{
  "best_metric": 0.22296833992004395,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.5586592178770949,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "eval_loss": 3.2835192680358887,
      "eval_runtime": 17.0347,
      "eval_samples_per_second": 35.398,
      "eval_steps_per_second": 8.864,
      "step": 1
    },
    {
      "epoch": 0.008379888268156424,
      "grad_norm": 0.6404779553413391,
      "learning_rate": 3e-05,
      "loss": 2.4727,
      "step": 3
    },
    {
      "epoch": 0.01675977653631285,
      "grad_norm": 0.7394810914993286,
      "learning_rate": 6e-05,
      "loss": 2.6608,
      "step": 6
    },
    {
      "epoch": 0.025139664804469275,
      "grad_norm": 0.7213653326034546,
      "learning_rate": 9e-05,
      "loss": 2.8923,
      "step": 9
    },
    {
      "epoch": 0.0335195530726257,
      "grad_norm": 0.9916292428970337,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4576,
      "step": 12
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.8784328699111938,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.013,
      "step": 15
    },
    {
      "epoch": 0.05027932960893855,
      "grad_norm": 0.6947599649429321,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6163,
      "step": 18
    },
    {
      "epoch": 0.05865921787709497,
      "grad_norm": 0.9758700728416443,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.3896,
      "step": 21
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": 0.7843855023384094,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0163,
      "step": 24
    },
    {
      "epoch": 0.07541899441340782,
      "grad_norm": 0.9721394777297974,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.104,
      "step": 27
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 0.7433673143386841,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1567,
      "step": 30
    },
    {
      "epoch": 0.09217877094972067,
      "grad_norm": 0.730903148651123,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1533,
      "step": 33
    },
    {
      "epoch": 0.1005586592178771,
      "grad_norm": 0.6961589455604553,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.212,
      "step": 36
    },
    {
      "epoch": 0.10893854748603352,
      "grad_norm": 0.9013598561286926,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1623,
      "step": 39
    },
    {
      "epoch": 0.11731843575418995,
      "grad_norm": 1.0598002672195435,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2984,
      "step": 42
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 1.1929737329483032,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3138,
      "step": 45
    },
    {
      "epoch": 0.1340782122905028,
      "grad_norm": 1.1458548307418823,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0941,
      "step": 48
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 1.0100281238555908,
      "eval_runtime": 17.101,
      "eval_samples_per_second": 35.261,
      "eval_steps_per_second": 8.83,
      "step": 50
    },
    {
      "epoch": 0.1424581005586592,
      "grad_norm": 4.544776916503906,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.6615,
      "step": 51
    },
    {
      "epoch": 0.15083798882681565,
      "grad_norm": 2.975677967071533,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.7424,
      "step": 54
    },
    {
      "epoch": 0.15921787709497207,
      "grad_norm": 1.2031599283218384,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0062,
      "step": 57
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 0.7234984636306763,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6319,
      "step": 60
    },
    {
      "epoch": 0.17597765363128492,
      "grad_norm": 0.6598789691925049,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5383,
      "step": 63
    },
    {
      "epoch": 0.18435754189944134,
      "grad_norm": 0.5707410573959351,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.51,
      "step": 66
    },
    {
      "epoch": 0.19273743016759776,
      "grad_norm": 0.44198137521743774,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.447,
      "step": 69
    },
    {
      "epoch": 0.2011173184357542,
      "grad_norm": 0.5998854637145996,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.412,
      "step": 72
    },
    {
      "epoch": 0.20949720670391062,
      "grad_norm": 0.5717155337333679,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4041,
      "step": 75
    },
    {
      "epoch": 0.21787709497206703,
      "grad_norm": 0.6459977626800537,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5011,
      "step": 78
    },
    {
      "epoch": 0.22625698324022347,
      "grad_norm": 0.6296533346176147,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4557,
      "step": 81
    },
    {
      "epoch": 0.2346368715083799,
      "grad_norm": 0.914438009262085,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4752,
      "step": 84
    },
    {
      "epoch": 0.2430167597765363,
      "grad_norm": 1.0927045345306396,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.4553,
      "step": 87
    },
    {
      "epoch": 0.25139664804469275,
      "grad_norm": 1.3984386920928955,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4644,
      "step": 90
    },
    {
      "epoch": 0.25977653631284914,
      "grad_norm": 1.0319483280181885,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4658,
      "step": 93
    },
    {
      "epoch": 0.2681564245810056,
      "grad_norm": 0.9646169543266296,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3963,
      "step": 96
    },
    {
      "epoch": 0.276536312849162,
      "grad_norm": 1.8801255226135254,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4449,
      "step": 99
    },
    {
      "epoch": 0.27932960893854747,
      "eval_loss": 0.5376428961753845,
      "eval_runtime": 17.1283,
      "eval_samples_per_second": 35.205,
      "eval_steps_per_second": 8.816,
      "step": 100
    },
    {
      "epoch": 0.2849162011173184,
      "grad_norm": 2.7768867015838623,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.171,
      "step": 102
    },
    {
      "epoch": 0.29329608938547486,
      "grad_norm": 1.3445883989334106,
      "learning_rate": 5e-05,
      "loss": 0.5237,
      "step": 105
    },
    {
      "epoch": 0.3016759776536313,
      "grad_norm": 1.087411880493164,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4251,
      "step": 108
    },
    {
      "epoch": 0.3100558659217877,
      "grad_norm": 0.613654613494873,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.2683,
      "step": 111
    },
    {
      "epoch": 0.31843575418994413,
      "grad_norm": 0.8458730578422546,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.279,
      "step": 114
    },
    {
      "epoch": 0.3268156424581006,
      "grad_norm": 0.5617647171020508,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.253,
      "step": 117
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 0.6647018194198608,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2877,
      "step": 120
    },
    {
      "epoch": 0.3435754189944134,
      "grad_norm": 0.4727783501148224,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2442,
      "step": 123
    },
    {
      "epoch": 0.35195530726256985,
      "grad_norm": 0.5167345404624939,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2438,
      "step": 126
    },
    {
      "epoch": 0.36033519553072624,
      "grad_norm": 0.6400461792945862,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2373,
      "step": 129
    },
    {
      "epoch": 0.3687150837988827,
      "grad_norm": 0.7134339809417725,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2713,
      "step": 132
    },
    {
      "epoch": 0.3770949720670391,
      "grad_norm": 0.6741611361503601,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2519,
      "step": 135
    },
    {
      "epoch": 0.3854748603351955,
      "grad_norm": 0.6766725182533264,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3096,
      "step": 138
    },
    {
      "epoch": 0.39385474860335196,
      "grad_norm": 0.7892684936523438,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3055,
      "step": 141
    },
    {
      "epoch": 0.4022346368715084,
      "grad_norm": 0.6781839728355408,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3243,
      "step": 144
    },
    {
      "epoch": 0.4106145251396648,
      "grad_norm": 0.8571739196777344,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3238,
      "step": 147
    },
    {
      "epoch": 0.41899441340782123,
      "grad_norm": 1.0887181758880615,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3541,
      "step": 150
    },
    {
      "epoch": 0.41899441340782123,
      "eval_loss": 0.2837798595428467,
      "eval_runtime": 17.1062,
      "eval_samples_per_second": 35.25,
      "eval_steps_per_second": 8.827,
      "step": 150
    },
    {
      "epoch": 0.4273743016759777,
      "grad_norm": 1.305745244026184,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5962,
      "step": 153
    },
    {
      "epoch": 0.43575418994413406,
      "grad_norm": 0.8109059929847717,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.2629,
      "step": 156
    },
    {
      "epoch": 0.4441340782122905,
      "grad_norm": 1.5648621320724487,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2267,
      "step": 159
    },
    {
      "epoch": 0.45251396648044695,
      "grad_norm": 1.0514497756958008,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2514,
      "step": 162
    },
    {
      "epoch": 0.46089385474860334,
      "grad_norm": 0.6054957509040833,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1733,
      "step": 165
    },
    {
      "epoch": 0.4692737430167598,
      "grad_norm": 0.910860538482666,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2035,
      "step": 168
    },
    {
      "epoch": 0.4776536312849162,
      "grad_norm": 1.2614514827728271,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2135,
      "step": 171
    },
    {
      "epoch": 0.4860335195530726,
      "grad_norm": 0.7164639234542847,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.1844,
      "step": 174
    },
    {
      "epoch": 0.49441340782122906,
      "grad_norm": 0.6105827689170837,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2386,
      "step": 177
    },
    {
      "epoch": 0.5027932960893855,
      "grad_norm": 0.95228511095047,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2286,
      "step": 180
    },
    {
      "epoch": 0.5111731843575419,
      "grad_norm": 0.7105367183685303,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.1992,
      "step": 183
    },
    {
      "epoch": 0.5195530726256983,
      "grad_norm": 0.7583916187286377,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2144,
      "step": 186
    },
    {
      "epoch": 0.5279329608938548,
      "grad_norm": 0.7920324206352234,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2418,
      "step": 189
    },
    {
      "epoch": 0.5363128491620112,
      "grad_norm": 0.847964346408844,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.259,
      "step": 192
    },
    {
      "epoch": 0.5446927374301676,
      "grad_norm": 0.6220384836196899,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.282,
      "step": 195
    },
    {
      "epoch": 0.553072625698324,
      "grad_norm": 0.7298959493637085,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2359,
      "step": 198
    },
    {
      "epoch": 0.5586592178770949,
      "eval_loss": 0.22296833992004395,
      "eval_runtime": 17.0705,
      "eval_samples_per_second": 35.324,
      "eval_steps_per_second": 8.846,
      "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": 6.61808020979712e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}