{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 1000,
  "global_step": 3180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047175374454534735,
      "grad_norm": 0.6658920049667358,
      "learning_rate": 2.0545073375262055e-06,
      "loss": 0.7831,
      "step": 50
    },
    {
      "epoch": 0.09435074890906947,
      "grad_norm": 0.6541114449501038,
      "learning_rate": 4.150943396226416e-06,
      "loss": 0.6891,
      "step": 100
    },
    {
      "epoch": 0.1415261233636042,
      "grad_norm": 0.64142906665802,
      "learning_rate": 6.247379454926625e-06,
      "loss": 0.6727,
      "step": 150
    },
    {
      "epoch": 0.18870149781813894,
      "grad_norm": 0.645492434501648,
      "learning_rate": 8.343815513626834e-06,
      "loss": 0.6608,
      "step": 200
    },
    {
      "epoch": 0.23587687227267368,
      "grad_norm": 0.6750236749649048,
      "learning_rate": 1.0440251572327045e-05,
      "loss": 0.6656,
      "step": 250
    },
    {
      "epoch": 0.2830522467272084,
      "grad_norm": 0.6192681789398193,
      "learning_rate": 1.2536687631027256e-05,
      "loss": 0.6613,
      "step": 300
    },
    {
      "epoch": 0.33022762118174315,
      "grad_norm": 0.6124400496482849,
      "learning_rate": 1.4633123689727464e-05,
      "loss": 0.6612,
      "step": 350
    },
    {
      "epoch": 0.3774029956362779,
      "grad_norm": 0.5999819040298462,
      "learning_rate": 1.6729559748427675e-05,
      "loss": 0.6587,
      "step": 400
    },
    {
      "epoch": 0.4245783700908126,
      "grad_norm": 0.6131274104118347,
      "learning_rate": 1.8825995807127882e-05,
      "loss": 0.6613,
      "step": 450
    },
    {
      "epoch": 0.47175374454534735,
      "grad_norm": 0.5893041491508484,
      "learning_rate": 1.9996731117142877e-05,
      "loss": 0.6615,
      "step": 500
    },
    {
      "epoch": 0.518929118999882,
      "grad_norm": 0.546073853969574,
      "learning_rate": 1.996500635384337e-05,
      "loss": 0.6598,
      "step": 550
    },
    {
      "epoch": 0.5661044934544168,
      "grad_norm": 0.5713281035423279,
      "learning_rate": 1.9899637947477248e-05,
      "loss": 0.6586,
      "step": 600
    },
    {
      "epoch": 0.6132798679089515,
      "grad_norm": 0.5555443167686462,
      "learning_rate": 1.9800846593471427e-05,
      "loss": 0.6602,
      "step": 650
    },
    {
      "epoch": 0.6604552423634863,
      "grad_norm": 0.5415436625480652,
      "learning_rate": 1.966896582909968e-05,
      "loss": 0.6577,
      "step": 700
    },
    {
      "epoch": 0.707630616818021,
      "grad_norm": 0.5836868286132812,
      "learning_rate": 1.9504440907401113e-05,
      "loss": 0.6544,
      "step": 750
    },
    {
      "epoch": 0.7548059912725558,
      "grad_norm": 0.539230465888977,
      "learning_rate": 1.9307827293926344e-05,
      "loss": 0.6577,
      "step": 800
    },
    {
      "epoch": 0.8019813657270904,
      "grad_norm": 0.5532299280166626,
      "learning_rate": 1.9079788791386468e-05,
      "loss": 0.6569,
      "step": 850
    },
    {
      "epoch": 0.8491567401816252,
      "grad_norm": 0.5102491974830627,
      "learning_rate": 1.8821095298536435e-05,
      "loss": 0.6502,
      "step": 900
    },
    {
      "epoch": 0.8963321146361599,
      "grad_norm": 0.5178349614143372,
      "learning_rate": 1.853262021085921e-05,
      "loss": 0.6559,
      "step": 950
    },
    {
      "epoch": 0.9435074890906947,
      "grad_norm": 0.5248669385910034,
      "learning_rate": 1.821533747182645e-05,
      "loss": 0.6549,
      "step": 1000
    },
    {
      "epoch": 0.9435074890906947,
      "eval_loss": 0.6482675671577454,
      "eval_runtime": 113.518,
      "eval_samples_per_second": 66.395,
      "eval_steps_per_second": 2.079,
      "step": 1000
    },
    {
      "epoch": 0.9906828635452294,
      "grad_norm": 0.5705227255821228,
      "learning_rate": 1.787031828469124e-05,
      "loss": 0.6477,
      "step": 1050
    },
    {
      "epoch": 1.0377402995636278,
      "grad_norm": 0.5323419570922852,
      "learning_rate": 1.7498727495914378e-05,
      "loss": 0.5975,
      "step": 1100
    },
    {
      "epoch": 1.0849156740181625,
      "grad_norm": 0.5340594053268433,
      "learning_rate": 1.710181966243447e-05,
      "loss": 0.5819,
      "step": 1150
    },
    {
      "epoch": 1.1320910484726974,
      "grad_norm": 0.49585267901420593,
      "learning_rate": 1.6680934816059403e-05,
      "loss": 0.5819,
      "step": 1200
    },
    {
      "epoch": 1.179266422927232,
      "grad_norm": 0.500704824924469,
      "learning_rate": 1.623749393927938e-05,
      "loss": 0.5853,
      "step": 1250
    },
    {
      "epoch": 1.2264417973817667,
      "grad_norm": 0.49850329756736755,
      "learning_rate": 1.5772994167775986e-05,
      "loss": 0.5844,
      "step": 1300
    },
    {
      "epoch": 1.2736171718363014,
      "grad_norm": 0.5016334652900696,
      "learning_rate": 1.5289003735824454e-05,
      "loss": 0.5866,
      "step": 1350
    },
    {
      "epoch": 1.320792546290836,
      "grad_norm": 0.5468031764030457,
      "learning_rate": 1.4787156681654358e-05,
      "loss": 0.5819,
      "step": 1400
    },
    {
      "epoch": 1.367967920745371,
      "grad_norm": 0.5233626961708069,
      "learning_rate": 1.426914733064444e-05,
      "loss": 0.5849,
      "step": 1450
    },
    {
      "epoch": 1.4151432951999057,
      "grad_norm": 0.5027523040771484,
      "learning_rate": 1.373672457497717e-05,
      "loss": 0.5844,
      "step": 1500
    },
    {
      "epoch": 1.4623186696544404,
      "grad_norm": 0.5051872730255127,
      "learning_rate": 1.3191685969066082e-05,
      "loss": 0.5846,
      "step": 1550
    },
    {
      "epoch": 1.5094940441089753,
      "grad_norm": 0.5215147733688354,
      "learning_rate": 1.2635871660690677e-05,
      "loss": 0.5829,
      "step": 1600
    },
    {
      "epoch": 1.55666941856351,
      "grad_norm": 0.5042491555213928,
      "learning_rate": 1.2071158178328547e-05,
      "loss": 0.5854,
      "step": 1650
    },
    {
      "epoch": 1.6038447930180446,
      "grad_norm": 0.5223520994186401,
      "learning_rate": 1.1499452095659713e-05,
      "loss": 0.5833,
      "step": 1700
    },
    {
      "epoch": 1.6510201674725793,
      "grad_norm": 0.4980650246143341,
      "learning_rate": 1.092268359463302e-05,
      "loss": 0.5808,
      "step": 1750
    },
    {
      "epoch": 1.698195541927114,
      "grad_norm": 0.5121437907218933,
      "learning_rate": 1.0342799948826788e-05,
      "loss": 0.5823,
      "step": 1800
    },
    {
      "epoch": 1.7453709163816487,
      "grad_norm": 0.4902792274951935,
      "learning_rate": 9.761758949105056e-06,
      "loss": 0.5824,
      "step": 1850
    },
    {
      "epoch": 1.7925462908361836,
      "grad_norm": 0.4946081042289734,
      "learning_rate": 9.18152229376561e-06,
      "loss": 0.5814,
      "step": 1900
    },
    {
      "epoch": 1.8397216652907182,
      "grad_norm": 0.5029374361038208,
      "learning_rate": 8.604048965495786e-06,
      "loss": 0.5795,
      "step": 1950
    },
    {
      "epoch": 1.8868970397452531,
      "grad_norm": 0.47936609387397766,
      "learning_rate": 8.031288617496686e-06,
      "loss": 0.5796,
      "step": 2000
    },
    {
      "epoch": 1.8868970397452531,
      "eval_loss": 0.6402788162231445,
      "eval_runtime": 113.5077,
      "eval_samples_per_second": 66.401,
      "eval_steps_per_second": 2.079,
      "step": 2000
    },
    {
      "epoch": 1.9340724141997878,
      "grad_norm": 0.5165300369262695,
      "learning_rate": 7.465174991105405e-06,
      "loss": 0.5762,
      "step": 2050
    },
    {
      "epoch": 1.9812477886543225,
      "grad_norm": 0.49469050765037537,
      "learning_rate": 6.90761938713854e-06,
      "loss": 0.5747,
      "step": 2100
    },
    {
      "epoch": 2.028305224672721,
      "grad_norm": 0.5297324061393738,
      "learning_rate": 6.360504212998903e-06,
      "loss": 0.5171,
      "step": 2150
    },
    {
      "epoch": 2.0754805991272556,
      "grad_norm": 0.5692960023880005,
      "learning_rate": 5.825676627331614e-06,
      "loss": 0.471,
      "step": 2200
    },
    {
      "epoch": 2.1226559735817903,
      "grad_norm": 0.5705838799476624,
      "learning_rate": 5.304942303686238e-06,
      "loss": 0.4737,
      "step": 2250
    },
    {
      "epoch": 2.169831348036325,
      "grad_norm": 0.5800350308418274,
      "learning_rate": 4.800059334240049e-06,
      "loss": 0.4734,
      "step": 2300
    },
    {
      "epoch": 2.2170067224908596,
      "grad_norm": 0.5653440952301025,
      "learning_rate": 4.3127322941645385e-06,
      "loss": 0.4713,
      "step": 2350
    },
    {
      "epoch": 2.2641820969453947,
      "grad_norm": 0.5822903513908386,
      "learning_rate": 3.844606486674862e-06,
      "loss": 0.4715,
      "step": 2400
    },
    {
      "epoch": 2.3113574713999294,
      "grad_norm": 0.599399209022522,
      "learning_rate": 3.3972623881920296e-06,
      "loss": 0.47,
      "step": 2450
    },
    {
      "epoch": 2.358532845854464,
      "grad_norm": 0.5810734033584595,
      "learning_rate": 2.9722103123719324e-06,
      "loss": 0.4661,
      "step": 2500
    },
    {
      "epoch": 2.405708220308999,
      "grad_norm": 0.5994310975074768,
      "learning_rate": 2.5708853110164346e-06,
      "loss": 0.4686,
      "step": 2550
    },
    {
      "epoch": 2.4528835947635335,
      "grad_norm": 0.577089786529541,
      "learning_rate": 2.194642329081902e-06,
      "loss": 0.4673,
      "step": 2600
    },
    {
      "epoch": 2.500058969218068,
      "grad_norm": 0.578800618648529,
      "learning_rate": 1.844751630142797e-06,
      "loss": 0.4664,
      "step": 2650
    },
    {
      "epoch": 2.547234343672603,
      "grad_norm": 0.5981403589248657,
      "learning_rate": 1.5223945077547253e-06,
      "loss": 0.4686,
      "step": 2700
    },
    {
      "epoch": 2.5944097181271375,
      "grad_norm": 0.6022927165031433,
      "learning_rate": 1.2286592971962152e-06,
      "loss": 0.4676,
      "step": 2750
    },
    {
      "epoch": 2.641585092581672,
      "grad_norm": 0.5744144916534424,
      "learning_rate": 9.645377010542212e-07,
      "loss": 0.4684,
      "step": 2800
    },
    {
      "epoch": 2.6887604670362073,
      "grad_norm": 0.5747597813606262,
      "learning_rate": 7.309214410588927e-07,
      "loss": 0.4632,
      "step": 2850
    },
    {
      "epoch": 2.735935841490742,
      "grad_norm": 0.5752475261688232,
      "learning_rate": 5.285992474715796e-07,
      "loss": 0.4643,
      "step": 2900
    },
    {
      "epoch": 2.7831112159452767,
      "grad_norm": 0.5861772894859314,
      "learning_rate": 3.5825419619046176e-07,
      "loss": 0.465,
      "step": 2950
    },
    {
      "epoch": 2.8302865903998113,
      "grad_norm": 0.5940195918083191,
      "learning_rate": 2.2046140256418713e-07,
      "loss": 0.4646,
      "step": 3000
    },
    {
      "epoch": 2.8302865903998113,
      "eval_loss": 0.6850141286849976,
      "eval_runtime": 113.5772,
      "eval_samples_per_second": 66.36,
      "eval_steps_per_second": 2.078,
      "step": 3000
    },
    {
      "epoch": 2.877461964854346,
      "grad_norm": 0.5916756987571716,
      "learning_rate": 1.1568607969963175e-07,
      "loss": 0.4644,
      "step": 3050
    },
    {
      "epoch": 2.9246373393088807,
      "grad_norm": 0.5982924103736877,
      "learning_rate": 4.42819678192774e-08,
      "loss": 0.4691,
      "step": 3100
    },
    {
      "epoch": 2.9718127137634154,
      "grad_norm": 0.5770459175109863,
      "learning_rate": 6.490139970976029e-09,
      "loss": 0.4661,
      "step": 3150
    },
    {
      "epoch": 3.0,
      "step": 3180,
      "total_flos": 1.7575386520355865e+19,
      "train_loss": 0.5721450322828953,
      "train_runtime": 14690.2311,
      "train_samples_per_second": 13.852,
      "train_steps_per_second": 0.216
    }
  ],
  "logging_steps": 50,
  "max_steps": 3180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7575386520355865e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}