{
  "best_metric": 0.3190205991268158,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.3062200956937799,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006124401913875598,
      "grad_norm": 1.2583987712860107,
      "learning_rate": 5e-05,
      "loss": 0.2871,
      "step": 1
    },
    {
      "epoch": 0.006124401913875598,
      "eval_loss": 1.9122283458709717,
      "eval_runtime": 2.0275,
      "eval_samples_per_second": 24.662,
      "eval_steps_per_second": 6.412,
      "step": 1
    },
    {
      "epoch": 0.012248803827751197,
      "grad_norm": 1.311158537864685,
      "learning_rate": 0.0001,
      "loss": 0.2762,
      "step": 2
    },
    {
      "epoch": 0.018373205741626795,
      "grad_norm": 0.7718752026557922,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.2922,
      "step": 3
    },
    {
      "epoch": 0.024497607655502393,
      "grad_norm": 0.8217308521270752,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.2966,
      "step": 4
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 1.2334226369857788,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.8513,
      "step": 5
    },
    {
      "epoch": 0.03674641148325359,
      "grad_norm": 1.3985689878463745,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.2628,
      "step": 6
    },
    {
      "epoch": 0.042870813397129184,
      "grad_norm": 1.1988945007324219,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.2283,
      "step": 7
    },
    {
      "epoch": 0.048995215311004786,
      "grad_norm": 1.4839463233947754,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.3611,
      "step": 8
    },
    {
      "epoch": 0.05511961722488038,
      "grad_norm": 1.1175360679626465,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.1326,
      "step": 9
    },
    {
      "epoch": 0.06124401913875598,
      "grad_norm": 0.8393290042877197,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.1623,
      "step": 10
    },
    {
      "epoch": 0.06736842105263158,
      "grad_norm": 1.0493677854537964,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.8706,
      "step": 11
    },
    {
      "epoch": 0.07349282296650718,
      "grad_norm": 0.7625401616096497,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.7608,
      "step": 12
    },
    {
      "epoch": 0.07961722488038278,
      "grad_norm": 0.4153471887111664,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.2783,
      "step": 13
    },
    {
      "epoch": 0.08574162679425837,
      "grad_norm": 0.2964439392089844,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.202,
      "step": 14
    },
    {
      "epoch": 0.09186602870813397,
      "grad_norm": 0.16517241299152374,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.18,
      "step": 15
    },
    {
      "epoch": 0.09799043062200957,
      "grad_norm": 0.3973408341407776,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.1642,
      "step": 16
    },
    {
      "epoch": 0.10411483253588517,
      "grad_norm": 0.4092251658439636,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.2857,
      "step": 17
    },
    {
      "epoch": 0.11023923444976076,
      "grad_norm": 1.2130886316299438,
      "learning_rate": 7.75e-05,
      "loss": 0.8226,
      "step": 18
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 1.355413556098938,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.9582,
      "step": 19
    },
    {
      "epoch": 0.12248803827751197,
      "grad_norm": 1.478370189666748,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.1041,
      "step": 20
    },
    {
      "epoch": 0.12861244019138757,
      "grad_norm": 1.226299524307251,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.0495,
      "step": 21
    },
    {
      "epoch": 0.13473684210526315,
      "grad_norm": 1.4787882566452026,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.9458,
      "step": 22
    },
    {
      "epoch": 0.14086124401913874,
      "grad_norm": 1.3268910646438599,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.8899,
      "step": 23
    },
    {
      "epoch": 0.14698564593301436,
      "grad_norm": 0.9856330156326294,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.5583,
      "step": 24
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 1.1389474868774414,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.6596,
      "step": 25
    },
    {
      "epoch": 0.15311004784688995,
      "eval_loss": 0.424012690782547,
      "eval_runtime": 2.0563,
      "eval_samples_per_second": 24.316,
      "eval_steps_per_second": 6.322,
      "step": 25
    },
    {
      "epoch": 0.15923444976076556,
      "grad_norm": 0.3771899342536926,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.2051,
      "step": 26
    },
    {
      "epoch": 0.16535885167464115,
      "grad_norm": 0.3396134376525879,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.1877,
      "step": 27
    },
    {
      "epoch": 0.17148325358851674,
      "grad_norm": 0.28315144777297974,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.1407,
      "step": 28
    },
    {
      "epoch": 0.17760765550239235,
      "grad_norm": 0.5146012306213379,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.1578,
      "step": 29
    },
    {
      "epoch": 0.18373205741626794,
      "grad_norm": 0.9754877090454102,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.5997,
      "step": 30
    },
    {
      "epoch": 0.18985645933014353,
      "grad_norm": 2.0145418643951416,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.7871,
      "step": 31
    },
    {
      "epoch": 0.19598086124401914,
      "grad_norm": 3.73909854888916,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.8302,
      "step": 32
    },
    {
      "epoch": 0.20210526315789473,
      "grad_norm": 1.4725128412246704,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.7317,
      "step": 33
    },
    {
      "epoch": 0.20822966507177035,
      "grad_norm": 2.3814151287078857,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.802,
      "step": 34
    },
    {
      "epoch": 0.21435406698564594,
      "grad_norm": 1.2523080110549927,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.6503,
      "step": 35
    },
    {
      "epoch": 0.22047846889952152,
      "grad_norm": 1.2774503231048584,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.5147,
      "step": 36
    },
    {
      "epoch": 0.22660287081339714,
      "grad_norm": 0.9718907475471497,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.4658,
      "step": 37
    },
    {
      "epoch": 0.23272727272727273,
      "grad_norm": 0.34255456924438477,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.2052,
      "step": 38
    },
    {
      "epoch": 0.23885167464114831,
      "grad_norm": 0.3709205090999603,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.1799,
      "step": 39
    },
    {
      "epoch": 0.24497607655502393,
      "grad_norm": 0.3074520528316498,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.1566,
      "step": 40
    },
    {
      "epoch": 0.25110047846889955,
      "grad_norm": 0.6865524649620056,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.1098,
      "step": 41
    },
    {
      "epoch": 0.25722488038277513,
      "grad_norm": 0.7394497394561768,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.2496,
      "step": 42
    },
    {
      "epoch": 0.2633492822966507,
      "grad_norm": 1.2238065004348755,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.544,
      "step": 43
    },
    {
      "epoch": 0.2694736842105263,
      "grad_norm": 1.4266135692596436,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.5695,
      "step": 44
    },
    {
      "epoch": 0.2755980861244019,
      "grad_norm": 1.3586610555648804,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.6553,
      "step": 45
    },
    {
      "epoch": 0.2817224880382775,
      "grad_norm": 1.0930596590042114,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.5945,
      "step": 46
    },
    {
      "epoch": 0.28784688995215313,
      "grad_norm": 1.1304785013198853,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.5402,
      "step": 47
    },
    {
      "epoch": 0.2939712918660287,
      "grad_norm": 0.9247140288352966,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.514,
      "step": 48
    },
    {
      "epoch": 0.3000956937799043,
      "grad_norm": 0.7985676527023315,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.359,
      "step": 49
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 1.2171745300292969,
      "learning_rate": 1e-05,
      "loss": 0.3971,
      "step": 50
    },
    {
      "epoch": 0.3062200956937799,
      "eval_loss": 0.3190205991268158,
      "eval_runtime": 2.0665,
      "eval_samples_per_second": 24.196,
      "eval_steps_per_second": 6.291,
      "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": 1.589463780163584e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}