{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.946341463414634,
  "eval_steps": 500,
  "global_step": 612,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 5.756045341491699,
      "learning_rate": 1.4516129032258066e-06,
      "loss": 0.8809,
      "step": 10
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 3.873936176300049,
      "learning_rate": 3.0645161290322584e-06,
      "loss": 0.8044,
      "step": 20
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 1.6314491033554077,
      "learning_rate": 4.67741935483871e-06,
      "loss": 0.7459,
      "step": 30
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 2.0878822803497314,
      "learning_rate": 6.290322580645162e-06,
      "loss": 0.727,
      "step": 40
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 1.7192010879516602,
      "learning_rate": 7.903225806451613e-06,
      "loss": 0.6279,
      "step": 50
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 1.5417181253433228,
      "learning_rate": 9.516129032258065e-06,
      "loss": 0.6367,
      "step": 60
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 1.7374225854873657,
      "learning_rate": 9.996003750499608e-06,
      "loss": 0.689,
      "step": 70
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 1.3835179805755615,
      "learning_rate": 9.976445660039118e-06,
      "loss": 0.6537,
      "step": 80
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 1.206093192100525,
      "learning_rate": 9.940655438201113e-06,
      "loss": 0.6421,
      "step": 90
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 1.456930160522461,
      "learning_rate": 9.888749825250151e-06,
      "loss": 0.6039,
      "step": 100
    },
    {
      "epoch": 1.0682926829268293,
      "grad_norm": 1.419948935508728,
      "learning_rate": 9.820898126506978e-06,
      "loss": 0.5969,
      "step": 110
    },
    {
      "epoch": 1.1658536585365853,
      "grad_norm": 1.9503365755081177,
      "learning_rate": 9.737321660109767e-06,
      "loss": 0.516,
      "step": 120
    },
    {
      "epoch": 1.2634146341463415,
      "grad_norm": 1.587859869003296,
      "learning_rate": 9.638293035120342e-06,
      "loss": 0.5287,
      "step": 130
    },
    {
      "epoch": 1.3609756097560974,
      "grad_norm": 1.4838457107543945,
      "learning_rate": 9.524135262330098e-06,
      "loss": 0.5411,
      "step": 140
    },
    {
      "epoch": 1.4585365853658536,
      "grad_norm": 1.41899836063385,
      "learning_rate": 9.395220700665924e-06,
      "loss": 0.5023,
      "step": 150
    },
    {
      "epoch": 1.5560975609756098,
      "grad_norm": 1.7997419834136963,
      "learning_rate": 9.251969842632785e-06,
      "loss": 0.5487,
      "step": 160
    },
    {
      "epoch": 1.653658536585366,
      "grad_norm": 1.1504219770431519,
      "learning_rate": 9.094849942754564e-06,
      "loss": 0.491,
      "step": 170
    },
    {
      "epoch": 1.751219512195122,
      "grad_norm": 1.4111475944519043,
      "learning_rate": 8.924373493486941e-06,
      "loss": 0.4901,
      "step": 180
    },
    {
      "epoch": 1.848780487804878,
      "grad_norm": 1.6067090034484863,
      "learning_rate": 8.741096553573506e-06,
      "loss": 0.5439,
      "step": 190
    },
    {
      "epoch": 1.946341463414634,
      "grad_norm": 1.2158631086349487,
      "learning_rate": 8.545616934297733e-06,
      "loss": 0.5212,
      "step": 200
    },
    {
      "epoch": 2.0390243902439025,
      "grad_norm": 1.3324558734893799,
      "learning_rate": 8.338572249546813e-06,
      "loss": 0.49,
      "step": 210
    },
    {
      "epoch": 2.1365853658536587,
      "grad_norm": 1.4280637502670288,
      "learning_rate": 8.120637836047698e-06,
      "loss": 0.4122,
      "step": 220
    },
    {
      "epoch": 2.234146341463415,
      "grad_norm": 1.0540653467178345,
      "learning_rate": 7.892524550559056e-06,
      "loss": 0.3693,
      "step": 230
    },
    {
      "epoch": 2.3317073170731706,
      "grad_norm": 1.2099759578704834,
      "learning_rate": 7.654976451204288e-06,
      "loss": 0.3851,
      "step": 240
    },
    {
      "epoch": 2.4292682926829268,
      "grad_norm": 1.056799292564392,
      "learning_rate": 7.408768370508577e-06,
      "loss": 0.377,
      "step": 250
    },
    {
      "epoch": 2.526829268292683,
      "grad_norm": 1.4203627109527588,
      "learning_rate": 7.154703388056246e-06,
      "loss": 0.3864,
      "step": 260
    },
    {
      "epoch": 2.624390243902439,
      "grad_norm": 0.9842203259468079,
      "learning_rate": 6.893610211012067e-06,
      "loss": 0.3881,
      "step": 270
    },
    {
      "epoch": 2.721951219512195,
      "grad_norm": 0.9598954916000366,
      "learning_rate": 6.6263404710507495e-06,
      "loss": 0.4051,
      "step": 280
    },
    {
      "epoch": 2.819512195121951,
      "grad_norm": 1.2445122003555298,
      "learning_rate": 6.3537659465114275e-06,
      "loss": 0.4061,
      "step": 290
    },
    {
      "epoch": 2.9170731707317072,
      "grad_norm": 1.1891133785247803,
      "learning_rate": 6.076775718837911e-06,
      "loss": 0.3537,
      "step": 300
    },
    {
      "epoch": 3.0097560975609756,
      "grad_norm": 1.345109224319458,
      "learning_rate": 5.796273272579823e-06,
      "loss": 0.3309,
      "step": 310
    },
    {
      "epoch": 3.107317073170732,
      "grad_norm": 0.9590056538581848,
      "learning_rate": 5.513173548413789e-06,
      "loss": 0.2277,
      "step": 320
    },
    {
      "epoch": 3.204878048780488,
      "grad_norm": 1.3723112344741821,
      "learning_rate": 5.228399958797117e-06,
      "loss": 0.2754,
      "step": 330
    },
    {
      "epoch": 3.3024390243902437,
      "grad_norm": 1.052578091621399,
      "learning_rate": 4.9428813759883e-06,
      "loss": 0.2226,
      "step": 340
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.3540409803390503,
      "learning_rate": 4.6575491022587714e-06,
      "loss": 0.3032,
      "step": 350
    },
    {
      "epoch": 3.497560975609756,
      "grad_norm": 0.979840099811554,
      "learning_rate": 4.373333832178478e-06,
      "loss": 0.2326,
      "step": 360
    },
    {
      "epoch": 3.5951219512195123,
      "grad_norm": 1.1373505592346191,
      "learning_rate": 4.091162616883634e-06,
      "loss": 0.3115,
      "step": 370
    },
    {
      "epoch": 3.692682926829268,
      "grad_norm": 1.0093439817428589,
      "learning_rate": 3.8119558402285994e-06,
      "loss": 0.2202,
      "step": 380
    },
    {
      "epoch": 3.790243902439024,
      "grad_norm": 1.2901158332824707,
      "learning_rate": 3.5366242166850624e-06,
      "loss": 0.2969,
      "step": 390
    },
    {
      "epoch": 3.8878048780487804,
      "grad_norm": 0.9081848859786987,
      "learning_rate": 3.2660658207807205e-06,
      "loss": 0.237,
      "step": 400
    },
    {
      "epoch": 3.9853658536585366,
      "grad_norm": 1.0115485191345215,
      "learning_rate": 3.0011631577668327e-06,
      "loss": 0.2668,
      "step": 410
    },
    {
      "epoch": 4.078048780487805,
      "grad_norm": 1.3101578950881958,
      "learning_rate": 2.7427802850695306e-06,
      "loss": 0.1837,
      "step": 420
    },
    {
      "epoch": 4.175609756097561,
      "grad_norm": 1.2633917331695557,
      "learning_rate": 2.4917599939140884e-06,
      "loss": 0.196,
      "step": 430
    },
    {
      "epoch": 4.273170731707317,
      "grad_norm": 0.7994241714477539,
      "learning_rate": 2.2489210603151144e-06,
      "loss": 0.1483,
      "step": 440
    },
    {
      "epoch": 4.3707317073170735,
      "grad_norm": 1.1350624561309814,
      "learning_rate": 2.015055574399388e-06,
      "loss": 0.1495,
      "step": 450
    },
    {
      "epoch": 4.46829268292683,
      "grad_norm": 1.1117892265319824,
      "learning_rate": 1.7909263567724917e-06,
      "loss": 0.1489,
      "step": 460
    },
    {
      "epoch": 4.565853658536585,
      "grad_norm": 0.9958974719047546,
      "learning_rate": 1.5772644703565564e-06,
      "loss": 0.1702,
      "step": 470
    },
    {
      "epoch": 4.663414634146341,
      "grad_norm": 1.1438698768615723,
      "learning_rate": 1.3747668358149658e-06,
      "loss": 0.1774,
      "step": 480
    },
    {
      "epoch": 4.760975609756097,
      "grad_norm": 0.9679899215698242,
      "learning_rate": 1.1840939583419986e-06,
      "loss": 0.1462,
      "step": 490
    },
    {
      "epoch": 4.8585365853658535,
      "grad_norm": 1.017114520072937,
      "learning_rate": 1.0058677732321826e-06,
      "loss": 0.1865,
      "step": 500
    },
    {
      "epoch": 4.95609756097561,
      "grad_norm": 1.2413111925125122,
      "learning_rate": 8.406696172566258e-07,
      "loss": 0.1795,
      "step": 510
    },
    {
      "epoch": 5.048780487804878,
      "grad_norm": 0.7522889971733093,
      "learning_rate": 6.890383324633121e-07,
      "loss": 0.157,
      "step": 520
    },
    {
      "epoch": 5.146341463414634,
      "grad_norm": 0.9641028046607971,
      "learning_rate": 5.514685085863286e-07,
      "loss": 0.1632,
      "step": 530
    },
    {
      "epoch": 5.2439024390243905,
      "grad_norm": 1.0888645648956299,
      "learning_rate": 4.2840886979696074e-07,
      "loss": 0.1269,
      "step": 540
    },
    {
      "epoch": 5.341463414634147,
      "grad_norm": 0.7203080058097839,
      "learning_rate": 3.2026081105871634e-07,
      "loss": 0.1096,
      "step": 550
    },
    {
      "epoch": 5.439024390243903,
      "grad_norm": 1.3017480373382568,
      "learning_rate": 2.2737708886037823e-07,
      "loss": 0.1133,
      "step": 560
    },
    {
      "epoch": 5.536585365853659,
      "grad_norm": 0.9247483015060425,
      "learning_rate": 1.5006067059766484e-07,
      "loss": 0.1188,
      "step": 570
    },
    {
      "epoch": 5.634146341463414,
      "grad_norm": 0.8894818425178528,
      "learning_rate": 8.856374635655696e-08,
      "loss": 0.1069,
      "step": 580
    },
    {
      "epoch": 5.7317073170731705,
      "grad_norm": 0.981769323348999,
      "learning_rate": 4.3086906321652136e-08,
      "loss": 0.0943,
      "step": 590
    },
    {
      "epoch": 5.829268292682927,
      "grad_norm": 0.441194087266922,
      "learning_rate": 1.3778486492681542e-08,
      "loss": 0.1061,
      "step": 600
    },
    {
      "epoch": 5.926829268292683,
      "grad_norm": 0.8621994256973267,
      "learning_rate": 7.340848433040615e-10,
      "loss": 0.1294,
      "step": 610
    },
    {
      "epoch": 5.946341463414634,
      "step": 612,
      "total_flos": 66516718592000.0,
      "train_loss": 0.3622722171880061,
      "train_runtime": 10104.8075,
      "train_samples_per_second": 0.485,
      "train_steps_per_second": 0.061
    }
  ],
  "logging_steps": 10,
  "max_steps": 612,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 66516718592000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}