{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 16,
  "global_step": 84,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 1.8297373056411743,
      "learning_rate": 0.0,
      "loss": 1.5186,
      "step": 1
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 1.4678523540496826,
      "learning_rate": 2e-05,
      "loss": 1.418,
      "step": 2
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 1.0438460111618042,
      "learning_rate": 4e-05,
      "loss": 1.2285,
      "step": 3
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.742932140827179,
      "learning_rate": 6e-05,
      "loss": 1.2422,
      "step": 4
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.4183550775051117,
      "learning_rate": 8e-05,
      "loss": 1.2275,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.12873150408267975,
      "learning_rate": 0.0001,
      "loss": 1.1387,
      "step": 6
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.17560885846614838,
      "learning_rate": 9.996442287522857e-05,
      "loss": 1.0962,
      "step": 7
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.18623290956020355,
      "learning_rate": 9.985774775566131e-05,
      "loss": 1.0532,
      "step": 8
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.1544376015663147,
      "learning_rate": 9.96801433165888e-05,
      "loss": 1.0806,
      "step": 9
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.10102612525224686,
      "learning_rate": 9.943189038713501e-05,
      "loss": 1.0811,
      "step": 10
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 0.09069132059812546,
      "learning_rate": 9.911338150620863e-05,
      "loss": 1.0449,
      "step": 11
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.08455435931682587,
      "learning_rate": 9.872512030181845e-05,
      "loss": 1.0342,
      "step": 12
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 0.0736464411020279,
      "learning_rate": 9.826772069473393e-05,
      "loss": 1.0332,
      "step": 13
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.07477279007434845,
      "learning_rate": 9.774190592775023e-05,
      "loss": 1.0386,
      "step": 14
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.08049094676971436,
      "learning_rate": 9.714850742209276e-05,
      "loss": 0.9907,
      "step": 15
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.0877717137336731,
      "learning_rate": 9.648846346276929e-05,
      "loss": 1.0596,
      "step": 16
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 0.07514107972383499,
      "learning_rate": 9.576281771494855e-05,
      "loss": 0.9673,
      "step": 17
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.062063198536634445,
      "learning_rate": 9.497271757371094e-05,
      "loss": 0.9551,
      "step": 18
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 0.07104654610157013,
      "learning_rate": 9.411941234978122e-05,
      "loss": 0.9761,
      "step": 19
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.06187346205115318,
      "learning_rate": 9.320425129411139e-05,
      "loss": 0.9277,
      "step": 20
    },
    {
      "epoch": 0.23809523809523808,
      "eval_loss": 0.96728515625,
      "eval_runtime": 2.1916,
      "eval_samples_per_second": 3.194,
      "eval_steps_per_second": 0.456,
      "step": 20
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.05663936585187912,
      "learning_rate": 9.222868146443759e-05,
      "loss": 0.9604,
      "step": 21
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.05731222778558731,
      "learning_rate": 9.119424543718442e-05,
      "loss": 0.9243,
      "step": 22
    },
    {
      "epoch": 0.27380952380952384,
      "grad_norm": 0.05133267119526863,
      "learning_rate": 9.010257886833456e-05,
      "loss": 0.9751,
      "step": 23
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.04777716472744942,
      "learning_rate": 8.895540790712036e-05,
      "loss": 0.9746,
      "step": 24
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.045849982649087906,
      "learning_rate": 8.775454646662724e-05,
      "loss": 0.9517,
      "step": 25
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.04803798347711563,
      "learning_rate": 8.650189335562414e-05,
      "loss": 0.9429,
      "step": 26
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.044138673692941666,
      "learning_rate": 8.519942927615666e-05,
      "loss": 0.9141,
      "step": 27
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.04704608768224716,
      "learning_rate": 8.384921369164991e-05,
      "loss": 0.9238,
      "step": 28
    },
    {
      "epoch": 0.34523809523809523,
      "grad_norm": 0.048233769834041595,
      "learning_rate": 8.24533815704736e-05,
      "loss": 0.8965,
      "step": 29
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.04642269015312195,
      "learning_rate": 8.101414001011817e-05,
      "loss": 0.9116,
      "step": 30
    },
    {
      "epoch": 0.36904761904761907,
      "grad_norm": 0.0460088811814785,
      "learning_rate": 7.953376474732003e-05,
      "loss": 0.9565,
      "step": 31
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.046662453562021255,
      "learning_rate": 7.801459655965401e-05,
      "loss": 0.9019,
      "step": 32
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.039389073848724365,
      "learning_rate": 7.645903756428279e-05,
      "loss": 0.9131,
      "step": 33
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.04949357360601425,
      "learning_rate": 7.486954741971603e-05,
      "loss": 0.9282,
      "step": 34
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.04726392403244972,
      "learning_rate": 7.324863943658474e-05,
      "loss": 0.8413,
      "step": 35
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.039772726595401764,
      "learning_rate": 7.159887660358036e-05,
      "loss": 0.918,
      "step": 36
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 0.9139404296875,
      "eval_runtime": 2.2237,
      "eval_samples_per_second": 3.148,
      "eval_steps_per_second": 0.45,
      "step": 36
    },
    {
      "epoch": 0.44047619047619047,
      "grad_norm": 0.043901924043893814,
      "learning_rate": 6.992286753484306e-05,
      "loss": 0.8901,
      "step": 37
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.042629700154066086,
      "learning_rate": 6.822326234520645e-05,
      "loss": 0.895,
      "step": 38
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.04164420813322067,
      "learning_rate": 6.650274845982136e-05,
      "loss": 0.9111,
      "step": 39
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.04184504970908165,
      "learning_rate": 6.476404636478432e-05,
      "loss": 0.9346,
      "step": 40
    },
    {
      "epoch": 0.4880952380952381,
      "grad_norm": 0.04184267669916153,
      "learning_rate": 6.300990530548979e-05,
      "loss": 0.9438,
      "step": 41
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.04311750829219818,
      "learning_rate": 6.124309893950809e-05,
      "loss": 0.8452,
      "step": 42
    },
    {
      "epoch": 0.5119047619047619,
      "grad_norm": 0.04182306304574013,
      "learning_rate": 5.946642095086278e-05,
      "loss": 0.9224,
      "step": 43
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.04190509393811226,
      "learning_rate": 5.7682680632641896e-05,
      "loss": 0.8579,
      "step": 44
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.04373576119542122,
      "learning_rate": 5.589469844492816e-05,
      "loss": 0.8521,
      "step": 45
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.04035841301083565,
      "learning_rate": 5.410530155507184e-05,
      "loss": 0.8486,
      "step": 46
    },
    {
      "epoch": 0.5595238095238095,
      "grad_norm": 0.039293766021728516,
      "learning_rate": 5.231731936735811e-05,
      "loss": 0.8433,
      "step": 47
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.04082417115569115,
      "learning_rate": 5.053357904913724e-05,
      "loss": 0.8843,
      "step": 48
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.03880985453724861,
      "learning_rate": 4.875690106049193e-05,
      "loss": 0.8705,
      "step": 49
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.03803550451993942,
      "learning_rate": 4.6990094694510245e-05,
      "loss": 0.9028,
      "step": 50
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.041803404688835144,
      "learning_rate": 4.5235953635215686e-05,
      "loss": 0.9111,
      "step": 51
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.0422697439789772,
      "learning_rate": 4.349725154017864e-05,
      "loss": 1.0361,
      "step": 52
    },
    {
      "epoch": 0.6190476190476191,
      "eval_loss": 0.8909912109375,
      "eval_runtime": 2.2014,
      "eval_samples_per_second": 3.18,
      "eval_steps_per_second": 0.454,
      "step": 52
    },
    {
      "epoch": 0.6309523809523809,
      "grad_norm": 0.04307297617197037,
      "learning_rate": 4.177673765479357e-05,
      "loss": 0.8306,
      "step": 53
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.04303174093365669,
      "learning_rate": 4.007713246515695e-05,
      "loss": 0.8286,
      "step": 54
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 0.04310578480362892,
      "learning_rate": 3.8401123396419656e-05,
      "loss": 0.8804,
      "step": 55
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.04220642149448395,
      "learning_rate": 3.675136056341528e-05,
      "loss": 0.8823,
      "step": 56
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.040107909590005875,
      "learning_rate": 3.513045258028399e-05,
      "loss": 0.8765,
      "step": 57
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 0.0407722108066082,
      "learning_rate": 3.354096243571724e-05,
      "loss": 0.8794,
      "step": 58
    },
    {
      "epoch": 0.7023809523809523,
      "grad_norm": 0.03676525130867958,
      "learning_rate": 3.1985403440346004e-05,
      "loss": 0.8931,
      "step": 59
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.0536477155983448,
      "learning_rate": 3.0466235252679976e-05,
      "loss": 0.8384,
      "step": 60
    },
    {
      "epoch": 0.7261904761904762,
      "grad_norm": 0.04375791177153587,
      "learning_rate": 2.898585998988182e-05,
      "loss": 0.8291,
      "step": 61
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 0.044466741383075714,
      "learning_rate": 2.7546618429526404e-05,
      "loss": 0.8633,
      "step": 62
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.03879433125257492,
      "learning_rate": 2.6150786308350112e-05,
      "loss": 0.8804,
      "step": 63
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.040222495794296265,
      "learning_rate": 2.480057072384334e-05,
      "loss": 0.9189,
      "step": 64
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 0.041920360177755356,
      "learning_rate": 2.3498106644375867e-05,
      "loss": 0.8818,
      "step": 65
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.0415637381374836,
      "learning_rate": 2.2245453533372768e-05,
      "loss": 0.813,
      "step": 66
    },
    {
      "epoch": 0.7976190476190477,
      "grad_norm": 0.04325433075428009,
      "learning_rate": 2.1044592092879643e-05,
      "loss": 0.8223,
      "step": 67
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.04423648864030838,
      "learning_rate": 1.9897421131665462e-05,
      "loss": 0.8062,
      "step": 68
    },
    {
      "epoch": 0.8095238095238095,
      "eval_loss": 0.8812255859375,
      "eval_runtime": 2.2121,
      "eval_samples_per_second": 3.164,
      "eval_steps_per_second": 0.452,
      "step": 68
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.039397336542606354,
      "learning_rate": 1.8805754562815585e-05,
      "loss": 0.8755,
      "step": 69
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.040991201996803284,
      "learning_rate": 1.7771318535562435e-05,
      "loss": 0.8965,
      "step": 70
    },
    {
      "epoch": 0.8452380952380952,
      "grad_norm": 0.044761158525943756,
      "learning_rate": 1.679574870588862e-05,
      "loss": 0.8242,
      "step": 71
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.04137815907597542,
      "learning_rate": 1.588058765021879e-05,
      "loss": 0.8257,
      "step": 72
    },
    {
      "epoch": 0.8690476190476191,
      "grad_norm": 0.04023851081728935,
      "learning_rate": 1.5027282426289077e-05,
      "loss": 0.8477,
      "step": 73
    },
    {
      "epoch": 0.8809523809523809,
      "grad_norm": 0.0424995981156826,
      "learning_rate": 1.4237182285051453e-05,
      "loss": 0.8237,
      "step": 74
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.040652044117450714,
      "learning_rate": 1.3511536537230707e-05,
      "loss": 0.8911,
      "step": 75
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.04382263123989105,
      "learning_rate": 1.2851492577907251e-05,
      "loss": 0.8218,
      "step": 76
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.04112011939287186,
      "learning_rate": 1.225809407224978e-05,
      "loss": 0.8481,
      "step": 77
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.039530232548713684,
      "learning_rate": 1.1732279305266082e-05,
      "loss": 0.8555,
      "step": 78
    },
    {
      "epoch": 0.9404761904761905,
      "grad_norm": 0.04221143573522568,
      "learning_rate": 1.1274879698181547e-05,
      "loss": 0.8223,
      "step": 79
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.03821280598640442,
      "learning_rate": 1.0886618493791376e-05,
      "loss": 0.8403,
      "step": 80
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.0420861579477787,
      "learning_rate": 1.0568109612865e-05,
      "loss": 0.7808,
      "step": 81
    },
    {
      "epoch": 0.9761904761904762,
      "grad_norm": 0.03845471143722534,
      "learning_rate": 1.0319856683411197e-05,
      "loss": 0.8726,
      "step": 82
    },
    {
      "epoch": 0.9880952380952381,
      "grad_norm": 0.04941664636135101,
      "learning_rate": 1.0142252244338688e-05,
      "loss": 0.8208,
      "step": 83
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04132900387048721,
      "learning_rate": 1.0035577124771419e-05,
      "loss": 0.8257,
      "step": 84
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8758544921875,
      "eval_runtime": 2.2462,
      "eval_samples_per_second": 3.116,
      "eval_steps_per_second": 0.445,
      "step": 84
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 84,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.150868985823887e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}