{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1892147587511826,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001892147587511826,
      "grad_norm": 2.3839447749196552e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.001892147587511826,
      "eval_loss": 11.5,
      "eval_runtime": 4.1507,
      "eval_samples_per_second": 214.421,
      "eval_steps_per_second": 53.726,
      "step": 1
    },
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 4.638839527615346e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.005676442762535478,
      "grad_norm": 3.479818406049162e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 3.919842856703326e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00946073793755913,
      "grad_norm": 2.621494058985263e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 6.282983667915687e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 5.2673090976895764e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 4.525974873104133e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.017029328287606435,
      "grad_norm": 4.623180575435981e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.01892147587511826,
      "grad_norm": 4.1833834984572604e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.020813623462630087,
      "grad_norm": 3.8247926568146795e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.02270577105014191,
      "grad_norm": 3.979763641837053e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.02459791863765374,
      "grad_norm": 3.845677201752551e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 5.9959787904517725e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.02838221381267739,
      "grad_norm": 3.9593734982190654e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.030274361400189215,
      "grad_norm": 4.5368968130787835e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.03216650898770104,
      "grad_norm": 4.2684645450208336e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.03405865657521287,
      "grad_norm": 4.794902270077728e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.03595080416272469,
      "grad_norm": 5.0609214667929336e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.03784295175023652,
      "grad_norm": 4.8287631216226146e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.039735099337748346,
      "grad_norm": 3.278631265857257e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.041627246925260174,
      "grad_norm": 5.529154441319406e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.043519394512771994,
      "grad_norm": 4.465828897082247e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.04541154210028382,
      "grad_norm": 5.3063722589286044e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.04730368968779565,
      "grad_norm": 4.9931979447137564e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.04919583727530748,
      "grad_norm": 7.026691309874877e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.0510879848628193,
      "grad_norm": 5.010387030779384e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 7.026026287348941e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.05487228003784295,
      "grad_norm": 5.239866368356161e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.05676442762535478,
      "grad_norm": 3.271478635724634e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0586565752128666,
      "grad_norm": 6.0700585891027004e-05,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.06054872280037843,
      "grad_norm": 8.431349124293774e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.06244087038789026,
      "grad_norm": 7.989972800714895e-05,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.06433301797540208,
      "grad_norm": 9.198014595312998e-05,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 6.828641198808327e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.06811731315042574,
      "grad_norm": 8.098001853795722e-05,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.07000946073793755,
      "grad_norm": 7.835058204364032e-05,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.07190160832544938,
      "grad_norm": 9.395871893502772e-05,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.07379375591296121,
      "grad_norm": 7.016255403868854e-05,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.07568590350047304,
      "grad_norm": 8.687914669280872e-05,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.07757805108798486,
      "grad_norm": 0.00012134222924942151,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 9.552970732329413e-05,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.08136234626300852,
      "grad_norm": 9.902394231176004e-05,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.08325449385052035,
      "grad_norm": 9.72863199422136e-05,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.08514664143803216,
      "grad_norm": 0.00011048799206037074,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.08703878902554399,
      "grad_norm": 8.787698607193306e-05,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.08893093661305582,
      "grad_norm": 0.0001252793736057356,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.09082308420056764,
      "grad_norm": 0.0001618423848412931,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.09271523178807947,
      "grad_norm": 9.405127639183775e-05,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.0946073793755913,
      "grad_norm": 9.213040175382048e-05,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.0946073793755913,
      "eval_loss": 11.5,
      "eval_runtime": 4.122,
      "eval_samples_per_second": 215.916,
      "eval_steps_per_second": 54.1,
      "step": 50
    },
    {
      "epoch": 0.09649952696310313,
      "grad_norm": 0.00012417437392286956,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.09839167455061495,
      "grad_norm": 8.053371857386082e-05,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.10028382213812677,
      "grad_norm": 0.00012267443526070565,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.1021759697256386,
      "grad_norm": 9.22976469155401e-05,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.10406811731315042,
      "grad_norm": 0.00014841851952951401,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.00010376374120824039,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.10785241248817408,
      "grad_norm": 0.00013921655772719532,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.1097445600756859,
      "grad_norm": 0.00014789735723752528,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.11163670766319773,
      "grad_norm": 0.00011552827345440164,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.11352885525070956,
      "grad_norm": 0.00011432983592385426,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.11542100283822138,
      "grad_norm": 0.0001263416197616607,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.1173131504257332,
      "grad_norm": 0.00011249220551690087,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.11920529801324503,
      "grad_norm": 0.00010807299258885905,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.12109744560075686,
      "grad_norm": 0.0001297717826673761,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.12298959318826869,
      "grad_norm": 0.00014674756675958633,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.12488174077578051,
      "grad_norm": 0.0002308681287104264,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.12677388836329234,
      "grad_norm": 0.0002709355321712792,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.12866603595080417,
      "grad_norm": 0.00012638290354516357,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.130558183538316,
      "grad_norm": 0.00017550082702655345,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.00018102949252352118,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.13434247871333965,
      "grad_norm": 0.00020361885253805667,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.13623462630085148,
      "grad_norm": 0.0001768656075000763,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.13812677388836328,
      "grad_norm": 0.0001600666146259755,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.1400189214758751,
      "grad_norm": 0.000227691387408413,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.14191106906338694,
      "grad_norm": 0.0002127019251929596,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.14380321665089876,
      "grad_norm": 0.0002423242840450257,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.1456953642384106,
      "grad_norm": 0.0002810981823131442,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.14758751182592242,
      "grad_norm": 0.00021749395818915218,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.14947965941343425,
      "grad_norm": 0.00019683352729771286,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.15137180700094607,
      "grad_norm": 0.0001746660564094782,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.1532639545884579,
      "grad_norm": 0.00017801375361159444,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.15515610217596973,
      "grad_norm": 0.0002609042276162654,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.15704824976348156,
      "grad_norm": 0.00022626941790804267,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.00014837666822131723,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.1608325449385052,
      "grad_norm": 0.00017812247097026557,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.16272469252601704,
      "grad_norm": 0.0003273199254181236,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.16461684011352887,
      "grad_norm": 0.0001915306638693437,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.1665089877010407,
      "grad_norm": 0.00027566467178985476,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.1684011352885525,
      "grad_norm": 0.00033509283093735576,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.17029328287606432,
      "grad_norm": 0.00022767751943320036,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.17218543046357615,
      "grad_norm": 0.0003614956222008914,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.17407757805108798,
      "grad_norm": 0.00018008582992479205,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.1759697256385998,
      "grad_norm": 0.00024141301400959492,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.17786187322611163,
      "grad_norm": 0.00018027549958787858,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.17975402081362346,
      "grad_norm": 0.00021589604148175567,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.1816461684011353,
      "grad_norm": 0.00026545184664428234,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.18353831598864712,
      "grad_norm": 0.00031433062395080924,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.00024231721181422472,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.18732261116367077,
      "grad_norm": 0.00027983065228909254,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.1892147587511826,
      "grad_norm": 0.0003798572579398751,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.1892147587511826,
      "eval_loss": 11.5,
      "eval_runtime": 4.1411,
      "eval_samples_per_second": 214.918,
      "eval_steps_per_second": 53.85,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 16079231385600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}