{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6715002788622422,
  "eval_steps": 100,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022308979364194088,
      "grad_norm": 3.6059792041778564,
      "learning_rate": 0.00019999016517595753,
      "loss": 3.6749305725097656,
      "step": 10
    },
    {
      "epoch": 0.044617958728388175,
      "grad_norm": 1.686761498451233,
      "learning_rate": 0.00019987954562051725,
      "loss": 0.9972598075866699,
      "step": 20
    },
    {
      "epoch": 0.06692693809258227,
      "grad_norm": 1.0181570053100586,
      "learning_rate": 0.00019964614941176195,
      "loss": 0.7280679225921631,
      "step": 30
    },
    {
      "epoch": 0.08923591745677635,
      "grad_norm": 0.9052721261978149,
      "learning_rate": 0.00019929026345133122,
      "loss": 0.6308993339538574,
      "step": 40
    },
    {
      "epoch": 0.11154489682097044,
      "grad_norm": 0.8318365812301636,
      "learning_rate": 0.00019881232521105089,
      "loss": 0.6105688571929931,
      "step": 50
    },
    {
      "epoch": 0.13385387618516453,
      "grad_norm": 0.9255080223083496,
      "learning_rate": 0.00019821292219517192,
      "loss": 0.5463937282562256,
      "step": 60
    },
    {
      "epoch": 0.1561628555493586,
      "grad_norm": 0.8712772727012634,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.513142728805542,
      "step": 70
    },
    {
      "epoch": 0.1784718349135527,
      "grad_norm": 0.6806803941726685,
      "learning_rate": 0.00019665281749908033,
      "loss": 0.45452089309692384,
      "step": 80
    },
    {
      "epoch": 0.2007808142777468,
      "grad_norm": 0.8569662570953369,
      "learning_rate": 0.0001956940335732209,
      "loss": 0.4099240303039551,
      "step": 90
    },
    {
      "epoch": 0.22308979364194087,
      "grad_norm": 0.5690306425094604,
      "learning_rate": 0.00019461761802307495,
      "loss": 0.4181380748748779,
      "step": 100
    },
    {
      "epoch": 0.22308979364194087,
      "eval_loss": 7.142496585845947,
      "eval_runtime": 196.0856,
      "eval_samples_per_second": 2.3,
      "eval_steps_per_second": 2.3,
      "step": 100
    },
    {
      "epoch": 0.24539877300613497,
      "grad_norm": 0.5885435938835144,
      "learning_rate": 0.00019342489402945998,
      "loss": 0.3779646873474121,
      "step": 110
    },
    {
      "epoch": 0.26770775237032907,
      "grad_norm": 0.7473471164703369,
      "learning_rate": 0.00019211732774502372,
      "loss": 0.3981457710266113,
      "step": 120
    },
    {
      "epoch": 0.29001673173452314,
      "grad_norm": 0.5102096796035767,
      "learning_rate": 0.00019069652649198005,
      "loss": 0.355985426902771,
      "step": 130
    },
    {
      "epoch": 0.3123257110987172,
      "grad_norm": 0.9202075004577637,
      "learning_rate": 0.00018916423678631272,
      "loss": 0.4652230262756348,
      "step": 140
    },
    {
      "epoch": 0.33463469046291133,
      "grad_norm": 0.47609537839889526,
      "learning_rate": 0.00018752234219087538,
      "loss": 0.31681218147277834,
      "step": 150
    },
    {
      "epoch": 0.3569436698271054,
      "grad_norm": 0.6477280855178833,
      "learning_rate": 0.00018577286100002723,
      "loss": 0.414081335067749,
      "step": 160
    },
    {
      "epoch": 0.3792526491912995,
      "grad_norm": 0.5019633769989014,
      "learning_rate": 0.00018391794375865024,
      "loss": 0.4289548873901367,
      "step": 170
    },
    {
      "epoch": 0.4015616285554936,
      "grad_norm": 0.906410813331604,
      "learning_rate": 0.0001819598706185979,
      "loss": 0.33823583126068113,
      "step": 180
    },
    {
      "epoch": 0.42387060791968767,
      "grad_norm": 0.5761931538581848,
      "learning_rate": 0.00017990104853582493,
      "loss": 0.3813004493713379,
      "step": 190
    },
    {
      "epoch": 0.44617958728388174,
      "grad_norm": 0.49768441915512085,
      "learning_rate": 0.00017774400831164323,
      "loss": 0.39550683498382566,
      "step": 200
    },
    {
      "epoch": 0.44617958728388174,
      "eval_loss": 6.169673442840576,
      "eval_runtime": 191.4793,
      "eval_samples_per_second": 2.355,
      "eval_steps_per_second": 2.355,
      "step": 200
    },
    {
      "epoch": 0.46848856664807587,
      "grad_norm": 0.4040807783603668,
      "learning_rate": 0.0001754914014817416,
      "loss": 0.3376659870147705,
      "step": 210
    },
    {
      "epoch": 0.49079754601226994,
      "grad_norm": 0.7800427675247192,
      "learning_rate": 0.00017314599705679277,
      "loss": 0.34065258502960205,
      "step": 220
    },
    {
      "epoch": 0.5131065253764641,
      "grad_norm": 0.37761184573173523,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.3312467098236084,
      "step": 230
    },
    {
      "epoch": 0.5354155047406581,
      "grad_norm": 0.5092398524284363,
      "learning_rate": 0.0001681884382763505,
      "loss": 0.3050385475158691,
      "step": 240
    },
    {
      "epoch": 0.5577244841048522,
      "grad_norm": 0.4748888313770294,
      "learning_rate": 0.00016558237798618245,
      "loss": 0.3287826061248779,
      "step": 250
    },
    {
      "epoch": 0.5800334634690463,
      "grad_norm": 0.5076217651367188,
      "learning_rate": 0.00016289570074050493,
      "loss": 0.35127427577972414,
      "step": 260
    },
    {
      "epoch": 0.6023424428332403,
      "grad_norm": 0.42200589179992676,
      "learning_rate": 0.00016013170912984058,
      "loss": 0.3230970144271851,
      "step": 270
    },
    {
      "epoch": 0.6246514221974344,
      "grad_norm": 0.5083448886871338,
      "learning_rate": 0.0001572938007831798,
      "loss": 0.3022065877914429,
      "step": 280
    },
    {
      "epoch": 0.6469604015616286,
      "grad_norm": 0.45063674449920654,
      "learning_rate": 0.00015438546419145488,
      "loss": 0.353403902053833,
      "step": 290
    },
    {
      "epoch": 0.6692693809258227,
      "grad_norm": 0.3552491366863251,
      "learning_rate": 0.00015141027441932216,
      "loss": 0.3080631494522095,
      "step": 300
    },
    {
      "epoch": 0.6692693809258227,
      "eval_loss": 5.376068592071533,
      "eval_runtime": 187.8009,
      "eval_samples_per_second": 2.401,
      "eval_steps_per_second": 2.401,
      "step": 300
    },
    {
      "epoch": 0.6915783602900167,
      "grad_norm": 0.4308546483516693,
      "learning_rate": 0.000148371888710524,
      "loss": 0.3246779918670654,
      "step": 310
    },
    {
      "epoch": 0.7138873396542108,
      "grad_norm": 0.6152803301811218,
      "learning_rate": 0.00014527404199223172,
      "loss": 0.35356783866882324,
      "step": 320
    },
    {
      "epoch": 0.7361963190184049,
      "grad_norm": 0.5230463147163391,
      "learning_rate": 0.0001421205422838971,
      "loss": 0.3224280834197998,
      "step": 330
    },
    {
      "epoch": 0.758505298382599,
      "grad_norm": 0.6994717121124268,
      "learning_rate": 0.0001389152660162549,
      "loss": 0.32481276988983154,
      "step": 340
    },
    {
      "epoch": 0.7808142777467931,
      "grad_norm": 0.5130417943000793,
      "learning_rate": 0.0001356621532662313,
      "loss": 0.28367717266082765,
      "step": 350
    },
    {
      "epoch": 0.8031232571109872,
      "grad_norm": 0.59247887134552,
      "learning_rate": 0.00013236520291361515,
      "loss": 0.3666529655456543,
      "step": 360
    },
    {
      "epoch": 0.8254322364751813,
      "grad_norm": 0.3807213306427002,
      "learning_rate": 0.00012902846772544624,
      "loss": 0.3158045530319214,
      "step": 370
    },
    {
      "epoch": 0.8477412158393753,
      "grad_norm": 0.49467733502388,
      "learning_rate": 0.00012565604937416267,
      "loss": 0.2739120006561279,
      "step": 380
    },
    {
      "epoch": 0.8700501952035694,
      "grad_norm": 0.3233357071876526,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.29424002170562746,
      "step": 390
    },
    {
      "epoch": 0.8923591745677635,
      "grad_norm": 0.5100898146629333,
      "learning_rate": 0.00011882078409326002,
      "loss": 0.3178868293762207,
      "step": 400
    },
    {
      "epoch": 0.8923591745677635,
      "eval_loss": 5.181941986083984,
      "eval_runtime": 187.4258,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 400
    },
    {
      "epoch": 0.9146681539319577,
      "grad_norm": 0.3522528409957886,
      "learning_rate": 0.000115366339394453,
      "loss": 0.3059010744094849,
      "step": 410
    },
    {
      "epoch": 0.9369771332961517,
      "grad_norm": 0.3386065661907196,
      "learning_rate": 0.0001118930056657367,
      "loss": 0.29911515712738035,
      "step": 420
    },
    {
      "epoch": 0.9592861126603458,
      "grad_norm": 0.4055585563182831,
      "learning_rate": 0.00010840505249292476,
      "loss": 0.266009521484375,
      "step": 430
    },
    {
      "epoch": 0.9815950920245399,
      "grad_norm": 0.6631172299385071,
      "learning_rate": 0.00010490676743274181,
      "loss": 0.28707849979400635,
      "step": 440
    },
    {
      "epoch": 1.0022308979364194,
      "grad_norm": 0.4735918641090393,
      "learning_rate": 0.00010140245074235624,
      "loss": 0.3470479726791382,
      "step": 450
    },
    {
      "epoch": 1.0245398773006136,
      "grad_norm": 0.4347779452800751,
      "learning_rate": 9.789641009330111e-05,
      "loss": 0.2632521867752075,
      "step": 460
    },
    {
      "epoch": 1.0468488566648075,
      "grad_norm": 0.3260243833065033,
      "learning_rate": 9.439295527628081e-05,
      "loss": 0.2586169958114624,
      "step": 470
    },
    {
      "epoch": 1.0691578360290017,
      "grad_norm": 0.4574776291847229,
      "learning_rate": 9.0896392903373e-05,
      "loss": 0.2648995637893677,
      "step": 480
    },
    {
      "epoch": 1.0914668153931957,
      "grad_norm": 0.4806566834449768,
      "learning_rate": 8.741102111413748e-05,
      "loss": 0.24064080715179442,
      "step": 490
    },
    {
      "epoch": 1.1137757947573899,
      "grad_norm": 0.4908582270145416,
      "learning_rate": 8.39411242921403e-05,
      "loss": 0.25490708351135255,
      "step": 500
    },
    {
      "epoch": 1.1137757947573899,
      "eval_loss": 5.465029239654541,
      "eval_runtime": 190.4691,
      "eval_samples_per_second": 2.368,
      "eval_steps_per_second": 2.368,
      "step": 500
    },
    {
      "epoch": 1.136084774121584,
      "grad_norm": 0.4439888894557953,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.2863529920578003,
      "step": 510
    },
    {
      "epoch": 1.158393753485778,
      "grad_norm": 0.43033894896507263,
      "learning_rate": 7.706479272814023e-05,
      "loss": 0.2422431468963623,
      "step": 520
    },
    {
      "epoch": 1.1807027328499722,
      "grad_norm": 0.44316694140434265,
      "learning_rate": 7.366681069756352e-05,
      "loss": 0.27856547832489015,
      "step": 530
    },
    {
      "epoch": 1.2030117122141661,
      "grad_norm": 0.5816928744316101,
      "learning_rate": 7.030119866660564e-05,
      "loss": 0.26144585609436033,
      "step": 540
    },
    {
      "epoch": 1.2253206915783603,
      "grad_norm": 0.383112370967865,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.2592925548553467,
      "step": 550
    },
    {
      "epoch": 1.2476296709425543,
      "grad_norm": 0.4637056589126587,
      "learning_rate": 6.368358840407753e-05,
      "loss": 0.2502119779586792,
      "step": 560
    },
    {
      "epoch": 1.2699386503067485,
      "grad_norm": 0.3978555202484131,
      "learning_rate": 6.043972485149414e-05,
      "loss": 0.24019856452941896,
      "step": 570
    },
    {
      "epoch": 1.2922476296709426,
      "grad_norm": 0.3794662654399872,
      "learning_rate": 5.7244490656971815e-05,
      "loss": 0.23192195892333983,
      "step": 580
    },
    {
      "epoch": 1.3145566090351366,
      "grad_norm": 0.34926116466522217,
      "learning_rate": 5.410181355324622e-05,
      "loss": 0.26394219398498536,
      "step": 590
    },
    {
      "epoch": 1.3368655883993308,
      "grad_norm": 0.4157903492450714,
      "learning_rate": 5.1015556667395636e-05,
      "loss": 0.2660749197006226,
      "step": 600
    },
    {
      "epoch": 1.3368655883993308,
      "eval_loss": 5.384934425354004,
      "eval_runtime": 188.6552,
      "eval_samples_per_second": 2.391,
      "eval_steps_per_second": 2.391,
      "step": 600
    },
    {
      "epoch": 1.3591745677635247,
      "grad_norm": 0.5136097073554993,
      "learning_rate": 4.7989513772102537e-05,
      "loss": 0.23524351119995118,
      "step": 610
    },
    {
      "epoch": 1.381483547127719,
      "grad_norm": 0.3920697867870331,
      "learning_rate": 4.502740462216919e-05,
      "loss": 0.2516023635864258,
      "step": 620
    },
    {
      "epoch": 1.4037925264919129,
      "grad_norm": 0.5687846541404724,
      "learning_rate": 4.213287038201943e-05,
      "loss": 0.23717131614685058,
      "step": 630
    },
    {
      "epoch": 1.426101505856107,
      "grad_norm": 0.8705297112464905,
      "learning_rate": 3.930946914980744e-05,
      "loss": 0.22555122375488282,
      "step": 640
    },
    {
      "epoch": 1.4484104852203012,
      "grad_norm": 0.4317159652709961,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 0.2330761432647705,
      "step": 650
    },
    {
      "epoch": 1.4707194645844952,
      "grad_norm": 0.2786170244216919,
      "learning_rate": 3.388985663525702e-05,
      "loss": 0.24024245738983155,
      "step": 660
    },
    {
      "epoch": 1.4930284439486894,
      "grad_norm": 0.5246191620826721,
      "learning_rate": 3.130030739650983e-05,
      "loss": 0.21560235023498536,
      "step": 670
    },
    {
      "epoch": 1.5153374233128836,
      "grad_norm": 0.3500918745994568,
      "learning_rate": 2.879520706358446e-05,
      "loss": 0.26663081645965575,
      "step": 680
    },
    {
      "epoch": 1.5376464026770775,
      "grad_norm": 0.44421038031578064,
      "learning_rate": 2.6377635024089087e-05,
      "loss": 0.28586716651916505,
      "step": 690
    },
    {
      "epoch": 1.5599553820412715,
      "grad_norm": 0.5229424238204956,
      "learning_rate": 2.4050563071720867e-05,
      "loss": 0.2517236709594727,
      "step": 700
    },
    {
      "epoch": 1.5599553820412715,
      "eval_loss": 5.481088161468506,
      "eval_runtime": 189.8684,
      "eval_samples_per_second": 2.375,
      "eval_steps_per_second": 2.375,
      "step": 700
    },
    {
      "epoch": 1.5822643614054657,
      "grad_norm": 0.4634057879447937,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.2557069778442383,
      "step": 710
    },
    {
      "epoch": 1.6045733407696599,
      "grad_norm": 0.4304831624031067,
      "learning_rate": 1.967924685193552e-05,
      "loss": 0.2168825626373291,
      "step": 720
    },
    {
      "epoch": 1.6268823201338538,
      "grad_norm": 0.4848768711090088,
      "learning_rate": 1.7640376012808536e-05,
      "loss": 0.238733172416687,
      "step": 730
    },
    {
      "epoch": 1.649191299498048,
      "grad_norm": 0.5546223521232605,
      "learning_rate": 1.5702745512117324e-05,
      "loss": 0.26332356929779055,
      "step": 740
    },
    {
      "epoch": 1.6715002788622422,
      "grad_norm": 0.4730488955974579,
      "learning_rate": 1.3868737176759106e-05,
      "loss": 0.25144917964935304,
      "step": 750
    }
  ],
  "logging_steps": 10,
  "max_steps": 898,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2067018135111296e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}