{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 612,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.049215625961242696,
      "grad_norm": 7.928234577178955,
      "learning_rate": 2.9032258064516133e-05,
      "loss": 1.9090152740478517,
      "step": 10
    },
    {
      "epoch": 0.09843125192248539,
      "grad_norm": 2.6403849124908447,
      "learning_rate": 6.129032258064517e-05,
      "loss": 0.9645010948181152,
      "step": 20
    },
    {
      "epoch": 0.14764687788372807,
      "grad_norm": 1.6458303928375244,
      "learning_rate": 9.35483870967742e-05,
      "loss": 0.8380620956420899,
      "step": 30
    },
    {
      "epoch": 0.19686250384497078,
      "grad_norm": 1.5055936574935913,
      "learning_rate": 9.995322651386344e-05,
      "loss": 0.7867818832397461,
      "step": 40
    },
    {
      "epoch": 0.24607812980621346,
      "grad_norm": 1.3379383087158203,
      "learning_rate": 9.976335919762912e-05,
      "loss": 0.7690763950347901,
      "step": 50
    },
    {
      "epoch": 0.29529375576745615,
      "grad_norm": 1.324133276939392,
      "learning_rate": 9.942802927959443e-05,
      "loss": 0.7235389709472656,
      "step": 60
    },
    {
      "epoch": 0.3445093817286989,
      "grad_norm": 1.2422536611557007,
      "learning_rate": 9.894821695810459e-05,
      "loss": 0.7124866962432861,
      "step": 70
    },
    {
      "epoch": 0.39372500768994156,
      "grad_norm": 1.169839859008789,
      "learning_rate": 9.832532476606302e-05,
      "loss": 0.6995785236358643,
      "step": 80
    },
    {
      "epoch": 0.44294063365118425,
      "grad_norm": 1.1593093872070312,
      "learning_rate": 9.756117347120639e-05,
      "loss": 0.706026029586792,
      "step": 90
    },
    {
      "epoch": 0.4921562596124269,
      "grad_norm": 1.1816542148590088,
      "learning_rate": 9.665799675384311e-05,
      "loss": 0.7048482894897461,
      "step": 100
    },
    {
      "epoch": 0.4921562596124269,
      "eval_loss": 0.6306583881378174,
      "eval_runtime": 85.8033,
      "eval_samples_per_second": 0.956,
      "eval_steps_per_second": 0.245,
      "step": 100
    },
    {
      "epoch": 0.5413718855736697,
      "grad_norm": 1.168054223060608,
      "learning_rate": 9.561843467761258e-05,
      "loss": 0.6828868865966797,
      "step": 110
    },
    {
      "epoch": 0.5905875115349123,
      "grad_norm": 1.172663688659668,
      "learning_rate": 9.4445525972351e-05,
      "loss": 0.6790279388427735,
      "step": 120
    },
    {
      "epoch": 0.639803137496155,
      "grad_norm": 1.1787928342819214,
      "learning_rate": 9.314269915162114e-05,
      "loss": 0.6702056884765625,
      "step": 130
    },
    {
      "epoch": 0.6890187634573978,
      "grad_norm": 1.116205096244812,
      "learning_rate": 9.1713762490871e-05,
      "loss": 0.6747151374816894,
      "step": 140
    },
    {
      "epoch": 0.7382343894186404,
      "grad_norm": 1.1296623945236206,
      "learning_rate": 9.016289289551514e-05,
      "loss": 0.6601762771606445,
      "step": 150
    },
    {
      "epoch": 0.7874500153798831,
      "grad_norm": 1.1211893558502197,
      "learning_rate": 8.84946236914791e-05,
      "loss": 0.6768590450286865,
      "step": 160
    },
    {
      "epoch": 0.8366656413411258,
      "grad_norm": 1.0513691902160645,
      "learning_rate": 8.671383137389579e-05,
      "loss": 0.6323463916778564,
      "step": 170
    },
    {
      "epoch": 0.8858812673023685,
      "grad_norm": 1.0022355318069458,
      "learning_rate": 8.482572135268844e-05,
      "loss": 0.6322056293487549,
      "step": 180
    },
    {
      "epoch": 0.9350968932636112,
      "grad_norm": 1.000985860824585,
      "learning_rate": 8.283581273670739e-05,
      "loss": 0.6177332401275635,
      "step": 190
    },
    {
      "epoch": 0.9843125192248539,
      "grad_norm": 0.9906076192855835,
      "learning_rate": 8.074992220089769e-05,
      "loss": 0.6302848815917969,
      "step": 200
    },
    {
      "epoch": 0.9843125192248539,
      "eval_loss": 0.589972198009491,
      "eval_runtime": 85.6924,
      "eval_samples_per_second": 0.957,
      "eval_steps_per_second": 0.245,
      "step": 200
    },
    {
      "epoch": 1.0295293755767456,
      "grad_norm": 1.4410972595214844,
      "learning_rate": 7.857414698365524e-05,
      "loss": 0.5482802867889405,
      "step": 210
    },
    {
      "epoch": 1.0787450015379882,
      "grad_norm": 1.017478346824646,
      "learning_rate": 7.631484706407179e-05,
      "loss": 0.47220849990844727,
      "step": 220
    },
    {
      "epoch": 1.127960627499231,
      "grad_norm": 1.2113254070281982,
      "learning_rate": 7.397862657116618e-05,
      "loss": 0.4781786918640137,
      "step": 230
    },
    {
      "epoch": 1.1771762534604737,
      "grad_norm": 1.1292043924331665,
      "learning_rate": 7.157231447944408e-05,
      "loss": 0.4690592288970947,
      "step": 240
    },
    {
      "epoch": 1.2263918794217163,
      "grad_norm": 1.1661441326141357,
      "learning_rate": 6.910294464721507e-05,
      "loss": 0.4781680107116699,
      "step": 250
    },
    {
      "epoch": 1.275607505382959,
      "grad_norm": 1.2012077569961548,
      "learning_rate": 6.65777352560166e-05,
      "loss": 0.4640467166900635,
      "step": 260
    },
    {
      "epoch": 1.3248231313442018,
      "grad_norm": 1.126498818397522,
      "learning_rate": 6.400406771124536e-05,
      "loss": 0.4692594051361084,
      "step": 270
    },
    {
      "epoch": 1.3740387573054444,
      "grad_norm": 1.130981683731079,
      "learning_rate": 6.138946506567077e-05,
      "loss": 0.481608247756958,
      "step": 280
    },
    {
      "epoch": 1.4232543832666873,
      "grad_norm": 1.186328649520874,
      "learning_rate": 5.874157002890155e-05,
      "loss": 0.48310260772705077,
      "step": 290
    },
    {
      "epoch": 1.47247000922793,
      "grad_norm": 1.121436357498169,
      "learning_rate": 5.60681226270845e-05,
      "loss": 0.47539544105529785,
      "step": 300
    },
    {
      "epoch": 1.47247000922793,
      "eval_loss": 0.5823286771774292,
      "eval_runtime": 85.7117,
      "eval_samples_per_second": 0.957,
      "eval_steps_per_second": 0.245,
      "step": 300
    },
    {
      "epoch": 1.5216856351891725,
      "grad_norm": 1.114135503768921,
      "learning_rate": 5.3376937578138864e-05,
      "loss": 0.47582225799560546,
      "step": 310
    },
    {
      "epoch": 1.5709012611504152,
      "grad_norm": 1.1961369514465332,
      "learning_rate": 5.067588144866022e-05,
      "loss": 0.4710520267486572,
      "step": 320
    },
    {
      "epoch": 1.6201168871116578,
      "grad_norm": 1.0863640308380127,
      "learning_rate": 4.7972849659266014e-05,
      "loss": 0.46131091117858886,
      "step": 330
    },
    {
      "epoch": 1.6693325130729006,
      "grad_norm": 1.1118478775024414,
      "learning_rate": 4.527574340559844e-05,
      "loss": 0.46948895454406736,
      "step": 340
    },
    {
      "epoch": 1.7185481390341435,
      "grad_norm": 1.15009343624115,
      "learning_rate": 4.259244656244647e-05,
      "loss": 0.4635800361633301,
      "step": 350
    },
    {
      "epoch": 1.7677637649953861,
      "grad_norm": 1.1832060813903809,
      "learning_rate": 3.9930802638498e-05,
      "loss": 0.4711782932281494,
      "step": 360
    },
    {
      "epoch": 1.8169793909566287,
      "grad_norm": 1.3281469345092773,
      "learning_rate": 3.72985918490859e-05,
      "loss": 0.4741796970367432,
      "step": 370
    },
    {
      "epoch": 1.8661950169178714,
      "grad_norm": 1.1587272882461548,
      "learning_rate": 3.470350837394581e-05,
      "loss": 0.45445003509521487,
      "step": 380
    },
    {
      "epoch": 1.915410642879114,
      "grad_norm": 1.1648741960525513,
      "learning_rate": 3.2153137866463446e-05,
      "loss": 0.4263807773590088,
      "step": 390
    },
    {
      "epoch": 1.9646262688403568,
      "grad_norm": 1.0927444696426392,
      "learning_rate": 2.9654935280153906e-05,
      "loss": 0.443405818939209,
      "step": 400
    },
    {
      "epoch": 1.9646262688403568,
      "eval_loss": 0.5655035376548767,
      "eval_runtime": 86.0143,
      "eval_samples_per_second": 0.953,
      "eval_steps_per_second": 0.244,
      "step": 400
    },
    {
      "epoch": 2.0098431251922486,
      "grad_norm": 0.8720270395278931,
      "learning_rate": 2.721620307718793e-05,
      "loss": 0.4128866195678711,
      "step": 410
    },
    {
      "epoch": 2.0590587511534912,
      "grad_norm": 1.3858129978179932,
      "learning_rate": 2.4844069882663534e-05,
      "loss": 0.3000333786010742,
      "step": 420
    },
    {
      "epoch": 2.108274377114734,
      "grad_norm": 1.2642326354980469,
      "learning_rate": 2.2545469647018448e-05,
      "loss": 0.2930248975753784,
      "step": 430
    },
    {
      "epoch": 2.1574900030759765,
      "grad_norm": 1.232212781906128,
      "learning_rate": 2.0327121377493495e-05,
      "loss": 0.28675529956817625,
      "step": 440
    },
    {
      "epoch": 2.206705629037219,
      "grad_norm": 1.1859720945358276,
      "learning_rate": 1.819550949789342e-05,
      "loss": 0.2949700117111206,
      "step": 450
    },
    {
      "epoch": 2.255921254998462,
      "grad_norm": 1.1339415311813354,
      "learning_rate": 1.615686489405541e-05,
      "loss": 0.2928622245788574,
      "step": 460
    },
    {
      "epoch": 2.305136880959705,
      "grad_norm": 1.349238634109497,
      "learning_rate": 1.4217146700431011e-05,
      "loss": 0.2952066421508789,
      "step": 470
    },
    {
      "epoch": 2.3543525069209474,
      "grad_norm": 1.1220487356185913,
      "learning_rate": 1.2382024881020937e-05,
      "loss": 0.2783914804458618,
      "step": 480
    },
    {
      "epoch": 2.40356813288219,
      "grad_norm": 1.2111746072769165,
      "learning_rate": 1.0656863655579974e-05,
      "loss": 0.29411156177520753,
      "step": 490
    },
    {
      "epoch": 2.4527837588434327,
      "grad_norm": 1.251997709274292,
      "learning_rate": 9.046705819538786e-06,
      "loss": 0.28312842845916747,
      "step": 500
    },
    {
      "epoch": 2.4527837588434327,
      "eval_loss": 0.6120470762252808,
      "eval_runtime": 86.0803,
      "eval_samples_per_second": 0.953,
      "eval_steps_per_second": 0.244,
      "step": 500
    },
    {
      "epoch": 2.5019993848046753,
      "grad_norm": 1.2783576250076294,
      "learning_rate": 7.556258003476929e-06,
      "loss": 0.29095680713653566,
      "step": 510
    },
    {
      "epoch": 2.551215010765918,
      "grad_norm": 1.2363778352737427,
      "learning_rate": 6.189876915234627e-06,
      "loss": 0.2860475301742554,
      "step": 520
    },
    {
      "epoch": 2.600430636727161,
      "grad_norm": 1.282787799835205,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.28925886154174807,
      "step": 530
    },
    {
      "epoch": 2.6496462626884036,
      "grad_norm": 1.2733683586120605,
      "learning_rate": 3.8449167897506466e-06,
      "loss": 0.2875803232192993,
      "step": 540
    },
    {
      "epoch": 2.6988618886496463,
      "grad_norm": 1.2200466394424438,
      "learning_rate": 2.8731922737163685e-06,
      "loss": 0.286954402923584,
      "step": 550
    },
    {
      "epoch": 2.748077514610889,
      "grad_norm": 1.189471960067749,
      "learning_rate": 2.039223491558234e-06,
      "loss": 0.2921234846115112,
      "step": 560
    },
    {
      "epoch": 2.7972931405721315,
      "grad_norm": 1.210889458656311,
      "learning_rate": 1.3454482061368956e-06,
      "loss": 0.28174967765808107,
      "step": 570
    },
    {
      "epoch": 2.8465087665333746,
      "grad_norm": 1.2910287380218506,
      "learning_rate": 7.938943826000022e-07,
      "loss": 0.2928427457809448,
      "step": 580
    },
    {
      "epoch": 2.8957243924946168,
      "grad_norm": 1.0850300788879395,
      "learning_rate": 3.861742604646834e-07,
      "loss": 0.27887468338012694,
      "step": 590
    },
    {
      "epoch": 2.94494001845586,
      "grad_norm": 1.184747576713562,
      "learning_rate": 1.2347964090210217e-07,
      "loss": 0.2920320272445679,
      "step": 600
    },
    {
      "epoch": 2.94494001845586,
      "eval_loss": 0.6133363842964172,
      "eval_runtime": 85.7742,
      "eval_samples_per_second": 0.956,
      "eval_steps_per_second": 0.245,
      "step": 600
    },
    {
      "epoch": 2.9941556444171025,
      "grad_norm": 1.2488678693771362,
      "learning_rate": 6.578402999540823e-09,
      "loss": 0.2868155002593994,
      "step": 610
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6133090853691101,
      "eval_runtime": 85.8551,
      "eval_samples_per_second": 0.955,
      "eval_steps_per_second": 0.245,
      "step": 612
    }
  ],
  "logging_steps": 10,
  "max_steps": 612,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0407602498605056e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}