{
  "best_metric": 0.9207891225814819,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.23446658851113716,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023446658851113715,
      "grad_norm": 23.405542373657227,
      "learning_rate": 1e-05,
      "loss": 5.4807,
      "step": 1
    },
    {
      "epoch": 0.0023446658851113715,
      "eval_loss": 1.620888352394104,
      "eval_runtime": 52.3146,
      "eval_samples_per_second": 13.725,
      "eval_steps_per_second": 3.441,
      "step": 1
    },
    {
      "epoch": 0.004689331770222743,
      "grad_norm": 30.190401077270508,
      "learning_rate": 2e-05,
      "loss": 5.8935,
      "step": 2
    },
    {
      "epoch": 0.007033997655334115,
      "grad_norm": 26.080381393432617,
      "learning_rate": 3e-05,
      "loss": 5.84,
      "step": 3
    },
    {
      "epoch": 0.009378663540445486,
      "grad_norm": 23.042579650878906,
      "learning_rate": 4e-05,
      "loss": 5.3222,
      "step": 4
    },
    {
      "epoch": 0.011723329425556858,
      "grad_norm": 23.48046112060547,
      "learning_rate": 5e-05,
      "loss": 5.391,
      "step": 5
    },
    {
      "epoch": 0.01406799531066823,
      "grad_norm": 16.22538185119629,
      "learning_rate": 6e-05,
      "loss": 4.4877,
      "step": 6
    },
    {
      "epoch": 0.016412661195779603,
      "grad_norm": 16.708181381225586,
      "learning_rate": 7e-05,
      "loss": 4.2436,
      "step": 7
    },
    {
      "epoch": 0.01875732708089097,
      "grad_norm": 13.979721069335938,
      "learning_rate": 8e-05,
      "loss": 4.0923,
      "step": 8
    },
    {
      "epoch": 0.021101992966002344,
      "grad_norm": 12.381362915039062,
      "learning_rate": 9e-05,
      "loss": 3.9154,
      "step": 9
    },
    {
      "epoch": 0.023446658851113716,
      "grad_norm": 11.103169441223145,
      "learning_rate": 0.0001,
      "loss": 4.0311,
      "step": 10
    },
    {
      "epoch": 0.02579132473622509,
      "grad_norm": 11.883439064025879,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.9611,
      "step": 11
    },
    {
      "epoch": 0.02813599062133646,
      "grad_norm": 10.65888500213623,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.92,
      "step": 12
    },
    {
      "epoch": 0.03048065650644783,
      "grad_norm": 14.587371826171875,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.176,
      "step": 13
    },
    {
      "epoch": 0.032825322391559206,
      "grad_norm": 9.647926330566406,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.3739,
      "step": 14
    },
    {
      "epoch": 0.035169988276670575,
      "grad_norm": 12.973896980285645,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.777,
      "step": 15
    },
    {
      "epoch": 0.03751465416178194,
      "grad_norm": 10.148499488830566,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.6683,
      "step": 16
    },
    {
      "epoch": 0.03985932004689332,
      "grad_norm": 10.17501163482666,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.4995,
      "step": 17
    },
    {
      "epoch": 0.04220398593200469,
      "grad_norm": 10.771862030029297,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.8145,
      "step": 18
    },
    {
      "epoch": 0.044548651817116064,
      "grad_norm": 7.992787837982178,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.294,
      "step": 19
    },
    {
      "epoch": 0.04689331770222743,
      "grad_norm": 8.624823570251465,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.1573,
      "step": 20
    },
    {
      "epoch": 0.0492379835873388,
      "grad_norm": 9.035672187805176,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.5599,
      "step": 21
    },
    {
      "epoch": 0.05158264947245018,
      "grad_norm": 9.139631271362305,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.5685,
      "step": 22
    },
    {
      "epoch": 0.053927315357561546,
      "grad_norm": 9.682453155517578,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.4256,
      "step": 23
    },
    {
      "epoch": 0.05627198124267292,
      "grad_norm": 8.52701473236084,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.0577,
      "step": 24
    },
    {
      "epoch": 0.05861664712778429,
      "grad_norm": 13.335333824157715,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.9149,
      "step": 25
    },
    {
      "epoch": 0.06096131301289566,
      "grad_norm": 8.877936363220215,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.4293,
      "step": 26
    },
    {
      "epoch": 0.06330597889800703,
      "grad_norm": 11.6506929397583,
      "learning_rate": 9.803768380684242e-05,
      "loss": 3.3192,
      "step": 27
    },
    {
      "epoch": 0.06565064478311841,
      "grad_norm": 11.447749137878418,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.2359,
      "step": 28
    },
    {
      "epoch": 0.06799531066822978,
      "grad_norm": 8.89906120300293,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.9944,
      "step": 29
    },
    {
      "epoch": 0.07033997655334115,
      "grad_norm": 8.394125938415527,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.9144,
      "step": 30
    },
    {
      "epoch": 0.07268464243845252,
      "grad_norm": 9.476370811462402,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.0997,
      "step": 31
    },
    {
      "epoch": 0.07502930832356389,
      "grad_norm": 8.897541046142578,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.0782,
      "step": 32
    },
    {
      "epoch": 0.07737397420867527,
      "grad_norm": 9.168450355529785,
      "learning_rate": 9.642770192448536e-05,
      "loss": 3.2234,
      "step": 33
    },
    {
      "epoch": 0.07971864009378664,
      "grad_norm": 8.860148429870605,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.9236,
      "step": 34
    },
    {
      "epoch": 0.08206330597889801,
      "grad_norm": 8.4860258102417,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.3617,
      "step": 35
    },
    {
      "epoch": 0.08440797186400938,
      "grad_norm": 8.206006050109863,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.0589,
      "step": 36
    },
    {
      "epoch": 0.08675263774912075,
      "grad_norm": 9.936936378479004,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.3066,
      "step": 37
    },
    {
      "epoch": 0.08909730363423213,
      "grad_norm": 8.540318489074707,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.3055,
      "step": 38
    },
    {
      "epoch": 0.0914419695193435,
      "grad_norm": 7.713901519775391,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.2,
      "step": 39
    },
    {
      "epoch": 0.09378663540445487,
      "grad_norm": 7.591506004333496,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.2786,
      "step": 40
    },
    {
      "epoch": 0.09613130128956623,
      "grad_norm": 7.995643615722656,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.1609,
      "step": 41
    },
    {
      "epoch": 0.0984759671746776,
      "grad_norm": 7.518246173858643,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.7857,
      "step": 42
    },
    {
      "epoch": 0.10082063305978899,
      "grad_norm": 9.68978214263916,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.7311,
      "step": 43
    },
    {
      "epoch": 0.10316529894490035,
      "grad_norm": 11.168111801147461,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.0827,
      "step": 44
    },
    {
      "epoch": 0.10550996483001172,
      "grad_norm": 9.186760902404785,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.5625,
      "step": 45
    },
    {
      "epoch": 0.10785463071512309,
      "grad_norm": 8.938870429992676,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.5811,
      "step": 46
    },
    {
      "epoch": 0.11019929660023446,
      "grad_norm": 9.78221321105957,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.5146,
      "step": 47
    },
    {
      "epoch": 0.11254396248534584,
      "grad_norm": 9.555784225463867,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4811,
      "step": 48
    },
    {
      "epoch": 0.11488862837045721,
      "grad_norm": 9.54387092590332,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.1377,
      "step": 49
    },
    {
      "epoch": 0.11723329425556858,
      "grad_norm": 11.764355659484863,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.9033,
      "step": 50
    },
    {
      "epoch": 0.11723329425556858,
      "eval_loss": 1.0513248443603516,
      "eval_runtime": 53.327,
      "eval_samples_per_second": 13.464,
      "eval_steps_per_second": 3.375,
      "step": 50
    },
    {
      "epoch": 0.11957796014067995,
      "grad_norm": 24.633373260498047,
      "learning_rate": 8.894386393810563e-05,
      "loss": 6.7308,
      "step": 51
    },
    {
      "epoch": 0.12192262602579132,
      "grad_norm": 17.573421478271484,
      "learning_rate": 8.842005554284296e-05,
      "loss": 5.7586,
      "step": 52
    },
    {
      "epoch": 0.1242672919109027,
      "grad_norm": 8.933952331542969,
      "learning_rate": 8.788574348801675e-05,
      "loss": 4.2271,
      "step": 53
    },
    {
      "epoch": 0.12661195779601406,
      "grad_norm": 9.926009178161621,
      "learning_rate": 8.73410738492077e-05,
      "loss": 4.4827,
      "step": 54
    },
    {
      "epoch": 0.12895662368112543,
      "grad_norm": 10.70360279083252,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.7757,
      "step": 55
    },
    {
      "epoch": 0.13130128956623682,
      "grad_norm": 8.511175155639648,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.934,
      "step": 56
    },
    {
      "epoch": 0.1336459554513482,
      "grad_norm": 7.956448078155518,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.9996,
      "step": 57
    },
    {
      "epoch": 0.13599062133645956,
      "grad_norm": 9.405022621154785,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.8999,
      "step": 58
    },
    {
      "epoch": 0.13833528722157093,
      "grad_norm": 7.946819305419922,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.9496,
      "step": 59
    },
    {
      "epoch": 0.1406799531066823,
      "grad_norm": 8.405508041381836,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.579,
      "step": 60
    },
    {
      "epoch": 0.14302461899179367,
      "grad_norm": 8.906330108642578,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.6143,
      "step": 61
    },
    {
      "epoch": 0.14536928487690504,
      "grad_norm": 9.379605293273926,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.7798,
      "step": 62
    },
    {
      "epoch": 0.1477139507620164,
      "grad_norm": 8.477218627929688,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.588,
      "step": 63
    },
    {
      "epoch": 0.15005861664712777,
      "grad_norm": 7.908034801483154,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.589,
      "step": 64
    },
    {
      "epoch": 0.15240328253223914,
      "grad_norm": 8.690335273742676,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.4561,
      "step": 65
    },
    {
      "epoch": 0.15474794841735054,
      "grad_norm": 8.06505298614502,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.8101,
      "step": 66
    },
    {
      "epoch": 0.1570926143024619,
      "grad_norm": 6.990350246429443,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.4838,
      "step": 67
    },
    {
      "epoch": 0.15943728018757328,
      "grad_norm": 7.266732692718506,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.2637,
      "step": 68
    },
    {
      "epoch": 0.16178194607268465,
      "grad_norm": 8.722139358520508,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.803,
      "step": 69
    },
    {
      "epoch": 0.16412661195779601,
      "grad_norm": 6.49424409866333,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.2726,
      "step": 70
    },
    {
      "epoch": 0.16647127784290738,
      "grad_norm": 8.221322059631348,
      "learning_rate": 7.66515864363997e-05,
      "loss": 4.0207,
      "step": 71
    },
    {
      "epoch": 0.16881594372801875,
      "grad_norm": 7.128183841705322,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.0073,
      "step": 72
    },
    {
      "epoch": 0.17116060961313012,
      "grad_norm": 7.4666619300842285,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.0837,
      "step": 73
    },
    {
      "epoch": 0.1735052754982415,
      "grad_norm": 6.74752950668335,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.2209,
      "step": 74
    },
    {
      "epoch": 0.17584994138335286,
      "grad_norm": 6.79481315612793,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.1971,
      "step": 75
    },
    {
      "epoch": 0.17819460726846426,
      "grad_norm": 7.2510528564453125,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.0597,
      "step": 76
    },
    {
      "epoch": 0.18053927315357562,
      "grad_norm": 7.681369781494141,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.7634,
      "step": 77
    },
    {
      "epoch": 0.182883939038687,
      "grad_norm": 8.846420288085938,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.0827,
      "step": 78
    },
    {
      "epoch": 0.18522860492379836,
      "grad_norm": 8.721245765686035,
      "learning_rate": 7.083909302476453e-05,
      "loss": 3.1422,
      "step": 79
    },
    {
      "epoch": 0.18757327080890973,
      "grad_norm": 7.962874412536621,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.2284,
      "step": 80
    },
    {
      "epoch": 0.1899179366940211,
      "grad_norm": 7.202088832855225,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.6309,
      "step": 81
    },
    {
      "epoch": 0.19226260257913247,
      "grad_norm": 7.756674289703369,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.0028,
      "step": 82
    },
    {
      "epoch": 0.19460726846424384,
      "grad_norm": 7.410325527191162,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.7875,
      "step": 83
    },
    {
      "epoch": 0.1969519343493552,
      "grad_norm": 7.595869064331055,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.9473,
      "step": 84
    },
    {
      "epoch": 0.19929660023446658,
      "grad_norm": 7.9515557289123535,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.1198,
      "step": 85
    },
    {
      "epoch": 0.20164126611957797,
      "grad_norm": 8.794443130493164,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.2781,
      "step": 86
    },
    {
      "epoch": 0.20398593200468934,
      "grad_norm": 9.458645820617676,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.2948,
      "step": 87
    },
    {
      "epoch": 0.2063305978898007,
      "grad_norm": 7.8468146324157715,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.0067,
      "step": 88
    },
    {
      "epoch": 0.20867526377491208,
      "grad_norm": 9.829216003417969,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.8751,
      "step": 89
    },
    {
      "epoch": 0.21101992966002345,
      "grad_norm": 7.089529991149902,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.7765,
      "step": 90
    },
    {
      "epoch": 0.21336459554513482,
      "grad_norm": 8.202539443969727,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.2057,
      "step": 91
    },
    {
      "epoch": 0.21570926143024619,
      "grad_norm": 8.448012351989746,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.3169,
      "step": 92
    },
    {
      "epoch": 0.21805392731535755,
      "grad_norm": 7.2261576652526855,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.8668,
      "step": 93
    },
    {
      "epoch": 0.22039859320046892,
      "grad_norm": 7.020049095153809,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.8429,
      "step": 94
    },
    {
      "epoch": 0.2227432590855803,
      "grad_norm": 7.415134906768799,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.5114,
      "step": 95
    },
    {
      "epoch": 0.2250879249706917,
      "grad_norm": 7.972723484039307,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.8023,
      "step": 96
    },
    {
      "epoch": 0.22743259085580306,
      "grad_norm": 8.125452995300293,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.9841,
      "step": 97
    },
    {
      "epoch": 0.22977725674091443,
      "grad_norm": 6.471831798553467,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.3228,
      "step": 98
    },
    {
      "epoch": 0.2321219226260258,
      "grad_norm": 6.832740783691406,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.2556,
      "step": 99
    },
    {
      "epoch": 0.23446658851113716,
      "grad_norm": 7.426825523376465,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.4321,
      "step": 100
    },
    {
      "epoch": 0.23446658851113716,
      "eval_loss": 0.9207891225814819,
      "eval_runtime": 53.3707,
      "eval_samples_per_second": 13.453,
      "eval_steps_per_second": 3.373,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.438154617698386e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}