{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1173,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02557544757033248,
      "grad_norm": 1.4732151620168266,
      "learning_rate": 5e-06,
      "loss": 0.8857,
      "step": 10
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": 2.487021273446104,
      "learning_rate": 5e-06,
      "loss": 0.7797,
      "step": 20
    },
    {
      "epoch": 0.07672634271099744,
      "grad_norm": 3.1294161768477546,
      "learning_rate": 5e-06,
      "loss": 0.7563,
      "step": 30
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": 0.8287185562040077,
      "learning_rate": 5e-06,
      "loss": 0.7317,
      "step": 40
    },
    {
      "epoch": 0.1278772378516624,
      "grad_norm": 0.8396366204298203,
      "learning_rate": 5e-06,
      "loss": 0.7124,
      "step": 50
    },
    {
      "epoch": 0.1534526854219949,
      "grad_norm": 0.675481475401149,
      "learning_rate": 5e-06,
      "loss": 0.7089,
      "step": 60
    },
    {
      "epoch": 0.17902813299232737,
      "grad_norm": 0.8292154979182814,
      "learning_rate": 5e-06,
      "loss": 0.6992,
      "step": 70
    },
    {
      "epoch": 0.20460358056265984,
      "grad_norm": 0.786706122696529,
      "learning_rate": 5e-06,
      "loss": 0.6922,
      "step": 80
    },
    {
      "epoch": 0.23017902813299232,
      "grad_norm": 0.6411055415388162,
      "learning_rate": 5e-06,
      "loss": 0.6885,
      "step": 90
    },
    {
      "epoch": 0.2557544757033248,
      "grad_norm": 0.5992551668740695,
      "learning_rate": 5e-06,
      "loss": 0.6729,
      "step": 100
    },
    {
      "epoch": 0.2813299232736573,
      "grad_norm": 0.6680597868527147,
      "learning_rate": 5e-06,
      "loss": 0.6687,
      "step": 110
    },
    {
      "epoch": 0.3069053708439898,
      "grad_norm": 0.5180401044360867,
      "learning_rate": 5e-06,
      "loss": 0.6746,
      "step": 120
    },
    {
      "epoch": 0.33248081841432225,
      "grad_norm": 0.7933457420559259,
      "learning_rate": 5e-06,
      "loss": 0.6763,
      "step": 130
    },
    {
      "epoch": 0.35805626598465473,
      "grad_norm": 0.6077558627807389,
      "learning_rate": 5e-06,
      "loss": 0.6653,
      "step": 140
    },
    {
      "epoch": 0.3836317135549872,
      "grad_norm": 0.5214150563798917,
      "learning_rate": 5e-06,
      "loss": 0.6637,
      "step": 150
    },
    {
      "epoch": 0.4092071611253197,
      "grad_norm": 0.4782424652477103,
      "learning_rate": 5e-06,
      "loss": 0.6743,
      "step": 160
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.5531417892206768,
      "learning_rate": 5e-06,
      "loss": 0.663,
      "step": 170
    },
    {
      "epoch": 0.46035805626598464,
      "grad_norm": 0.6140295950380247,
      "learning_rate": 5e-06,
      "loss": 0.6627,
      "step": 180
    },
    {
      "epoch": 0.4859335038363171,
      "grad_norm": 0.452088230614636,
      "learning_rate": 5e-06,
      "loss": 0.6565,
      "step": 190
    },
    {
      "epoch": 0.5115089514066496,
      "grad_norm": 0.5771504479981889,
      "learning_rate": 5e-06,
      "loss": 0.6544,
      "step": 200
    },
    {
      "epoch": 0.5370843989769821,
      "grad_norm": 0.5981768742786622,
      "learning_rate": 5e-06,
      "loss": 0.6648,
      "step": 210
    },
    {
      "epoch": 0.5626598465473146,
      "grad_norm": 0.6172970384456833,
      "learning_rate": 5e-06,
      "loss": 0.6531,
      "step": 220
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.4782698820225656,
      "learning_rate": 5e-06,
      "loss": 0.6564,
      "step": 230
    },
    {
      "epoch": 0.6138107416879796,
      "grad_norm": 0.7221555632733867,
      "learning_rate": 5e-06,
      "loss": 0.6472,
      "step": 240
    },
    {
      "epoch": 0.639386189258312,
      "grad_norm": 0.6008946634556908,
      "learning_rate": 5e-06,
      "loss": 0.6586,
      "step": 250
    },
    {
      "epoch": 0.6649616368286445,
      "grad_norm": 0.4981912776738461,
      "learning_rate": 5e-06,
      "loss": 0.6433,
      "step": 260
    },
    {
      "epoch": 0.690537084398977,
      "grad_norm": 0.4692459483664614,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 270
    },
    {
      "epoch": 0.7161125319693095,
      "grad_norm": 0.4193700978332349,
      "learning_rate": 5e-06,
      "loss": 0.6484,
      "step": 280
    },
    {
      "epoch": 0.7416879795396419,
      "grad_norm": 0.5445412936907831,
      "learning_rate": 5e-06,
      "loss": 0.6482,
      "step": 290
    },
    {
      "epoch": 0.7672634271099744,
      "grad_norm": 0.657805783671651,
      "learning_rate": 5e-06,
      "loss": 0.6488,
      "step": 300
    },
    {
      "epoch": 0.7928388746803069,
      "grad_norm": 0.5488970184879203,
      "learning_rate": 5e-06,
      "loss": 0.6474,
      "step": 310
    },
    {
      "epoch": 0.8184143222506394,
      "grad_norm": 0.5409806471796,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 320
    },
    {
      "epoch": 0.8439897698209718,
      "grad_norm": 0.5596800096190868,
      "learning_rate": 5e-06,
      "loss": 0.6435,
      "step": 330
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.4643925302456495,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 340
    },
    {
      "epoch": 0.8951406649616368,
      "grad_norm": 0.6375102071117671,
      "learning_rate": 5e-06,
      "loss": 0.6409,
      "step": 350
    },
    {
      "epoch": 0.9207161125319693,
      "grad_norm": 0.4775041999632585,
      "learning_rate": 5e-06,
      "loss": 0.6453,
      "step": 360
    },
    {
      "epoch": 0.9462915601023018,
      "grad_norm": 0.49604882534300143,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 370
    },
    {
      "epoch": 0.9718670076726342,
      "grad_norm": 0.45731037425025095,
      "learning_rate": 5e-06,
      "loss": 0.6414,
      "step": 380
    },
    {
      "epoch": 0.9974424552429667,
      "grad_norm": 0.4573950197808899,
      "learning_rate": 5e-06,
      "loss": 0.6452,
      "step": 390
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6434539556503296,
      "eval_runtime": 38.9026,
      "eval_samples_per_second": 270.779,
      "eval_steps_per_second": 1.08,
      "step": 391
    },
    {
      "epoch": 1.0230179028132993,
      "grad_norm": 0.7487458246165611,
      "learning_rate": 5e-06,
      "loss": 0.6099,
      "step": 400
    },
    {
      "epoch": 1.0485933503836318,
      "grad_norm": 0.4958215078357475,
      "learning_rate": 5e-06,
      "loss": 0.6049,
      "step": 410
    },
    {
      "epoch": 1.0741687979539642,
      "grad_norm": 0.5433206872781998,
      "learning_rate": 5e-06,
      "loss": 0.6013,
      "step": 420
    },
    {
      "epoch": 1.0997442455242967,
      "grad_norm": 0.5662951930987719,
      "learning_rate": 5e-06,
      "loss": 0.5995,
      "step": 430
    },
    {
      "epoch": 1.1253196930946292,
      "grad_norm": 0.4918784496618239,
      "learning_rate": 5e-06,
      "loss": 0.6027,
      "step": 440
    },
    {
      "epoch": 1.1508951406649617,
      "grad_norm": 0.5467386014101446,
      "learning_rate": 5e-06,
      "loss": 0.6103,
      "step": 450
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.7179950207720284,
      "learning_rate": 5e-06,
      "loss": 0.5999,
      "step": 460
    },
    {
      "epoch": 1.2020460358056266,
      "grad_norm": 0.5960679117502871,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 470
    },
    {
      "epoch": 1.227621483375959,
      "grad_norm": 0.5020974407898211,
      "learning_rate": 5e-06,
      "loss": 0.6013,
      "step": 480
    },
    {
      "epoch": 1.2531969309462916,
      "grad_norm": 0.5031636785755809,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 490
    },
    {
      "epoch": 1.278772378516624,
      "grad_norm": 0.5506207838193202,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 500
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.5156198566972936,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 510
    },
    {
      "epoch": 1.329923273657289,
      "grad_norm": 0.5484894340051472,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 520
    },
    {
      "epoch": 1.3554987212276215,
      "grad_norm": 0.47915499629457314,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 530
    },
    {
      "epoch": 1.381074168797954,
      "grad_norm": 0.8192433363651986,
      "learning_rate": 5e-06,
      "loss": 0.5987,
      "step": 540
    },
    {
      "epoch": 1.4066496163682864,
      "grad_norm": 0.49011715250049237,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 550
    },
    {
      "epoch": 1.432225063938619,
      "grad_norm": 0.7466359785733482,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 560
    },
    {
      "epoch": 1.4578005115089514,
      "grad_norm": 0.5087738931925487,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 570
    },
    {
      "epoch": 1.4833759590792839,
      "grad_norm": 0.6609977172284965,
      "learning_rate": 5e-06,
      "loss": 0.5994,
      "step": 580
    },
    {
      "epoch": 1.5089514066496164,
      "grad_norm": 0.503456913727176,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 590
    },
    {
      "epoch": 1.5345268542199488,
      "grad_norm": 0.5213824233459637,
      "learning_rate": 5e-06,
      "loss": 0.6072,
      "step": 600
    },
    {
      "epoch": 1.5601023017902813,
      "grad_norm": 0.45319447189866463,
      "learning_rate": 5e-06,
      "loss": 0.5915,
      "step": 610
    },
    {
      "epoch": 1.5856777493606138,
      "grad_norm": 0.457417614147174,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 620
    },
    {
      "epoch": 1.6112531969309463,
      "grad_norm": 0.5224900055650589,
      "learning_rate": 5e-06,
      "loss": 0.6002,
      "step": 630
    },
    {
      "epoch": 1.6368286445012787,
      "grad_norm": 0.4973950787447109,
      "learning_rate": 5e-06,
      "loss": 0.5946,
      "step": 640
    },
    {
      "epoch": 1.6624040920716112,
      "grad_norm": 0.4790552677041308,
      "learning_rate": 5e-06,
      "loss": 0.589,
      "step": 650
    },
    {
      "epoch": 1.6879795396419437,
      "grad_norm": 0.47449533507634256,
      "learning_rate": 5e-06,
      "loss": 0.5994,
      "step": 660
    },
    {
      "epoch": 1.7135549872122762,
      "grad_norm": 0.5393859616293808,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 670
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.42668160107621367,
      "learning_rate": 5e-06,
      "loss": 0.5943,
      "step": 680
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.5017031802880021,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 690
    },
    {
      "epoch": 1.7902813299232738,
      "grad_norm": 0.500629762210993,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 700
    },
    {
      "epoch": 1.815856777493606,
      "grad_norm": 0.45045745123083464,
      "learning_rate": 5e-06,
      "loss": 0.5996,
      "step": 710
    },
    {
      "epoch": 1.8414322250639388,
      "grad_norm": 0.6404335062666666,
      "learning_rate": 5e-06,
      "loss": 0.6001,
      "step": 720
    },
    {
      "epoch": 1.867007672634271,
      "grad_norm": 0.48025967143483794,
      "learning_rate": 5e-06,
      "loss": 0.5995,
      "step": 730
    },
    {
      "epoch": 1.8925831202046037,
      "grad_norm": 0.5055252053795981,
      "learning_rate": 5e-06,
      "loss": 0.5896,
      "step": 740
    },
    {
      "epoch": 1.918158567774936,
      "grad_norm": 0.6653435248566397,
      "learning_rate": 5e-06,
      "loss": 0.603,
      "step": 750
    },
    {
      "epoch": 1.9437340153452687,
      "grad_norm": 0.6727260672608437,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 760
    },
    {
      "epoch": 1.969309462915601,
      "grad_norm": 0.5907496423463581,
      "learning_rate": 5e-06,
      "loss": 0.6086,
      "step": 770
    },
    {
      "epoch": 1.9948849104859336,
      "grad_norm": 0.5760288384496973,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 780
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6335848569869995,
      "eval_runtime": 38.2748,
      "eval_samples_per_second": 275.22,
      "eval_steps_per_second": 1.097,
      "step": 782
    },
    {
      "epoch": 2.020460358056266,
      "grad_norm": 0.5888157228328489,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 790
    },
    {
      "epoch": 2.0460358056265986,
      "grad_norm": 0.5083129678011372,
      "learning_rate": 5e-06,
      "loss": 0.5592,
      "step": 800
    },
    {
      "epoch": 2.071611253196931,
      "grad_norm": 0.48204204488209723,
      "learning_rate": 5e-06,
      "loss": 0.5431,
      "step": 810
    },
    {
      "epoch": 2.0971867007672635,
      "grad_norm": 0.43509395294018177,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 820
    },
    {
      "epoch": 2.122762148337596,
      "grad_norm": 0.4873856782902337,
      "learning_rate": 5e-06,
      "loss": 0.549,
      "step": 830
    },
    {
      "epoch": 2.1483375959079285,
      "grad_norm": 0.47421724914953955,
      "learning_rate": 5e-06,
      "loss": 0.5595,
      "step": 840
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.5324778084056383,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 850
    },
    {
      "epoch": 2.1994884910485935,
      "grad_norm": 0.6187236206022877,
      "learning_rate": 5e-06,
      "loss": 0.5556,
      "step": 860
    },
    {
      "epoch": 2.2250639386189257,
      "grad_norm": 0.5533284770550284,
      "learning_rate": 5e-06,
      "loss": 0.5595,
      "step": 870
    },
    {
      "epoch": 2.2506393861892584,
      "grad_norm": 0.5115512932458932,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 880
    },
    {
      "epoch": 2.2762148337595907,
      "grad_norm": 0.8951470613775953,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 890
    },
    {
      "epoch": 2.3017902813299234,
      "grad_norm": 0.48320795887005585,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 900
    },
    {
      "epoch": 2.3273657289002556,
      "grad_norm": 0.5389304781613019,
      "learning_rate": 5e-06,
      "loss": 0.553,
      "step": 910
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.5504265312204787,
      "learning_rate": 5e-06,
      "loss": 0.5555,
      "step": 920
    },
    {
      "epoch": 2.3785166240409206,
      "grad_norm": 0.6781391025002083,
      "learning_rate": 5e-06,
      "loss": 0.5539,
      "step": 930
    },
    {
      "epoch": 2.4040920716112533,
      "grad_norm": 0.5284123264856311,
      "learning_rate": 5e-06,
      "loss": 0.5596,
      "step": 940
    },
    {
      "epoch": 2.4296675191815855,
      "grad_norm": 0.573703259910989,
      "learning_rate": 5e-06,
      "loss": 0.5575,
      "step": 950
    },
    {
      "epoch": 2.455242966751918,
      "grad_norm": 0.519429928779352,
      "learning_rate": 5e-06,
      "loss": 0.562,
      "step": 960
    },
    {
      "epoch": 2.4808184143222505,
      "grad_norm": 0.5716653700360348,
      "learning_rate": 5e-06,
      "loss": 0.5555,
      "step": 970
    },
    {
      "epoch": 2.506393861892583,
      "grad_norm": 0.45693028304624417,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 980
    },
    {
      "epoch": 2.531969309462916,
      "grad_norm": 0.5488274428294824,
      "learning_rate": 5e-06,
      "loss": 0.5573,
      "step": 990
    },
    {
      "epoch": 2.557544757033248,
      "grad_norm": 0.4681111347906789,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 1000
    },
    {
      "epoch": 2.5831202046035804,
      "grad_norm": 0.4588067639273481,
      "learning_rate": 5e-06,
      "loss": 0.5663,
      "step": 1010
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.6878919689252865,
      "learning_rate": 5e-06,
      "loss": 0.5639,
      "step": 1020
    },
    {
      "epoch": 2.634271099744246,
      "grad_norm": 0.4447545765506167,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 1030
    },
    {
      "epoch": 2.659846547314578,
      "grad_norm": 0.47570519434711034,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 1040
    },
    {
      "epoch": 2.6854219948849103,
      "grad_norm": 0.4839862926370354,
      "learning_rate": 5e-06,
      "loss": 0.5559,
      "step": 1050
    },
    {
      "epoch": 2.710997442455243,
      "grad_norm": 0.6321260475168335,
      "learning_rate": 5e-06,
      "loss": 0.5602,
      "step": 1060
    },
    {
      "epoch": 2.7365728900255757,
      "grad_norm": 0.660422843874434,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 1070
    },
    {
      "epoch": 2.762148337595908,
      "grad_norm": 0.6591827642794408,
      "learning_rate": 5e-06,
      "loss": 0.5561,
      "step": 1080
    },
    {
      "epoch": 2.78772378516624,
      "grad_norm": 0.5629633198627261,
      "learning_rate": 5e-06,
      "loss": 0.5536,
      "step": 1090
    },
    {
      "epoch": 2.813299232736573,
      "grad_norm": 0.4679817123851223,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 1100
    },
    {
      "epoch": 2.8388746803069056,
      "grad_norm": 0.5611457522346606,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 1110
    },
    {
      "epoch": 2.864450127877238,
      "grad_norm": 0.4877999696633639,
      "learning_rate": 5e-06,
      "loss": 0.5662,
      "step": 1120
    },
    {
      "epoch": 2.89002557544757,
      "grad_norm": 0.48460006644169323,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 1130
    },
    {
      "epoch": 2.915601023017903,
      "grad_norm": 0.47342607041413165,
      "learning_rate": 5e-06,
      "loss": 0.5613,
      "step": 1140
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.4640271559873245,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 1150
    },
    {
      "epoch": 2.9667519181585678,
      "grad_norm": 0.47736761450925297,
      "learning_rate": 5e-06,
      "loss": 0.5549,
      "step": 1160
    },
    {
      "epoch": 2.9923273657289,
      "grad_norm": 0.5483840655299442,
      "learning_rate": 5e-06,
      "loss": 0.5549,
      "step": 1170
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6347914934158325,
      "eval_runtime": 37.6736,
      "eval_samples_per_second": 279.612,
      "eval_steps_per_second": 1.115,
      "step": 1173
    },
    {
      "epoch": 3.0,
      "step": 1173,
      "total_flos": 1964818688901120.0,
      "train_loss": 0.6108124574228727,
      "train_runtime": 7401.7193,
      "train_samples_per_second": 81.12,
      "train_steps_per_second": 0.158
    }
  ],
  "logging_steps": 10,
  "max_steps": 1173,
  "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": 1964818688901120.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}