{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 730,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.136986301369863,
      "grad_norm": 5.2195892333984375,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.9148,
      "step": 10
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 2.442189931869507,
      "learning_rate": 5.405405405405406e-05,
      "loss": 0.6052,
      "step": 20
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 2.444631576538086,
      "learning_rate": 8.108108108108109e-05,
      "loss": 0.4321,
      "step": 30
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 1.6064536571502686,
      "learning_rate": 9.999537609289592e-05,
      "loss": 0.328,
      "step": 40
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.9033578038215637,
      "learning_rate": 9.991319708909113e-05,
      "loss": 0.2676,
      "step": 50
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.881839394569397,
      "learning_rate": 9.972845896501761e-05,
      "loss": 0.241,
      "step": 60
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.7620624899864197,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.2151,
      "step": 70
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.8047911524772644,
      "learning_rate": 9.905303367173336e-05,
      "loss": 0.1981,
      "step": 80
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 0.789812445640564,
      "learning_rate": 9.856373433235373e-05,
      "loss": 0.1722,
      "step": 90
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.8034406900405884,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.1565,
      "step": 100
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 0.6497238278388977,
      "learning_rate": 9.72869871403363e-05,
      "loss": 0.1428,
      "step": 110
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.7455314993858337,
      "learning_rate": 9.650216268344262e-05,
      "loss": 0.136,
      "step": 120
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 0.6564836502075195,
      "learning_rate": 9.562178792775936e-05,
      "loss": 0.1279,
      "step": 130
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.7567775845527649,
      "learning_rate": 9.464767182293739e-05,
      "loss": 0.1189,
      "step": 140
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 0.5241563320159912,
      "learning_rate": 9.35818159336245e-05,
      "loss": 0.1149,
      "step": 150
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.4330901801586151,
      "learning_rate": 9.242641032675117e-05,
      "loss": 0.1098,
      "step": 160
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 0.4459153413772583,
      "learning_rate": 9.118382907149165e-05,
      "loss": 0.1076,
      "step": 170
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.467021644115448,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.1097,
      "step": 180
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 0.7806321382522583,
      "learning_rate": 8.84475262669681e-05,
      "loss": 0.0992,
      "step": 190
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.7798169851303101,
      "learning_rate": 8.695942713471577e-05,
      "loss": 0.1018,
      "step": 200
    },
    {
      "epoch": 2.8767123287671232,
      "grad_norm": 0.40669694542884827,
      "learning_rate": 8.539538563544163e-05,
      "loss": 0.1017,
      "step": 210
    },
    {
      "epoch": 3.0136986301369864,
      "grad_norm": 0.680648922920227,
      "learning_rate": 8.375861548274418e-05,
      "loss": 0.1015,
      "step": 220
    },
    {
      "epoch": 3.1506849315068495,
      "grad_norm": 0.7035002112388611,
      "learning_rate": 8.205247982939123e-05,
      "loss": 0.0918,
      "step": 230
    },
    {
      "epoch": 3.287671232876712,
      "grad_norm": 0.7396689653396606,
      "learning_rate": 8.028048435688333e-05,
      "loss": 0.0935,
      "step": 240
    },
    {
      "epoch": 3.4246575342465753,
      "grad_norm": 0.746228039264679,
      "learning_rate": 7.844627007215613e-05,
      "loss": 0.0903,
      "step": 250
    },
    {
      "epoch": 3.5616438356164384,
      "grad_norm": 0.4722535014152527,
      "learning_rate": 7.655360582622286e-05,
      "loss": 0.0891,
      "step": 260
    },
    {
      "epoch": 3.6986301369863015,
      "grad_norm": 0.5862498879432678,
      "learning_rate": 7.460638057012955e-05,
      "loss": 0.0906,
      "step": 270
    },
    {
      "epoch": 3.8356164383561646,
      "grad_norm": 0.5559934973716736,
      "learning_rate": 7.260859536413429e-05,
      "loss": 0.0839,
      "step": 280
    },
    {
      "epoch": 3.9726027397260273,
      "grad_norm": 0.5900849103927612,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.0882,
      "step": 290
    },
    {
      "epoch": 4.109589041095891,
      "grad_norm": 0.7324544787406921,
      "learning_rate": 6.847786034900649e-05,
      "loss": 0.0827,
      "step": 300
    },
    {
      "epoch": 4.2465753424657535,
      "grad_norm": 0.5513842701911926,
      "learning_rate": 6.635339816587109e-05,
      "loss": 0.0874,
      "step": 310
    },
    {
      "epoch": 4.383561643835616,
      "grad_norm": 0.44522860646247864,
      "learning_rate": 6.41953338448822e-05,
      "loss": 0.0824,
      "step": 320
    },
    {
      "epoch": 4.52054794520548,
      "grad_norm": 0.64205002784729,
      "learning_rate": 6.200810166777597e-05,
      "loss": 0.0837,
      "step": 330
    },
    {
      "epoch": 4.657534246575342,
      "grad_norm": 0.35937950015068054,
      "learning_rate": 5.979619584892834e-05,
      "loss": 0.0791,
      "step": 340
    },
    {
      "epoch": 4.794520547945205,
      "grad_norm": 0.3836668133735657,
      "learning_rate": 5.756416130087001e-05,
      "loss": 0.0787,
      "step": 350
    },
    {
      "epoch": 4.931506849315069,
      "grad_norm": 0.5425627827644348,
      "learning_rate": 5.53165842956294e-05,
      "loss": 0.077,
      "step": 360
    },
    {
      "epoch": 5.068493150684931,
      "grad_norm": 0.5653792023658752,
      "learning_rate": 5.305808304109214e-05,
      "loss": 0.0809,
      "step": 370
    },
    {
      "epoch": 5.205479452054795,
      "grad_norm": 0.6761691570281982,
      "learning_rate": 5.0793298191740404e-05,
      "loss": 0.0815,
      "step": 380
    },
    {
      "epoch": 5.342465753424658,
      "grad_norm": 0.39536017179489136,
      "learning_rate": 4.8526883313270106e-05,
      "loss": 0.0853,
      "step": 390
    },
    {
      "epoch": 5.47945205479452,
      "grad_norm": 0.47267112135887146,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.0756,
      "step": 400
    },
    {
      "epoch": 5.616438356164384,
      "grad_norm": 0.42643123865127563,
      "learning_rate": 4.400778490947157e-05,
      "loss": 0.0743,
      "step": 410
    },
    {
      "epoch": 5.7534246575342465,
      "grad_norm": 0.44257625937461853,
      "learning_rate": 4.176438699964646e-05,
      "loss": 0.0755,
      "step": 420
    },
    {
      "epoch": 5.890410958904109,
      "grad_norm": 0.41078025102615356,
      "learning_rate": 3.953791121209458e-05,
      "loss": 0.0747,
      "step": 430
    },
    {
      "epoch": 6.027397260273973,
      "grad_norm": 0.4885757863521576,
      "learning_rate": 3.733293239698359e-05,
      "loss": 0.0732,
      "step": 440
    },
    {
      "epoch": 6.164383561643835,
      "grad_norm": 0.6123595237731934,
      "learning_rate": 3.515398123358627e-05,
      "loss": 0.0761,
      "step": 450
    },
    {
      "epoch": 6.301369863013699,
      "grad_norm": 0.3499448001384735,
      "learning_rate": 3.3005534920869176e-05,
      "loss": 0.0767,
      "step": 460
    },
    {
      "epoch": 6.438356164383562,
      "grad_norm": 0.43977606296539307,
      "learning_rate": 3.0892007977970086e-05,
      "loss": 0.0731,
      "step": 470
    },
    {
      "epoch": 6.575342465753424,
      "grad_norm": 0.29874327778816223,
      "learning_rate": 2.8817743173466636e-05,
      "loss": 0.0735,
      "step": 480
    },
    {
      "epoch": 6.712328767123288,
      "grad_norm": 0.3531714975833893,
      "learning_rate": 2.678700260207449e-05,
      "loss": 0.0721,
      "step": 490
    },
    {
      "epoch": 6.8493150684931505,
      "grad_norm": 0.3463064730167389,
      "learning_rate": 2.4803958927109965e-05,
      "loss": 0.073,
      "step": 500
    },
    {
      "epoch": 6.986301369863014,
      "grad_norm": 0.3994370698928833,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.0713,
      "step": 510
    },
    {
      "epoch": 7.123287671232877,
      "grad_norm": 0.3885277211666107,
      "learning_rate": 2.09971545214401e-05,
      "loss": 0.0768,
      "step": 520
    },
    {
      "epoch": 7.260273972602739,
      "grad_norm": 0.5557729005813599,
      "learning_rate": 1.918121582045132e-05,
      "loss": 0.0681,
      "step": 530
    },
    {
      "epoch": 7.397260273972603,
      "grad_norm": 0.34055230021476746,
      "learning_rate": 1.7428602003011134e-05,
      "loss": 0.0697,
      "step": 540
    },
    {
      "epoch": 7.534246575342466,
      "grad_norm": 0.3750840723514557,
      "learning_rate": 1.5742914251607793e-05,
      "loss": 0.0679,
      "step": 550
    },
    {
      "epoch": 7.671232876712329,
      "grad_norm": 0.48403847217559814,
      "learning_rate": 1.412761623242404e-05,
      "loss": 0.0669,
      "step": 560
    },
    {
      "epoch": 7.808219178082192,
      "grad_norm": 0.37212374806404114,
      "learning_rate": 1.2586026978370629e-05,
      "loss": 0.0689,
      "step": 570
    },
    {
      "epoch": 7.945205479452055,
      "grad_norm": 0.4119841158390045,
      "learning_rate": 1.1121314069304811e-05,
      "loss": 0.0699,
      "step": 580
    },
    {
      "epoch": 8.082191780821917,
      "grad_norm": 0.529219388961792,
      "learning_rate": 9.73648712344707e-06,
      "loss": 0.0694,
      "step": 590
    },
    {
      "epoch": 8.219178082191782,
      "grad_norm": 0.3745039701461792,
      "learning_rate": 8.434391613369258e-06,
      "loss": 0.0666,
      "step": 600
    },
    {
      "epoch": 8.356164383561644,
      "grad_norm": 0.4455980956554413,
      "learning_rate": 7.217703019261135e-06,
      "loss": 0.0706,
      "step": 610
    },
    {
      "epoch": 8.493150684931507,
      "grad_norm": 0.53988116979599,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.0707,
      "step": 620
    },
    {
      "epoch": 8.63013698630137,
      "grad_norm": 0.33156082034111023,
      "learning_rate": 5.050365913739441e-06,
      "loss": 0.0645,
      "step": 630
    },
    {
      "epoch": 8.767123287671232,
      "grad_norm": 0.3420356810092926,
      "learning_rate": 4.1041707373120356e-06,
      "loss": 0.0654,
      "step": 640
    },
    {
      "epoch": 8.904109589041095,
      "grad_norm": 0.39363735914230347,
      "learning_rate": 3.252279996338492e-06,
      "loss": 0.0699,
      "step": 650
    },
    {
      "epoch": 9.04109589041096,
      "grad_norm": 0.6195297241210938,
      "learning_rate": 2.496444112952734e-06,
      "loss": 0.0689,
      "step": 660
    },
    {
      "epoch": 9.178082191780822,
      "grad_norm": 0.4905112087726593,
      "learning_rate": 1.8382161406113208e-06,
      "loss": 0.0654,
      "step": 670
    },
    {
      "epoch": 9.315068493150685,
      "grad_norm": 0.43245476484298706,
      "learning_rate": 1.2789485729575612e-06,
      "loss": 0.0708,
      "step": 680
    },
    {
      "epoch": 9.452054794520548,
      "grad_norm": 0.4771445393562317,
      "learning_rate": 8.197905647857384e-07,
      "loss": 0.0707,
      "step": 690
    },
    {
      "epoch": 9.58904109589041,
      "grad_norm": 0.23996645212173462,
      "learning_rate": 4.6168557081582854e-07,
      "loss": 0.0634,
      "step": 700
    },
    {
      "epoch": 9.726027397260275,
      "grad_norm": 0.5234819054603577,
      "learning_rate": 2.0536940713028474e-07,
      "loss": 0.0659,
      "step": 710
    },
    {
      "epoch": 9.863013698630137,
      "grad_norm": 0.3188411295413971,
      "learning_rate": 5.1368739256296706e-08,
      "loss": 0.066,
      "step": 720
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.543819785118103,
      "learning_rate": 0.0,
      "loss": 0.0664,
      "step": 730
    },
    {
      "epoch": 10.0,
      "step": 730,
      "total_flos": 1.0568936642296032e+17,
      "train_loss": 0.11973448420224124,
      "train_runtime": 466.7787,
      "train_samples_per_second": 198.659,
      "train_steps_per_second": 1.564
    }
  ],
  "logging_steps": 10,
  "max_steps": 730,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 20000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0568936642296032e+17,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}