{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9946268656716417,
  "eval_steps": 500,
  "global_step": 1254,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023880597014925373,
      "grad_norm": 10.273793568807084,
      "learning_rate": 5e-06,
      "loss": 0.8832,
      "step": 10
    },
    {
      "epoch": 0.04776119402985075,
      "grad_norm": 17.413079986249713,
      "learning_rate": 5e-06,
      "loss": 0.7826,
      "step": 20
    },
    {
      "epoch": 0.07164179104477612,
      "grad_norm": 1.7682355694433471,
      "learning_rate": 5e-06,
      "loss": 0.7785,
      "step": 30
    },
    {
      "epoch": 0.0955223880597015,
      "grad_norm": 1.2119658541333866,
      "learning_rate": 5e-06,
      "loss": 0.7537,
      "step": 40
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 0.8476848561416307,
      "learning_rate": 5e-06,
      "loss": 0.7389,
      "step": 50
    },
    {
      "epoch": 0.14328358208955225,
      "grad_norm": 0.7667403306996323,
      "learning_rate": 5e-06,
      "loss": 0.7217,
      "step": 60
    },
    {
      "epoch": 0.16716417910447762,
      "grad_norm": 0.8702244781914732,
      "learning_rate": 5e-06,
      "loss": 0.7085,
      "step": 70
    },
    {
      "epoch": 0.191044776119403,
      "grad_norm": 1.3853703465833076,
      "learning_rate": 5e-06,
      "loss": 0.6971,
      "step": 80
    },
    {
      "epoch": 0.21492537313432836,
      "grad_norm": 1.2094222885220798,
      "learning_rate": 5e-06,
      "loss": 0.6882,
      "step": 90
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 0.7689681572000278,
      "learning_rate": 5e-06,
      "loss": 0.6849,
      "step": 100
    },
    {
      "epoch": 0.2626865671641791,
      "grad_norm": 0.7780597190717987,
      "learning_rate": 5e-06,
      "loss": 0.6818,
      "step": 110
    },
    {
      "epoch": 0.2865671641791045,
      "grad_norm": 0.5000855152810337,
      "learning_rate": 5e-06,
      "loss": 0.6816,
      "step": 120
    },
    {
      "epoch": 0.31044776119402984,
      "grad_norm": 0.7276396850932823,
      "learning_rate": 5e-06,
      "loss": 0.6736,
      "step": 130
    },
    {
      "epoch": 0.33432835820895523,
      "grad_norm": 0.6186133127584187,
      "learning_rate": 5e-06,
      "loss": 0.6818,
      "step": 140
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 0.48005981720062146,
      "learning_rate": 5e-06,
      "loss": 0.673,
      "step": 150
    },
    {
      "epoch": 0.382089552238806,
      "grad_norm": 0.5023606142200144,
      "learning_rate": 5e-06,
      "loss": 0.6773,
      "step": 160
    },
    {
      "epoch": 0.4059701492537313,
      "grad_norm": 0.5808170399886017,
      "learning_rate": 5e-06,
      "loss": 0.6677,
      "step": 170
    },
    {
      "epoch": 0.4298507462686567,
      "grad_norm": 0.4379969982797677,
      "learning_rate": 5e-06,
      "loss": 0.6685,
      "step": 180
    },
    {
      "epoch": 0.4537313432835821,
      "grad_norm": 0.5347993662162854,
      "learning_rate": 5e-06,
      "loss": 0.6752,
      "step": 190
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.5389725567643092,
      "learning_rate": 5e-06,
      "loss": 0.6648,
      "step": 200
    },
    {
      "epoch": 0.5014925373134328,
      "grad_norm": 0.48052530490608086,
      "learning_rate": 5e-06,
      "loss": 0.6641,
      "step": 210
    },
    {
      "epoch": 0.5253731343283582,
      "grad_norm": 0.5805014519700745,
      "learning_rate": 5e-06,
      "loss": 0.6591,
      "step": 220
    },
    {
      "epoch": 0.5492537313432836,
      "grad_norm": 0.48958097076386,
      "learning_rate": 5e-06,
      "loss": 0.6655,
      "step": 230
    },
    {
      "epoch": 0.573134328358209,
      "grad_norm": 0.49437501765783676,
      "learning_rate": 5e-06,
      "loss": 0.6683,
      "step": 240
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.45944903239035917,
      "learning_rate": 5e-06,
      "loss": 0.659,
      "step": 250
    },
    {
      "epoch": 0.6208955223880597,
      "grad_norm": 0.4748455280427033,
      "learning_rate": 5e-06,
      "loss": 0.6583,
      "step": 260
    },
    {
      "epoch": 0.6447761194029851,
      "grad_norm": 0.507103510913949,
      "learning_rate": 5e-06,
      "loss": 0.6583,
      "step": 270
    },
    {
      "epoch": 0.6686567164179105,
      "grad_norm": 0.48478059033960125,
      "learning_rate": 5e-06,
      "loss": 0.6587,
      "step": 280
    },
    {
      "epoch": 0.6925373134328359,
      "grad_norm": 0.5180513023339883,
      "learning_rate": 5e-06,
      "loss": 0.6557,
      "step": 290
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.6977133509211488,
      "learning_rate": 5e-06,
      "loss": 0.6596,
      "step": 300
    },
    {
      "epoch": 0.7402985074626866,
      "grad_norm": 0.6751977610973682,
      "learning_rate": 5e-06,
      "loss": 0.6631,
      "step": 310
    },
    {
      "epoch": 0.764179104477612,
      "grad_norm": 0.5497977666993439,
      "learning_rate": 5e-06,
      "loss": 0.6538,
      "step": 320
    },
    {
      "epoch": 0.7880597014925373,
      "grad_norm": 0.4930749400299794,
      "learning_rate": 5e-06,
      "loss": 0.6533,
      "step": 330
    },
    {
      "epoch": 0.8119402985074626,
      "grad_norm": 0.42531288506677356,
      "learning_rate": 5e-06,
      "loss": 0.654,
      "step": 340
    },
    {
      "epoch": 0.835820895522388,
      "grad_norm": 0.3981313944033897,
      "learning_rate": 5e-06,
      "loss": 0.6588,
      "step": 350
    },
    {
      "epoch": 0.8597014925373134,
      "grad_norm": 0.5280916740215565,
      "learning_rate": 5e-06,
      "loss": 0.6467,
      "step": 360
    },
    {
      "epoch": 0.8835820895522388,
      "grad_norm": 0.42664364036263097,
      "learning_rate": 5e-06,
      "loss": 0.6547,
      "step": 370
    },
    {
      "epoch": 0.9074626865671642,
      "grad_norm": 0.4407169068422887,
      "learning_rate": 5e-06,
      "loss": 0.6576,
      "step": 380
    },
    {
      "epoch": 0.9313432835820895,
      "grad_norm": 0.5863915466432706,
      "learning_rate": 5e-06,
      "loss": 0.6517,
      "step": 390
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.591205757573771,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 400
    },
    {
      "epoch": 0.9791044776119403,
      "grad_norm": 0.4729812620066271,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 410
    },
    {
      "epoch": 0.9982089552238806,
      "eval_loss": 0.6459853649139404,
      "eval_runtime": 145.5401,
      "eval_samples_per_second": 77.532,
      "eval_steps_per_second": 0.612,
      "step": 418
    },
    {
      "epoch": 1.0029850746268656,
      "grad_norm": 0.7406302510482085,
      "learning_rate": 5e-06,
      "loss": 0.6464,
      "step": 420
    },
    {
      "epoch": 1.026865671641791,
      "grad_norm": 0.5814842349080193,
      "learning_rate": 5e-06,
      "loss": 0.6064,
      "step": 430
    },
    {
      "epoch": 1.0507462686567164,
      "grad_norm": 0.49550119932649633,
      "learning_rate": 5e-06,
      "loss": 0.6082,
      "step": 440
    },
    {
      "epoch": 1.0746268656716418,
      "grad_norm": 0.5636659335114863,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 450
    },
    {
      "epoch": 1.0985074626865672,
      "grad_norm": 0.5990578133097235,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 460
    },
    {
      "epoch": 1.1223880597014926,
      "grad_norm": 0.5395914783918955,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 470
    },
    {
      "epoch": 1.146268656716418,
      "grad_norm": 0.5134850748551497,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 480
    },
    {
      "epoch": 1.1701492537313434,
      "grad_norm": 0.6291645545602457,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 490
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.5896587056027497,
      "learning_rate": 5e-06,
      "loss": 0.6078,
      "step": 500
    },
    {
      "epoch": 1.217910447761194,
      "grad_norm": 0.44004057090652665,
      "learning_rate": 5e-06,
      "loss": 0.6028,
      "step": 510
    },
    {
      "epoch": 1.2417910447761193,
      "grad_norm": 0.6082489861086471,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 520
    },
    {
      "epoch": 1.2656716417910447,
      "grad_norm": 0.4757708288590624,
      "learning_rate": 5e-06,
      "loss": 0.6128,
      "step": 530
    },
    {
      "epoch": 1.2895522388059701,
      "grad_norm": 0.4866590721782206,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 540
    },
    {
      "epoch": 1.3134328358208955,
      "grad_norm": 0.4646472106430823,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 550
    },
    {
      "epoch": 1.337313432835821,
      "grad_norm": 0.44517915287397264,
      "learning_rate": 5e-06,
      "loss": 0.6079,
      "step": 560
    },
    {
      "epoch": 1.3611940298507463,
      "grad_norm": 0.6694478573734268,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 570
    },
    {
      "epoch": 1.3850746268656717,
      "grad_norm": 0.5078303398930042,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 580
    },
    {
      "epoch": 1.408955223880597,
      "grad_norm": 0.503001629794063,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 590
    },
    {
      "epoch": 1.4328358208955223,
      "grad_norm": 0.5438514985018119,
      "learning_rate": 5e-06,
      "loss": 0.613,
      "step": 600
    },
    {
      "epoch": 1.4567164179104477,
      "grad_norm": 0.5056414273287846,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 610
    },
    {
      "epoch": 1.480597014925373,
      "grad_norm": 0.4588677461940861,
      "learning_rate": 5e-06,
      "loss": 0.6126,
      "step": 620
    },
    {
      "epoch": 1.5044776119402985,
      "grad_norm": 0.5151479126151606,
      "learning_rate": 5e-06,
      "loss": 0.608,
      "step": 630
    },
    {
      "epoch": 1.528358208955224,
      "grad_norm": 0.46401616793533473,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 640
    },
    {
      "epoch": 1.5522388059701493,
      "grad_norm": 0.48451525361860803,
      "learning_rate": 5e-06,
      "loss": 0.605,
      "step": 650
    },
    {
      "epoch": 1.5761194029850745,
      "grad_norm": 0.47997260631095534,
      "learning_rate": 5e-06,
      "loss": 0.6109,
      "step": 660
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4897371630270623,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 670
    },
    {
      "epoch": 1.6238805970149253,
      "grad_norm": 0.5654442922228684,
      "learning_rate": 5e-06,
      "loss": 0.6123,
      "step": 680
    },
    {
      "epoch": 1.6477611940298509,
      "grad_norm": 0.5784991723951006,
      "learning_rate": 5e-06,
      "loss": 0.5942,
      "step": 690
    },
    {
      "epoch": 1.671641791044776,
      "grad_norm": 0.4722303828551024,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 700
    },
    {
      "epoch": 1.6955223880597015,
      "grad_norm": 0.4839424076756933,
      "learning_rate": 5e-06,
      "loss": 0.6091,
      "step": 710
    },
    {
      "epoch": 1.7194029850746269,
      "grad_norm": 0.47764784827023116,
      "learning_rate": 5e-06,
      "loss": 0.6123,
      "step": 720
    },
    {
      "epoch": 1.7432835820895523,
      "grad_norm": 0.6621875079490905,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 730
    },
    {
      "epoch": 1.7671641791044777,
      "grad_norm": 0.41773352573318373,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 740
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.5339311769344796,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 750
    },
    {
      "epoch": 1.8149253731343284,
      "grad_norm": 0.41758051779371724,
      "learning_rate": 5e-06,
      "loss": 0.602,
      "step": 760
    },
    {
      "epoch": 1.8388059701492536,
      "grad_norm": 0.48493110488320246,
      "learning_rate": 5e-06,
      "loss": 0.609,
      "step": 770
    },
    {
      "epoch": 1.8626865671641792,
      "grad_norm": 0.503079485131092,
      "learning_rate": 5e-06,
      "loss": 0.6108,
      "step": 780
    },
    {
      "epoch": 1.8865671641791044,
      "grad_norm": 0.49999802261208487,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 790
    },
    {
      "epoch": 1.9104477611940298,
      "grad_norm": 0.49289621093364544,
      "learning_rate": 5e-06,
      "loss": 0.6071,
      "step": 800
    },
    {
      "epoch": 1.9343283582089552,
      "grad_norm": 0.5213797280676552,
      "learning_rate": 5e-06,
      "loss": 0.6006,
      "step": 810
    },
    {
      "epoch": 1.9582089552238806,
      "grad_norm": 0.48494536428497287,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 820
    },
    {
      "epoch": 1.982089552238806,
      "grad_norm": 0.6304797916900879,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 830
    },
    {
      "epoch": 1.9988059701492538,
      "eval_loss": 0.6354221701622009,
      "eval_runtime": 145.6955,
      "eval_samples_per_second": 77.449,
      "eval_steps_per_second": 0.611,
      "step": 837
    },
    {
      "epoch": 2.005970149253731,
      "grad_norm": 0.7544412739259527,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 840
    },
    {
      "epoch": 2.029850746268657,
      "grad_norm": 0.6076312693154532,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 850
    },
    {
      "epoch": 2.053731343283582,
      "grad_norm": 0.5264338967840297,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 860
    },
    {
      "epoch": 2.0776119402985076,
      "grad_norm": 0.5190037883143301,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 870
    },
    {
      "epoch": 2.1014925373134328,
      "grad_norm": 0.46674031058869914,
      "learning_rate": 5e-06,
      "loss": 0.5611,
      "step": 880
    },
    {
      "epoch": 2.1253731343283584,
      "grad_norm": 0.5072546488653424,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 890
    },
    {
      "epoch": 2.1492537313432836,
      "grad_norm": 0.6009874453432602,
      "learning_rate": 5e-06,
      "loss": 0.5611,
      "step": 900
    },
    {
      "epoch": 2.173134328358209,
      "grad_norm": 0.46110082010928216,
      "learning_rate": 5e-06,
      "loss": 0.5618,
      "step": 910
    },
    {
      "epoch": 2.1970149253731344,
      "grad_norm": 0.5163994956633559,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 920
    },
    {
      "epoch": 2.2208955223880595,
      "grad_norm": 0.6176077747391998,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 930
    },
    {
      "epoch": 2.244776119402985,
      "grad_norm": 0.46798047694883976,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 940
    },
    {
      "epoch": 2.2686567164179103,
      "grad_norm": 0.5458770025747796,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 950
    },
    {
      "epoch": 2.292537313432836,
      "grad_norm": 0.4522021510300349,
      "learning_rate": 5e-06,
      "loss": 0.5582,
      "step": 960
    },
    {
      "epoch": 2.316417910447761,
      "grad_norm": 0.4993495813706899,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 970
    },
    {
      "epoch": 2.3402985074626868,
      "grad_norm": 0.5148727234502507,
      "learning_rate": 5e-06,
      "loss": 0.5627,
      "step": 980
    },
    {
      "epoch": 2.364179104477612,
      "grad_norm": 0.4746669105759272,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 990
    },
    {
      "epoch": 2.388059701492537,
      "grad_norm": 0.49984909528425026,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1000
    },
    {
      "epoch": 2.4119402985074627,
      "grad_norm": 0.44986277151799875,
      "learning_rate": 5e-06,
      "loss": 0.5616,
      "step": 1010
    },
    {
      "epoch": 2.435820895522388,
      "grad_norm": 0.48588485615374555,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 1020
    },
    {
      "epoch": 2.4597014925373135,
      "grad_norm": 0.48231851620423527,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 1030
    },
    {
      "epoch": 2.4835820895522387,
      "grad_norm": 0.5353905043801261,
      "learning_rate": 5e-06,
      "loss": 0.572,
      "step": 1040
    },
    {
      "epoch": 2.5074626865671643,
      "grad_norm": 0.4911575383473398,
      "learning_rate": 5e-06,
      "loss": 0.561,
      "step": 1050
    },
    {
      "epoch": 2.5313432835820895,
      "grad_norm": 0.5322320223748976,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 1060
    },
    {
      "epoch": 2.5552238805970147,
      "grad_norm": 0.47802103841875787,
      "learning_rate": 5e-06,
      "loss": 0.5648,
      "step": 1070
    },
    {
      "epoch": 2.5791044776119403,
      "grad_norm": 0.5461878411480141,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1080
    },
    {
      "epoch": 2.602985074626866,
      "grad_norm": 0.5723521540745492,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1090
    },
    {
      "epoch": 2.626865671641791,
      "grad_norm": 0.43486752386685085,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 1100
    },
    {
      "epoch": 2.6507462686567163,
      "grad_norm": 0.4851163868024419,
      "learning_rate": 5e-06,
      "loss": 0.5628,
      "step": 1110
    },
    {
      "epoch": 2.674626865671642,
      "grad_norm": 0.4819830185138904,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 1120
    },
    {
      "epoch": 2.698507462686567,
      "grad_norm": 0.4782708772767338,
      "learning_rate": 5e-06,
      "loss": 0.5715,
      "step": 1130
    },
    {
      "epoch": 2.7223880597014927,
      "grad_norm": 0.4564853695633748,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 1140
    },
    {
      "epoch": 2.746268656716418,
      "grad_norm": 0.5672636342724084,
      "learning_rate": 5e-06,
      "loss": 0.5703,
      "step": 1150
    },
    {
      "epoch": 2.7701492537313435,
      "grad_norm": 0.46200475373217254,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 1160
    },
    {
      "epoch": 2.7940298507462686,
      "grad_norm": 0.439779919962293,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 1170
    },
    {
      "epoch": 2.817910447761194,
      "grad_norm": 0.48759282182632596,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 1180
    },
    {
      "epoch": 2.8417910447761194,
      "grad_norm": 0.5417263063839436,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 1190
    },
    {
      "epoch": 2.8656716417910446,
      "grad_norm": 0.4780631102145764,
      "learning_rate": 5e-06,
      "loss": 0.5677,
      "step": 1200
    },
    {
      "epoch": 2.8895522388059702,
      "grad_norm": 0.500379213535652,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 1210
    },
    {
      "epoch": 2.9134328358208954,
      "grad_norm": 0.5402151963225374,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 1220
    },
    {
      "epoch": 2.937313432835821,
      "grad_norm": 0.4522864472397569,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 1230
    },
    {
      "epoch": 2.961194029850746,
      "grad_norm": 0.4647996850215528,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1240
    },
    {
      "epoch": 2.9850746268656714,
      "grad_norm": 0.4918905334543915,
      "learning_rate": 5e-06,
      "loss": 0.5716,
      "step": 1250
    },
    {
      "epoch": 2.9946268656716417,
      "eval_loss": 0.636893630027771,
      "eval_runtime": 143.3398,
      "eval_samples_per_second": 78.722,
      "eval_steps_per_second": 0.621,
      "step": 1254
    },
    {
      "epoch": 2.9946268656716417,
      "step": 1254,
      "total_flos": 2100077946470400.0,
      "train_loss": 0.6183488205479283,
      "train_runtime": 21046.2129,
      "train_samples_per_second": 30.56,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 10,
  "max_steps": 1254,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2100077946470400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}