{
  "best_metric": 1.0454801321029663,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.07964954201513341,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010619938935351122,
      "grad_norm": 50.445369720458984,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 43.7219,
      "step": 1
    },
    {
      "epoch": 0.0010619938935351122,
      "eval_loss": 1.3181114196777344,
      "eval_runtime": 4.7962,
      "eval_samples_per_second": 10.425,
      "eval_steps_per_second": 2.71,
      "step": 1
    },
    {
      "epoch": 0.0021239877870702245,
      "grad_norm": 22.956039428710938,
      "learning_rate": 6.666666666666667e-05,
      "loss": 40.9591,
      "step": 2
    },
    {
      "epoch": 0.0031859816806053365,
      "grad_norm": 66.04405975341797,
      "learning_rate": 0.0001,
      "loss": 70.2201,
      "step": 3
    },
    {
      "epoch": 0.004247975574140449,
      "grad_norm": 46.3990592956543,
      "learning_rate": 9.99571699711836e-05,
      "loss": 51.5672,
      "step": 4
    },
    {
      "epoch": 0.005309969467675561,
      "grad_norm": 30.05483055114746,
      "learning_rate": 9.982876141412856e-05,
      "loss": 43.201,
      "step": 5
    },
    {
      "epoch": 0.006371963361210673,
      "grad_norm": 24.478403091430664,
      "learning_rate": 9.961501876182148e-05,
      "loss": 38.8057,
      "step": 6
    },
    {
      "epoch": 0.007433957254745785,
      "grad_norm": 24.022966384887695,
      "learning_rate": 9.931634888554937e-05,
      "loss": 37.9515,
      "step": 7
    },
    {
      "epoch": 0.008495951148280898,
      "grad_norm": 21.067651748657227,
      "learning_rate": 9.893332032039701e-05,
      "loss": 41.8724,
      "step": 8
    },
    {
      "epoch": 0.009557945041816009,
      "grad_norm": 17.71038818359375,
      "learning_rate": 9.846666218300807e-05,
      "loss": 38.8532,
      "step": 9
    },
    {
      "epoch": 0.010619938935351122,
      "grad_norm": 23.2802791595459,
      "learning_rate": 9.791726278367022e-05,
      "loss": 44.3834,
      "step": 10
    },
    {
      "epoch": 0.011681932828886235,
      "grad_norm": 25.220415115356445,
      "learning_rate": 9.728616793536588e-05,
      "loss": 43.2465,
      "step": 11
    },
    {
      "epoch": 0.012743926722421346,
      "grad_norm": 30.065141677856445,
      "learning_rate": 9.657457896300791e-05,
      "loss": 42.4665,
      "step": 12
    },
    {
      "epoch": 0.013805920615956459,
      "grad_norm": 47.5212287902832,
      "learning_rate": 9.578385041664925e-05,
      "loss": 50.1018,
      "step": 13
    },
    {
      "epoch": 0.01486791450949157,
      "grad_norm": 34.7642936706543,
      "learning_rate": 9.491548749301997e-05,
      "loss": 40.72,
      "step": 14
    },
    {
      "epoch": 0.01592990840302668,
      "grad_norm": 23.62519073486328,
      "learning_rate": 9.397114317029975e-05,
      "loss": 42.3325,
      "step": 15
    },
    {
      "epoch": 0.016991902296561796,
      "grad_norm": 42.359012603759766,
      "learning_rate": 9.295261506157986e-05,
      "loss": 54.7568,
      "step": 16
    },
    {
      "epoch": 0.018053896190096907,
      "grad_norm": 21.744274139404297,
      "learning_rate": 9.186184199300464e-05,
      "loss": 36.6027,
      "step": 17
    },
    {
      "epoch": 0.019115890083632018,
      "grad_norm": 17.517501831054688,
      "learning_rate": 9.070090031310558e-05,
      "loss": 33.6735,
      "step": 18
    },
    {
      "epoch": 0.020177883977167133,
      "grad_norm": 13.376629829406738,
      "learning_rate": 8.947199994035401e-05,
      "loss": 34.858,
      "step": 19
    },
    {
      "epoch": 0.021239877870702244,
      "grad_norm": 16.480670928955078,
      "learning_rate": 8.817748015645558e-05,
      "loss": 35.9226,
      "step": 20
    },
    {
      "epoch": 0.022301871764237355,
      "grad_norm": 14.814435958862305,
      "learning_rate": 8.681980515339464e-05,
      "loss": 36.5462,
      "step": 21
    },
    {
      "epoch": 0.02336386565777247,
      "grad_norm": 15.242733001708984,
      "learning_rate": 8.540155934270471e-05,
      "loss": 38.7139,
      "step": 22
    },
    {
      "epoch": 0.02442585955130758,
      "grad_norm": 16.00188636779785,
      "learning_rate": 8.392544243589427e-05,
      "loss": 39.0224,
      "step": 23
    },
    {
      "epoch": 0.025487853444842692,
      "grad_norm": 16.244796752929688,
      "learning_rate": 8.239426430539243e-05,
      "loss": 38.5783,
      "step": 24
    },
    {
      "epoch": 0.026549847338377803,
      "grad_norm": 26.823301315307617,
      "learning_rate": 8.081093963579707e-05,
      "loss": 38.7784,
      "step": 25
    },
    {
      "epoch": 0.026549847338377803,
      "eval_loss": 1.1134846210479736,
      "eval_runtime": 5.1844,
      "eval_samples_per_second": 9.644,
      "eval_steps_per_second": 2.508,
      "step": 25
    },
    {
      "epoch": 0.027611841231912918,
      "grad_norm": 16.71857261657715,
      "learning_rate": 7.917848237560709e-05,
      "loss": 36.6123,
      "step": 26
    },
    {
      "epoch": 0.02867383512544803,
      "grad_norm": 10.87404727935791,
      "learning_rate": 7.75e-05,
      "loss": 37.5371,
      "step": 27
    },
    {
      "epoch": 0.02973582901898314,
      "grad_norm": 56.00872039794922,
      "learning_rate": 7.577868759557654e-05,
      "loss": 64.4314,
      "step": 28
    },
    {
      "epoch": 0.030797822912518254,
      "grad_norm": 22.56377601623535,
      "learning_rate": 7.401782177833148e-05,
      "loss": 35.6372,
      "step": 29
    },
    {
      "epoch": 0.03185981680605336,
      "grad_norm": 12.734387397766113,
      "learning_rate": 7.222075445642904e-05,
      "loss": 32.3161,
      "step": 30
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 14.141098976135254,
      "learning_rate": 7.03909064496551e-05,
      "loss": 34.3303,
      "step": 31
    },
    {
      "epoch": 0.03398380459312359,
      "grad_norm": 9.78072738647461,
      "learning_rate": 6.853176097769229e-05,
      "loss": 32.2263,
      "step": 32
    },
    {
      "epoch": 0.0350457984866587,
      "grad_norm": 12.632477760314941,
      "learning_rate": 6.664685702961344e-05,
      "loss": 33.7613,
      "step": 33
    },
    {
      "epoch": 0.036107792380193814,
      "grad_norm": 14.908531188964844,
      "learning_rate": 6.473978262721463e-05,
      "loss": 36.611,
      "step": 34
    },
    {
      "epoch": 0.037169786273728925,
      "grad_norm": 22.300689697265625,
      "learning_rate": 6.281416799501188e-05,
      "loss": 36.3684,
      "step": 35
    },
    {
      "epoch": 0.038231780167264036,
      "grad_norm": 22.755752563476562,
      "learning_rate": 6.087367864990233e-05,
      "loss": 37.6983,
      "step": 36
    },
    {
      "epoch": 0.03929377406079915,
      "grad_norm": 22.28518295288086,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 37.6341,
      "step": 37
    },
    {
      "epoch": 0.040355767954334265,
      "grad_norm": 29.46213150024414,
      "learning_rate": 5.696287243144013e-05,
      "loss": 41.3437,
      "step": 38
    },
    {
      "epoch": 0.041417761847869376,
      "grad_norm": 9.17482852935791,
      "learning_rate": 5.500000000000001e-05,
      "loss": 36.185,
      "step": 39
    },
    {
      "epoch": 0.04247975574140449,
      "grad_norm": 11.093894004821777,
      "learning_rate": 5.303712756855988e-05,
      "loss": 38.199,
      "step": 40
    },
    {
      "epoch": 0.0435417496349396,
      "grad_norm": 48.82663345336914,
      "learning_rate": 5.107799157635538e-05,
      "loss": 52.5876,
      "step": 41
    },
    {
      "epoch": 0.04460374352847471,
      "grad_norm": 14.177578926086426,
      "learning_rate": 4.912632135009769e-05,
      "loss": 33.7556,
      "step": 42
    },
    {
      "epoch": 0.04566573742200982,
      "grad_norm": 12.167204856872559,
      "learning_rate": 4.718583200498814e-05,
      "loss": 31.3788,
      "step": 43
    },
    {
      "epoch": 0.04672773131554494,
      "grad_norm": 14.164153099060059,
      "learning_rate": 4.526021737278538e-05,
      "loss": 30.4894,
      "step": 44
    },
    {
      "epoch": 0.04778972520908005,
      "grad_norm": 13.399406433105469,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 32.0962,
      "step": 45
    },
    {
      "epoch": 0.04885171910261516,
      "grad_norm": 15.352862358093262,
      "learning_rate": 4.146823902230772e-05,
      "loss": 34.1184,
      "step": 46
    },
    {
      "epoch": 0.04991371299615027,
      "grad_norm": 15.30873966217041,
      "learning_rate": 3.960909355034491e-05,
      "loss": 33.8862,
      "step": 47
    },
    {
      "epoch": 0.050975706889685383,
      "grad_norm": 14.761381149291992,
      "learning_rate": 3.777924554357096e-05,
      "loss": 33.5394,
      "step": 48
    },
    {
      "epoch": 0.052037700783220495,
      "grad_norm": 18.559497833251953,
      "learning_rate": 3.598217822166854e-05,
      "loss": 37.7572,
      "step": 49
    },
    {
      "epoch": 0.053099694676755606,
      "grad_norm": 29.4871826171875,
      "learning_rate": 3.422131240442349e-05,
      "loss": 37.6346,
      "step": 50
    },
    {
      "epoch": 0.053099694676755606,
      "eval_loss": 1.0646418333053589,
      "eval_runtime": 5.2151,
      "eval_samples_per_second": 9.587,
      "eval_steps_per_second": 2.493,
      "step": 50
    },
    {
      "epoch": 0.054161688570290724,
      "grad_norm": 14.636504173278809,
      "learning_rate": 3.250000000000001e-05,
      "loss": 35.0866,
      "step": 51
    },
    {
      "epoch": 0.055223682463825835,
      "grad_norm": 8.89908218383789,
      "learning_rate": 3.082151762439293e-05,
      "loss": 37.663,
      "step": 52
    },
    {
      "epoch": 0.056285676357360946,
      "grad_norm": 54.20383834838867,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 56.8162,
      "step": 53
    },
    {
      "epoch": 0.05734767025089606,
      "grad_norm": 16.383342742919922,
      "learning_rate": 2.760573569460757e-05,
      "loss": 33.3728,
      "step": 54
    },
    {
      "epoch": 0.05840966414443117,
      "grad_norm": 12.869865417480469,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 31.2535,
      "step": 55
    },
    {
      "epoch": 0.05947165803796628,
      "grad_norm": 11.180938720703125,
      "learning_rate": 2.459844065729529e-05,
      "loss": 31.5559,
      "step": 56
    },
    {
      "epoch": 0.06053365193150139,
      "grad_norm": 11.862079620361328,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 31.4833,
      "step": 57
    },
    {
      "epoch": 0.06159564582503651,
      "grad_norm": 12.11618423461914,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 32.5211,
      "step": 58
    },
    {
      "epoch": 0.06265763971857162,
      "grad_norm": 15.875182151794434,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 34.1747,
      "step": 59
    },
    {
      "epoch": 0.06371963361210672,
      "grad_norm": 19.710519790649414,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 35.3909,
      "step": 60
    },
    {
      "epoch": 0.06478162750564184,
      "grad_norm": 17.533973693847656,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 35.6223,
      "step": 61
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 22.0009822845459,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 36.3417,
      "step": 62
    },
    {
      "epoch": 0.06690561529271206,
      "grad_norm": 29.81911849975586,
      "learning_rate": 1.602885682970026e-05,
      "loss": 38.5256,
      "step": 63
    },
    {
      "epoch": 0.06796760918624718,
      "grad_norm": 7.941569805145264,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 36.4495,
      "step": 64
    },
    {
      "epoch": 0.06902960307978229,
      "grad_norm": 13.770777702331543,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 37.7728,
      "step": 65
    },
    {
      "epoch": 0.0700915969733174,
      "grad_norm": 51.46889877319336,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 54.747,
      "step": 66
    },
    {
      "epoch": 0.07115359086685251,
      "grad_norm": 12.53438949584961,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 30.7638,
      "step": 67
    },
    {
      "epoch": 0.07221558476038763,
      "grad_norm": 12.685519218444824,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 32.179,
      "step": 68
    },
    {
      "epoch": 0.07327757865392275,
      "grad_norm": 9.042292594909668,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 30.5281,
      "step": 69
    },
    {
      "epoch": 0.07433957254745785,
      "grad_norm": 11.904223442077637,
      "learning_rate": 1.1066679679603e-05,
      "loss": 31.7732,
      "step": 70
    },
    {
      "epoch": 0.07540156644099297,
      "grad_norm": 14.069729804992676,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 34.6085,
      "step": 71
    },
    {
      "epoch": 0.07646356033452807,
      "grad_norm": 13.064727783203125,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 32.5403,
      "step": 72
    },
    {
      "epoch": 0.07752555422806319,
      "grad_norm": 14.395278930664062,
      "learning_rate": 1.017123858587145e-05,
      "loss": 32.8443,
      "step": 73
    },
    {
      "epoch": 0.0785875481215983,
      "grad_norm": 16.937580108642578,
      "learning_rate": 1.00428300288164e-05,
      "loss": 34.9566,
      "step": 74
    },
    {
      "epoch": 0.07964954201513341,
      "grad_norm": 27.33036231994629,
      "learning_rate": 1e-05,
      "loss": 37.9665,
      "step": 75
    },
    {
      "epoch": 0.07964954201513341,
      "eval_loss": 1.0454801321029663,
      "eval_runtime": 5.1978,
      "eval_samples_per_second": 9.619,
      "eval_steps_per_second": 2.501,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.8034986327841178e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}