{
  "best_metric": 1.5217487812042236,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.4512126339537507,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022560631697687537,
      "eval_loss": 3.3649473190307617,
      "eval_runtime": 54.2845,
      "eval_samples_per_second": 13.761,
      "eval_steps_per_second": 3.445,
      "step": 1
    },
    {
      "epoch": 0.00676818950930626,
      "grad_norm": 1.2129340171813965,
      "learning_rate": 3e-05,
      "loss": 2.763,
      "step": 3
    },
    {
      "epoch": 0.01353637901861252,
      "grad_norm": 1.154921054840088,
      "learning_rate": 6e-05,
      "loss": 2.9516,
      "step": 6
    },
    {
      "epoch": 0.02030456852791878,
      "grad_norm": 1.3365858793258667,
      "learning_rate": 9e-05,
      "loss": 2.9188,
      "step": 9
    },
    {
      "epoch": 0.02707275803722504,
      "grad_norm": 1.8777188062667847,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.7929,
      "step": 12
    },
    {
      "epoch": 0.0338409475465313,
      "grad_norm": 1.3505871295928955,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.8142,
      "step": 15
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 1.1927076578140259,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.6162,
      "step": 18
    },
    {
      "epoch": 0.047377326565143825,
      "grad_norm": 1.1493228673934937,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.7126,
      "step": 21
    },
    {
      "epoch": 0.05414551607445008,
      "grad_norm": 1.4219441413879395,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.6204,
      "step": 24
    },
    {
      "epoch": 0.06091370558375635,
      "grad_norm": 1.7288366556167603,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.7133,
      "step": 27
    },
    {
      "epoch": 0.0676818950930626,
      "grad_norm": 1.3019883632659912,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.7191,
      "step": 30
    },
    {
      "epoch": 0.07445008460236886,
      "grad_norm": 1.5910074710845947,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.5894,
      "step": 33
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 1.8645638227462769,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.6618,
      "step": 36
    },
    {
      "epoch": 0.08798646362098139,
      "grad_norm": 1.4430954456329346,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.6318,
      "step": 39
    },
    {
      "epoch": 0.09475465313028765,
      "grad_norm": 2.860017776489258,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.6897,
      "step": 42
    },
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 1.660325050354004,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.7107,
      "step": 45
    },
    {
      "epoch": 0.10829103214890017,
      "grad_norm": 2.1997733116149902,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4415,
      "step": 48
    },
    {
      "epoch": 0.11280315848843768,
      "eval_loss": 2.5045340061187744,
      "eval_runtime": 55.4736,
      "eval_samples_per_second": 13.466,
      "eval_steps_per_second": 3.371,
      "step": 50
    },
    {
      "epoch": 0.11505922165820642,
      "grad_norm": 2.115299701690674,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.5328,
      "step": 51
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 2.0220117568969727,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.5892,
      "step": 54
    },
    {
      "epoch": 0.12859560067681894,
      "grad_norm": 1.6082484722137451,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.5735,
      "step": 57
    },
    {
      "epoch": 0.1353637901861252,
      "grad_norm": 1.0228571891784668,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.395,
      "step": 60
    },
    {
      "epoch": 0.14213197969543148,
      "grad_norm": 0.975939929485321,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.3764,
      "step": 63
    },
    {
      "epoch": 0.14890016920473773,
      "grad_norm": 1.2392593622207642,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.4016,
      "step": 66
    },
    {
      "epoch": 0.155668358714044,
      "grad_norm": 1.229074239730835,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.4136,
      "step": 69
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 1.160683274269104,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.1337,
      "step": 72
    },
    {
      "epoch": 0.1692047377326565,
      "grad_norm": 1.4279489517211914,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.1827,
      "step": 75
    },
    {
      "epoch": 0.17597292724196278,
      "grad_norm": 1.3950401544570923,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.34,
      "step": 78
    },
    {
      "epoch": 0.18274111675126903,
      "grad_norm": 1.2206807136535645,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.2317,
      "step": 81
    },
    {
      "epoch": 0.1895093062605753,
      "grad_norm": 1.6452642679214478,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.137,
      "step": 84
    },
    {
      "epoch": 0.19627749576988154,
      "grad_norm": 1.9977295398712158,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.1137,
      "step": 87
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 1.7939214706420898,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0652,
      "step": 90
    },
    {
      "epoch": 0.2098138747884941,
      "grad_norm": 2.428151845932007,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.0015,
      "step": 93
    },
    {
      "epoch": 0.21658206429780033,
      "grad_norm": 2.4842824935913086,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.1849,
      "step": 96
    },
    {
      "epoch": 0.2233502538071066,
      "grad_norm": 2.673194646835327,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.8844,
      "step": 99
    },
    {
      "epoch": 0.22560631697687536,
      "eval_loss": 1.9572558403015137,
      "eval_runtime": 55.4987,
      "eval_samples_per_second": 13.46,
      "eval_steps_per_second": 3.369,
      "step": 100
    },
    {
      "epoch": 0.23011844331641285,
      "grad_norm": 2.131408929824829,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.2441,
      "step": 102
    },
    {
      "epoch": 0.23688663282571912,
      "grad_norm": 2.081399440765381,
      "learning_rate": 5e-05,
      "loss": 2.3219,
      "step": 105
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 1.4835395812988281,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.176,
      "step": 108
    },
    {
      "epoch": 0.25042301184433163,
      "grad_norm": 1.476472020149231,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.9463,
      "step": 111
    },
    {
      "epoch": 0.2571912013536379,
      "grad_norm": 1.4163830280303955,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.0727,
      "step": 114
    },
    {
      "epoch": 0.2639593908629442,
      "grad_norm": 1.5342260599136353,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.858,
      "step": 117
    },
    {
      "epoch": 0.2707275803722504,
      "grad_norm": 1.5253146886825562,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.8902,
      "step": 120
    },
    {
      "epoch": 0.27749576988155666,
      "grad_norm": 1.7602707147598267,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.6547,
      "step": 123
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 1.6635607481002808,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.8572,
      "step": 126
    },
    {
      "epoch": 0.2910321489001692,
      "grad_norm": 1.924639105796814,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.8875,
      "step": 129
    },
    {
      "epoch": 0.29780033840947545,
      "grad_norm": 1.8324716091156006,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.5726,
      "step": 132
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 2.137519121170044,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.6311,
      "step": 135
    },
    {
      "epoch": 0.311336717428088,
      "grad_norm": 2.6914830207824707,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.8127,
      "step": 138
    },
    {
      "epoch": 0.31810490693739424,
      "grad_norm": 2.32242751121521,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.536,
      "step": 141
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 2.783191204071045,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.6442,
      "step": 144
    },
    {
      "epoch": 0.3316412859560068,
      "grad_norm": 3.8185131549835205,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.5812,
      "step": 147
    },
    {
      "epoch": 0.338409475465313,
      "grad_norm": 4.207033157348633,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.4215,
      "step": 150
    },
    {
      "epoch": 0.338409475465313,
      "eval_loss": 1.613823652267456,
      "eval_runtime": 55.6384,
      "eval_samples_per_second": 13.426,
      "eval_steps_per_second": 3.361,
      "step": 150
    },
    {
      "epoch": 0.34517766497461927,
      "grad_norm": 1.9749424457550049,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.1616,
      "step": 153
    },
    {
      "epoch": 0.35194585448392557,
      "grad_norm": 2.1206893920898438,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.1542,
      "step": 156
    },
    {
      "epoch": 0.3587140439932318,
      "grad_norm": 2.122969150543213,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.9048,
      "step": 159
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 2.1160035133361816,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8025,
      "step": 162
    },
    {
      "epoch": 0.37225042301184436,
      "grad_norm": 2.0058743953704834,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.7525,
      "step": 165
    },
    {
      "epoch": 0.3790186125211506,
      "grad_norm": 1.7620965242385864,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.4851,
      "step": 168
    },
    {
      "epoch": 0.38578680203045684,
      "grad_norm": 2.089890718460083,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5668,
      "step": 171
    },
    {
      "epoch": 0.3925549915397631,
      "grad_norm": 1.8286525011062622,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3543,
      "step": 174
    },
    {
      "epoch": 0.3993231810490694,
      "grad_norm": 2.1308631896972656,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.4603,
      "step": 177
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 2.0532541275024414,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4869,
      "step": 180
    },
    {
      "epoch": 0.4128595600676819,
      "grad_norm": 2.347409963607788,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2985,
      "step": 183
    },
    {
      "epoch": 0.4196277495769882,
      "grad_norm": 1.9288790225982666,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.4297,
      "step": 186
    },
    {
      "epoch": 0.4263959390862944,
      "grad_norm": 2.8015472888946533,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.543,
      "step": 189
    },
    {
      "epoch": 0.43316412859560066,
      "grad_norm": 2.930189371109009,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.3146,
      "step": 192
    },
    {
      "epoch": 0.43993231810490696,
      "grad_norm": 2.7898826599121094,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.4502,
      "step": 195
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 3.787993907928467,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.4229,
      "step": 198
    },
    {
      "epoch": 0.4512126339537507,
      "eval_loss": 1.5217487812042236,
      "eval_runtime": 55.7179,
      "eval_samples_per_second": 13.407,
      "eval_steps_per_second": 3.356,
      "step": 200
    }
  ],
  "logging_steps": 3,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.660993159135232e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}