{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 940,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 10.06272029876709,
      "learning_rate": 9.893617021276596e-05,
      "loss": 0.2002,
      "step": 10
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 9.355937004089355,
      "learning_rate": 9.787234042553192e-05,
      "loss": 0.1577,
      "step": 20
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 6.437077522277832,
      "learning_rate": 9.680851063829788e-05,
      "loss": 0.0686,
      "step": 30
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 7.390567302703857,
      "learning_rate": 9.574468085106384e-05,
      "loss": 0.0587,
      "step": 40
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 1.0643635988235474,
      "learning_rate": 9.468085106382978e-05,
      "loss": 0.0391,
      "step": 50
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 4.998205184936523,
      "learning_rate": 9.361702127659576e-05,
      "loss": 0.0309,
      "step": 60
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 3.10650372505188,
      "learning_rate": 9.25531914893617e-05,
      "loss": 0.0189,
      "step": 70
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 3.8945138454437256,
      "learning_rate": 9.148936170212766e-05,
      "loss": 0.036,
      "step": 80
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 1.1039351224899292,
      "learning_rate": 9.042553191489363e-05,
      "loss": 0.009,
      "step": 90
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.013753031380474567,
      "eval_mse": 0.013753034174442291,
      "eval_runtime": 14.0344,
      "eval_samples_per_second": 13.324,
      "eval_steps_per_second": 1.71,
      "step": 94
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 1.4354372024536133,
      "learning_rate": 8.936170212765958e-05,
      "loss": 0.0189,
      "step": 100
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 2.4736692905426025,
      "learning_rate": 8.829787234042553e-05,
      "loss": 0.0203,
      "step": 110
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 4.297308921813965,
      "learning_rate": 8.723404255319149e-05,
      "loss": 0.0142,
      "step": 120
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.9237638711929321,
      "learning_rate": 8.617021276595745e-05,
      "loss": 0.0196,
      "step": 130
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.5327073335647583,
      "learning_rate": 8.510638297872341e-05,
      "loss": 0.005,
      "step": 140
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 4.415370464324951,
      "learning_rate": 8.404255319148937e-05,
      "loss": 0.0154,
      "step": 150
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 4.288142681121826,
      "learning_rate": 8.297872340425533e-05,
      "loss": 0.0079,
      "step": 160
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 3.239485025405884,
      "learning_rate": 8.191489361702128e-05,
      "loss": 0.0193,
      "step": 170
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 4.977686882019043,
      "learning_rate": 8.085106382978723e-05,
      "loss": 0.0073,
      "step": 180
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.012815679423511028,
      "eval_mse": 0.012815679423511028,
      "eval_runtime": 13.7185,
      "eval_samples_per_second": 13.631,
      "eval_steps_per_second": 1.749,
      "step": 188
    },
    {
      "epoch": 2.021276595744681,
      "grad_norm": 0.5058400630950928,
      "learning_rate": 7.978723404255319e-05,
      "loss": 0.0292,
      "step": 190
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.8780695199966431,
      "learning_rate": 7.872340425531916e-05,
      "loss": 0.0057,
      "step": 200
    },
    {
      "epoch": 2.2340425531914896,
      "grad_norm": 1.6473358869552612,
      "learning_rate": 7.76595744680851e-05,
      "loss": 0.0038,
      "step": 210
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.6567038297653198,
      "learning_rate": 7.659574468085106e-05,
      "loss": 0.0064,
      "step": 220
    },
    {
      "epoch": 2.4468085106382977,
      "grad_norm": 0.7227131724357605,
      "learning_rate": 7.553191489361703e-05,
      "loss": 0.0274,
      "step": 230
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 2.78585147857666,
      "learning_rate": 7.446808510638298e-05,
      "loss": 0.0153,
      "step": 240
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 0.9734132885932922,
      "learning_rate": 7.340425531914894e-05,
      "loss": 0.0051,
      "step": 250
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.26271963119506836,
      "learning_rate": 7.23404255319149e-05,
      "loss": 0.0178,
      "step": 260
    },
    {
      "epoch": 2.872340425531915,
      "grad_norm": 0.6783913373947144,
      "learning_rate": 7.127659574468085e-05,
      "loss": 0.0084,
      "step": 270
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 2.631406307220459,
      "learning_rate": 7.021276595744681e-05,
      "loss": 0.0054,
      "step": 280
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.013233263976871967,
      "eval_mse": 0.013233264908194542,
      "eval_runtime": 13.8981,
      "eval_samples_per_second": 13.455,
      "eval_steps_per_second": 1.727,
      "step": 282
    },
    {
      "epoch": 3.0851063829787235,
      "grad_norm": 0.7301953434944153,
      "learning_rate": 6.914893617021277e-05,
      "loss": 0.0032,
      "step": 290
    },
    {
      "epoch": 3.1914893617021276,
      "grad_norm": 0.15255877375602722,
      "learning_rate": 6.808510638297873e-05,
      "loss": 0.0035,
      "step": 300
    },
    {
      "epoch": 3.297872340425532,
      "grad_norm": 1.292937994003296,
      "learning_rate": 6.702127659574469e-05,
      "loss": 0.0097,
      "step": 310
    },
    {
      "epoch": 3.404255319148936,
      "grad_norm": 0.5148919224739075,
      "learning_rate": 6.595744680851063e-05,
      "loss": 0.0042,
      "step": 320
    },
    {
      "epoch": 3.5106382978723403,
      "grad_norm": 0.4015097916126251,
      "learning_rate": 6.489361702127659e-05,
      "loss": 0.0086,
      "step": 330
    },
    {
      "epoch": 3.617021276595745,
      "grad_norm": 3.0170764923095703,
      "learning_rate": 6.382978723404256e-05,
      "loss": 0.007,
      "step": 340
    },
    {
      "epoch": 3.723404255319149,
      "grad_norm": 3.584163188934326,
      "learning_rate": 6.276595744680851e-05,
      "loss": 0.0144,
      "step": 350
    },
    {
      "epoch": 3.829787234042553,
      "grad_norm": 1.1259922981262207,
      "learning_rate": 6.170212765957447e-05,
      "loss": 0.0083,
      "step": 360
    },
    {
      "epoch": 3.9361702127659575,
      "grad_norm": 0.7375078797340393,
      "learning_rate": 6.063829787234043e-05,
      "loss": 0.0212,
      "step": 370
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.017101282253861427,
      "eval_mse": 0.017101280391216278,
      "eval_runtime": 13.872,
      "eval_samples_per_second": 13.48,
      "eval_steps_per_second": 1.73,
      "step": 376
    },
    {
      "epoch": 4.042553191489362,
      "grad_norm": 2.1846752166748047,
      "learning_rate": 5.9574468085106384e-05,
      "loss": 0.0195,
      "step": 380
    },
    {
      "epoch": 4.148936170212766,
      "grad_norm": 5.545344829559326,
      "learning_rate": 5.851063829787234e-05,
      "loss": 0.0105,
      "step": 390
    },
    {
      "epoch": 4.25531914893617,
      "grad_norm": 0.2653953731060028,
      "learning_rate": 5.744680851063831e-05,
      "loss": 0.0025,
      "step": 400
    },
    {
      "epoch": 4.361702127659575,
      "grad_norm": 1.925662875175476,
      "learning_rate": 5.638297872340426e-05,
      "loss": 0.0086,
      "step": 410
    },
    {
      "epoch": 4.468085106382979,
      "grad_norm": 1.8210370540618896,
      "learning_rate": 5.531914893617022e-05,
      "loss": 0.0043,
      "step": 420
    },
    {
      "epoch": 4.574468085106383,
      "grad_norm": 0.3224211037158966,
      "learning_rate": 5.425531914893617e-05,
      "loss": 0.0032,
      "step": 430
    },
    {
      "epoch": 4.680851063829787,
      "grad_norm": 1.967247486114502,
      "learning_rate": 5.319148936170213e-05,
      "loss": 0.0019,
      "step": 440
    },
    {
      "epoch": 4.787234042553192,
      "grad_norm": 0.4594058692455292,
      "learning_rate": 5.212765957446809e-05,
      "loss": 0.003,
      "step": 450
    },
    {
      "epoch": 4.8936170212765955,
      "grad_norm": 1.7685928344726562,
      "learning_rate": 5.1063829787234044e-05,
      "loss": 0.0098,
      "step": 460
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2480486631393433,
      "learning_rate": 5e-05,
      "loss": 0.0037,
      "step": 470
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.012585950084030628,
      "eval_mse": 0.012585948221385479,
      "eval_runtime": 13.9988,
      "eval_samples_per_second": 13.358,
      "eval_steps_per_second": 1.714,
      "step": 470
    },
    {
      "epoch": 5.1063829787234045,
      "grad_norm": 0.3565947413444519,
      "learning_rate": 4.893617021276596e-05,
      "loss": 0.0022,
      "step": 480
    },
    {
      "epoch": 5.212765957446808,
      "grad_norm": 1.9558695554733276,
      "learning_rate": 4.787234042553192e-05,
      "loss": 0.0024,
      "step": 490
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 2.0850021839141846,
      "learning_rate": 4.680851063829788e-05,
      "loss": 0.0017,
      "step": 500
    },
    {
      "epoch": 5.425531914893617,
      "grad_norm": 0.6376081705093384,
      "learning_rate": 4.574468085106383e-05,
      "loss": 0.0024,
      "step": 510
    },
    {
      "epoch": 5.531914893617021,
      "grad_norm": 0.6883834600448608,
      "learning_rate": 4.468085106382979e-05,
      "loss": 0.0027,
      "step": 520
    },
    {
      "epoch": 5.638297872340425,
      "grad_norm": 0.7575547695159912,
      "learning_rate": 4.3617021276595746e-05,
      "loss": 0.0089,
      "step": 530
    },
    {
      "epoch": 5.74468085106383,
      "grad_norm": 0.9643301367759705,
      "learning_rate": 4.2553191489361704e-05,
      "loss": 0.0019,
      "step": 540
    },
    {
      "epoch": 5.851063829787234,
      "grad_norm": 0.4256587326526642,
      "learning_rate": 4.148936170212766e-05,
      "loss": 0.0076,
      "step": 550
    },
    {
      "epoch": 5.957446808510638,
      "grad_norm": 0.6945656538009644,
      "learning_rate": 4.0425531914893614e-05,
      "loss": 0.0015,
      "step": 560
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.012150809168815613,
      "eval_mse": 0.012150808237493038,
      "eval_runtime": 13.8305,
      "eval_samples_per_second": 13.521,
      "eval_steps_per_second": 1.735,
      "step": 564
    },
    {
      "epoch": 6.0638297872340425,
      "grad_norm": 0.319540798664093,
      "learning_rate": 3.936170212765958e-05,
      "loss": 0.0019,
      "step": 570
    },
    {
      "epoch": 6.170212765957447,
      "grad_norm": 1.3060803413391113,
      "learning_rate": 3.829787234042553e-05,
      "loss": 0.0078,
      "step": 580
    },
    {
      "epoch": 6.276595744680851,
      "grad_norm": 0.2700423300266266,
      "learning_rate": 3.723404255319149e-05,
      "loss": 0.0011,
      "step": 590
    },
    {
      "epoch": 6.382978723404255,
      "grad_norm": 0.3229953348636627,
      "learning_rate": 3.617021276595745e-05,
      "loss": 0.0012,
      "step": 600
    },
    {
      "epoch": 6.48936170212766,
      "grad_norm": 1.5781389474868774,
      "learning_rate": 3.5106382978723407e-05,
      "loss": 0.0016,
      "step": 610
    },
    {
      "epoch": 6.595744680851064,
      "grad_norm": 1.4765293598175049,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 0.0022,
      "step": 620
    },
    {
      "epoch": 6.702127659574468,
      "grad_norm": 0.3169589340686798,
      "learning_rate": 3.2978723404255317e-05,
      "loss": 0.0017,
      "step": 630
    },
    {
      "epoch": 6.808510638297872,
      "grad_norm": 0.05266076698899269,
      "learning_rate": 3.191489361702128e-05,
      "loss": 0.0012,
      "step": 640
    },
    {
      "epoch": 6.914893617021277,
      "grad_norm": 1.669859766960144,
      "learning_rate": 3.085106382978723e-05,
      "loss": 0.0044,
      "step": 650
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.01300265546888113,
      "eval_mse": 0.01300265546888113,
      "eval_runtime": 13.9251,
      "eval_samples_per_second": 13.429,
      "eval_steps_per_second": 1.724,
      "step": 658
    },
    {
      "epoch": 7.0212765957446805,
      "grad_norm": 0.5370873808860779,
      "learning_rate": 2.9787234042553192e-05,
      "loss": 0.0013,
      "step": 660
    },
    {
      "epoch": 7.127659574468085,
      "grad_norm": 1.7552562952041626,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 0.0097,
      "step": 670
    },
    {
      "epoch": 7.23404255319149,
      "grad_norm": 0.7278550863265991,
      "learning_rate": 2.765957446808511e-05,
      "loss": 0.0021,
      "step": 680
    },
    {
      "epoch": 7.340425531914893,
      "grad_norm": 0.3339664041996002,
      "learning_rate": 2.6595744680851064e-05,
      "loss": 0.0013,
      "step": 690
    },
    {
      "epoch": 7.446808510638298,
      "grad_norm": 0.2945927381515503,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.0006,
      "step": 700
    },
    {
      "epoch": 7.553191489361702,
      "grad_norm": 0.47596001625061035,
      "learning_rate": 2.446808510638298e-05,
      "loss": 0.0016,
      "step": 710
    },
    {
      "epoch": 7.659574468085106,
      "grad_norm": 0.6078076362609863,
      "learning_rate": 2.340425531914894e-05,
      "loss": 0.0007,
      "step": 720
    },
    {
      "epoch": 7.76595744680851,
      "grad_norm": 0.16935944557189941,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.0005,
      "step": 730
    },
    {
      "epoch": 7.872340425531915,
      "grad_norm": 0.29044824838638306,
      "learning_rate": 2.1276595744680852e-05,
      "loss": 0.0006,
      "step": 740
    },
    {
      "epoch": 7.9787234042553195,
      "grad_norm": 0.8321860432624817,
      "learning_rate": 2.0212765957446807e-05,
      "loss": 0.0005,
      "step": 750
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.012086642906069756,
      "eval_mse": 0.012086641043424606,
      "eval_runtime": 13.9355,
      "eval_samples_per_second": 13.419,
      "eval_steps_per_second": 1.722,
      "step": 752
    },
    {
      "epoch": 8.085106382978724,
      "grad_norm": 0.5752009153366089,
      "learning_rate": 1.9148936170212766e-05,
      "loss": 0.0003,
      "step": 760
    },
    {
      "epoch": 8.191489361702128,
      "grad_norm": 0.2549976408481598,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.0002,
      "step": 770
    },
    {
      "epoch": 8.297872340425531,
      "grad_norm": 0.41198980808258057,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 0.0015,
      "step": 780
    },
    {
      "epoch": 8.404255319148936,
      "grad_norm": 0.25298696756362915,
      "learning_rate": 1.595744680851064e-05,
      "loss": 0.0037,
      "step": 790
    },
    {
      "epoch": 8.51063829787234,
      "grad_norm": 0.38285136222839355,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 0.0008,
      "step": 800
    },
    {
      "epoch": 8.617021276595745,
      "grad_norm": 0.2713870704174042,
      "learning_rate": 1.3829787234042554e-05,
      "loss": 0.0003,
      "step": 810
    },
    {
      "epoch": 8.72340425531915,
      "grad_norm": 0.038877371698617935,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.0016,
      "step": 820
    },
    {
      "epoch": 8.829787234042554,
      "grad_norm": 0.5373714566230774,
      "learning_rate": 1.170212765957447e-05,
      "loss": 0.0004,
      "step": 830
    },
    {
      "epoch": 8.936170212765958,
      "grad_norm": 0.03909245505928993,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 0.0002,
      "step": 840
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.01240901555866003,
      "eval_mse": 0.01240901555866003,
      "eval_runtime": 13.8515,
      "eval_samples_per_second": 13.5,
      "eval_steps_per_second": 1.733,
      "step": 846
    },
    {
      "epoch": 9.042553191489361,
      "grad_norm": 0.5892852544784546,
      "learning_rate": 9.574468085106383e-06,
      "loss": 0.0006,
      "step": 850
    },
    {
      "epoch": 9.148936170212766,
      "grad_norm": 0.5549539923667908,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.0002,
      "step": 860
    },
    {
      "epoch": 9.25531914893617,
      "grad_norm": 0.04103722795844078,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.0002,
      "step": 870
    },
    {
      "epoch": 9.361702127659575,
      "grad_norm": 0.3398093283176422,
      "learning_rate": 6.3829787234042555e-06,
      "loss": 0.0002,
      "step": 880
    },
    {
      "epoch": 9.46808510638298,
      "grad_norm": 0.24325959384441376,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.0002,
      "step": 890
    },
    {
      "epoch": 9.574468085106384,
      "grad_norm": 0.1950555145740509,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.0002,
      "step": 900
    },
    {
      "epoch": 9.680851063829786,
      "grad_norm": 0.8445388674736023,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.0005,
      "step": 910
    },
    {
      "epoch": 9.787234042553191,
      "grad_norm": 0.035643890500068665,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.0001,
      "step": 920
    },
    {
      "epoch": 9.893617021276595,
      "grad_norm": 0.12715914845466614,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 0.0021,
      "step": 930
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.24454765021800995,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "step": 940
    }
  ],
  "logging_steps": 10,
  "max_steps": 940,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}