{
  "best_metric": 0.09838873893022537,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.866738894907909,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01733477789815818,
      "grad_norm": 1.1709370613098145,
      "learning_rate": 5e-05,
      "loss": 0.2777,
      "step": 1
    },
    {
      "epoch": 0.01733477789815818,
      "eval_loss": 0.9326940774917603,
      "eval_runtime": 3.8155,
      "eval_samples_per_second": 13.105,
      "eval_steps_per_second": 3.407,
      "step": 1
    },
    {
      "epoch": 0.03466955579631636,
      "grad_norm": 2.190261125564575,
      "learning_rate": 0.0001,
      "loss": 0.4933,
      "step": 2
    },
    {
      "epoch": 0.05200433369447454,
      "grad_norm": 2.1287896633148193,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.4731,
      "step": 3
    },
    {
      "epoch": 0.06933911159263272,
      "grad_norm": 1.1221868991851807,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.1852,
      "step": 4
    },
    {
      "epoch": 0.0866738894907909,
      "grad_norm": 0.45097607374191284,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.101,
      "step": 5
    },
    {
      "epoch": 0.10400866738894908,
      "grad_norm": 0.40417975187301636,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0906,
      "step": 6
    },
    {
      "epoch": 0.12134344528710726,
      "grad_norm": 0.2923962473869324,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0912,
      "step": 7
    },
    {
      "epoch": 0.13867822318526543,
      "grad_norm": 0.3543075919151306,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.097,
      "step": 8
    },
    {
      "epoch": 0.1560130010834236,
      "grad_norm": 0.32288411259651184,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.1074,
      "step": 9
    },
    {
      "epoch": 0.1733477789815818,
      "grad_norm": 0.23518748581409454,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.1114,
      "step": 10
    },
    {
      "epoch": 0.19068255687973998,
      "grad_norm": 0.2938070297241211,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.1206,
      "step": 11
    },
    {
      "epoch": 0.20801733477789816,
      "grad_norm": 0.36567267775535583,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.1452,
      "step": 12
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.18887048959732056,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0555,
      "step": 13
    },
    {
      "epoch": 0.24268689057421453,
      "grad_norm": 0.19256988167762756,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0435,
      "step": 14
    },
    {
      "epoch": 0.2600216684723727,
      "grad_norm": 0.20813193917274475,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.054,
      "step": 15
    },
    {
      "epoch": 0.27735644637053086,
      "grad_norm": 0.30661728978157043,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0655,
      "step": 16
    },
    {
      "epoch": 0.29469122426868904,
      "grad_norm": 0.2554875910282135,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0658,
      "step": 17
    },
    {
      "epoch": 0.3120260021668472,
      "grad_norm": 0.19838938117027283,
      "learning_rate": 7.75e-05,
      "loss": 0.0707,
      "step": 18
    },
    {
      "epoch": 0.3293607800650054,
      "grad_norm": 0.22489877045154572,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0779,
      "step": 19
    },
    {
      "epoch": 0.3466955579631636,
      "grad_norm": 0.26527872681617737,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0898,
      "step": 20
    },
    {
      "epoch": 0.3640303358613218,
      "grad_norm": 0.23718084394931793,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0846,
      "step": 21
    },
    {
      "epoch": 0.38136511375947996,
      "grad_norm": 0.329249769449234,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0866,
      "step": 22
    },
    {
      "epoch": 0.39869989165763814,
      "grad_norm": 0.2758727967739105,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.1015,
      "step": 23
    },
    {
      "epoch": 0.4160346695557963,
      "grad_norm": 0.39751315116882324,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.1253,
      "step": 24
    },
    {
      "epoch": 0.4333694474539545,
      "grad_norm": 0.4145531952381134,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.1512,
      "step": 25
    },
    {
      "epoch": 0.4333694474539545,
      "eval_loss": 0.10687629878520966,
      "eval_runtime": 3.472,
      "eval_samples_per_second": 14.401,
      "eval_steps_per_second": 3.744,
      "step": 25
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 0.08605414628982544,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0314,
      "step": 26
    },
    {
      "epoch": 0.46803900325027087,
      "grad_norm": 0.1190139502286911,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0437,
      "step": 27
    },
    {
      "epoch": 0.48537378114842905,
      "grad_norm": 0.13927221298217773,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0511,
      "step": 28
    },
    {
      "epoch": 0.5027085590465872,
      "grad_norm": 0.20223039388656616,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0631,
      "step": 29
    },
    {
      "epoch": 0.5200433369447454,
      "grad_norm": 0.17049828171730042,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0607,
      "step": 30
    },
    {
      "epoch": 0.5373781148429035,
      "grad_norm": 0.45451751351356506,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0692,
      "step": 31
    },
    {
      "epoch": 0.5547128927410617,
      "grad_norm": 0.22615575790405273,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0783,
      "step": 32
    },
    {
      "epoch": 0.5720476706392199,
      "grad_norm": 0.2533192038536072,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0794,
      "step": 33
    },
    {
      "epoch": 0.5893824485373781,
      "grad_norm": 0.21578319370746613,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0759,
      "step": 34
    },
    {
      "epoch": 0.6067172264355363,
      "grad_norm": 0.26224207878112793,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0896,
      "step": 35
    },
    {
      "epoch": 0.6240520043336945,
      "grad_norm": 0.3087189197540283,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.097,
      "step": 36
    },
    {
      "epoch": 0.6413867822318526,
      "grad_norm": 0.3518355190753937,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.121,
      "step": 37
    },
    {
      "epoch": 0.6587215601300108,
      "grad_norm": 0.1477062702178955,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0455,
      "step": 38
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.1556491106748581,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0385,
      "step": 39
    },
    {
      "epoch": 0.6933911159263272,
      "grad_norm": 0.1597602367401123,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0482,
      "step": 40
    },
    {
      "epoch": 0.7107258938244854,
      "grad_norm": 0.23317818343639374,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0582,
      "step": 41
    },
    {
      "epoch": 0.7280606717226435,
      "grad_norm": 0.2035202533006668,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0653,
      "step": 42
    },
    {
      "epoch": 0.7453954496208017,
      "grad_norm": 0.2277495265007019,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.071,
      "step": 43
    },
    {
      "epoch": 0.7627302275189599,
      "grad_norm": 0.24984626471996307,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0752,
      "step": 44
    },
    {
      "epoch": 0.7800650054171181,
      "grad_norm": 0.19852232933044434,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0763,
      "step": 45
    },
    {
      "epoch": 0.7973997833152763,
      "grad_norm": 0.24323515594005585,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0701,
      "step": 46
    },
    {
      "epoch": 0.8147345612134345,
      "grad_norm": 0.2687220573425293,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0959,
      "step": 47
    },
    {
      "epoch": 0.8320693391115926,
      "grad_norm": 0.2877626121044159,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0928,
      "step": 48
    },
    {
      "epoch": 0.8494041170097508,
      "grad_norm": 0.4412320554256439,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.1296,
      "step": 49
    },
    {
      "epoch": 0.866738894907909,
      "grad_norm": 0.4098319411277771,
      "learning_rate": 1e-05,
      "loss": 0.15,
      "step": 50
    },
    {
      "epoch": 0.866738894907909,
      "eval_loss": 0.09838873893022537,
      "eval_runtime": 3.5061,
      "eval_samples_per_second": 14.261,
      "eval_steps_per_second": 3.708,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}