{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002,
      "grad_norm": 5.551233768463135,
      "learning_rate": 0.0,
      "loss": 43.93932342529297,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.35080099105835,
      "learning_rate": 2.94e-05,
      "loss": 43.64981764190051,
      "step": 50
    },
    {
      "epoch": 0.02,
      "grad_norm": 5.6910929679870605,
      "learning_rate": 5.94e-05,
      "loss": 40.47484375,
      "step": 100
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.369699954986572,
      "learning_rate": 8.939999999999999e-05,
      "loss": 37.00744873046875,
      "step": 150
    },
    {
      "epoch": 0.04,
      "grad_norm": 4.0027079582214355,
      "learning_rate": 0.0001194,
      "loss": 33.13272216796875,
      "step": 200
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.570080041885376,
      "learning_rate": 0.0001494,
      "loss": 30.27530517578125,
      "step": 250
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.417503595352173,
      "learning_rate": 0.00017939999999999997,
      "loss": 29.3436669921875,
      "step": 300
    },
    {
      "epoch": 0.07,
      "grad_norm": 3.3700530529022217,
      "learning_rate": 0.00020939999999999997,
      "loss": 28.82450927734375,
      "step": 350
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.179579496383667,
      "learning_rate": 0.0002394,
      "loss": 28.15291015625,
      "step": 400
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.0590453147888184,
      "learning_rate": 0.0002694,
      "loss": 27.42884521484375,
      "step": 450
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.864997625350952,
      "learning_rate": 0.00029939999999999996,
      "loss": 27.338408203125,
      "step": 500
    },
    {
      "epoch": 0.11,
      "grad_norm": 2.719647169113159,
      "learning_rate": 0.00029991224218749483,
      "loss": 27.45952880859375,
      "step": 550
    },
    {
      "epoch": 0.12,
      "grad_norm": 3.106184720993042,
      "learning_rate": 0.00029964187595418377,
      "loss": 26.478095703125,
      "step": 600
    },
    {
      "epoch": 0.13,
      "grad_norm": 2.9786314964294434,
      "learning_rate": 0.0002991891941455865,
      "loss": 26.3969140625,
      "step": 650
    },
    {
      "epoch": 0.14,
      "grad_norm": 3.4186649322509766,
      "learning_rate": 0.0002985547482847564,
      "loss": 26.35082763671875,
      "step": 700
    },
    {
      "epoch": 0.15,
      "grad_norm": 3.016622304916382,
      "learning_rate": 0.00029773931134624614,
      "loss": 26.2290625,
      "step": 750
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.8012444972991943,
      "learning_rate": 0.0002967438768143568,
      "loss": 25.8839404296875,
      "step": 800
    },
    {
      "epoch": 0.17,
      "grad_norm": 3.0996336936950684,
      "learning_rate": 0.0002955696574727306,
      "loss": 25.84023681640625,
      "step": 850
    },
    {
      "epoch": 0.18,
      "grad_norm": 3.161088705062866,
      "learning_rate": 0.0002942180839267606,
      "loss": 25.78875732421875,
      "step": 900
    },
    {
      "epoch": 0.19,
      "grad_norm": 3.0394628047943115,
      "learning_rate": 0.00029269080286061866,
      "loss": 25.57990966796875,
      "step": 950
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.1691832542419434,
      "learning_rate": 0.0002909896750310243,
      "loss": 25.3314111328125,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "grad_norm": 3.3732755184173584,
      "learning_rate": 0.0002891167730001992,
      "loss": 25.2071630859375,
      "step": 1050
    },
    {
      "epoch": 0.22,
      "grad_norm": 3.613858461380005,
      "learning_rate": 0.00028707437861076943,
      "loss": 25.27132080078125,
      "step": 1100
    },
    {
      "epoch": 0.23,
      "grad_norm": 3.145481824874878,
      "learning_rate": 0.0002848649802056918,
      "loss": 25.17646240234375,
      "step": 1150
    },
    {
      "epoch": 0.24,
      "grad_norm": 3.1994168758392334,
      "learning_rate": 0.00028249126959659126,
      "loss": 24.8016015625,
      "step": 1200
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.9414961338043213,
      "learning_rate": 0.00027995613878420276,
      "loss": 24.93425537109375,
      "step": 1250
    },
    {
      "epoch": 0.26,
      "grad_norm": 3.3210513591766357,
      "learning_rate": 0.00027726267643491434,
      "loss": 24.86907958984375,
      "step": 1300
    },
    {
      "epoch": 0.27,
      "grad_norm": 3.235185384750366,
      "learning_rate": 0.00027441416411770245,
      "loss": 24.840205078125,
      "step": 1350
    },
    {
      "epoch": 0.28,
      "grad_norm": 3.130532741546631,
      "learning_rate": 0.00027141407230604596,
      "loss": 24.85203857421875,
      "step": 1400
    },
    {
      "epoch": 0.29,
      "grad_norm": 3.515564203262329,
      "learning_rate": 0.0002682660561496887,
      "loss": 24.42603515625,
      "step": 1450
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.041907787322998,
      "learning_rate": 0.00026497395102140247,
      "loss": 24.52408203125,
      "step": 1500
    },
    {
      "epoch": 0.31,
      "grad_norm": 3.3526618480682373,
      "learning_rate": 0.0002615417678441761,
      "loss": 24.54887939453125,
      "step": 1550
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.3341870307922363,
      "learning_rate": 0.0002579736882045238,
      "loss": 24.48134521484375,
      "step": 1600
    },
    {
      "epoch": 0.33,
      "grad_norm": 3.107917070388794,
      "learning_rate": 0.00025427405925786595,
      "loss": 24.417197265625,
      "step": 1650
    },
    {
      "epoch": 0.34,
      "grad_norm": 3.5469655990600586,
      "learning_rate": 0.0002504473884321899,
      "loss": 24.3250341796875,
      "step": 1700
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.412889003753662,
      "learning_rate": 0.0002464983379364433,
      "loss": 24.1046923828125,
      "step": 1750
    },
    {
      "epoch": 0.36,
      "grad_norm": 3.5492677688598633,
      "learning_rate": 0.00024243171908035053,
      "loss": 24.25704345703125,
      "step": 1800
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.6415436267852783,
      "learning_rate": 0.00023825248641257327,
      "loss": 23.98925048828125,
      "step": 1850
    },
    {
      "epoch": 0.38,
      "grad_norm": 3.313443899154663,
      "learning_rate": 0.00023396573168435567,
      "loss": 24.17134521484375,
      "step": 1900
    },
    {
      "epoch": 0.39,
      "grad_norm": 3.796315908432007,
      "learning_rate": 0.00022957667764601008,
      "loss": 23.89406005859375,
      "step": 1950
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.2706825733184814,
      "learning_rate": 0.00022509067168380038,
      "loss": 24.1194677734375,
      "step": 2000
    },
    {
      "epoch": 0.41,
      "grad_norm": 3.441154718399048,
      "learning_rate": 0.00022051317930497523,
      "loss": 24.1999072265625,
      "step": 2050
    },
    {
      "epoch": 0.42,
      "grad_norm": 3.518808364868164,
      "learning_rate": 0.0002158497774788896,
      "loss": 23.89898193359375,
      "step": 2100
    },
    {
      "epoch": 0.43,
      "grad_norm": 3.7033307552337646,
      "learning_rate": 0.0002111061478423265,
      "loss": 23.790986328125,
      "step": 2150
    },
    {
      "epoch": 0.44,
      "grad_norm": 3.673150062561035,
      "learning_rate": 0.00020628806977729812,
      "loss": 24.0228662109375,
      "step": 2200
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.573422908782959,
      "learning_rate": 0.0002014014133697585,
      "loss": 23.67351318359375,
      "step": 2250
    },
    {
      "epoch": 0.46,
      "grad_norm": 4.668125629425049,
      "learning_rate": 0.0001964521322578086,
      "loss": 23.75174560546875,
      "step": 2300
    },
    {
      "epoch": 0.47,
      "grad_norm": 4.469000339508057,
      "learning_rate": 0.00019144625637810503,
      "loss": 23.79510986328125,
      "step": 2350
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.140970230102539,
      "learning_rate": 0.0001863898846193111,
      "loss": 23.70107421875,
      "step": 2400
    },
    {
      "epoch": 0.49,
      "grad_norm": 4.114079475402832,
      "learning_rate": 0.00018128917739154056,
      "loss": 23.66251708984375,
      "step": 2450
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.908941268920898,
      "learning_rate": 0.0001761503491208467,
      "loss": 23.6627685546875,
      "step": 2500
    },
    {
      "epoch": 0.51,
      "grad_norm": 3.531893491744995,
      "learning_rate": 0.00017097966067790163,
      "loss": 23.67588623046875,
      "step": 2550
    },
    {
      "epoch": 0.52,
      "grad_norm": 3.9994258880615234,
      "learning_rate": 0.00016578341175008948,
      "loss": 23.6676025390625,
      "step": 2600
    },
    {
      "epoch": 0.53,
      "grad_norm": 4.651762962341309,
      "learning_rate": 0.00016056793316630803,
      "loss": 23.414052734375,
      "step": 2650
    },
    {
      "epoch": 0.54,
      "grad_norm": 3.7902722358703613,
      "learning_rate": 0.00015533957918382874,
      "loss": 23.56423828125,
      "step": 2700
    },
    {
      "epoch": 0.55,
      "grad_norm": 4.4413838386535645,
      "learning_rate": 0.0001501047197466131,
      "loss": 23.55817626953125,
      "step": 2750
    },
    {
      "epoch": 0.56,
      "grad_norm": 3.6125080585479736,
      "learning_rate": 0.0001448697327245171,
      "loss": 23.47991455078125,
      "step": 2800
    },
    {
      "epoch": 0.57,
      "grad_norm": 4.151065826416016,
      "learning_rate": 0.0001396409961428391,
      "loss": 23.5330859375,
      "step": 2850
    },
    {
      "epoch": 0.58,
      "grad_norm": 5.125370025634766,
      "learning_rate": 0.0001344248804116789,
      "loss": 23.56696533203125,
      "step": 2900
    },
    {
      "epoch": 0.59,
      "grad_norm": 3.613190174102783,
      "learning_rate": 0.00012922774056457376,
      "loss": 23.46764404296875,
      "step": 2950
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.484012126922607,
      "learning_rate": 0.00012405590851586945,
      "loss": 23.2342529296875,
      "step": 3000
    },
    {
      "epoch": 0.61,
      "grad_norm": 4.2972092628479,
      "learning_rate": 0.00011891568534625763,
      "loss": 23.21994140625,
      "step": 3050
    },
    {
      "epoch": 0.62,
      "grad_norm": 4.617368698120117,
      "learning_rate": 0.00011381333362587972,
      "loss": 23.39466552734375,
      "step": 3100
    },
    {
      "epoch": 0.63,
      "grad_norm": 4.377896785736084,
      "learning_rate": 0.0001087550697843501,
      "loss": 23.0036181640625,
      "step": 3150
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.8239970207214355,
      "learning_rate": 0.00010374705653699379,
      "loss": 23.21521484375,
      "step": 3200
    },
    {
      "epoch": 0.65,
      "grad_norm": 3.8129734992980957,
      "learning_rate": 9.879539537652734e-05,
      "loss": 23.19203125,
      "step": 3250
    },
    {
      "epoch": 0.66,
      "grad_norm": 4.068327903747559,
      "learning_rate": 9.390611913932994e-05,
      "loss": 22.90923583984375,
      "step": 3300
    },
    {
      "epoch": 0.67,
      "grad_norm": 4.683315277099609,
      "learning_rate": 8.90851846553613e-05,
      "loss": 23.061630859375,
      "step": 3350
    },
    {
      "epoch": 0.68,
      "grad_norm": 4.174139976501465,
      "learning_rate": 8.433846549068207e-05,
      "loss": 23.2664208984375,
      "step": 3400
    },
    {
      "epoch": 0.69,
      "grad_norm": 4.326903820037842,
      "learning_rate": 7.967174479141851e-05,
      "loss": 22.98652099609375,
      "step": 3450
    },
    {
      "epoch": 0.7,
      "grad_norm": 4.383793354034424,
      "learning_rate": 7.509070823788932e-05,
      "loss": 23.09397216796875,
      "step": 3500
    },
    {
      "epoch": 0.71,
      "grad_norm": 4.890023231506348,
      "learning_rate": 7.060093711748041e-05,
      "loss": 23.15705078125,
      "step": 3550
    },
    {
      "epoch": 0.72,
      "grad_norm": 4.316667556762695,
      "learning_rate": 6.620790152470581e-05,
      "loss": 23.2762353515625,
      "step": 3600
    },
    {
      "epoch": 0.73,
      "grad_norm": 4.178554534912109,
      "learning_rate": 6.191695369674005e-05,
      "loss": 23.15247314453125,
      "step": 3650
    },
    {
      "epoch": 0.74,
      "grad_norm": 4.168890476226807,
      "learning_rate": 5.773332149254167e-05,
      "loss": 22.8707421875,
      "step": 3700
    },
    {
      "epoch": 0.75,
      "grad_norm": 4.778957843780518,
      "learning_rate": 5.3662102023512335e-05,
      "loss": 23.31576904296875,
      "step": 3750
    },
    {
      "epoch": 0.76,
      "grad_norm": 4.6559576988220215,
      "learning_rate": 4.970825544345178e-05,
      "loss": 22.9227734375,
      "step": 3800
    },
    {
      "epoch": 0.77,
      "grad_norm": 4.201073169708252,
      "learning_rate": 4.5876598905374424e-05,
      "loss": 23.15135498046875,
      "step": 3850
    },
    {
      "epoch": 0.78,
      "grad_norm": 4.3280181884765625,
      "learning_rate": 4.217180069255052e-05,
      "loss": 22.96529052734375,
      "step": 3900
    },
    {
      "epoch": 0.79,
      "grad_norm": 4.0987229347229,
      "learning_rate": 3.859837453092184e-05,
      "loss": 23.18628173828125,
      "step": 3950
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.1396098136901855,
      "learning_rate": 3.5160674089822415e-05,
      "loss": 23.08689453125,
      "step": 4000
    },
    {
      "epoch": 0.81,
      "grad_norm": 4.06009578704834,
      "learning_rate": 3.186288767770243e-05,
      "loss": 23.24049072265625,
      "step": 4050
    },
    {
      "epoch": 0.82,
      "grad_norm": 4.152278423309326,
      "learning_rate": 2.8709033139320016e-05,
      "loss": 23.12670654296875,
      "step": 4100
    },
    {
      "epoch": 0.83,
      "grad_norm": 4.040670394897461,
      "learning_rate": 2.570295296061618e-05,
      "loss": 22.70718505859375,
      "step": 4150
    },
    {
      "epoch": 0.84,
      "grad_norm": 4.150204181671143,
      "learning_rate": 2.2848309587237545e-05,
      "loss": 22.81280517578125,
      "step": 4200
    },
    {
      "epoch": 0.85,
      "grad_norm": 4.331852436065674,
      "learning_rate": 2.014858096241036e-05,
      "loss": 23.07447021484375,
      "step": 4250
    },
    {
      "epoch": 0.86,
      "grad_norm": 4.494900226593018,
      "learning_rate": 1.7607056289602783e-05,
      "loss": 23.06335205078125,
      "step": 4300
    },
    {
      "epoch": 0.87,
      "grad_norm": 3.983609199523926,
      "learning_rate": 1.5226832025136698e-05,
      "loss": 22.91209228515625,
      "step": 4350
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.992405891418457,
      "learning_rate": 1.3010808105632909e-05,
      "loss": 23.0981298828125,
      "step": 4400
    },
    {
      "epoch": 0.89,
      "grad_norm": 3.8591504096984863,
      "learning_rate": 1.0961684414885064e-05,
      "loss": 23.1151025390625,
      "step": 4450
    },
    {
      "epoch": 0.9,
      "grad_norm": 3.8510167598724365,
      "learning_rate": 9.081957494466985e-06,
      "loss": 23.03157470703125,
      "step": 4500
    },
    {
      "epoch": 0.91,
      "grad_norm": 4.121877193450928,
      "learning_rate": 7.3739175020815e-06,
      "loss": 22.97037353515625,
      "step": 4550
    },
    {
      "epoch": 0.92,
      "grad_norm": 4.034373760223389,
      "learning_rate": 5.839645421355926e-06,
      "loss": 22.92754150390625,
      "step": 4600
    },
    {
      "epoch": 0.93,
      "grad_norm": 4.7229461669921875,
      "learning_rate": 4.48101052648413e-06,
      "loss": 23.0431982421875,
      "step": 4650
    },
    {
      "epoch": 0.94,
      "grad_norm": 3.8502602577209473,
      "learning_rate": 3.299668104803843e-06,
      "loss": 22.8787841796875,
      "step": 4700
    },
    {
      "epoch": 0.95,
      "grad_norm": 4.068970203399658,
      "learning_rate": 2.297057440084049e-06,
      "loss": 23.1052392578125,
      "step": 4750
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.614439964294434,
      "learning_rate": 1.4744000589793581e-06,
      "loss": 22.9152294921875,
      "step": 4800
    },
    {
      "epoch": 0.97,
      "grad_norm": 4.608243465423584,
      "learning_rate": 8.326982427880103e-07,
      "loss": 22.91056884765625,
      "step": 4850
    },
    {
      "epoch": 0.98,
      "grad_norm": 4.816669940948486,
      "learning_rate": 3.727338063264418e-07,
      "loss": 22.81651611328125,
      "step": 4900
    },
    {
      "epoch": 0.99,
      "grad_norm": 3.9090330600738525,
      "learning_rate": 9.50671454083729e-08,
      "loss": 22.8877197265625,
      "step": 4950
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.918071985244751,
      "learning_rate": 3.655408888914024e-11,
      "loss": 22.89197265625,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 262180700160000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}