{
  "best_metric": 0.9804583191871643,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.012340727485885293,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024681454971770586,
      "grad_norm": 0.6548905968666077,
      "learning_rate": 5e-05,
      "loss": 1.5551,
      "step": 1
    },
    {
      "epoch": 0.00024681454971770586,
      "eval_loss": 1.9421532154083252,
      "eval_runtime": 3.8553,
      "eval_samples_per_second": 12.969,
      "eval_steps_per_second": 3.372,
      "step": 1
    },
    {
      "epoch": 0.0004936290994354117,
      "grad_norm": 0.677850604057312,
      "learning_rate": 0.0001,
      "loss": 1.607,
      "step": 2
    },
    {
      "epoch": 0.0007404436491531176,
      "grad_norm": 0.6717300415039062,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.5447,
      "step": 3
    },
    {
      "epoch": 0.0009872581988708234,
      "grad_norm": 0.5053644776344299,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.4959,
      "step": 4
    },
    {
      "epoch": 0.0012340727485885294,
      "grad_norm": 0.6726400256156921,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.4017,
      "step": 5
    },
    {
      "epoch": 0.0014808872983062351,
      "grad_norm": 0.880503237247467,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.3722,
      "step": 6
    },
    {
      "epoch": 0.001727701848023941,
      "grad_norm": 0.7695256471633911,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.3935,
      "step": 7
    },
    {
      "epoch": 0.001974516397741647,
      "grad_norm": 0.9781736731529236,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.3271,
      "step": 8
    },
    {
      "epoch": 0.002221330947459353,
      "grad_norm": 1.1546648740768433,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.3649,
      "step": 9
    },
    {
      "epoch": 0.002468145497177059,
      "grad_norm": 1.2356321811676025,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.3527,
      "step": 10
    },
    {
      "epoch": 0.0027149600468947643,
      "grad_norm": 1.4574170112609863,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.3231,
      "step": 11
    },
    {
      "epoch": 0.0029617745966124703,
      "grad_norm": 2.0851118564605713,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.2202,
      "step": 12
    },
    {
      "epoch": 0.0032085891463301762,
      "grad_norm": 1.0589816570281982,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.4527,
      "step": 13
    },
    {
      "epoch": 0.003455403696047882,
      "grad_norm": 1.0790549516677856,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.5426,
      "step": 14
    },
    {
      "epoch": 0.0037022182457655877,
      "grad_norm": 0.7226734757423401,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.4222,
      "step": 15
    },
    {
      "epoch": 0.003949032795483294,
      "grad_norm": 0.5526368021965027,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.3393,
      "step": 16
    },
    {
      "epoch": 0.004195847345201,
      "grad_norm": 0.4406169056892395,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.2386,
      "step": 17
    },
    {
      "epoch": 0.004442661894918706,
      "grad_norm": 0.4329923391342163,
      "learning_rate": 7.75e-05,
      "loss": 1.227,
      "step": 18
    },
    {
      "epoch": 0.004689476444636412,
      "grad_norm": 0.608071506023407,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.3089,
      "step": 19
    },
    {
      "epoch": 0.004936290994354118,
      "grad_norm": 0.7732976675033569,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.2208,
      "step": 20
    },
    {
      "epoch": 0.005183105544071823,
      "grad_norm": 0.928796648979187,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.1878,
      "step": 21
    },
    {
      "epoch": 0.005429920093789529,
      "grad_norm": 0.8442566394805908,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.2422,
      "step": 22
    },
    {
      "epoch": 0.005676734643507235,
      "grad_norm": 1.0397518873214722,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.9998,
      "step": 23
    },
    {
      "epoch": 0.0059235491932249406,
      "grad_norm": 1.0411866903305054,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.0243,
      "step": 24
    },
    {
      "epoch": 0.0061703637429426465,
      "grad_norm": 1.360701084136963,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.1418,
      "step": 25
    },
    {
      "epoch": 0.0061703637429426465,
      "eval_loss": 1.0591540336608887,
      "eval_runtime": 3.4971,
      "eval_samples_per_second": 14.298,
      "eval_steps_per_second": 3.717,
      "step": 25
    },
    {
      "epoch": 0.0064171782926603525,
      "grad_norm": 0.3678169846534729,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.4322,
      "step": 26
    },
    {
      "epoch": 0.0066639928423780585,
      "grad_norm": 0.41855236887931824,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.3597,
      "step": 27
    },
    {
      "epoch": 0.006910807392095764,
      "grad_norm": 0.4745751619338989,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.3224,
      "step": 28
    },
    {
      "epoch": 0.0071576219418134695,
      "grad_norm": 0.559587836265564,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.3037,
      "step": 29
    },
    {
      "epoch": 0.0074044364915311755,
      "grad_norm": 0.5168178081512451,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.3006,
      "step": 30
    },
    {
      "epoch": 0.0076512510412488815,
      "grad_norm": 0.6175752282142639,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.2705,
      "step": 31
    },
    {
      "epoch": 0.007898065590966587,
      "grad_norm": 0.6352323293685913,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.1419,
      "step": 32
    },
    {
      "epoch": 0.008144880140684293,
      "grad_norm": 0.7056966423988342,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.1645,
      "step": 33
    },
    {
      "epoch": 0.008391694690402,
      "grad_norm": 0.6783286929130554,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.104,
      "step": 34
    },
    {
      "epoch": 0.008638509240119704,
      "grad_norm": 0.7926774024963379,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.9757,
      "step": 35
    },
    {
      "epoch": 0.008885323789837411,
      "grad_norm": 1.0232789516448975,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.0068,
      "step": 36
    },
    {
      "epoch": 0.009132138339555116,
      "grad_norm": 1.2049612998962402,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.0109,
      "step": 37
    },
    {
      "epoch": 0.009378952889272823,
      "grad_norm": 0.2999906539916992,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.337,
      "step": 38
    },
    {
      "epoch": 0.009625767438990528,
      "grad_norm": 0.2730841338634491,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.3385,
      "step": 39
    },
    {
      "epoch": 0.009872581988708235,
      "grad_norm": 0.33873268961906433,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.3549,
      "step": 40
    },
    {
      "epoch": 0.01011939653842594,
      "grad_norm": 0.3427824079990387,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.3463,
      "step": 41
    },
    {
      "epoch": 0.010366211088143645,
      "grad_norm": 0.38400933146476746,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.2599,
      "step": 42
    },
    {
      "epoch": 0.010613025637861352,
      "grad_norm": 0.4481218755245209,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.2069,
      "step": 43
    },
    {
      "epoch": 0.010859840187579057,
      "grad_norm": 0.5700804591178894,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.2132,
      "step": 44
    },
    {
      "epoch": 0.011106654737296764,
      "grad_norm": 0.5816468000411987,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.1683,
      "step": 45
    },
    {
      "epoch": 0.01135346928701447,
      "grad_norm": 0.6591303944587708,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.142,
      "step": 46
    },
    {
      "epoch": 0.011600283836732176,
      "grad_norm": 0.7625118494033813,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.9836,
      "step": 47
    },
    {
      "epoch": 0.011847098386449881,
      "grad_norm": 0.9183720350265503,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.9474,
      "step": 48
    },
    {
      "epoch": 0.012093912936167586,
      "grad_norm": 0.9961158037185669,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.9135,
      "step": 49
    },
    {
      "epoch": 0.012340727485885293,
      "grad_norm": 1.5027074813842773,
      "learning_rate": 1e-05,
      "loss": 1.0364,
      "step": 50
    },
    {
      "epoch": 0.012340727485885293,
      "eval_loss": 0.9804583191871643,
      "eval_runtime": 3.5086,
      "eval_samples_per_second": 14.251,
      "eval_steps_per_second": 3.705,
      "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": 5.969948642440643e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}