{
  "best_metric": 11.930052757263184,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.16427104722792607,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032854209445585215,
      "grad_norm": 0.04851006716489792,
      "learning_rate": 5e-05,
      "loss": 11.9397,
      "step": 1
    },
    {
      "epoch": 0.0032854209445585215,
      "eval_loss": 11.939081192016602,
      "eval_runtime": 0.1666,
      "eval_samples_per_second": 300.068,
      "eval_steps_per_second": 78.018,
      "step": 1
    },
    {
      "epoch": 0.006570841889117043,
      "grad_norm": 0.044286660850048065,
      "learning_rate": 0.0001,
      "loss": 11.9403,
      "step": 2
    },
    {
      "epoch": 0.009856262833675565,
      "grad_norm": 0.049766551703214645,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9385,
      "step": 3
    },
    {
      "epoch": 0.013141683778234086,
      "grad_norm": 0.05622759088873863,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9403,
      "step": 4
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.05857555940747261,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9386,
      "step": 5
    },
    {
      "epoch": 0.01971252566735113,
      "grad_norm": 0.07766827940940857,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9391,
      "step": 6
    },
    {
      "epoch": 0.02299794661190965,
      "grad_norm": 0.07366184890270233,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9411,
      "step": 7
    },
    {
      "epoch": 0.026283367556468172,
      "grad_norm": 0.09200644493103027,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.943,
      "step": 8
    },
    {
      "epoch": 0.029568788501026694,
      "grad_norm": 0.08810490369796753,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9415,
      "step": 9
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.0925133004784584,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9378,
      "step": 10
    },
    {
      "epoch": 0.036139630390143736,
      "grad_norm": 0.09532303363084793,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9376,
      "step": 11
    },
    {
      "epoch": 0.03942505133470226,
      "grad_norm": 0.10714438557624817,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9384,
      "step": 12
    },
    {
      "epoch": 0.04271047227926078,
      "grad_norm": 0.06553089618682861,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9386,
      "step": 13
    },
    {
      "epoch": 0.0459958932238193,
      "grad_norm": 0.05890142545104027,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.938,
      "step": 14
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.06354363262653351,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9377,
      "step": 15
    },
    {
      "epoch": 0.052566735112936344,
      "grad_norm": 0.07029973715543747,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9366,
      "step": 16
    },
    {
      "epoch": 0.05585215605749486,
      "grad_norm": 0.07899687439203262,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9355,
      "step": 17
    },
    {
      "epoch": 0.05913757700205339,
      "grad_norm": 0.09725009649991989,
      "learning_rate": 7.75e-05,
      "loss": 11.9373,
      "step": 18
    },
    {
      "epoch": 0.06242299794661191,
      "grad_norm": 0.11167705059051514,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9356,
      "step": 19
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.11074248701334,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9364,
      "step": 20
    },
    {
      "epoch": 0.06899383983572896,
      "grad_norm": 0.11366985738277435,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9362,
      "step": 21
    },
    {
      "epoch": 0.07227926078028747,
      "grad_norm": 0.10831017792224884,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9371,
      "step": 22
    },
    {
      "epoch": 0.075564681724846,
      "grad_norm": 0.1166386604309082,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9347,
      "step": 23
    },
    {
      "epoch": 0.07885010266940452,
      "grad_norm": 0.12967684864997864,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9342,
      "step": 24
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.14143593609333038,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9341,
      "step": 25
    },
    {
      "epoch": 0.08213552361396304,
      "eval_loss": 11.933411598205566,
      "eval_runtime": 0.1694,
      "eval_samples_per_second": 295.171,
      "eval_steps_per_second": 76.744,
      "step": 25
    },
    {
      "epoch": 0.08542094455852156,
      "grad_norm": 0.0746845081448555,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9349,
      "step": 26
    },
    {
      "epoch": 0.08870636550308009,
      "grad_norm": 0.08587120473384857,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9355,
      "step": 27
    },
    {
      "epoch": 0.0919917864476386,
      "grad_norm": 0.09801056236028671,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9345,
      "step": 28
    },
    {
      "epoch": 0.09527720739219712,
      "grad_norm": 0.10124927014112473,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9342,
      "step": 29
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.1071905717253685,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9341,
      "step": 30
    },
    {
      "epoch": 0.10184804928131416,
      "grad_norm": 0.13783201575279236,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9321,
      "step": 31
    },
    {
      "epoch": 0.10513347022587269,
      "grad_norm": 0.12671908736228943,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9357,
      "step": 32
    },
    {
      "epoch": 0.10841889117043121,
      "grad_norm": 0.1352739781141281,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9353,
      "step": 33
    },
    {
      "epoch": 0.11170431211498973,
      "grad_norm": 0.13712292909622192,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9337,
      "step": 34
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.1451713740825653,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9328,
      "step": 35
    },
    {
      "epoch": 0.11827515400410678,
      "grad_norm": 0.13962270319461823,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9299,
      "step": 36
    },
    {
      "epoch": 0.1215605749486653,
      "grad_norm": 0.1617678552865982,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9311,
      "step": 37
    },
    {
      "epoch": 0.12484599589322382,
      "grad_norm": 0.1094789206981659,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9343,
      "step": 38
    },
    {
      "epoch": 0.12813141683778234,
      "grad_norm": 0.09994740039110184,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9339,
      "step": 39
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.1053725853562355,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.9345,
      "step": 40
    },
    {
      "epoch": 0.1347022587268994,
      "grad_norm": 0.1118607148528099,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9358,
      "step": 41
    },
    {
      "epoch": 0.13798767967145792,
      "grad_norm": 0.11891821771860123,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9318,
      "step": 42
    },
    {
      "epoch": 0.14127310061601642,
      "grad_norm": 0.14357700943946838,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.9331,
      "step": 43
    },
    {
      "epoch": 0.14455852156057494,
      "grad_norm": 0.14908310770988464,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9308,
      "step": 44
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.13474707305431366,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9332,
      "step": 45
    },
    {
      "epoch": 0.151129363449692,
      "grad_norm": 0.14854881167411804,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9322,
      "step": 46
    },
    {
      "epoch": 0.15441478439425052,
      "grad_norm": 0.1468830704689026,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9309,
      "step": 47
    },
    {
      "epoch": 0.15770020533880905,
      "grad_norm": 0.14374658465385437,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9291,
      "step": 48
    },
    {
      "epoch": 0.16098562628336754,
      "grad_norm": 0.15578904747962952,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.9302,
      "step": 49
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.16485072672367096,
      "learning_rate": 1e-05,
      "loss": 11.9277,
      "step": 50
    },
    {
      "epoch": 0.16427104722792607,
      "eval_loss": 11.930052757263184,
      "eval_runtime": 0.1707,
      "eval_samples_per_second": 292.919,
      "eval_steps_per_second": 76.159,
      "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}