{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.007518796992481,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 9.266636334359646e-05,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.03007518796992481,
      "eval_loss": 11.5,
      "eval_runtime": 0.3095,
      "eval_samples_per_second": 1437.638,
      "eval_steps_per_second": 45.229,
      "step": 1
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 9.364843572257087e-05,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.00010662364365998656,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 9.021838195621967e-05,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 7.925021054688841e-05,
      "learning_rate": 5.05e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 8.351929864147678e-05,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 9.711394523037598e-05,
      "learning_rate": 7.07e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 9.60054385359399e-05,
      "learning_rate": 8.080000000000001e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 0.00012731400784105062,
      "learning_rate": 9.09e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.00011434268526500091,
      "learning_rate": 0.000101,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 9.765291906660423e-05,
      "learning_rate": 9.987777777777779e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.3609022556390977,
      "grad_norm": 9.876976400846615e-05,
      "learning_rate": 9.875555555555555e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.39097744360902253,
      "grad_norm": 0.00011370878928573802,
      "learning_rate": 9.763333333333334e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.0001137641811510548,
      "learning_rate": 9.651111111111111e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.0001710877986624837,
      "learning_rate": 9.538888888888889e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.48120300751879697,
      "grad_norm": 0.0001575473725097254,
      "learning_rate": 9.426666666666668e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.5112781954887218,
      "grad_norm": 0.0001343897165497765,
      "learning_rate": 9.314444444444445e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.5413533834586466,
      "grad_norm": 0.00015038810670375824,
      "learning_rate": 9.202222222222223e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.00013464110088534653,
      "learning_rate": 9.09e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.0001557513460284099,
      "learning_rate": 8.977777777777778e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.00022612961765844375,
      "learning_rate": 8.865555555555555e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.6616541353383458,
      "grad_norm": 0.00020132240024395287,
      "learning_rate": 8.753333333333334e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.6917293233082706,
      "grad_norm": 0.00018423757865093648,
      "learning_rate": 8.641111111111111e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.7218045112781954,
      "grad_norm": 0.00016721716383472085,
      "learning_rate": 8.528888888888889e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.0001902187941595912,
      "learning_rate": 8.416666666666668e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.7819548872180451,
      "grad_norm": 0.00020407498232088983,
      "learning_rate": 8.304444444444444e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.8120300751879699,
      "grad_norm": 0.0002489977050572634,
      "learning_rate": 8.192222222222222e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.00030909531051293015,
      "learning_rate": 8.080000000000001e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.8721804511278195,
      "grad_norm": 0.000234145627473481,
      "learning_rate": 7.967777777777777e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.0002202718605985865,
      "learning_rate": 7.855555555555556e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.9323308270676691,
      "grad_norm": 0.0002214343985542655,
      "learning_rate": 7.743333333333334e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.9624060150375939,
      "grad_norm": 0.00025516573805361986,
      "learning_rate": 7.631111111111111e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.9924812030075187,
      "grad_norm": 0.00025323766749352217,
      "learning_rate": 7.51888888888889e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 1.0225563909774436,
      "grad_norm": 0.00027011558995582163,
      "learning_rate": 7.406666666666666e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.0002727561804931611,
      "learning_rate": 7.294444444444445e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 1.0827067669172932,
      "grad_norm": 0.00034800541470758617,
      "learning_rate": 7.182222222222222e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 1.112781954887218,
      "grad_norm": 0.0003243626852054149,
      "learning_rate": 7.07e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.0002872659242711961,
      "learning_rate": 6.957777777777777e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 1.1729323308270676,
      "grad_norm": 0.00030295943724922836,
      "learning_rate": 6.845555555555556e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 1.2030075187969924,
      "grad_norm": 0.00025122929946519434,
      "learning_rate": 6.733333333333333e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 1.2330827067669172,
      "grad_norm": 0.00027522369055077434,
      "learning_rate": 6.621111111111111e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.00043568338151089847,
      "learning_rate": 6.50888888888889e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 1.2932330827067668,
      "grad_norm": 0.0003823314909823239,
      "learning_rate": 6.396666666666666e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 1.3233082706766917,
      "grad_norm": 0.00034535420127213,
      "learning_rate": 6.284444444444445e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 1.3533834586466165,
      "grad_norm": 0.0003590960695873946,
      "learning_rate": 6.172222222222223e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 1.3834586466165413,
      "grad_norm": 0.00029228764469735324,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 1.413533834586466,
      "grad_norm": 0.0002954736119136214,
      "learning_rate": 5.9477777777777784e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 1.443609022556391,
      "grad_norm": 0.0005244979402050376,
      "learning_rate": 5.835555555555555e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.00042245551594533026,
      "learning_rate": 5.723333333333333e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 0.00039055367233231664,
      "learning_rate": 5.6111111111111114e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 1.5037593984962405,
      "eval_loss": 11.5,
      "eval_runtime": 0.305,
      "eval_samples_per_second": 1458.84,
      "eval_steps_per_second": 45.896,
      "step": 50
    },
    {
      "epoch": 1.5338345864661656,
      "grad_norm": 0.0003437866980675608,
      "learning_rate": 5.498888888888888e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 1.5639097744360901,
      "grad_norm": 0.00032857232145033777,
      "learning_rate": 5.3866666666666664e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 1.5939849624060152,
      "grad_norm": 0.00038689709617756307,
      "learning_rate": 5.274444444444445e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 1.6240601503759398,
      "grad_norm": 0.0004355922865215689,
      "learning_rate": 5.162222222222222e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 1.6541353383458648,
      "grad_norm": 0.0005018658121116459,
      "learning_rate": 5.05e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.00045422802213579416,
      "learning_rate": 4.9377777777777776e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.0003774865763261914,
      "learning_rate": 4.825555555555556e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 1.744360902255639,
      "grad_norm": 0.00042634535930119455,
      "learning_rate": 4.713333333333334e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 1.774436090225564,
      "grad_norm": 0.000391370733268559,
      "learning_rate": 4.601111111111111e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 1.8045112781954886,
      "grad_norm": 0.00042282594949938357,
      "learning_rate": 4.488888888888889e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 1.8345864661654137,
      "grad_norm": 0.0005342218209989369,
      "learning_rate": 4.376666666666667e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 1.8646616541353382,
      "grad_norm": 0.0004987895372323692,
      "learning_rate": 4.2644444444444443e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.00042961034341715276,
      "learning_rate": 4.152222222222222e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 1.9248120300751879,
      "grad_norm": 0.00040588382398709655,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 1.954887218045113,
      "grad_norm": 0.00041778653394430876,
      "learning_rate": 3.927777777777778e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 1.9849624060150375,
      "grad_norm": 0.00044860667549073696,
      "learning_rate": 3.8155555555555555e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 2.0150375939849625,
      "grad_norm": 0.00040975239244289696,
      "learning_rate": 3.703333333333333e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 2.045112781954887,
      "grad_norm": 0.00044060847721993923,
      "learning_rate": 3.591111111111111e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 2.075187969924812,
      "grad_norm": 0.0006466583581641316,
      "learning_rate": 3.4788888888888886e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.000526844582054764,
      "learning_rate": 3.366666666666667e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 2.1353383458646618,
      "grad_norm": 0.0005004553822800517,
      "learning_rate": 3.254444444444445e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 2.1654135338345863,
      "grad_norm": 0.0004915460012853146,
      "learning_rate": 3.142222222222222e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 2.1954887218045114,
      "grad_norm": 0.0004236290114931762,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 2.225563909774436,
      "grad_norm": 0.000418194686062634,
      "learning_rate": 2.9177777777777776e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 2.255639097744361,
      "grad_norm": 0.0006017014384269714,
      "learning_rate": 2.8055555555555557e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.0006093091797083616,
      "learning_rate": 2.6933333333333332e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.0005279547767713666,
      "learning_rate": 2.581111111111111e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 2.345864661654135,
      "grad_norm": 0.000503562914673239,
      "learning_rate": 2.4688888888888888e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 2.3759398496240602,
      "grad_norm": 0.0005086955497972667,
      "learning_rate": 2.356666666666667e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 2.406015037593985,
      "grad_norm": 0.0005278786411508918,
      "learning_rate": 2.2444444444444444e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 2.43609022556391,
      "grad_norm": 0.0005769961280748248,
      "learning_rate": 2.1322222222222222e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 2.4661654135338344,
      "grad_norm": 0.0006405999301932752,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 2.4962406015037595,
      "grad_norm": 0.000521977839525789,
      "learning_rate": 1.9077777777777778e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.0004871116252616048,
      "learning_rate": 1.7955555555555556e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 2.556390977443609,
      "grad_norm": 0.0005196544225327671,
      "learning_rate": 1.6833333333333334e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 2.5864661654135337,
      "grad_norm": 0.00043869740329682827,
      "learning_rate": 1.571111111111111e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 2.6165413533834587,
      "grad_norm": 0.0005383821553550661,
      "learning_rate": 1.4588888888888888e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 2.6466165413533833,
      "grad_norm": 0.0007268090848810971,
      "learning_rate": 1.3466666666666666e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 2.6766917293233083,
      "grad_norm": 0.0006505560595542192,
      "learning_rate": 1.2344444444444444e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 2.706766917293233,
      "grad_norm": 0.0005259292083792388,
      "learning_rate": 1.1222222222222222e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.0004948357818648219,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 2.7669172932330826,
      "grad_norm": 0.00042854080675169826,
      "learning_rate": 8.977777777777778e-06,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 2.7969924812030076,
      "grad_norm": 0.00048204101040028036,
      "learning_rate": 7.855555555555556e-06,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 2.827067669172932,
      "grad_norm": 0.0006985705113038421,
      "learning_rate": 6.733333333333333e-06,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.0005821044323965907,
      "learning_rate": 5.611111111111111e-06,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 2.887218045112782,
      "grad_norm": 0.0005263919592835009,
      "learning_rate": 4.488888888888889e-06,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 2.917293233082707,
      "grad_norm": 0.0005317186005413532,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 0.00046762413694523275,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 2.9774436090225564,
      "grad_norm": 0.0006510710809379816,
      "learning_rate": 1.1222222222222222e-06,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 3.007518796992481,
      "grad_norm": 0.00044690861250273883,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 3.007518796992481,
      "eval_loss": 11.5,
      "eval_runtime": 0.3049,
      "eval_samples_per_second": 1459.491,
      "eval_steps_per_second": 45.917,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 128633851084800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}