{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994683678894205,
  "eval_steps": 500,
  "global_step": 940,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01063264221158958,
      "grad_norm": 5.609270095825195,
      "learning_rate": 0.00019808510638297873,
      "loss": 2.4434,
      "step": 10
    },
    {
      "epoch": 0.02126528442317916,
      "grad_norm": 4.589075088500977,
      "learning_rate": 0.00019595744680851065,
      "loss": 1.6902,
      "step": 20
    },
    {
      "epoch": 0.03189792663476874,
      "grad_norm": 3.7465291023254395,
      "learning_rate": 0.00019382978723404257,
      "loss": 1.3148,
      "step": 30
    },
    {
      "epoch": 0.04253056884635832,
      "grad_norm": 3.543064594268799,
      "learning_rate": 0.00019170212765957448,
      "loss": 1.4302,
      "step": 40
    },
    {
      "epoch": 0.0531632110579479,
      "grad_norm": 2.68544340133667,
      "learning_rate": 0.0001895744680851064,
      "loss": 1.3222,
      "step": 50
    },
    {
      "epoch": 0.06379585326953748,
      "grad_norm": 2.752901792526245,
      "learning_rate": 0.00018744680851063832,
      "loss": 1.2792,
      "step": 60
    },
    {
      "epoch": 0.07442849548112707,
      "grad_norm": 2.7944841384887695,
      "learning_rate": 0.0001853191489361702,
      "loss": 1.3764,
      "step": 70
    },
    {
      "epoch": 0.08506113769271664,
      "grad_norm": 3.0340654850006104,
      "learning_rate": 0.00018319148936170215,
      "loss": 1.2255,
      "step": 80
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 2.5017054080963135,
      "learning_rate": 0.00018106382978723404,
      "loss": 1.1689,
      "step": 90
    },
    {
      "epoch": 0.1063264221158958,
      "grad_norm": 4.572251319885254,
      "learning_rate": 0.00017893617021276596,
      "loss": 1.1418,
      "step": 100
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 3.354853630065918,
      "learning_rate": 0.00017680851063829787,
      "loss": 1.3103,
      "step": 110
    },
    {
      "epoch": 0.12759170653907495,
      "grad_norm": 2.387272834777832,
      "learning_rate": 0.0001746808510638298,
      "loss": 1.2848,
      "step": 120
    },
    {
      "epoch": 0.13822434875066453,
      "grad_norm": 2.579465627670288,
      "learning_rate": 0.0001725531914893617,
      "loss": 1.2395,
      "step": 130
    },
    {
      "epoch": 0.14885699096225413,
      "grad_norm": 2.9512267112731934,
      "learning_rate": 0.00017042553191489362,
      "loss": 1.3716,
      "step": 140
    },
    {
      "epoch": 0.1594896331738437,
      "grad_norm": 2.6200809478759766,
      "learning_rate": 0.00016829787234042554,
      "loss": 1.2647,
      "step": 150
    },
    {
      "epoch": 0.17012227538543329,
      "grad_norm": 2.7764666080474854,
      "learning_rate": 0.00016617021276595746,
      "loss": 1.0862,
      "step": 160
    },
    {
      "epoch": 0.18075491759702286,
      "grad_norm": 2.454061269760132,
      "learning_rate": 0.00016404255319148937,
      "loss": 1.2213,
      "step": 170
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 2.483651876449585,
      "learning_rate": 0.0001619148936170213,
      "loss": 1.1895,
      "step": 180
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 3.5856575965881348,
      "learning_rate": 0.0001597872340425532,
      "loss": 1.2322,
      "step": 190
    },
    {
      "epoch": 0.2126528442317916,
      "grad_norm": 2.1436448097229004,
      "learning_rate": 0.00015765957446808512,
      "loss": 1.2782,
      "step": 200
    },
    {
      "epoch": 0.22328548644338117,
      "grad_norm": 2.569831609725952,
      "learning_rate": 0.00015553191489361701,
      "loss": 1.171,
      "step": 210
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 2.5455546379089355,
      "learning_rate": 0.00015340425531914896,
      "loss": 1.3055,
      "step": 220
    },
    {
      "epoch": 0.24455077086656035,
      "grad_norm": 1.7153586149215698,
      "learning_rate": 0.00015127659574468085,
      "loss": 1.0822,
      "step": 230
    },
    {
      "epoch": 0.2551834130781499,
      "grad_norm": 2.549631357192993,
      "learning_rate": 0.00014914893617021276,
      "loss": 1.3206,
      "step": 240
    },
    {
      "epoch": 0.2658160552897395,
      "grad_norm": 2.53717041015625,
      "learning_rate": 0.00014702127659574468,
      "loss": 1.1995,
      "step": 250
    },
    {
      "epoch": 0.27644869750132905,
      "grad_norm": 2.331685781478882,
      "learning_rate": 0.0001448936170212766,
      "loss": 1.2426,
      "step": 260
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 2.6866092681884766,
      "learning_rate": 0.00014276595744680851,
      "loss": 1.1314,
      "step": 270
    },
    {
      "epoch": 0.29771398192450826,
      "grad_norm": 2.107909679412842,
      "learning_rate": 0.00014063829787234043,
      "loss": 1.1542,
      "step": 280
    },
    {
      "epoch": 0.3083466241360978,
      "grad_norm": 1.8758138418197632,
      "learning_rate": 0.00013851063829787235,
      "loss": 1.1377,
      "step": 290
    },
    {
      "epoch": 0.3189792663476874,
      "grad_norm": 1.647929072380066,
      "learning_rate": 0.00013638297872340427,
      "loss": 1.0096,
      "step": 300
    },
    {
      "epoch": 0.32961190855927697,
      "grad_norm": 2.186124563217163,
      "learning_rate": 0.00013425531914893618,
      "loss": 1.1746,
      "step": 310
    },
    {
      "epoch": 0.34024455077086657,
      "grad_norm": 2.4536380767822266,
      "learning_rate": 0.0001321276595744681,
      "loss": 1.1833,
      "step": 320
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.8024215698242188,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.9309,
      "step": 330
    },
    {
      "epoch": 0.3615098351940457,
      "grad_norm": 3.0355000495910645,
      "learning_rate": 0.0001278723404255319,
      "loss": 1.0863,
      "step": 340
    },
    {
      "epoch": 0.3721424774056353,
      "grad_norm": 1.9415550231933594,
      "learning_rate": 0.00012574468085106382,
      "loss": 1.0507,
      "step": 350
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 2.327995538711548,
      "learning_rate": 0.00012361702127659577,
      "loss": 1.2524,
      "step": 360
    },
    {
      "epoch": 0.3934077618288145,
      "grad_norm": 2.001037120819092,
      "learning_rate": 0.00012148936170212766,
      "loss": 1.0437,
      "step": 370
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 2.1419551372528076,
      "learning_rate": 0.00011936170212765959,
      "loss": 1.0968,
      "step": 380
    },
    {
      "epoch": 0.41467304625199364,
      "grad_norm": 2.3085482120513916,
      "learning_rate": 0.0001172340425531915,
      "loss": 1.1706,
      "step": 390
    },
    {
      "epoch": 0.4253056884635832,
      "grad_norm": 4.618401050567627,
      "learning_rate": 0.0001151063829787234,
      "loss": 1.0685,
      "step": 400
    },
    {
      "epoch": 0.4359383306751728,
      "grad_norm": 2.421363115310669,
      "learning_rate": 0.00011297872340425532,
      "loss": 1.0373,
      "step": 410
    },
    {
      "epoch": 0.44657097288676234,
      "grad_norm": 1.6373859643936157,
      "learning_rate": 0.00011085106382978725,
      "loss": 1.0669,
      "step": 420
    },
    {
      "epoch": 0.45720361509835195,
      "grad_norm": 2.3031554222106934,
      "learning_rate": 0.00010872340425531916,
      "loss": 1.1394,
      "step": 430
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 1.9488067626953125,
      "learning_rate": 0.00010659574468085107,
      "loss": 1.0347,
      "step": 440
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 1.8650946617126465,
      "learning_rate": 0.00010446808510638298,
      "loss": 1.1159,
      "step": 450
    },
    {
      "epoch": 0.4891015417331207,
      "grad_norm": 1.8462837934494019,
      "learning_rate": 0.0001023404255319149,
      "loss": 1.0389,
      "step": 460
    },
    {
      "epoch": 0.49973418394471025,
      "grad_norm": 2.5941386222839355,
      "learning_rate": 0.00010021276595744682,
      "loss": 1.1587,
      "step": 470
    },
    {
      "epoch": 0.5103668261562998,
      "grad_norm": 1.34873366355896,
      "learning_rate": 9.808510638297873e-05,
      "loss": 1.1095,
      "step": 480
    },
    {
      "epoch": 0.5209994683678895,
      "grad_norm": 2.2580478191375732,
      "learning_rate": 9.595744680851064e-05,
      "loss": 1.1268,
      "step": 490
    },
    {
      "epoch": 0.531632110579479,
      "grad_norm": 2.389127731323242,
      "learning_rate": 9.382978723404256e-05,
      "loss": 1.2718,
      "step": 500
    },
    {
      "epoch": 0.5422647527910686,
      "grad_norm": 2.1379384994506836,
      "learning_rate": 9.170212765957448e-05,
      "loss": 1.0394,
      "step": 510
    },
    {
      "epoch": 0.5528973950026581,
      "grad_norm": 2.5996925830841064,
      "learning_rate": 8.95744680851064e-05,
      "loss": 1.0508,
      "step": 520
    },
    {
      "epoch": 0.5635300372142478,
      "grad_norm": 2.143913984298706,
      "learning_rate": 8.74468085106383e-05,
      "loss": 1.0038,
      "step": 530
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 2.285888910293579,
      "learning_rate": 8.531914893617021e-05,
      "loss": 1.2064,
      "step": 540
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 2.3260293006896973,
      "learning_rate": 8.319148936170213e-05,
      "loss": 1.0499,
      "step": 550
    },
    {
      "epoch": 0.5954279638490165,
      "grad_norm": 2.3417248725891113,
      "learning_rate": 8.106382978723405e-05,
      "loss": 1.1371,
      "step": 560
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.194345474243164,
      "learning_rate": 7.893617021276596e-05,
      "loss": 1.0571,
      "step": 570
    },
    {
      "epoch": 0.6166932482721956,
      "grad_norm": 2.3759639263153076,
      "learning_rate": 7.680851063829788e-05,
      "loss": 0.9709,
      "step": 580
    },
    {
      "epoch": 0.6273258904837852,
      "grad_norm": 1.7851307392120361,
      "learning_rate": 7.46808510638298e-05,
      "loss": 1.0751,
      "step": 590
    },
    {
      "epoch": 0.6379585326953748,
      "grad_norm": 2.1073718070983887,
      "learning_rate": 7.25531914893617e-05,
      "loss": 1.0453,
      "step": 600
    },
    {
      "epoch": 0.6485911749069644,
      "grad_norm": 3.0715222358703613,
      "learning_rate": 7.042553191489362e-05,
      "loss": 1.019,
      "step": 610
    },
    {
      "epoch": 0.6592238171185539,
      "grad_norm": 2.7208268642425537,
      "learning_rate": 6.829787234042554e-05,
      "loss": 0.919,
      "step": 620
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 1.7897045612335205,
      "learning_rate": 6.617021276595745e-05,
      "loss": 0.9964,
      "step": 630
    },
    {
      "epoch": 0.6804891015417331,
      "grad_norm": 2.317929744720459,
      "learning_rate": 6.404255319148937e-05,
      "loss": 1.1598,
      "step": 640
    },
    {
      "epoch": 0.6911217437533227,
      "grad_norm": 1.826894760131836,
      "learning_rate": 6.191489361702127e-05,
      "loss": 1.117,
      "step": 650
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 2.0165112018585205,
      "learning_rate": 5.9787234042553196e-05,
      "loss": 1.0511,
      "step": 660
    },
    {
      "epoch": 0.7123870281765019,
      "grad_norm": 1.6636179685592651,
      "learning_rate": 5.7659574468085106e-05,
      "loss": 1.0488,
      "step": 670
    },
    {
      "epoch": 0.7230196703880915,
      "grad_norm": 2.3491950035095215,
      "learning_rate": 5.553191489361702e-05,
      "loss": 1.2297,
      "step": 680
    },
    {
      "epoch": 0.733652312599681,
      "grad_norm": 2.28796124458313,
      "learning_rate": 5.3404255319148946e-05,
      "loss": 1.1457,
      "step": 690
    },
    {
      "epoch": 0.7442849548112705,
      "grad_norm": 2.550320863723755,
      "learning_rate": 5.1276595744680856e-05,
      "loss": 1.069,
      "step": 700
    },
    {
      "epoch": 0.7549175970228602,
      "grad_norm": 1.5172102451324463,
      "learning_rate": 4.9148936170212766e-05,
      "loss": 0.849,
      "step": 710
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 1.7714675664901733,
      "learning_rate": 4.702127659574468e-05,
      "loss": 1.1457,
      "step": 720
    },
    {
      "epoch": 0.7761828814460393,
      "grad_norm": 1.587169885635376,
      "learning_rate": 4.489361702127659e-05,
      "loss": 0.9438,
      "step": 730
    },
    {
      "epoch": 0.786815523657629,
      "grad_norm": 2.464047908782959,
      "learning_rate": 4.276595744680851e-05,
      "loss": 1.0606,
      "step": 740
    },
    {
      "epoch": 0.7974481658692185,
      "grad_norm": 1.6491392850875854,
      "learning_rate": 4.063829787234043e-05,
      "loss": 1.0333,
      "step": 750
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 2.159282684326172,
      "learning_rate": 3.8510638297872344e-05,
      "loss": 0.9192,
      "step": 760
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 1.6473966836929321,
      "learning_rate": 3.638297872340426e-05,
      "loss": 1.0218,
      "step": 770
    },
    {
      "epoch": 0.8293460925039873,
      "grad_norm": 2.5140249729156494,
      "learning_rate": 3.425531914893617e-05,
      "loss": 1.1425,
      "step": 780
    },
    {
      "epoch": 0.8399787347155768,
      "grad_norm": 1.8191956281661987,
      "learning_rate": 3.212765957446809e-05,
      "loss": 1.0179,
      "step": 790
    },
    {
      "epoch": 0.8506113769271664,
      "grad_norm": 1.570918083190918,
      "learning_rate": 3e-05,
      "loss": 1.0624,
      "step": 800
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 2.4648308753967285,
      "learning_rate": 2.7872340425531918e-05,
      "loss": 1.0768,
      "step": 810
    },
    {
      "epoch": 0.8718766613503456,
      "grad_norm": 2.4284791946411133,
      "learning_rate": 2.574468085106383e-05,
      "loss": 1.0748,
      "step": 820
    },
    {
      "epoch": 0.8825093035619351,
      "grad_norm": 2.543541193008423,
      "learning_rate": 2.3617021276595748e-05,
      "loss": 1.051,
      "step": 830
    },
    {
      "epoch": 0.8931419457735247,
      "grad_norm": 2.0287232398986816,
      "learning_rate": 2.148936170212766e-05,
      "loss": 0.9987,
      "step": 840
    },
    {
      "epoch": 0.9037745879851143,
      "grad_norm": 2.2504048347473145,
      "learning_rate": 1.9361702127659575e-05,
      "loss": 0.9468,
      "step": 850
    },
    {
      "epoch": 0.9144072301967039,
      "grad_norm": 1.889223337173462,
      "learning_rate": 1.723404255319149e-05,
      "loss": 1.1471,
      "step": 860
    },
    {
      "epoch": 0.9250398724082934,
      "grad_norm": 2.414099931716919,
      "learning_rate": 1.5106382978723405e-05,
      "loss": 1.0941,
      "step": 870
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 1.7655644416809082,
      "learning_rate": 1.2978723404255318e-05,
      "loss": 1.0504,
      "step": 880
    },
    {
      "epoch": 0.9463051568314726,
      "grad_norm": 1.6641113758087158,
      "learning_rate": 1.0851063829787235e-05,
      "loss": 1.1144,
      "step": 890
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 2.2806735038757324,
      "learning_rate": 8.72340425531915e-06,
      "loss": 1.0884,
      "step": 900
    },
    {
      "epoch": 0.9675704412546517,
      "grad_norm": 2.1201162338256836,
      "learning_rate": 6.595744680851064e-06,
      "loss": 1.0405,
      "step": 910
    },
    {
      "epoch": 0.9782030834662414,
      "grad_norm": 1.651154637336731,
      "learning_rate": 4.468085106382979e-06,
      "loss": 0.9533,
      "step": 920
    },
    {
      "epoch": 0.988835725677831,
      "grad_norm": 2.6276893615722656,
      "learning_rate": 2.3404255319148935e-06,
      "loss": 1.0675,
      "step": 930
    },
    {
      "epoch": 0.9994683678894205,
      "grad_norm": 1.7685601711273193,
      "learning_rate": 2.1276595744680852e-07,
      "loss": 0.8962,
      "step": 940
    }
  ],
  "logging_steps": 10,
  "max_steps": 940,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2872735048949760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}