{
  "best_metric": 1.1233247518539429,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3436426116838488,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 0.39795026183128357,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1706,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "eval_loss": 1.394996166229248,
      "eval_runtime": 41.1487,
      "eval_samples_per_second": 11.908,
      "eval_steps_per_second": 5.954,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 0.43744540214538574,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.217,
      "step": 2
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.45329102873802185,
      "learning_rate": 1e-05,
      "loss": 1.2021,
      "step": 3
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.47084182500839233,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.235,
      "step": 4
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 0.4676068127155304,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.27,
      "step": 5
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.4271283447742462,
      "learning_rate": 2e-05,
      "loss": 1.1783,
      "step": 6
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 0.4685676395893097,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.2112,
      "step": 7
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.434590220451355,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.1869,
      "step": 8
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.44050467014312744,
      "learning_rate": 3e-05,
      "loss": 1.2167,
      "step": 9
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.3955245316028595,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1806,
      "step": 10
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 0.3721248507499695,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.1545,
      "step": 11
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.31409817934036255,
      "learning_rate": 4e-05,
      "loss": 1.2273,
      "step": 12
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 0.29699209332466125,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.1168,
      "step": 13
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 0.2954188585281372,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.2048,
      "step": 14
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.2993329167366028,
      "learning_rate": 5e-05,
      "loss": 1.1181,
      "step": 15
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.28740134835243225,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.1234,
      "step": 16
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 0.31010302901268005,
      "learning_rate": 5.666666666666667e-05,
      "loss": 1.2198,
      "step": 17
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.30725136399269104,
      "learning_rate": 6e-05,
      "loss": 1.1898,
      "step": 18
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 0.26591724157333374,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.2076,
      "step": 19
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.25425398349761963,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1782,
      "step": 20
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 0.25563672184944153,
      "learning_rate": 7e-05,
      "loss": 1.102,
      "step": 21
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.2525363564491272,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.1132,
      "step": 22
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 0.27992483973503113,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.1971,
      "step": 23
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.24994660913944244,
      "learning_rate": 8e-05,
      "loss": 1.1438,
      "step": 24
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 0.27021530270576477,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2105,
      "step": 25
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.26155591011047363,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.2296,
      "step": 26
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.25747400522232056,
      "learning_rate": 9e-05,
      "loss": 1.1667,
      "step": 27
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.25319820642471313,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.262,
      "step": 28
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 0.26420244574546814,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.2049,
      "step": 29
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.25196051597595215,
      "learning_rate": 0.0001,
      "loss": 1.1626,
      "step": 30
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 0.2579573690891266,
      "learning_rate": 9.994965332706573e-05,
      "loss": 1.2421,
      "step": 31
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.24934573471546173,
      "learning_rate": 9.979871469976196e-05,
      "loss": 1.1968,
      "step": 32
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.2536607086658478,
      "learning_rate": 9.954748808839674e-05,
      "loss": 1.1794,
      "step": 33
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.2625012695789337,
      "learning_rate": 9.919647942993148e-05,
      "loss": 1.1416,
      "step": 34
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.257440447807312,
      "learning_rate": 9.874639560909117e-05,
      "loss": 1.2098,
      "step": 35
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.2822026014328003,
      "learning_rate": 9.819814303479267e-05,
      "loss": 1.1966,
      "step": 36
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 0.27574318647384644,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2154,
      "step": 37
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.27795401215553284,
      "learning_rate": 9.681174353198687e-05,
      "loss": 1.1431,
      "step": 38
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.26681026816368103,
      "learning_rate": 9.597638862757255e-05,
      "loss": 1.1735,
      "step": 39
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.2776302397251129,
      "learning_rate": 9.504844339512095e-05,
      "loss": 1.24,
      "step": 40
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.3019616901874542,
      "learning_rate": 9.40297765928369e-05,
      "loss": 1.201,
      "step": 41
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.291785329580307,
      "learning_rate": 9.292243968009331e-05,
      "loss": 1.1569,
      "step": 42
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 0.29259058833122253,
      "learning_rate": 9.172866268606513e-05,
      "loss": 1.1203,
      "step": 43
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.31598636507987976,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2352,
      "step": 44
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.3215610086917877,
      "learning_rate": 8.90915741234015e-05,
      "loss": 1.1668,
      "step": 45
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.3626932203769684,
      "learning_rate": 8.765357330018056e-05,
      "loss": 1.1811,
      "step": 46
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 0.40073418617248535,
      "learning_rate": 8.613974319136958e-05,
      "loss": 1.2598,
      "step": 47
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.39903056621551514,
      "learning_rate": 8.455313244934324e-05,
      "loss": 1.2176,
      "step": 48
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.4395723342895508,
      "learning_rate": 8.289693629698564e-05,
      "loss": 1.2958,
      "step": 49
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.479213684797287,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.2257,
      "step": 50
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 1.254024863243103,
      "eval_runtime": 41.6511,
      "eval_samples_per_second": 11.764,
      "eval_steps_per_second": 5.882,
      "step": 50
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 0.7763431072235107,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1863,
      "step": 51
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 0.6419703960418701,
      "learning_rate": 7.754484907260513e-05,
      "loss": 1.2078,
      "step": 52
    },
    {
      "epoch": 0.18213058419243985,
      "grad_norm": 0.4610435366630554,
      "learning_rate": 7.564496387029532e-05,
      "loss": 1.1107,
      "step": 53
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.31423109769821167,
      "learning_rate": 7.369343312364993e-05,
      "loss": 1.0897,
      "step": 54
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 0.22052399814128876,
      "learning_rate": 7.169418695587791e-05,
      "loss": 1.0426,
      "step": 55
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.18192903697490692,
      "learning_rate": 6.965125158269619e-05,
      "loss": 1.0934,
      "step": 56
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.186998650431633,
      "learning_rate": 6.756874120406714e-05,
      "loss": 1.159,
      "step": 57
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 0.19652201235294342,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0594,
      "step": 58
    },
    {
      "epoch": 0.2027491408934708,
      "grad_norm": 0.21376550197601318,
      "learning_rate": 6.330184227833376e-05,
      "loss": 1.08,
      "step": 59
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.20765534043312073,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.9949,
      "step": 60
    },
    {
      "epoch": 0.20962199312714777,
      "grad_norm": 0.2084871083498001,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 1.0845,
      "step": 61
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 0.20915870368480682,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 1.0677,
      "step": 62
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.19567368924617767,
      "learning_rate": 5.448196544517168e-05,
      "loss": 1.0483,
      "step": 63
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.2006818801164627,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 1.1014,
      "step": 64
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 0.1980873942375183,
      "learning_rate": 5e-05,
      "loss": 1.0755,
      "step": 65
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.1960572451353073,
      "learning_rate": 4.775675848247427e-05,
      "loss": 1.0844,
      "step": 66
    },
    {
      "epoch": 0.23024054982817868,
      "grad_norm": 0.18849298357963562,
      "learning_rate": 4.551803455482833e-05,
      "loss": 1.0507,
      "step": 67
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 0.19031502306461334,
      "learning_rate": 4.328833670911724e-05,
      "loss": 1.0865,
      "step": 68
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.1852409988641739,
      "learning_rate": 4.107215526006817e-05,
      "loss": 1.0678,
      "step": 69
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 0.1880156397819519,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.1267,
      "step": 70
    },
    {
      "epoch": 0.24398625429553264,
      "grad_norm": 0.190456360578537,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 1.1162,
      "step": 71
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.18321743607521057,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1242,
      "step": 72
    },
    {
      "epoch": 0.2508591065292096,
      "grad_norm": 0.2000783532857895,
      "learning_rate": 3.243125879593286e-05,
      "loss": 1.1294,
      "step": 73
    },
    {
      "epoch": 0.2542955326460481,
      "grad_norm": 0.21174149215221405,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 1.1342,
      "step": 74
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.19860917329788208,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 1.1456,
      "step": 75
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 0.20266704261302948,
      "learning_rate": 2.630656687635007e-05,
      "loss": 1.1071,
      "step": 76
    },
    {
      "epoch": 0.2646048109965636,
      "grad_norm": 0.20789256691932678,
      "learning_rate": 2.43550361297047e-05,
      "loss": 1.0829,
      "step": 77
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.20565740764141083,
      "learning_rate": 2.245515092739488e-05,
      "loss": 1.1548,
      "step": 78
    },
    {
      "epoch": 0.27147766323024053,
      "grad_norm": 0.2065347284078598,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0775,
      "step": 79
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 0.20886455476284027,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 1.1291,
      "step": 80
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 0.2221737802028656,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 1.1161,
      "step": 81
    },
    {
      "epoch": 0.281786941580756,
      "grad_norm": 0.2226671576499939,
      "learning_rate": 1.544686755065677e-05,
      "loss": 1.1343,
      "step": 82
    },
    {
      "epoch": 0.2852233676975945,
      "grad_norm": 0.23488934338092804,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 1.1316,
      "step": 83
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.22793255746364594,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 1.1914,
      "step": 84
    },
    {
      "epoch": 0.2920962199312715,
      "grad_norm": 0.21478554606437683,
      "learning_rate": 1.090842587659851e-05,
      "loss": 1.1428,
      "step": 85
    },
    {
      "epoch": 0.29553264604810997,
      "grad_norm": 0.23316501080989838,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1249,
      "step": 86
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 0.23652265965938568,
      "learning_rate": 8.271337313934869e-06,
      "loss": 1.189,
      "step": 87
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 0.23535004258155823,
      "learning_rate": 7.077560319906695e-06,
      "loss": 1.0792,
      "step": 88
    },
    {
      "epoch": 0.30584192439862545,
      "grad_norm": 0.258597195148468,
      "learning_rate": 5.9702234071631e-06,
      "loss": 1.1569,
      "step": 89
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.2510943114757538,
      "learning_rate": 4.951556604879048e-06,
      "loss": 1.1356,
      "step": 90
    },
    {
      "epoch": 0.3127147766323024,
      "grad_norm": 0.2706563472747803,
      "learning_rate": 4.023611372427471e-06,
      "loss": 1.1213,
      "step": 91
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 0.27767154574394226,
      "learning_rate": 3.18825646801314e-06,
      "loss": 1.1168,
      "step": 92
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 0.2995973229408264,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1346,
      "step": 93
    },
    {
      "epoch": 0.3230240549828179,
      "grad_norm": 0.3433845341205597,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 1.1632,
      "step": 94
    },
    {
      "epoch": 0.32646048109965636,
      "grad_norm": 0.3424028754234314,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 1.2433,
      "step": 95
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.3730294704437256,
      "learning_rate": 8.035205700685167e-07,
      "loss": 1.1239,
      "step": 96
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.40019187331199646,
      "learning_rate": 4.52511911603265e-07,
      "loss": 1.273,
      "step": 97
    },
    {
      "epoch": 0.33676975945017185,
      "grad_norm": 0.4186374843120575,
      "learning_rate": 2.012853002380466e-07,
      "loss": 1.1646,
      "step": 98
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 0.471892386674881,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 1.2248,
      "step": 99
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 0.5741357803344727,
      "learning_rate": 0.0,
      "loss": 1.3389,
      "step": 100
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 1.1233247518539429,
      "eval_runtime": 41.6622,
      "eval_samples_per_second": 11.761,
      "eval_steps_per_second": 5.881,
      "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": 5,
        "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": 1.4302829573308416e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}