{
  "best_metric": 0.9462701082229614,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0006646709920131472,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.646709920131472e-06,
      "grad_norm": 2.2269399166107178,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 1.428,
      "step": 1
    },
    {
      "epoch": 6.646709920131472e-06,
      "eval_loss": 2.6203625202178955,
      "eval_runtime": 14473.0812,
      "eval_samples_per_second": 8.754,
      "eval_steps_per_second": 8.754,
      "step": 1
    },
    {
      "epoch": 1.3293419840262944e-05,
      "grad_norm": 3.4928505420684814,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 1.6908,
      "step": 2
    },
    {
      "epoch": 1.9940129760394414e-05,
      "grad_norm": 3.1937475204467773,
      "learning_rate": 4.5e-07,
      "loss": 1.8925,
      "step": 3
    },
    {
      "epoch": 2.6586839680525888e-05,
      "grad_norm": 3.009830951690674,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.7325,
      "step": 4
    },
    {
      "epoch": 3.323354960065736e-05,
      "grad_norm": 2.3588366508483887,
      "learning_rate": 7.5e-07,
      "loss": 1.7412,
      "step": 5
    },
    {
      "epoch": 3.988025952078883e-05,
      "grad_norm": 2.889117956161499,
      "learning_rate": 9e-07,
      "loss": 1.6918,
      "step": 6
    },
    {
      "epoch": 4.65269694409203e-05,
      "grad_norm": 2.40836763381958,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.4917,
      "step": 7
    },
    {
      "epoch": 5.3173679361051776e-05,
      "grad_norm": 2.8656005859375,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.5208,
      "step": 8
    },
    {
      "epoch": 5.982038928118325e-05,
      "grad_norm": 2.2026925086975098,
      "learning_rate": 1.35e-06,
      "loss": 1.4446,
      "step": 9
    },
    {
      "epoch": 6.646709920131472e-05,
      "grad_norm": 1.8242329359054565,
      "learning_rate": 1.5e-06,
      "loss": 1.2512,
      "step": 10
    },
    {
      "epoch": 7.31138091214462e-05,
      "grad_norm": 2.175368547439575,
      "learning_rate": 1.65e-06,
      "loss": 1.5656,
      "step": 11
    },
    {
      "epoch": 7.976051904157766e-05,
      "grad_norm": 2.1395835876464844,
      "learning_rate": 1.8e-06,
      "loss": 1.4403,
      "step": 12
    },
    {
      "epoch": 8.640722896170913e-05,
      "grad_norm": 2.2977042198181152,
      "learning_rate": 1.95e-06,
      "loss": 1.4933,
      "step": 13
    },
    {
      "epoch": 9.30539388818406e-05,
      "grad_norm": 2.4743711948394775,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 1.5174,
      "step": 14
    },
    {
      "epoch": 9.970064880197208e-05,
      "grad_norm": 2.9381775856018066,
      "learning_rate": 2.25e-06,
      "loss": 1.9124,
      "step": 15
    },
    {
      "epoch": 0.00010634735872210355,
      "grad_norm": 2.731985092163086,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.553,
      "step": 16
    },
    {
      "epoch": 0.00011299406864223503,
      "grad_norm": 3.0935258865356445,
      "learning_rate": 2.55e-06,
      "loss": 1.8532,
      "step": 17
    },
    {
      "epoch": 0.0001196407785623665,
      "grad_norm": 3.5391767024993896,
      "learning_rate": 2.7e-06,
      "loss": 1.8584,
      "step": 18
    },
    {
      "epoch": 0.00012628748848249796,
      "grad_norm": 3.584444522857666,
      "learning_rate": 2.8500000000000002e-06,
      "loss": 1.698,
      "step": 19
    },
    {
      "epoch": 0.00013293419840262945,
      "grad_norm": 2.080763339996338,
      "learning_rate": 3e-06,
      "loss": 1.5809,
      "step": 20
    },
    {
      "epoch": 0.0001395809083227609,
      "grad_norm": 2.934476613998413,
      "learning_rate": 3.15e-06,
      "loss": 1.6294,
      "step": 21
    },
    {
      "epoch": 0.0001462276182428924,
      "grad_norm": 2.98819899559021,
      "learning_rate": 3.3e-06,
      "loss": 1.6853,
      "step": 22
    },
    {
      "epoch": 0.00015287432816302385,
      "grad_norm": 1.7770015001296997,
      "learning_rate": 3.4500000000000004e-06,
      "loss": 1.3249,
      "step": 23
    },
    {
      "epoch": 0.00015952103808315532,
      "grad_norm": 2.5164477825164795,
      "learning_rate": 3.6e-06,
      "loss": 1.2805,
      "step": 24
    },
    {
      "epoch": 0.0001661677480032868,
      "grad_norm": 1.4407439231872559,
      "learning_rate": 3.75e-06,
      "loss": 1.2659,
      "step": 25
    },
    {
      "epoch": 0.00017281445792341826,
      "grad_norm": 2.501211404800415,
      "learning_rate": 3.9e-06,
      "loss": 1.6157,
      "step": 26
    },
    {
      "epoch": 0.00017946116784354975,
      "grad_norm": 2.0206544399261475,
      "learning_rate": 4.05e-06,
      "loss": 1.5844,
      "step": 27
    },
    {
      "epoch": 0.0001861078777636812,
      "grad_norm": 2.0773091316223145,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 1.5952,
      "step": 28
    },
    {
      "epoch": 0.0001927545876838127,
      "grad_norm": 1.5942881107330322,
      "learning_rate": 4.35e-06,
      "loss": 1.4008,
      "step": 29
    },
    {
      "epoch": 0.00019940129760394416,
      "grad_norm": 5.619721412658691,
      "learning_rate": 4.5e-06,
      "loss": 2.3372,
      "step": 30
    },
    {
      "epoch": 0.00020604800752407562,
      "grad_norm": 2.7660560607910156,
      "learning_rate": 4.65e-06,
      "loss": 1.528,
      "step": 31
    },
    {
      "epoch": 0.0002126947174442071,
      "grad_norm": 1.9410547018051147,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.5532,
      "step": 32
    },
    {
      "epoch": 0.00021934142736433857,
      "grad_norm": 3.1958677768707275,
      "learning_rate": 4.95e-06,
      "loss": 1.8329,
      "step": 33
    },
    {
      "epoch": 0.00022598813728447005,
      "grad_norm": 2.895124673843384,
      "learning_rate": 5.1e-06,
      "loss": 1.5769,
      "step": 34
    },
    {
      "epoch": 0.0002326348472046015,
      "grad_norm": 2.196526050567627,
      "learning_rate": 5.25e-06,
      "loss": 1.2884,
      "step": 35
    },
    {
      "epoch": 0.000239281557124733,
      "grad_norm": 3.751549243927002,
      "learning_rate": 5.4e-06,
      "loss": 1.6195,
      "step": 36
    },
    {
      "epoch": 0.0002459282670448645,
      "grad_norm": 3.5527710914611816,
      "learning_rate": 5.55e-06,
      "loss": 1.7122,
      "step": 37
    },
    {
      "epoch": 0.0002525749769649959,
      "grad_norm": 5.175699710845947,
      "learning_rate": 5.7000000000000005e-06,
      "loss": 1.465,
      "step": 38
    },
    {
      "epoch": 0.0002592216868851274,
      "grad_norm": 2.5664188861846924,
      "learning_rate": 5.850000000000001e-06,
      "loss": 1.2144,
      "step": 39
    },
    {
      "epoch": 0.0002658683968052589,
      "grad_norm": 3.9935264587402344,
      "learning_rate": 6e-06,
      "loss": 1.48,
      "step": 40
    },
    {
      "epoch": 0.00027251510672539033,
      "grad_norm": 2.4363529682159424,
      "learning_rate": 6.1499999999999996e-06,
      "loss": 1.1634,
      "step": 41
    },
    {
      "epoch": 0.0002791618166455218,
      "grad_norm": 3.078923225402832,
      "learning_rate": 6.3e-06,
      "loss": 1.5748,
      "step": 42
    },
    {
      "epoch": 0.0002858085265656533,
      "grad_norm": 1.8742955923080444,
      "learning_rate": 6.45e-06,
      "loss": 1.0593,
      "step": 43
    },
    {
      "epoch": 0.0002924552364857848,
      "grad_norm": 3.1210315227508545,
      "learning_rate": 6.6e-06,
      "loss": 1.3772,
      "step": 44
    },
    {
      "epoch": 0.0002991019464059162,
      "grad_norm": 2.9279181957244873,
      "learning_rate": 6.750000000000001e-06,
      "loss": 1.2248,
      "step": 45
    },
    {
      "epoch": 0.0003057486563260477,
      "grad_norm": 2.645423173904419,
      "learning_rate": 6.900000000000001e-06,
      "loss": 1.2477,
      "step": 46
    },
    {
      "epoch": 0.0003123953662461792,
      "grad_norm": 2.495187997817993,
      "learning_rate": 7.049999999999999e-06,
      "loss": 1.4032,
      "step": 47
    },
    {
      "epoch": 0.00031904207616631063,
      "grad_norm": 2.673903226852417,
      "learning_rate": 7.2e-06,
      "loss": 1.1914,
      "step": 48
    },
    {
      "epoch": 0.0003256887860864421,
      "grad_norm": 2.6068954467773438,
      "learning_rate": 7.35e-06,
      "loss": 1.0256,
      "step": 49
    },
    {
      "epoch": 0.0003323354960065736,
      "grad_norm": 3.2939798831939697,
      "learning_rate": 7.5e-06,
      "loss": 1.3065,
      "step": 50
    },
    {
      "epoch": 0.0003323354960065736,
      "eval_loss": 1.5138180255889893,
      "eval_runtime": 14565.0239,
      "eval_samples_per_second": 8.699,
      "eval_steps_per_second": 8.699,
      "step": 50
    },
    {
      "epoch": 0.0003389822059267051,
      "grad_norm": 2.8654468059539795,
      "learning_rate": 7.65e-06,
      "loss": 1.1624,
      "step": 51
    },
    {
      "epoch": 0.0003456289158468365,
      "grad_norm": 2.272857904434204,
      "learning_rate": 7.8e-06,
      "loss": 1.1302,
      "step": 52
    },
    {
      "epoch": 0.000352275625766968,
      "grad_norm": 2.6928863525390625,
      "learning_rate": 7.95e-06,
      "loss": 1.0018,
      "step": 53
    },
    {
      "epoch": 0.0003589223356870995,
      "grad_norm": 2.3181257247924805,
      "learning_rate": 8.1e-06,
      "loss": 1.0608,
      "step": 54
    },
    {
      "epoch": 0.00036556904560723093,
      "grad_norm": 2.339890480041504,
      "learning_rate": 8.25e-06,
      "loss": 1.3231,
      "step": 55
    },
    {
      "epoch": 0.0003722157555273624,
      "grad_norm": 2.5133416652679443,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.0261,
      "step": 56
    },
    {
      "epoch": 0.0003788624654474939,
      "grad_norm": 3.086866855621338,
      "learning_rate": 8.55e-06,
      "loss": 1.0834,
      "step": 57
    },
    {
      "epoch": 0.0003855091753676254,
      "grad_norm": 3.0155768394470215,
      "learning_rate": 8.7e-06,
      "loss": 1.2312,
      "step": 58
    },
    {
      "epoch": 0.00039215588528775683,
      "grad_norm": 3.622910976409912,
      "learning_rate": 8.85e-06,
      "loss": 1.1429,
      "step": 59
    },
    {
      "epoch": 0.0003988025952078883,
      "grad_norm": 3.1045446395874023,
      "learning_rate": 9e-06,
      "loss": 1.171,
      "step": 60
    },
    {
      "epoch": 0.0004054493051280198,
      "grad_norm": 4.79334831237793,
      "learning_rate": 9.15e-06,
      "loss": 1.1557,
      "step": 61
    },
    {
      "epoch": 0.00041209601504815124,
      "grad_norm": 2.8625354766845703,
      "learning_rate": 9.3e-06,
      "loss": 1.1203,
      "step": 62
    },
    {
      "epoch": 0.0004187427249682827,
      "grad_norm": 2.51842999458313,
      "learning_rate": 9.450000000000001e-06,
      "loss": 1.2729,
      "step": 63
    },
    {
      "epoch": 0.0004253894348884142,
      "grad_norm": 3.3374531269073486,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.3126,
      "step": 64
    },
    {
      "epoch": 0.0004320361448085457,
      "grad_norm": 2.5058956146240234,
      "learning_rate": 9.75e-06,
      "loss": 0.9902,
      "step": 65
    },
    {
      "epoch": 0.00043868285472867713,
      "grad_norm": 3.0709550380706787,
      "learning_rate": 9.9e-06,
      "loss": 1.2788,
      "step": 66
    },
    {
      "epoch": 0.0004453295646488086,
      "grad_norm": 2.5809314250946045,
      "learning_rate": 1.005e-05,
      "loss": 1.1198,
      "step": 67
    },
    {
      "epoch": 0.0004519762745689401,
      "grad_norm": 2.069631576538086,
      "learning_rate": 1.02e-05,
      "loss": 0.9917,
      "step": 68
    },
    {
      "epoch": 0.00045862298448907154,
      "grad_norm": 2.5883145332336426,
      "learning_rate": 1.035e-05,
      "loss": 0.9174,
      "step": 69
    },
    {
      "epoch": 0.000465269694409203,
      "grad_norm": 2.756114959716797,
      "learning_rate": 1.05e-05,
      "loss": 1.1093,
      "step": 70
    },
    {
      "epoch": 0.0004719164043293345,
      "grad_norm": 3.360435724258423,
      "learning_rate": 1.065e-05,
      "loss": 1.0979,
      "step": 71
    },
    {
      "epoch": 0.000478563114249466,
      "grad_norm": 3.1470789909362793,
      "learning_rate": 1.08e-05,
      "loss": 1.0453,
      "step": 72
    },
    {
      "epoch": 0.00048520982416959743,
      "grad_norm": 3.178271770477295,
      "learning_rate": 1.095e-05,
      "loss": 1.0648,
      "step": 73
    },
    {
      "epoch": 0.000491856534089729,
      "grad_norm": 2.739807367324829,
      "learning_rate": 1.11e-05,
      "loss": 0.8553,
      "step": 74
    },
    {
      "epoch": 0.0004985032440098604,
      "grad_norm": 4.323954105377197,
      "learning_rate": 1.125e-05,
      "loss": 0.8544,
      "step": 75
    },
    {
      "epoch": 0.0005051499539299918,
      "grad_norm": 3.024756908416748,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 0.9233,
      "step": 76
    },
    {
      "epoch": 0.0005117966638501233,
      "grad_norm": 2.125073194503784,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 1.0506,
      "step": 77
    },
    {
      "epoch": 0.0005184433737702548,
      "grad_norm": 3.106951951980591,
      "learning_rate": 1.1700000000000001e-05,
      "loss": 1.0027,
      "step": 78
    },
    {
      "epoch": 0.0005250900836903863,
      "grad_norm": 2.5821290016174316,
      "learning_rate": 1.185e-05,
      "loss": 0.871,
      "step": 79
    },
    {
      "epoch": 0.0005317367936105178,
      "grad_norm": 1.9004353284835815,
      "learning_rate": 1.2e-05,
      "loss": 1.1965,
      "step": 80
    },
    {
      "epoch": 0.0005383835035306493,
      "grad_norm": 2.6640169620513916,
      "learning_rate": 1.215e-05,
      "loss": 0.8976,
      "step": 81
    },
    {
      "epoch": 0.0005450302134507807,
      "grad_norm": 2.3155083656311035,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 1.1266,
      "step": 82
    },
    {
      "epoch": 0.0005516769233709121,
      "grad_norm": 2.9848148822784424,
      "learning_rate": 1.245e-05,
      "loss": 1.1542,
      "step": 83
    },
    {
      "epoch": 0.0005583236332910436,
      "grad_norm": 1.9199186563491821,
      "learning_rate": 1.26e-05,
      "loss": 1.0858,
      "step": 84
    },
    {
      "epoch": 0.0005649703432111751,
      "grad_norm": 2.5137338638305664,
      "learning_rate": 1.275e-05,
      "loss": 0.8041,
      "step": 85
    },
    {
      "epoch": 0.0005716170531313066,
      "grad_norm": 3.3150558471679688,
      "learning_rate": 1.29e-05,
      "loss": 1.0045,
      "step": 86
    },
    {
      "epoch": 0.0005782637630514381,
      "grad_norm": 2.7405173778533936,
      "learning_rate": 1.305e-05,
      "loss": 0.8205,
      "step": 87
    },
    {
      "epoch": 0.0005849104729715696,
      "grad_norm": 2.6088101863861084,
      "learning_rate": 1.32e-05,
      "loss": 1.0735,
      "step": 88
    },
    {
      "epoch": 0.000591557182891701,
      "grad_norm": 2.574469566345215,
      "learning_rate": 1.3350000000000001e-05,
      "loss": 0.9404,
      "step": 89
    },
    {
      "epoch": 0.0005982038928118324,
      "grad_norm": 2.537645101547241,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.9955,
      "step": 90
    },
    {
      "epoch": 0.0006048506027319639,
      "grad_norm": 2.123636245727539,
      "learning_rate": 1.3650000000000001e-05,
      "loss": 1.134,
      "step": 91
    },
    {
      "epoch": 0.0006114973126520954,
      "grad_norm": 2.873260974884033,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 1.0197,
      "step": 92
    },
    {
      "epoch": 0.0006181440225722269,
      "grad_norm": 2.5287506580352783,
      "learning_rate": 1.395e-05,
      "loss": 1.1108,
      "step": 93
    },
    {
      "epoch": 0.0006247907324923584,
      "grad_norm": 2.4545209407806396,
      "learning_rate": 1.4099999999999999e-05,
      "loss": 1.0198,
      "step": 94
    },
    {
      "epoch": 0.0006314374424124899,
      "grad_norm": 2.532094955444336,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 1.2803,
      "step": 95
    },
    {
      "epoch": 0.0006380841523326213,
      "grad_norm": 2.8775060176849365,
      "learning_rate": 1.44e-05,
      "loss": 1.032,
      "step": 96
    },
    {
      "epoch": 0.0006447308622527527,
      "grad_norm": 2.783856153488159,
      "learning_rate": 1.455e-05,
      "loss": 1.1775,
      "step": 97
    },
    {
      "epoch": 0.0006513775721728842,
      "grad_norm": 2.1079962253570557,
      "learning_rate": 1.47e-05,
      "loss": 1.2117,
      "step": 98
    },
    {
      "epoch": 0.0006580242820930157,
      "grad_norm": 3.4485764503479004,
      "learning_rate": 1.485e-05,
      "loss": 1.0452,
      "step": 99
    },
    {
      "epoch": 0.0006646709920131472,
      "grad_norm": 2.6486401557922363,
      "learning_rate": 1.5e-05,
      "loss": 1.1055,
      "step": 100
    },
    {
      "epoch": 0.0006646709920131472,
      "eval_loss": 0.9462701082229614,
      "eval_runtime": 14553.4829,
      "eval_samples_per_second": 8.706,
      "eval_steps_per_second": 8.706,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 6.26343737819136e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}