{
  "best_metric": 3.767355442047119,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 2.4877250409165304,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02618657937806874,
      "grad_norm": 0.8365817070007324,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 4.3524,
      "step": 1
    },
    {
      "epoch": 0.02618657937806874,
      "eval_loss": 4.789937496185303,
      "eval_runtime": 0.2765,
      "eval_samples_per_second": 180.833,
      "eval_steps_per_second": 47.017,
      "step": 1
    },
    {
      "epoch": 0.05237315875613748,
      "grad_norm": 1.151999831199646,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.528,
      "step": 2
    },
    {
      "epoch": 0.07855973813420622,
      "grad_norm": 1.1144686937332153,
      "learning_rate": 0.0001,
      "loss": 4.5486,
      "step": 3
    },
    {
      "epoch": 0.10474631751227496,
      "grad_norm": 0.9449473023414612,
      "learning_rate": 9.997376600647783e-05,
      "loss": 4.6597,
      "step": 4
    },
    {
      "epoch": 0.1309328968903437,
      "grad_norm": 0.8100228905677795,
      "learning_rate": 9.989509461357426e-05,
      "loss": 4.6623,
      "step": 5
    },
    {
      "epoch": 0.15711947626841244,
      "grad_norm": 0.8471514582633972,
      "learning_rate": 9.976407754861426e-05,
      "loss": 4.6003,
      "step": 6
    },
    {
      "epoch": 0.18330605564648117,
      "grad_norm": 0.9861735701560974,
      "learning_rate": 9.958086757163489e-05,
      "loss": 4.5851,
      "step": 7
    },
    {
      "epoch": 0.20949263502454993,
      "grad_norm": 1.1125617027282715,
      "learning_rate": 9.934567829727386e-05,
      "loss": 4.5956,
      "step": 8
    },
    {
      "epoch": 0.23567921440261866,
      "grad_norm": 1.0278071165084839,
      "learning_rate": 9.905878394570453e-05,
      "loss": 4.7214,
      "step": 9
    },
    {
      "epoch": 0.2618657937806874,
      "grad_norm": 2.4233837127685547,
      "learning_rate": 9.872051902290737e-05,
      "loss": 4.0809,
      "step": 10
    },
    {
      "epoch": 0.28805237315875615,
      "grad_norm": 0.6828261613845825,
      "learning_rate": 9.833127793065098e-05,
      "loss": 4.1133,
      "step": 11
    },
    {
      "epoch": 0.3142389525368249,
      "grad_norm": 1.080686330795288,
      "learning_rate": 9.789151450663723e-05,
      "loss": 4.1603,
      "step": 12
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.7597512602806091,
      "learning_rate": 9.740174149534693e-05,
      "loss": 4.2075,
      "step": 13
    },
    {
      "epoch": 0.36661211129296234,
      "grad_norm": 0.6978819370269775,
      "learning_rate": 9.686252995020249e-05,
      "loss": 4.155,
      "step": 14
    },
    {
      "epoch": 0.39279869067103107,
      "grad_norm": 0.5029189586639404,
      "learning_rate": 9.627450856774539e-05,
      "loss": 4.2456,
      "step": 15
    },
    {
      "epoch": 0.41898527004909986,
      "grad_norm": 0.49850398302078247,
      "learning_rate": 9.563836295460398e-05,
      "loss": 4.375,
      "step": 16
    },
    {
      "epoch": 0.4451718494271686,
      "grad_norm": 0.6559662222862244,
      "learning_rate": 9.495483482810688e-05,
      "loss": 4.3,
      "step": 17
    },
    {
      "epoch": 0.4713584288052373,
      "grad_norm": 1.1999343633651733,
      "learning_rate": 9.422472115147382e-05,
      "loss": 4.4429,
      "step": 18
    },
    {
      "epoch": 0.49754500818330605,
      "grad_norm": 1.2498600482940674,
      "learning_rate": 9.3448873204592e-05,
      "loss": 4.5719,
      "step": 19
    },
    {
      "epoch": 0.5237315875613748,
      "grad_norm": 0.8708962798118591,
      "learning_rate": 9.2628195591462e-05,
      "loss": 3.7549,
      "step": 20
    },
    {
      "epoch": 0.5499181669394435,
      "grad_norm": 0.6062394380569458,
      "learning_rate": 9.176364518546989e-05,
      "loss": 3.9636,
      "step": 21
    },
    {
      "epoch": 0.5761047463175123,
      "grad_norm": 0.46776407957077026,
      "learning_rate": 9.08562300137157e-05,
      "loss": 4.0005,
      "step": 22
    },
    {
      "epoch": 0.602291325695581,
      "grad_norm": 0.41210252046585083,
      "learning_rate": 8.990700808169889e-05,
      "loss": 3.9414,
      "step": 23
    },
    {
      "epoch": 0.6284779050736498,
      "grad_norm": 0.4796847701072693,
      "learning_rate": 8.891708613973126e-05,
      "loss": 4.0629,
      "step": 24
    },
    {
      "epoch": 0.6546644844517185,
      "grad_norm": 0.42416390776634216,
      "learning_rate": 8.788761839251559e-05,
      "loss": 4.0834,
      "step": 25
    },
    {
      "epoch": 0.6546644844517185,
      "eval_loss": 4.142909526824951,
      "eval_runtime": 0.2882,
      "eval_samples_per_second": 173.488,
      "eval_steps_per_second": 45.107,
      "step": 25
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.4640260636806488,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.2203,
      "step": 26
    },
    {
      "epoch": 0.707037643207856,
      "grad_norm": 0.5100923776626587,
      "learning_rate": 8.571489144483944e-05,
      "loss": 4.181,
      "step": 27
    },
    {
      "epoch": 0.7332242225859247,
      "grad_norm": 0.6287262439727783,
      "learning_rate": 8.457416554680877e-05,
      "loss": 4.3732,
      "step": 28
    },
    {
      "epoch": 0.7594108019639935,
      "grad_norm": 0.5281463265419006,
      "learning_rate": 8.339895749467238e-05,
      "loss": 3.7263,
      "step": 29
    },
    {
      "epoch": 0.7855973813420621,
      "grad_norm": 0.41669386625289917,
      "learning_rate": 8.219063752844926e-05,
      "loss": 3.7891,
      "step": 30
    },
    {
      "epoch": 0.8117839607201309,
      "grad_norm": 0.39933446049690247,
      "learning_rate": 8.095061449516903e-05,
      "loss": 3.8458,
      "step": 31
    },
    {
      "epoch": 0.8379705400981997,
      "grad_norm": 0.42396020889282227,
      "learning_rate": 7.968033420621935e-05,
      "loss": 3.8991,
      "step": 32
    },
    {
      "epoch": 0.8641571194762684,
      "grad_norm": 0.45608440041542053,
      "learning_rate": 7.838127775159452e-05,
      "loss": 3.9113,
      "step": 33
    },
    {
      "epoch": 0.8903436988543372,
      "grad_norm": 0.5071250200271606,
      "learning_rate": 7.705495977301078e-05,
      "loss": 3.9696,
      "step": 34
    },
    {
      "epoch": 0.9165302782324058,
      "grad_norm": 0.408988356590271,
      "learning_rate": 7.570292669790186e-05,
      "loss": 4.0264,
      "step": 35
    },
    {
      "epoch": 0.9427168576104746,
      "grad_norm": 0.41267451643943787,
      "learning_rate": 7.43267549363537e-05,
      "loss": 4.0024,
      "step": 36
    },
    {
      "epoch": 0.9689034369885434,
      "grad_norm": 0.6320325136184692,
      "learning_rate": 7.292804904308087e-05,
      "loss": 4.0503,
      "step": 37
    },
    {
      "epoch": 0.9950900163666121,
      "grad_norm": 0.7328307628631592,
      "learning_rate": 7.150843984658754e-05,
      "loss": 4.1336,
      "step": 38
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 1.987341284751892,
      "learning_rate": 7.006958254769438e-05,
      "loss": 6.7162,
      "step": 39
    },
    {
      "epoch": 1.0474631751227497,
      "grad_norm": 1.042544960975647,
      "learning_rate": 6.861315478964841e-05,
      "loss": 3.6702,
      "step": 40
    },
    {
      "epoch": 1.0736497545008183,
      "grad_norm": 0.6465303301811218,
      "learning_rate": 6.714085470206609e-05,
      "loss": 3.8179,
      "step": 41
    },
    {
      "epoch": 1.099836333878887,
      "grad_norm": 0.3951312005519867,
      "learning_rate": 6.56543989209901e-05,
      "loss": 3.7864,
      "step": 42
    },
    {
      "epoch": 1.1260229132569557,
      "grad_norm": 0.41512835025787354,
      "learning_rate": 6.415552058736854e-05,
      "loss": 3.7806,
      "step": 43
    },
    {
      "epoch": 1.1522094926350246,
      "grad_norm": 0.534665584564209,
      "learning_rate": 6.264596732629e-05,
      "loss": 3.8374,
      "step": 44
    },
    {
      "epoch": 1.1783960720130933,
      "grad_norm": 0.5684964060783386,
      "learning_rate": 6.112749920933111e-05,
      "loss": 3.9551,
      "step": 45
    },
    {
      "epoch": 1.204582651391162,
      "grad_norm": 0.6400809288024902,
      "learning_rate": 5.960188670239154e-05,
      "loss": 4.0032,
      "step": 46
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.7185765504837036,
      "learning_rate": 5.80709086014102e-05,
      "loss": 3.9989,
      "step": 47
    },
    {
      "epoch": 1.2569558101472995,
      "grad_norm": 0.5369796752929688,
      "learning_rate": 5.653634995836856e-05,
      "loss": 3.3087,
      "step": 48
    },
    {
      "epoch": 1.2831423895253682,
      "grad_norm": 0.3849294185638428,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.8981,
      "step": 49
    },
    {
      "epoch": 1.3093289689034369,
      "grad_norm": 0.34771353006362915,
      "learning_rate": 5.346365004163145e-05,
      "loss": 3.6507,
      "step": 50
    },
    {
      "epoch": 1.3093289689034369,
      "eval_loss": 3.856473922729492,
      "eval_runtime": 0.2803,
      "eval_samples_per_second": 178.389,
      "eval_steps_per_second": 46.381,
      "step": 50
    },
    {
      "epoch": 1.3355155482815058,
      "grad_norm": 0.37725579738616943,
      "learning_rate": 5.192909139858981e-05,
      "loss": 3.7317,
      "step": 51
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.4553833603858948,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 3.7528,
      "step": 52
    },
    {
      "epoch": 1.3878887070376433,
      "grad_norm": 0.4247891306877136,
      "learning_rate": 4.887250079066892e-05,
      "loss": 3.8082,
      "step": 53
    },
    {
      "epoch": 1.414075286415712,
      "grad_norm": 0.45754310488700867,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 3.8597,
      "step": 54
    },
    {
      "epoch": 1.4402618657937807,
      "grad_norm": 0.40189892053604126,
      "learning_rate": 4.584447941263149e-05,
      "loss": 3.8544,
      "step": 55
    },
    {
      "epoch": 1.4664484451718494,
      "grad_norm": 0.4472440779209137,
      "learning_rate": 4.43456010790099e-05,
      "loss": 3.902,
      "step": 56
    },
    {
      "epoch": 1.492635024549918,
      "grad_norm": 0.7986133694648743,
      "learning_rate": 4.285914529793391e-05,
      "loss": 4.3171,
      "step": 57
    },
    {
      "epoch": 1.518821603927987,
      "grad_norm": 0.47378429770469666,
      "learning_rate": 4.13868452103516e-05,
      "loss": 3.2801,
      "step": 58
    },
    {
      "epoch": 1.5450081833060556,
      "grad_norm": 0.609893798828125,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 3.5901,
      "step": 59
    },
    {
      "epoch": 1.5711947626841245,
      "grad_norm": 0.5858629941940308,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 3.601,
      "step": 60
    },
    {
      "epoch": 1.5973813420621932,
      "grad_norm": 0.37681153416633606,
      "learning_rate": 3.707195095691913e-05,
      "loss": 3.7124,
      "step": 61
    },
    {
      "epoch": 1.6235679214402619,
      "grad_norm": 0.338227778673172,
      "learning_rate": 3.567324506364632e-05,
      "loss": 3.7552,
      "step": 62
    },
    {
      "epoch": 1.6497545008183305,
      "grad_norm": 0.35423874855041504,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 3.7876,
      "step": 63
    },
    {
      "epoch": 1.6759410801963992,
      "grad_norm": 0.4390277862548828,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 3.8012,
      "step": 64
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.563541829586029,
      "learning_rate": 3.16187222484055e-05,
      "loss": 3.8544,
      "step": 65
    },
    {
      "epoch": 1.7283142389525368,
      "grad_norm": 0.7141799330711365,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 4.0238,
      "step": 66
    },
    {
      "epoch": 1.7545008183306057,
      "grad_norm": 0.4013899862766266,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 3.1346,
      "step": 67
    },
    {
      "epoch": 1.7806873977086743,
      "grad_norm": 0.3977162539958954,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 3.8809,
      "step": 68
    },
    {
      "epoch": 1.806873977086743,
      "grad_norm": 0.35375577211380005,
      "learning_rate": 2.660104250532764e-05,
      "loss": 3.6103,
      "step": 69
    },
    {
      "epoch": 1.8330605564648117,
      "grad_norm": 0.3449622094631195,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 3.6076,
      "step": 70
    },
    {
      "epoch": 1.8592471358428804,
      "grad_norm": 0.3213866651058197,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 3.712,
      "step": 71
    },
    {
      "epoch": 1.8854337152209493,
      "grad_norm": 0.34646686911582947,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.7291,
      "step": 72
    },
    {
      "epoch": 1.9116202945990182,
      "grad_norm": 0.3628241717815399,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 3.8293,
      "step": 73
    },
    {
      "epoch": 1.9378068739770868,
      "grad_norm": 0.37866660952568054,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 3.8291,
      "step": 74
    },
    {
      "epoch": 1.9639934533551555,
      "grad_norm": 0.4907776415348053,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 3.8753,
      "step": 75
    },
    {
      "epoch": 1.9639934533551555,
      "eval_loss": 3.767355442047119,
      "eval_runtime": 0.2893,
      "eval_samples_per_second": 172.844,
      "eval_steps_per_second": 44.939,
      "step": 75
    },
    {
      "epoch": 1.9901800327332242,
      "grad_norm": 0.8656964302062988,
      "learning_rate": 1.91437699862843e-05,
      "loss": 4.1986,
      "step": 76
    },
    {
      "epoch": 2.016366612111293,
      "grad_norm": 0.8424877524375916,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 6.5033,
      "step": 77
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 0.6298512816429138,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 3.5305,
      "step": 78
    },
    {
      "epoch": 2.06873977086743,
      "grad_norm": 0.577872633934021,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 3.5686,
      "step": 79
    },
    {
      "epoch": 2.0949263502454993,
      "grad_norm": 0.4558631479740143,
      "learning_rate": 1.577527884852619e-05,
      "loss": 3.619,
      "step": 80
    },
    {
      "epoch": 2.121112929623568,
      "grad_norm": 0.3921566903591156,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 3.6359,
      "step": 81
    },
    {
      "epoch": 2.1472995090016367,
      "grad_norm": 0.3551250398159027,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 3.7263,
      "step": 82
    },
    {
      "epoch": 2.1734860883797054,
      "grad_norm": 0.3237386643886566,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 3.7598,
      "step": 83
    },
    {
      "epoch": 2.199672667757774,
      "grad_norm": 0.4270864725112915,
      "learning_rate": 1.313747004979751e-05,
      "loss": 3.8036,
      "step": 84
    },
    {
      "epoch": 2.2258592471358427,
      "grad_norm": 0.5806615948677063,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 3.9918,
      "step": 85
    },
    {
      "epoch": 2.2520458265139114,
      "grad_norm": 0.4796655774116516,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 2.7358,
      "step": 86
    },
    {
      "epoch": 2.2782324058919805,
      "grad_norm": 0.5247834324836731,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 4.1886,
      "step": 87
    },
    {
      "epoch": 2.304418985270049,
      "grad_norm": 0.400111585855484,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 3.5208,
      "step": 88
    },
    {
      "epoch": 2.330605564648118,
      "grad_norm": 0.35815542936325073,
      "learning_rate": 1.094121605429547e-05,
      "loss": 3.6359,
      "step": 89
    },
    {
      "epoch": 2.3567921440261865,
      "grad_norm": 0.3279394209384918,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 3.6536,
      "step": 90
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 0.3094680905342102,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 3.7183,
      "step": 91
    },
    {
      "epoch": 2.409165302782324,
      "grad_norm": 0.3676002025604248,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 3.7482,
      "step": 92
    },
    {
      "epoch": 2.4353518821603926,
      "grad_norm": 0.3828237056732178,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 3.781,
      "step": 93
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.5239596366882324,
      "learning_rate": 1.002623399352217e-05,
      "loss": 3.8249,
      "step": 94
    },
    {
      "epoch": 2.4877250409165304,
      "grad_norm": 0.8069905638694763,
      "learning_rate": 1e-05,
      "loss": 4.1793,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.161007627599872e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}