norm": 0.6396908164024353,
      "learning_rate": 1.8448494112169234e-05,
      "loss": 0.4747,
      "step": 920
    },
    {
      "epoch": 0.7937693374586579,
      "grad_norm": 0.690779983997345,
      "learning_rate": 1.8394905791765714e-05,
      "loss": 0.4719,
      "step": 930
    },
    {
      "epoch": 0.8023044916248799,
      "grad_norm": 0.6640828251838684,
      "learning_rate": 1.8340488264274285e-05,
      "loss": 0.477,
      "step": 940
    },
    {
      "epoch": 0.8108396457911021,
      "grad_norm": 0.6492927074432373,
      "learning_rate": 1.8285246904787968e-05,
      "loss": 0.4626,
      "step": 950
    },
    {
      "epoch": 0.8193747999573242,
      "grad_norm": 0.6751061677932739,
      "learning_rate": 1.8229187169773805e-05,
      "loss": 0.4698,
      "step": 960
    },
    {
      "epoch": 0.8279099541235464,
      "grad_norm": 0.6475481390953064,
      "learning_rate": 1.8172314596533914e-05,
      "loss": 0.4698,
      "step": 970
    },
    {
      "epoch": 0.8364451082897685,
      "grad_norm": 0.6659871935844421,
      "learning_rate": 1.8114634802658542e-05,
      "loss": 0.4778,
      "step": 980
    },
    {
      "epoch": 0.8449802624559906,
      "grad_norm": 0.6479447484016418,
      "learning_rate": 1.8056153485471167e-05,
      "loss": 0.4703,
      "step": 990
    },
    {
      "epoch": 0.8535154166222128,
      "grad_norm": 0.7254726886749268,
      "learning_rate": 1.7996876421465764e-05,
      "loss": 0.4767,
      "step": 1000
    },
    {
      "epoch": 0.8620505707884348,
      "grad_norm": 0.6294846534729004,
      "learning_rate": 1.7936809465736223e-05,
      "loss": 0.4615,
      "step": 1010
    },
    {
      "epoch": 0.870585724954657,
      "grad_norm": 0.6530686020851135,
      "learning_rate": 1.7875958551398023e-05,
      "loss": 0.4642,
      "step": 1020
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.713152289390564,
      "learning_rate": 1.781432968900217e-05,
      "loss": 0.4692,
      "step": 1030
    },
    {
      "epoch": 0.8876560332871013,
      "grad_norm": 0.7651381492614746,
      "learning_rate": 1.775192896594151e-05,
      "loss": 0.4646,
      "step": 1040
    },
    {
      "epoch": 0.8961911874533234,
      "grad_norm": 0.5913043022155762,
      "learning_rate": 1.7688762545849466e-05,
      "loss": 0.4688,
      "step": 1050
    },
    {
      "epoch": 0.9047263416195455,
      "grad_norm": 0.6034150719642639,
      "learning_rate": 1.7624836667991195e-05,
      "loss": 0.4574,
      "step": 1060
    },
    {
      "epoch": 0.9132614957857677,
      "grad_norm": 0.6374826431274414,
      "learning_rate": 1.7560157646647335e-05,
      "loss": 0.4651,
      "step": 1070
    },
    {
      "epoch": 0.9217966499519897,
      "grad_norm": 0.6261687278747559,
      "learning_rate": 1.749473187049028e-05,
      "loss": 0.4608,
      "step": 1080
    },
    {
      "epoch": 0.9303318041182119,
      "grad_norm": 0.6067594885826111,
      "learning_rate": 1.742856580195316e-05,
      "loss": 0.4592,
      "step": 1090
    },
    {
      "epoch": 0.938866958284434,
      "grad_norm": 0.6240684986114502,
      "learning_rate": 1.7361665976591513e-05,
      "loss": 0.4663,
      "step": 1100
    },
    {
      "epoch": 0.9474021124506561,
      "grad_norm": 0.6192986965179443,
      "learning_rate": 1.7294039002437724e-05,
      "loss": 0.476,
      "step": 1110
    },
    {
      "epoch": 0.9559372666168783,
      "grad_norm": 0.6121706962585449,
      "learning_rate": 1.7225691559348333e-05,
      "loss": 0.4531,
      "step": 1120
    },
    {
      "epoch": 0.9644724207831004,
      "grad_norm": 0.5956526398658752,
      "learning_rate": 1.715663039834421e-05,
      "loss": 0.4643,
      "step": 1130
    },
    {
      "epoch": 0.9730075749493226,
      "grad_norm": 0.5699427127838135,
      "learning_rate": 1.7086862340943745e-05,
      "loss": 0.4601,
      "step": 1140
    },
    {
      "epoch": 0.9815427291155446,
      "grad_norm": 0.6840018630027771,
      "learning_rate": 1.701639427848903e-05,
      "loss": 0.4555,
      "step": 1150
    },
    {
      "epoch": 0.9900778832817668,
      "grad_norm": 0.6009624004364014,
      "learning_rate": 1.6945233171465193e-05,
      "loss": 0.4632,
      "step": 1160
    },
    {
      "epoch": 0.9986130374479889,
      "grad_norm": 0.5962963104248047,
      "learning_rate": 1.6873386048812854e-05,
      "loss": 0.4702,
      "step": 1170
    }
  ],
  "logging_steps": 10,
  "max_steps": 3513,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.729895927368909e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}