{
  "best_metric": 0.7386493682861328,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.017681902572716825,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017681902572716824,
      "grad_norm": 31.45827293395996,
      "learning_rate": 1e-05,
      "loss": 5.7904,
      "step": 1
    },
    {
      "epoch": 0.00017681902572716824,
      "eval_loss": 1.5057493448257446,
      "eval_runtime": 697.5779,
      "eval_samples_per_second": 13.654,
      "eval_steps_per_second": 3.415,
      "step": 1
    },
    {
      "epoch": 0.0003536380514543365,
      "grad_norm": 34.1806640625,
      "learning_rate": 2e-05,
      "loss": 6.1229,
      "step": 2
    },
    {
      "epoch": 0.0005304570771815047,
      "grad_norm": 22.680261611938477,
      "learning_rate": 3e-05,
      "loss": 5.8247,
      "step": 3
    },
    {
      "epoch": 0.000707276102908673,
      "grad_norm": 17.230327606201172,
      "learning_rate": 4e-05,
      "loss": 4.859,
      "step": 4
    },
    {
      "epoch": 0.0008840951286358412,
      "grad_norm": 15.331626892089844,
      "learning_rate": 5e-05,
      "loss": 4.4965,
      "step": 5
    },
    {
      "epoch": 0.0010609141543630094,
      "grad_norm": 12.390981674194336,
      "learning_rate": 6e-05,
      "loss": 3.9683,
      "step": 6
    },
    {
      "epoch": 0.0012377331800901778,
      "grad_norm": 10.394994735717773,
      "learning_rate": 7e-05,
      "loss": 3.7708,
      "step": 7
    },
    {
      "epoch": 0.001414552205817346,
      "grad_norm": 10.412393569946289,
      "learning_rate": 8e-05,
      "loss": 3.6026,
      "step": 8
    },
    {
      "epoch": 0.001591371231544514,
      "grad_norm": 10.695121765136719,
      "learning_rate": 9e-05,
      "loss": 3.4169,
      "step": 9
    },
    {
      "epoch": 0.0017681902572716825,
      "grad_norm": 9.828315734863281,
      "learning_rate": 0.0001,
      "loss": 3.6774,
      "step": 10
    },
    {
      "epoch": 0.0019450092829988506,
      "grad_norm": 14.590110778808594,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.6333,
      "step": 11
    },
    {
      "epoch": 0.002121828308726019,
      "grad_norm": 8.314573287963867,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.5488,
      "step": 12
    },
    {
      "epoch": 0.002298647334453187,
      "grad_norm": 8.966548919677734,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.4814,
      "step": 13
    },
    {
      "epoch": 0.0024754663601803555,
      "grad_norm": 7.582108497619629,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.3718,
      "step": 14
    },
    {
      "epoch": 0.0026522853859075237,
      "grad_norm": 6.994225025177002,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.2995,
      "step": 15
    },
    {
      "epoch": 0.002829104411634692,
      "grad_norm": 7.011326313018799,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.2847,
      "step": 16
    },
    {
      "epoch": 0.00300592343736186,
      "grad_norm": 6.379772663116455,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.1525,
      "step": 17
    },
    {
      "epoch": 0.003182742463089028,
      "grad_norm": 7.65142297744751,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.2565,
      "step": 18
    },
    {
      "epoch": 0.0033595614888161968,
      "grad_norm": 6.9947309494018555,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.109,
      "step": 19
    },
    {
      "epoch": 0.003536380514543365,
      "grad_norm": 6.524970054626465,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.1238,
      "step": 20
    },
    {
      "epoch": 0.003713199540270533,
      "grad_norm": 6.738452911376953,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.095,
      "step": 21
    },
    {
      "epoch": 0.0038900185659977013,
      "grad_norm": 6.129000186920166,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.178,
      "step": 22
    },
    {
      "epoch": 0.00406683759172487,
      "grad_norm": 5.906164646148682,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.1067,
      "step": 23
    },
    {
      "epoch": 0.004243656617452038,
      "grad_norm": 5.738907337188721,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.1284,
      "step": 24
    },
    {
      "epoch": 0.004420475643179206,
      "grad_norm": 6.172359943389893,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.0873,
      "step": 25
    },
    {
      "epoch": 0.004597294668906374,
      "grad_norm": 6.070489883422852,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.024,
      "step": 26
    },
    {
      "epoch": 0.0047741136946335425,
      "grad_norm": 5.165764331817627,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.6945,
      "step": 27
    },
    {
      "epoch": 0.004950932720360711,
      "grad_norm": 5.422625541687012,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.1162,
      "step": 28
    },
    {
      "epoch": 0.005127751746087879,
      "grad_norm": 5.724668979644775,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8799,
      "step": 29
    },
    {
      "epoch": 0.005304570771815047,
      "grad_norm": 5.608127593994141,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.1417,
      "step": 30
    },
    {
      "epoch": 0.005481389797542215,
      "grad_norm": 5.916441440582275,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.7373,
      "step": 31
    },
    {
      "epoch": 0.005658208823269384,
      "grad_norm": 6.396985054016113,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.9008,
      "step": 32
    },
    {
      "epoch": 0.005835027848996552,
      "grad_norm": 5.534632205963135,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.9336,
      "step": 33
    },
    {
      "epoch": 0.00601184687472372,
      "grad_norm": 5.079275131225586,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.8344,
      "step": 34
    },
    {
      "epoch": 0.006188665900450889,
      "grad_norm": 5.050607681274414,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.0011,
      "step": 35
    },
    {
      "epoch": 0.006365484926178056,
      "grad_norm": 4.718279838562012,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.8885,
      "step": 36
    },
    {
      "epoch": 0.006542303951905225,
      "grad_norm": 5.671701431274414,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.0087,
      "step": 37
    },
    {
      "epoch": 0.0067191229776323936,
      "grad_norm": 5.0960187911987305,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.8506,
      "step": 38
    },
    {
      "epoch": 0.006895942003359561,
      "grad_norm": 5.12495231628418,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.9755,
      "step": 39
    },
    {
      "epoch": 0.00707276102908673,
      "grad_norm": 5.502079010009766,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.7671,
      "step": 40
    },
    {
      "epoch": 0.007249580054813898,
      "grad_norm": 5.2155022621154785,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.9465,
      "step": 41
    },
    {
      "epoch": 0.007426399080541066,
      "grad_norm": 5.489111423492432,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.8452,
      "step": 42
    },
    {
      "epoch": 0.007603218106268235,
      "grad_norm": 4.807673454284668,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.6389,
      "step": 43
    },
    {
      "epoch": 0.0077800371319954025,
      "grad_norm": 4.675958633422852,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.7592,
      "step": 44
    },
    {
      "epoch": 0.007956856157722571,
      "grad_norm": 4.997447967529297,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.7375,
      "step": 45
    },
    {
      "epoch": 0.00813367518344974,
      "grad_norm": 5.734372615814209,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.6703,
      "step": 46
    },
    {
      "epoch": 0.008310494209176908,
      "grad_norm": 5.159792423248291,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.7582,
      "step": 47
    },
    {
      "epoch": 0.008487313234904075,
      "grad_norm": 5.002233028411865,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6302,
      "step": 48
    },
    {
      "epoch": 0.008664132260631244,
      "grad_norm": 7.093165397644043,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.654,
      "step": 49
    },
    {
      "epoch": 0.008840951286358412,
      "grad_norm": 8.698509216308594,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.8836,
      "step": 50
    },
    {
      "epoch": 0.008840951286358412,
      "eval_loss": 0.796090304851532,
      "eval_runtime": 702.1573,
      "eval_samples_per_second": 13.565,
      "eval_steps_per_second": 3.392,
      "step": 50
    },
    {
      "epoch": 0.009017770312085581,
      "grad_norm": 10.096370697021484,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.866,
      "step": 51
    },
    {
      "epoch": 0.009194589337812748,
      "grad_norm": 5.29091215133667,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.2826,
      "step": 52
    },
    {
      "epoch": 0.009371408363539916,
      "grad_norm": 8.30187702178955,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.2665,
      "step": 53
    },
    {
      "epoch": 0.009548227389267085,
      "grad_norm": 8.213489532470703,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.3482,
      "step": 54
    },
    {
      "epoch": 0.009725046414994254,
      "grad_norm": 4.872696876525879,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.0297,
      "step": 55
    },
    {
      "epoch": 0.009901865440721422,
      "grad_norm": 4.427055835723877,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.1758,
      "step": 56
    },
    {
      "epoch": 0.010078684466448589,
      "grad_norm": 4.391081809997559,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.0824,
      "step": 57
    },
    {
      "epoch": 0.010255503492175758,
      "grad_norm": 4.616461753845215,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.9979,
      "step": 58
    },
    {
      "epoch": 0.010432322517902926,
      "grad_norm": 5.5998854637146,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.1535,
      "step": 59
    },
    {
      "epoch": 0.010609141543630095,
      "grad_norm": 4.823612213134766,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.9943,
      "step": 60
    },
    {
      "epoch": 0.010785960569357263,
      "grad_norm": 4.2810773849487305,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.8258,
      "step": 61
    },
    {
      "epoch": 0.01096277959508443,
      "grad_norm": 4.464574813842773,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.0109,
      "step": 62
    },
    {
      "epoch": 0.011139598620811599,
      "grad_norm": 4.964107036590576,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.0339,
      "step": 63
    },
    {
      "epoch": 0.011316417646538767,
      "grad_norm": 4.688778400421143,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.8198,
      "step": 64
    },
    {
      "epoch": 0.011493236672265936,
      "grad_norm": 4.536004066467285,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.1435,
      "step": 65
    },
    {
      "epoch": 0.011670055697993105,
      "grad_norm": 4.5505475997924805,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.8332,
      "step": 66
    },
    {
      "epoch": 0.011846874723720272,
      "grad_norm": 3.98578143119812,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.7494,
      "step": 67
    },
    {
      "epoch": 0.01202369374944744,
      "grad_norm": 4.547332763671875,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.9165,
      "step": 68
    },
    {
      "epoch": 0.012200512775174609,
      "grad_norm": 3.9778659343719482,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.7262,
      "step": 69
    },
    {
      "epoch": 0.012377331800901777,
      "grad_norm": 4.422539710998535,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.8827,
      "step": 70
    },
    {
      "epoch": 0.012554150826628946,
      "grad_norm": 4.440034866333008,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.9343,
      "step": 71
    },
    {
      "epoch": 0.012730969852356113,
      "grad_norm": 4.438572883605957,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.8539,
      "step": 72
    },
    {
      "epoch": 0.012907788878083281,
      "grad_norm": 4.555628776550293,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.0262,
      "step": 73
    },
    {
      "epoch": 0.01308460790381045,
      "grad_norm": 4.12335729598999,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.85,
      "step": 74
    },
    {
      "epoch": 0.013261426929537619,
      "grad_norm": 4.22313928604126,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.7441,
      "step": 75
    },
    {
      "epoch": 0.013438245955264787,
      "grad_norm": 4.474804401397705,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.832,
      "step": 76
    },
    {
      "epoch": 0.013615064980991954,
      "grad_norm": 4.030309200286865,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.7783,
      "step": 77
    },
    {
      "epoch": 0.013791884006719123,
      "grad_norm": 4.222381591796875,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.9147,
      "step": 78
    },
    {
      "epoch": 0.013968703032446291,
      "grad_norm": 4.298746109008789,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.8797,
      "step": 79
    },
    {
      "epoch": 0.01414552205817346,
      "grad_norm": 4.495664119720459,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.0076,
      "step": 80
    },
    {
      "epoch": 0.014322341083900628,
      "grad_norm": 4.467094421386719,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.7632,
      "step": 81
    },
    {
      "epoch": 0.014499160109627795,
      "grad_norm": 4.033594608306885,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.8745,
      "step": 82
    },
    {
      "epoch": 0.014675979135354964,
      "grad_norm": 3.7200775146484375,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.7365,
      "step": 83
    },
    {
      "epoch": 0.014852798161082132,
      "grad_norm": 4.186917781829834,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.7117,
      "step": 84
    },
    {
      "epoch": 0.015029617186809301,
      "grad_norm": 4.097092151641846,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.9168,
      "step": 85
    },
    {
      "epoch": 0.01520643621253647,
      "grad_norm": 4.045411586761475,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.652,
      "step": 86
    },
    {
      "epoch": 0.015383255238263636,
      "grad_norm": 3.9682466983795166,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.7225,
      "step": 87
    },
    {
      "epoch": 0.015560074263990805,
      "grad_norm": 4.498869895935059,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.6963,
      "step": 88
    },
    {
      "epoch": 0.015736893289717974,
      "grad_norm": 4.063172817230225,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.4276,
      "step": 89
    },
    {
      "epoch": 0.015913712315445142,
      "grad_norm": 4.287618160247803,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.532,
      "step": 90
    },
    {
      "epoch": 0.01609053134117231,
      "grad_norm": 4.349016189575195,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.5787,
      "step": 91
    },
    {
      "epoch": 0.01626735036689948,
      "grad_norm": 4.420528888702393,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.7135,
      "step": 92
    },
    {
      "epoch": 0.016444169392626648,
      "grad_norm": 3.8942527770996094,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.4143,
      "step": 93
    },
    {
      "epoch": 0.016620988418353817,
      "grad_norm": 4.0477399826049805,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4438,
      "step": 94
    },
    {
      "epoch": 0.01679780744408098,
      "grad_norm": 4.152792453765869,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.6107,
      "step": 95
    },
    {
      "epoch": 0.01697462646980815,
      "grad_norm": 4.101984977722168,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.5281,
      "step": 96
    },
    {
      "epoch": 0.01715144549553532,
      "grad_norm": 4.297181129455566,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.5312,
      "step": 97
    },
    {
      "epoch": 0.017328264521262488,
      "grad_norm": 4.133391857147217,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.4468,
      "step": 98
    },
    {
      "epoch": 0.017505083546989656,
      "grad_norm": 4.21942663192749,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.4245,
      "step": 99
    },
    {
      "epoch": 0.017681902572716825,
      "grad_norm": 4.527026176452637,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.4347,
      "step": 100
    },
    {
      "epoch": 0.017681902572716825,
      "eval_loss": 0.7386493682861328,
      "eval_runtime": 702.0834,
      "eval_samples_per_second": 13.567,
      "eval_steps_per_second": 3.393,
      "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": 1.430999619600384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}