{
  "best_metric": 3.4378933906555176,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.030392827292758908,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006078565458551782,
      "grad_norm": 0.6025287508964539,
      "learning_rate": 5e-05,
      "loss": 3.6416,
      "step": 1
    },
    {
      "epoch": 0.0006078565458551782,
      "eval_loss": 4.720283031463623,
      "eval_runtime": 2.4554,
      "eval_samples_per_second": 20.363,
      "eval_steps_per_second": 5.294,
      "step": 1
    },
    {
      "epoch": 0.0012157130917103563,
      "grad_norm": 0.7891955971717834,
      "learning_rate": 0.0001,
      "loss": 4.1195,
      "step": 2
    },
    {
      "epoch": 0.0018235696375655346,
      "grad_norm": 0.8280964493751526,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.1603,
      "step": 3
    },
    {
      "epoch": 0.0024314261834207126,
      "grad_norm": 0.9342966675758362,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.1323,
      "step": 4
    },
    {
      "epoch": 0.003039282729275891,
      "grad_norm": 0.9619356989860535,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.0945,
      "step": 5
    },
    {
      "epoch": 0.003647139275131069,
      "grad_norm": 1.0246630907058716,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.024,
      "step": 6
    },
    {
      "epoch": 0.004254995820986247,
      "grad_norm": 0.9565690755844116,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.0031,
      "step": 7
    },
    {
      "epoch": 0.004862852366841425,
      "grad_norm": 1.0364619493484497,
      "learning_rate": 9.657457896300791e-05,
      "loss": 3.8772,
      "step": 8
    },
    {
      "epoch": 0.0054707089126966035,
      "grad_norm": 1.2275835275650024,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.0079,
      "step": 9
    },
    {
      "epoch": 0.006078565458551782,
      "grad_norm": 1.1928704977035522,
      "learning_rate": 9.397114317029975e-05,
      "loss": 3.9703,
      "step": 10
    },
    {
      "epoch": 0.00668642200440696,
      "grad_norm": 1.6559075117111206,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.002,
      "step": 11
    },
    {
      "epoch": 0.007294278550262138,
      "grad_norm": 1.6047799587249756,
      "learning_rate": 9.070090031310558e-05,
      "loss": 3.9494,
      "step": 12
    },
    {
      "epoch": 0.007902135096117317,
      "grad_norm": 2.2705578804016113,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.641,
      "step": 13
    },
    {
      "epoch": 0.008509991641972494,
      "grad_norm": 2.7151262760162354,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.7223,
      "step": 14
    },
    {
      "epoch": 0.009117848187827673,
      "grad_norm": 1.9043700695037842,
      "learning_rate": 8.467056167950311e-05,
      "loss": 3.6603,
      "step": 15
    },
    {
      "epoch": 0.00972570473368285,
      "grad_norm": 1.3960378170013428,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.6831,
      "step": 16
    },
    {
      "epoch": 0.01033356127953803,
      "grad_norm": 0.9238163828849792,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.6169,
      "step": 17
    },
    {
      "epoch": 0.010941417825393207,
      "grad_norm": 0.6945294737815857,
      "learning_rate": 7.75e-05,
      "loss": 3.6265,
      "step": 18
    },
    {
      "epoch": 0.011549274371248386,
      "grad_norm": 0.8358215093612671,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.6207,
      "step": 19
    },
    {
      "epoch": 0.012157130917103564,
      "grad_norm": 0.9271958470344543,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.5797,
      "step": 20
    },
    {
      "epoch": 0.012764987462958741,
      "grad_norm": 1.1820098161697388,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.6548,
      "step": 21
    },
    {
      "epoch": 0.01337284400881392,
      "grad_norm": 1.4449565410614014,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.6567,
      "step": 22
    },
    {
      "epoch": 0.013980700554669098,
      "grad_norm": 1.7002066373825073,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.8868,
      "step": 23
    },
    {
      "epoch": 0.014588557100524277,
      "grad_norm": 2.408024311065674,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.9967,
      "step": 24
    },
    {
      "epoch": 0.015196413646379454,
      "grad_norm": 4.712019443511963,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.1805,
      "step": 25
    },
    {
      "epoch": 0.015196413646379454,
      "eval_loss": 3.4724762439727783,
      "eval_runtime": 1.8364,
      "eval_samples_per_second": 27.227,
      "eval_steps_per_second": 7.079,
      "step": 25
    },
    {
      "epoch": 0.015804270192234633,
      "grad_norm": 0.6599547266960144,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.4072,
      "step": 26
    },
    {
      "epoch": 0.01641212673808981,
      "grad_norm": 0.7060936689376831,
      "learning_rate": 5.205685918464356e-05,
      "loss": 3.385,
      "step": 27
    },
    {
      "epoch": 0.017019983283944988,
      "grad_norm": 0.8498525619506836,
      "learning_rate": 4.912632135009769e-05,
      "loss": 3.4661,
      "step": 28
    },
    {
      "epoch": 0.01762783982980017,
      "grad_norm": 0.8462444543838501,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 3.4616,
      "step": 29
    },
    {
      "epoch": 0.018235696375655346,
      "grad_norm": 0.708667516708374,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.4996,
      "step": 30
    },
    {
      "epoch": 0.018843552921510524,
      "grad_norm": 0.7013354301452637,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.5255,
      "step": 31
    },
    {
      "epoch": 0.0194514094673657,
      "grad_norm": 0.7256174683570862,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.6334,
      "step": 32
    },
    {
      "epoch": 0.02005926601322088,
      "grad_norm": 0.7189586162567139,
      "learning_rate": 3.509700894014496e-05,
      "loss": 3.5756,
      "step": 33
    },
    {
      "epoch": 0.02066712255907606,
      "grad_norm": 0.9632193446159363,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.662,
      "step": 34
    },
    {
      "epoch": 0.021274979104931237,
      "grad_norm": 1.1224030256271362,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.6491,
      "step": 35
    },
    {
      "epoch": 0.021882835650786414,
      "grad_norm": 1.4623186588287354,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.8356,
      "step": 36
    },
    {
      "epoch": 0.02249069219664159,
      "grad_norm": 2.6539292335510254,
      "learning_rate": 2.53294383204969e-05,
      "loss": 3.9538,
      "step": 37
    },
    {
      "epoch": 0.023098548742496772,
      "grad_norm": 0.6411238312721252,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.4825,
      "step": 38
    },
    {
      "epoch": 0.02370640528835195,
      "grad_norm": 0.7229188680648804,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 3.4894,
      "step": 39
    },
    {
      "epoch": 0.024314261834207127,
      "grad_norm": 0.7024473547935486,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 3.3929,
      "step": 40
    },
    {
      "epoch": 0.024922118380062305,
      "grad_norm": 0.6970648765563965,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.3762,
      "step": 41
    },
    {
      "epoch": 0.025529974925917482,
      "grad_norm": 0.6724116802215576,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.4809,
      "step": 42
    },
    {
      "epoch": 0.026137831471772663,
      "grad_norm": 0.6194472312927246,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.4265,
      "step": 43
    },
    {
      "epoch": 0.02674568801762784,
      "grad_norm": 0.6786876916885376,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.6158,
      "step": 44
    },
    {
      "epoch": 0.027353544563483018,
      "grad_norm": 0.794440507888794,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 3.6502,
      "step": 45
    },
    {
      "epoch": 0.027961401109338195,
      "grad_norm": 0.752371072769165,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.6907,
      "step": 46
    },
    {
      "epoch": 0.028569257655193376,
      "grad_norm": 0.8845945000648499,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 3.5251,
      "step": 47
    },
    {
      "epoch": 0.029177114201048553,
      "grad_norm": 1.2242646217346191,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.6133,
      "step": 48
    },
    {
      "epoch": 0.02978497074690373,
      "grad_norm": 1.964848279953003,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 3.8659,
      "step": 49
    },
    {
      "epoch": 0.030392827292758908,
      "grad_norm": 3.6303746700286865,
      "learning_rate": 1e-05,
      "loss": 3.7604,
      "step": 50
    },
    {
      "epoch": 0.030392827292758908,
      "eval_loss": 3.4378933906555176,
      "eval_runtime": 1.8363,
      "eval_samples_per_second": 27.229,
      "eval_steps_per_second": 7.079,
      "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": 5.624057810649088e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}