{
  "best_metric": 5.867722511291504,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.704225352112676,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007042253521126761,
      "grad_norm": 2.1709582805633545,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 5.9888,
      "step": 1
    },
    {
      "epoch": 0.007042253521126761,
      "eval_loss": 6.261096477508545,
      "eval_runtime": 6.4702,
      "eval_samples_per_second": 9.273,
      "eval_steps_per_second": 1.236,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 2.2458949089050293,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 5.5952,
      "step": 2
    },
    {
      "epoch": 0.02112676056338028,
      "grad_norm": 2.041707992553711,
      "learning_rate": 5.000000000000001e-07,
      "loss": 6.4196,
      "step": 3
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 2.0842370986938477,
      "learning_rate": 6.666666666666667e-07,
      "loss": 5.9234,
      "step": 4
    },
    {
      "epoch": 0.035211267605633804,
      "grad_norm": 2.12766695022583,
      "learning_rate": 8.333333333333333e-07,
      "loss": 6.3325,
      "step": 5
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 2.3682479858398438,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 6.3195,
      "step": 6
    },
    {
      "epoch": 0.04929577464788732,
      "grad_norm": 1.981647253036499,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 6.0405,
      "step": 7
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 2.3705790042877197,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 6.3538,
      "step": 8
    },
    {
      "epoch": 0.06338028169014084,
      "grad_norm": 1.9218088388442993,
      "learning_rate": 1.5e-06,
      "loss": 7.0959,
      "step": 9
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 2.0986599922180176,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 6.0822,
      "step": 10
    },
    {
      "epoch": 0.07746478873239436,
      "grad_norm": 2.145479440689087,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 6.478,
      "step": 11
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 2.1634578704833984,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 6.8397,
      "step": 12
    },
    {
      "epoch": 0.09154929577464789,
      "grad_norm": 1.9787063598632812,
      "learning_rate": 2.166666666666667e-06,
      "loss": 5.9097,
      "step": 13
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 2.3650400638580322,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 6.5708,
      "step": 14
    },
    {
      "epoch": 0.1056338028169014,
      "grad_norm": 3.0832879543304443,
      "learning_rate": 2.5e-06,
      "loss": 6.2788,
      "step": 15
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 2.0778448581695557,
      "learning_rate": 2.666666666666667e-06,
      "loss": 6.6484,
      "step": 16
    },
    {
      "epoch": 0.11971830985915492,
      "grad_norm": 3.3111774921417236,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 6.7573,
      "step": 17
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 2.3213605880737305,
      "learning_rate": 3e-06,
      "loss": 6.2167,
      "step": 18
    },
    {
      "epoch": 0.13380281690140844,
      "grad_norm": 2.8803393840789795,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 6.7886,
      "step": 19
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 2.4236204624176025,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 6.174,
      "step": 20
    },
    {
      "epoch": 0.14788732394366197,
      "grad_norm": 2.1381118297576904,
      "learning_rate": 3.5e-06,
      "loss": 6.3105,
      "step": 21
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 2.8084843158721924,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 6.5019,
      "step": 22
    },
    {
      "epoch": 0.1619718309859155,
      "grad_norm": 2.57002854347229,
      "learning_rate": 3.833333333333334e-06,
      "loss": 6.6068,
      "step": 23
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 2.539491653442383,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.2395,
      "step": 24
    },
    {
      "epoch": 0.176056338028169,
      "grad_norm": 3.1248769760131836,
      "learning_rate": 4.166666666666667e-06,
      "loss": 6.7675,
      "step": 25
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 2.8243026733398438,
      "learning_rate": 4.333333333333334e-06,
      "loss": 6.3303,
      "step": 26
    },
    {
      "epoch": 0.19014084507042253,
      "grad_norm": 3.0351223945617676,
      "learning_rate": 4.5e-06,
      "loss": 6.3936,
      "step": 27
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 3.7776167392730713,
      "learning_rate": 4.666666666666667e-06,
      "loss": 6.4427,
      "step": 28
    },
    {
      "epoch": 0.20422535211267606,
      "grad_norm": 3.09165358543396,
      "learning_rate": 4.833333333333333e-06,
      "loss": 6.2771,
      "step": 29
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 2.897477388381958,
      "learning_rate": 5e-06,
      "loss": 6.6542,
      "step": 30
    },
    {
      "epoch": 0.21830985915492956,
      "grad_norm": 2.766329765319824,
      "learning_rate": 4.997482666353287e-06,
      "loss": 6.3455,
      "step": 31
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 2.775054454803467,
      "learning_rate": 4.989935734988098e-06,
      "loss": 6.5761,
      "step": 32
    },
    {
      "epoch": 0.2323943661971831,
      "grad_norm": 3.120526075363159,
      "learning_rate": 4.977374404419838e-06,
      "loss": 6.199,
      "step": 33
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 3.723641872406006,
      "learning_rate": 4.959823971496575e-06,
      "loss": 7.2368,
      "step": 34
    },
    {
      "epoch": 0.24647887323943662,
      "grad_norm": 3.0915040969848633,
      "learning_rate": 4.937319780454559e-06,
      "loss": 6.1556,
      "step": 35
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 2.8328888416290283,
      "learning_rate": 4.909907151739634e-06,
      "loss": 6.7386,
      "step": 36
    },
    {
      "epoch": 0.2605633802816901,
      "grad_norm": 2.697397232055664,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 6.3985,
      "step": 37
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 2.4430923461914062,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 5.5048,
      "step": 38
    },
    {
      "epoch": 0.2746478873239437,
      "grad_norm": 2.8614447116851807,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 5.8983,
      "step": 39
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 3.3354713916778564,
      "learning_rate": 4.752422169756048e-06,
      "loss": 6.2579,
      "step": 40
    },
    {
      "epoch": 0.2887323943661972,
      "grad_norm": 3.4687860012054443,
      "learning_rate": 4.701488829641845e-06,
      "loss": 6.2994,
      "step": 41
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 2.856947898864746,
      "learning_rate": 4.646121984004666e-06,
      "loss": 6.3684,
      "step": 42
    },
    {
      "epoch": 0.3028169014084507,
      "grad_norm": 3.9798505306243896,
      "learning_rate": 4.586433134303257e-06,
      "loss": 7.101,
      "step": 43
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 3.1907942295074463,
      "learning_rate": 4.522542485937369e-06,
      "loss": 6.0568,
      "step": 44
    },
    {
      "epoch": 0.31690140845070425,
      "grad_norm": 3.108004093170166,
      "learning_rate": 4.454578706170075e-06,
      "loss": 5.3406,
      "step": 45
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 3.317600727081299,
      "learning_rate": 4.382678665009028e-06,
      "loss": 6.5661,
      "step": 46
    },
    {
      "epoch": 0.33098591549295775,
      "grad_norm": 3.494509220123291,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 5.816,
      "step": 47
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 3.3108158111572266,
      "learning_rate": 4.227656622467162e-06,
      "loss": 5.4625,
      "step": 48
    },
    {
      "epoch": 0.34507042253521125,
      "grad_norm": 2.896949291229248,
      "learning_rate": 4.144846814849282e-06,
      "loss": 6.4299,
      "step": 49
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 2.9589807987213135,
      "learning_rate": 4.058724504646834e-06,
      "loss": 5.879,
      "step": 50
    },
    {
      "epoch": 0.352112676056338,
      "eval_loss": 6.142022609710693,
      "eval_runtime": 6.5937,
      "eval_samples_per_second": 9.1,
      "eval_steps_per_second": 1.213,
      "step": 50
    },
    {
      "epoch": 0.3591549295774648,
      "grad_norm": 3.2810099124908447,
      "learning_rate": 3.969463130731183e-06,
      "loss": 6.2124,
      "step": 51
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 3.4586217403411865,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 6.9627,
      "step": 52
    },
    {
      "epoch": 0.3732394366197183,
      "grad_norm": 3.5371925830841064,
      "learning_rate": 3.782248193514766e-06,
      "loss": 5.8214,
      "step": 53
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 3.8232100009918213,
      "learning_rate": 3.684671656182497e-06,
      "loss": 6.1178,
      "step": 54
    },
    {
      "epoch": 0.3873239436619718,
      "grad_norm": 4.544223785400391,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 6.2917,
      "step": 55
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 3.5962297916412354,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 5.5094,
      "step": 56
    },
    {
      "epoch": 0.4014084507042254,
      "grad_norm": 4.584772109985352,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 7.5249,
      "step": 57
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 4.308250427246094,
      "learning_rate": 3.272542485937369e-06,
      "loss": 6.3212,
      "step": 58
    },
    {
      "epoch": 0.4154929577464789,
      "grad_norm": 3.8824479579925537,
      "learning_rate": 3.165092113916688e-06,
      "loss": 5.7734,
      "step": 59
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 3.946568250656128,
      "learning_rate": 3.056302334890786e-06,
      "loss": 6.5095,
      "step": 60
    },
    {
      "epoch": 0.4295774647887324,
      "grad_norm": 3.413088083267212,
      "learning_rate": 2.946392236996592e-06,
      "loss": 6.5014,
      "step": 61
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 3.663517713546753,
      "learning_rate": 2.835583164544139e-06,
      "loss": 6.3028,
      "step": 62
    },
    {
      "epoch": 0.44366197183098594,
      "grad_norm": 3.5873265266418457,
      "learning_rate": 2.724098272258584e-06,
      "loss": 6.5212,
      "step": 63
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 3.847581148147583,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 6.2379,
      "step": 64
    },
    {
      "epoch": 0.45774647887323944,
      "grad_norm": 3.835568428039551,
      "learning_rate": 2.5e-06,
      "loss": 5.7499,
      "step": 65
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 4.436716079711914,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 6.0118,
      "step": 66
    },
    {
      "epoch": 0.47183098591549294,
      "grad_norm": 4.0455002784729,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 5.9979,
      "step": 67
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 4.169304847717285,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 5.4277,
      "step": 68
    },
    {
      "epoch": 0.4859154929577465,
      "grad_norm": 3.745866537094116,
      "learning_rate": 2.053607763003409e-06,
      "loss": 5.9037,
      "step": 69
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 5.223974704742432,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 6.1697,
      "step": 70
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.916987657546997,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 5.6168,
      "step": 71
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 3.2705447673797607,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 5.3624,
      "step": 72
    },
    {
      "epoch": 0.5140845070422535,
      "grad_norm": 4.038527488708496,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 5.6942,
      "step": 73
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 3.7204744815826416,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 5.8837,
      "step": 74
    },
    {
      "epoch": 0.528169014084507,
      "grad_norm": 4.190001487731934,
      "learning_rate": 1.415290652206105e-06,
      "loss": 5.6448,
      "step": 75
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 3.036896228790283,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 5.9509,
      "step": 76
    },
    {
      "epoch": 0.5422535211267606,
      "grad_norm": 4.141100883483887,
      "learning_rate": 1.217751806485235e-06,
      "loss": 5.5891,
      "step": 77
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 3.8306446075439453,
      "learning_rate": 1.122757546369744e-06,
      "loss": 6.0617,
      "step": 78
    },
    {
      "epoch": 0.5563380281690141,
      "grad_norm": 3.9133124351501465,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 5.6559,
      "step": 79
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 3.6098997592926025,
      "learning_rate": 9.412754953531664e-07,
      "loss": 5.2484,
      "step": 80
    },
    {
      "epoch": 0.5704225352112676,
      "grad_norm": 3.8136210441589355,
      "learning_rate": 8.551531851507186e-07,
      "loss": 5.834,
      "step": 81
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 4.0824480056762695,
      "learning_rate": 7.723433775328385e-07,
      "loss": 5.732,
      "step": 82
    },
    {
      "epoch": 0.5845070422535211,
      "grad_norm": 4.940346717834473,
      "learning_rate": 6.930128404315214e-07,
      "loss": 7.0341,
      "step": 83
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 3.8270716667175293,
      "learning_rate": 6.17321334990973e-07,
      "loss": 5.5377,
      "step": 84
    },
    {
      "epoch": 0.5985915492957746,
      "grad_norm": 3.9446895122528076,
      "learning_rate": 5.454212938299256e-07,
      "loss": 5.6576,
      "step": 85
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 4.037410259246826,
      "learning_rate": 4.774575140626317e-07,
      "loss": 5.758,
      "step": 86
    },
    {
      "epoch": 0.6126760563380281,
      "grad_norm": 4.448607921600342,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 5.8112,
      "step": 87
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 3.8815934658050537,
      "learning_rate": 3.538780159953348e-07,
      "loss": 5.6519,
      "step": 88
    },
    {
      "epoch": 0.6267605633802817,
      "grad_norm": 4.358070373535156,
      "learning_rate": 2.98511170358155e-07,
      "loss": 5.7299,
      "step": 89
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 3.2126142978668213,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 6.0813,
      "step": 90
    },
    {
      "epoch": 0.6408450704225352,
      "grad_norm": 3.676884651184082,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 5.6813,
      "step": 91
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 3.7823681831359863,
      "learning_rate": 1.59412823400657e-07,
      "loss": 6.4328,
      "step": 92
    },
    {
      "epoch": 0.6549295774647887,
      "grad_norm": 4.694835186004639,
      "learning_rate": 1.223587092621162e-07,
      "loss": 6.0319,
      "step": 93
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 4.232463836669922,
      "learning_rate": 9.00928482603669e-08,
      "loss": 6.6748,
      "step": 94
    },
    {
      "epoch": 0.6690140845070423,
      "grad_norm": 4.175792217254639,
      "learning_rate": 6.268021954544095e-08,
      "loss": 5.7904,
      "step": 95
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 3.6760425567626953,
      "learning_rate": 4.017602850342584e-08,
      "loss": 6.246,
      "step": 96
    },
    {
      "epoch": 0.6830985915492958,
      "grad_norm": 3.92482328414917,
      "learning_rate": 2.262559558016325e-08,
      "loss": 6.2813,
      "step": 97
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 3.756988525390625,
      "learning_rate": 1.006426501190233e-08,
      "loss": 6.542,
      "step": 98
    },
    {
      "epoch": 0.6971830985915493,
      "grad_norm": 3.8519887924194336,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 5.1306,
      "step": 99
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 5.956462383270264,
      "learning_rate": 0.0,
      "loss": 6.0674,
      "step": 100
    },
    {
      "epoch": 0.704225352112676,
      "eval_loss": 5.867722511291504,
      "eval_runtime": 6.5984,
      "eval_samples_per_second": 9.093,
      "eval_steps_per_second": 1.212,
      "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": 6.3324486107136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}