{
  "best_metric": 1.5862289667129517,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.14245014245014245,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014245014245014246,
      "grad_norm": 1.0964112281799316,
      "learning_rate": 1e-05,
      "loss": 1.0342,
      "step": 1
    },
    {
      "epoch": 0.0014245014245014246,
      "eval_loss": 3.0569612979888916,
      "eval_runtime": 52.6999,
      "eval_samples_per_second": 22.429,
      "eval_steps_per_second": 5.617,
      "step": 1
    },
    {
      "epoch": 0.002849002849002849,
      "grad_norm": 1.2476991415023804,
      "learning_rate": 2e-05,
      "loss": 1.23,
      "step": 2
    },
    {
      "epoch": 0.004273504273504274,
      "grad_norm": 1.2541226148605347,
      "learning_rate": 3e-05,
      "loss": 1.1837,
      "step": 3
    },
    {
      "epoch": 0.005698005698005698,
      "grad_norm": 1.0129095315933228,
      "learning_rate": 4e-05,
      "loss": 1.1769,
      "step": 4
    },
    {
      "epoch": 0.007122507122507123,
      "grad_norm": 0.8270882368087769,
      "learning_rate": 5e-05,
      "loss": 1.1487,
      "step": 5
    },
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.8069018721580505,
      "learning_rate": 6e-05,
      "loss": 1.164,
      "step": 6
    },
    {
      "epoch": 0.009971509971509971,
      "grad_norm": 0.9533993601799011,
      "learning_rate": 7e-05,
      "loss": 1.1895,
      "step": 7
    },
    {
      "epoch": 0.011396011396011397,
      "grad_norm": 0.9060405492782593,
      "learning_rate": 8e-05,
      "loss": 1.1757,
      "step": 8
    },
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 0.8857163190841675,
      "learning_rate": 9e-05,
      "loss": 1.182,
      "step": 9
    },
    {
      "epoch": 0.014245014245014245,
      "grad_norm": 0.9038103818893433,
      "learning_rate": 0.0001,
      "loss": 1.0661,
      "step": 10
    },
    {
      "epoch": 0.01566951566951567,
      "grad_norm": 0.9238746166229248,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1095,
      "step": 11
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.8789653778076172,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1214,
      "step": 12
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.9021486639976501,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0588,
      "step": 13
    },
    {
      "epoch": 0.019943019943019943,
      "grad_norm": 0.8770723938941956,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1249,
      "step": 14
    },
    {
      "epoch": 0.021367521367521368,
      "grad_norm": 0.8616719245910645,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1279,
      "step": 15
    },
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 0.8764058947563171,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0848,
      "step": 16
    },
    {
      "epoch": 0.024216524216524215,
      "grad_norm": 0.9556768536567688,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1552,
      "step": 17
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 1.0189157724380493,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2092,
      "step": 18
    },
    {
      "epoch": 0.027065527065527065,
      "grad_norm": 0.9661674499511719,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0818,
      "step": 19
    },
    {
      "epoch": 0.02849002849002849,
      "grad_norm": 1.045841932296753,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1308,
      "step": 20
    },
    {
      "epoch": 0.029914529914529916,
      "grad_norm": 1.1435943841934204,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1825,
      "step": 21
    },
    {
      "epoch": 0.03133903133903134,
      "grad_norm": 1.1487054824829102,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1784,
      "step": 22
    },
    {
      "epoch": 0.03276353276353276,
      "grad_norm": 1.2055588960647583,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.1226,
      "step": 23
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.2802751064300537,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1568,
      "step": 24
    },
    {
      "epoch": 0.03561253561253561,
      "grad_norm": 1.4110389947891235,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.055,
      "step": 25
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.9700711965560913,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2116,
      "step": 26
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 2.64133620262146,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2991,
      "step": 27
    },
    {
      "epoch": 0.039886039886039885,
      "grad_norm": 2.6047780513763428,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2222,
      "step": 28
    },
    {
      "epoch": 0.04131054131054131,
      "grad_norm": 3.3303184509277344,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.472,
      "step": 29
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 3.784749746322632,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.5193,
      "step": 30
    },
    {
      "epoch": 0.04415954415954416,
      "grad_norm": 3.1593785285949707,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2667,
      "step": 31
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 3.354853630065918,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3128,
      "step": 32
    },
    {
      "epoch": 0.04700854700854701,
      "grad_norm": 3.2841928005218506,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.4638,
      "step": 33
    },
    {
      "epoch": 0.04843304843304843,
      "grad_norm": 2.2572824954986572,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0007,
      "step": 34
    },
    {
      "epoch": 0.04985754985754986,
      "grad_norm": 2.9840335845947266,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.4514,
      "step": 35
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 2.9793078899383545,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1547,
      "step": 36
    },
    {
      "epoch": 0.05270655270655271,
      "grad_norm": 3.512005567550659,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1132,
      "step": 37
    },
    {
      "epoch": 0.05413105413105413,
      "grad_norm": 3.440730333328247,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.0643,
      "step": 38
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 4.317581653594971,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.4451,
      "step": 39
    },
    {
      "epoch": 0.05698005698005698,
      "grad_norm": 4.4717864990234375,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.1562,
      "step": 40
    },
    {
      "epoch": 0.0584045584045584,
      "grad_norm": 3.6913952827453613,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.0853,
      "step": 41
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 4.9976067543029785,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.937,
      "step": 42
    },
    {
      "epoch": 0.06125356125356125,
      "grad_norm": 5.239327430725098,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.2824,
      "step": 43
    },
    {
      "epoch": 0.06267806267806268,
      "grad_norm": 5.314414024353027,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.6655,
      "step": 44
    },
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 4.768639087677002,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6526,
      "step": 45
    },
    {
      "epoch": 0.06552706552706553,
      "grad_norm": 4.657253265380859,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.9453,
      "step": 46
    },
    {
      "epoch": 0.06695156695156695,
      "grad_norm": 5.566736698150635,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.1551,
      "step": 47
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 4.6059370040893555,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9702,
      "step": 48
    },
    {
      "epoch": 0.0698005698005698,
      "grad_norm": 5.48839807510376,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.4132,
      "step": 49
    },
    {
      "epoch": 0.07122507122507123,
      "grad_norm": 6.920680046081543,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7052,
      "step": 50
    },
    {
      "epoch": 0.07122507122507123,
      "eval_loss": 1.6620087623596191,
      "eval_runtime": 52.8879,
      "eval_samples_per_second": 22.349,
      "eval_steps_per_second": 5.597,
      "step": 50
    },
    {
      "epoch": 0.07264957264957266,
      "grad_norm": 1.8428657054901123,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2133,
      "step": 51
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.1231138706207275,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.4196,
      "step": 52
    },
    {
      "epoch": 0.0754985754985755,
      "grad_norm": 1.6163792610168457,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.3055,
      "step": 53
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.194074034690857,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1933,
      "step": 54
    },
    {
      "epoch": 0.07834757834757834,
      "grad_norm": 1.0080146789550781,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2088,
      "step": 55
    },
    {
      "epoch": 0.07977207977207977,
      "grad_norm": 0.73309326171875,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1147,
      "step": 56
    },
    {
      "epoch": 0.0811965811965812,
      "grad_norm": 0.6256619095802307,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0787,
      "step": 57
    },
    {
      "epoch": 0.08262108262108261,
      "grad_norm": 0.6739497184753418,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1465,
      "step": 58
    },
    {
      "epoch": 0.08404558404558404,
      "grad_norm": 0.7923569083213806,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.182,
      "step": 59
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.8488563299179077,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2106,
      "step": 60
    },
    {
      "epoch": 0.0868945868945869,
      "grad_norm": 0.8478406071662903,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1505,
      "step": 61
    },
    {
      "epoch": 0.08831908831908832,
      "grad_norm": 0.8413639068603516,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1692,
      "step": 62
    },
    {
      "epoch": 0.08974358974358974,
      "grad_norm": 0.7861711382865906,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1316,
      "step": 63
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.7624171376228333,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.1516,
      "step": 64
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.7577725648880005,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.115,
      "step": 65
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.7820805311203003,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0262,
      "step": 66
    },
    {
      "epoch": 0.09544159544159544,
      "grad_norm": 0.8114756345748901,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0623,
      "step": 67
    },
    {
      "epoch": 0.09686609686609686,
      "grad_norm": 0.8904410004615784,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0902,
      "step": 68
    },
    {
      "epoch": 0.09829059829059829,
      "grad_norm": 0.9297963976860046,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.1,
      "step": 69
    },
    {
      "epoch": 0.09971509971509972,
      "grad_norm": 1.0232235193252563,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.0924,
      "step": 70
    },
    {
      "epoch": 0.10113960113960115,
      "grad_norm": 1.0157926082611084,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0979,
      "step": 71
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.0584907531738281,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0371,
      "step": 72
    },
    {
      "epoch": 0.10398860398860399,
      "grad_norm": 1.143020749092102,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.026,
      "step": 73
    },
    {
      "epoch": 0.10541310541310542,
      "grad_norm": 1.184112548828125,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9999,
      "step": 74
    },
    {
      "epoch": 0.10683760683760683,
      "grad_norm": 1.411512851715088,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1171,
      "step": 75
    },
    {
      "epoch": 0.10826210826210826,
      "grad_norm": 1.5346912145614624,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0003,
      "step": 76
    },
    {
      "epoch": 0.10968660968660969,
      "grad_norm": 2.24712872505188,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2975,
      "step": 77
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.241441011428833,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0772,
      "step": 78
    },
    {
      "epoch": 0.11253561253561253,
      "grad_norm": 3.3355181217193604,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3215,
      "step": 79
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 2.3127119541168213,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0156,
      "step": 80
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 2.2935128211975098,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9638,
      "step": 81
    },
    {
      "epoch": 0.1168091168091168,
      "grad_norm": 2.777211904525757,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1279,
      "step": 82
    },
    {
      "epoch": 0.11823361823361823,
      "grad_norm": 2.671398639678955,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2885,
      "step": 83
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 3.616776943206787,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.5908,
      "step": 84
    },
    {
      "epoch": 0.12108262108262108,
      "grad_norm": 2.932478427886963,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.3571,
      "step": 85
    },
    {
      "epoch": 0.1225071225071225,
      "grad_norm": 2.3018410205841064,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0595,
      "step": 86
    },
    {
      "epoch": 0.12393162393162394,
      "grad_norm": 2.408008337020874,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.5027,
      "step": 87
    },
    {
      "epoch": 0.12535612535612536,
      "grad_norm": 2.7625410556793213,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.7931,
      "step": 88
    },
    {
      "epoch": 0.1267806267806268,
      "grad_norm": 3.301805257797241,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.9967,
      "step": 89
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 3.297290563583374,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0517,
      "step": 90
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 3.5428030490875244,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.2671,
      "step": 91
    },
    {
      "epoch": 0.13105413105413105,
      "grad_norm": 3.5359692573547363,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.1285,
      "step": 92
    },
    {
      "epoch": 0.13247863247863248,
      "grad_norm": 3.873988151550293,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.1496,
      "step": 93
    },
    {
      "epoch": 0.1339031339031339,
      "grad_norm": 4.848047733306885,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4119,
      "step": 94
    },
    {
      "epoch": 0.13532763532763534,
      "grad_norm": 5.2075300216674805,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6581,
      "step": 95
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 4.486565113067627,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.3495,
      "step": 96
    },
    {
      "epoch": 0.13817663817663817,
      "grad_norm": 4.8237175941467285,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.9713,
      "step": 97
    },
    {
      "epoch": 0.1396011396011396,
      "grad_norm": 5.597812175750732,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.4004,
      "step": 98
    },
    {
      "epoch": 0.14102564102564102,
      "grad_norm": 5.861245632171631,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.9003,
      "step": 99
    },
    {
      "epoch": 0.14245014245014245,
      "grad_norm": 7.58296012878418,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.8815,
      "step": 100
    },
    {
      "epoch": 0.14245014245014245,
      "eval_loss": 1.5862289667129517,
      "eval_runtime": 52.8852,
      "eval_samples_per_second": 22.35,
      "eval_steps_per_second": 5.597,
      "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": 4.154039461321114e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}