{
  "best_metric": 0.9053548574447632,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.00894094505789262,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017881890115785238,
      "grad_norm": 20.622814178466797,
      "learning_rate": 5e-05,
      "loss": 3.1079,
      "step": 1
    },
    {
      "epoch": 0.00017881890115785238,
      "eval_loss": 3.3165433406829834,
      "eval_runtime": 559.7058,
      "eval_samples_per_second": 67.31,
      "eval_steps_per_second": 8.415,
      "step": 1
    },
    {
      "epoch": 0.00035763780231570476,
      "grad_norm": 20.00335121154785,
      "learning_rate": 0.0001,
      "loss": 3.1477,
      "step": 2
    },
    {
      "epoch": 0.0005364567034735571,
      "grad_norm": 15.535104751586914,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.5567,
      "step": 3
    },
    {
      "epoch": 0.0007152756046314095,
      "grad_norm": 9.695021629333496,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.4166,
      "step": 4
    },
    {
      "epoch": 0.0008940945057892619,
      "grad_norm": 6.882876873016357,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9099,
      "step": 5
    },
    {
      "epoch": 0.0010729134069471142,
      "grad_norm": 4.3709025382995605,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.536,
      "step": 6
    },
    {
      "epoch": 0.0012517323081049666,
      "grad_norm": 3.735841751098633,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.5066,
      "step": 7
    },
    {
      "epoch": 0.001430551209262819,
      "grad_norm": 3.2322535514831543,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4056,
      "step": 8
    },
    {
      "epoch": 0.0016093701104206715,
      "grad_norm": 3.2769668102264404,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.4204,
      "step": 9
    },
    {
      "epoch": 0.0017881890115785239,
      "grad_norm": 1.9748518466949463,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2581,
      "step": 10
    },
    {
      "epoch": 0.0019670079127363763,
      "grad_norm": 2.2444496154785156,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.2769,
      "step": 11
    },
    {
      "epoch": 0.0021458268138942285,
      "grad_norm": 2.2840230464935303,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1215,
      "step": 12
    },
    {
      "epoch": 0.002324645715052081,
      "grad_norm": 1.9635887145996094,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1562,
      "step": 13
    },
    {
      "epoch": 0.0025034646162099333,
      "grad_norm": 2.1025938987731934,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.0349,
      "step": 14
    },
    {
      "epoch": 0.002682283517367786,
      "grad_norm": 1.5906882286071777,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.1028,
      "step": 15
    },
    {
      "epoch": 0.002861102418525638,
      "grad_norm": 1.7898417711257935,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0752,
      "step": 16
    },
    {
      "epoch": 0.0030399213196834907,
      "grad_norm": 1.6060125827789307,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1622,
      "step": 17
    },
    {
      "epoch": 0.003218740220841343,
      "grad_norm": 1.811711072921753,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1112,
      "step": 18
    },
    {
      "epoch": 0.003397559121999195,
      "grad_norm": 2.1851539611816406,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.9639,
      "step": 19
    },
    {
      "epoch": 0.0035763780231570477,
      "grad_norm": 1.4870500564575195,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0774,
      "step": 20
    },
    {
      "epoch": 0.0037551969243149,
      "grad_norm": 2.0393495559692383,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.189,
      "step": 21
    },
    {
      "epoch": 0.0039340158254727526,
      "grad_norm": 1.7980921268463135,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.142,
      "step": 22
    },
    {
      "epoch": 0.004112834726630605,
      "grad_norm": 1.8136911392211914,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.0606,
      "step": 23
    },
    {
      "epoch": 0.004291653627788457,
      "grad_norm": 2.0860252380371094,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.9348,
      "step": 24
    },
    {
      "epoch": 0.00447047252894631,
      "grad_norm": 2.184941530227661,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.0593,
      "step": 25
    },
    {
      "epoch": 0.00447047252894631,
      "eval_loss": 1.014263391494751,
      "eval_runtime": 559.1003,
      "eval_samples_per_second": 67.383,
      "eval_steps_per_second": 8.424,
      "step": 25
    },
    {
      "epoch": 0.004649291430104162,
      "grad_norm": 2.7061338424682617,
      "learning_rate": 5e-05,
      "loss": 0.8658,
      "step": 26
    },
    {
      "epoch": 0.004828110331262014,
      "grad_norm": 1.9943201541900635,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.9373,
      "step": 27
    },
    {
      "epoch": 0.005006929232419867,
      "grad_norm": 1.6644830703735352,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.9823,
      "step": 28
    },
    {
      "epoch": 0.005185748133577719,
      "grad_norm": 2.06219744682312,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9581,
      "step": 29
    },
    {
      "epoch": 0.005364567034735572,
      "grad_norm": 1.7488588094711304,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.1204,
      "step": 30
    },
    {
      "epoch": 0.005543385935893424,
      "grad_norm": 2.7978739738464355,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.1661,
      "step": 31
    },
    {
      "epoch": 0.005722204837051276,
      "grad_norm": 1.6409696340560913,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9434,
      "step": 32
    },
    {
      "epoch": 0.005901023738209128,
      "grad_norm": 2.0203638076782227,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.0251,
      "step": 33
    },
    {
      "epoch": 0.0060798426393669815,
      "grad_norm": 3.090269088745117,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0402,
      "step": 34
    },
    {
      "epoch": 0.006258661540524834,
      "grad_norm": 2.0892794132232666,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.0091,
      "step": 35
    },
    {
      "epoch": 0.006437480441682686,
      "grad_norm": 1.66879403591156,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.92,
      "step": 36
    },
    {
      "epoch": 0.006616299342840538,
      "grad_norm": 2.061055898666382,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.9722,
      "step": 37
    },
    {
      "epoch": 0.00679511824399839,
      "grad_norm": 2.040457010269165,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9406,
      "step": 38
    },
    {
      "epoch": 0.006973937145156243,
      "grad_norm": 1.8687992095947266,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.7691,
      "step": 39
    },
    {
      "epoch": 0.0071527560463140955,
      "grad_norm": 1.7558640241622925,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.8971,
      "step": 40
    },
    {
      "epoch": 0.007331574947471948,
      "grad_norm": 1.9526532888412476,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8504,
      "step": 41
    },
    {
      "epoch": 0.0075103938486298,
      "grad_norm": 1.6909708976745605,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9497,
      "step": 42
    },
    {
      "epoch": 0.007689212749787653,
      "grad_norm": 1.443602204322815,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.8797,
      "step": 43
    },
    {
      "epoch": 0.007868031650945505,
      "grad_norm": 1.661456823348999,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9609,
      "step": 44
    },
    {
      "epoch": 0.008046850552103357,
      "grad_norm": 1.4534142017364502,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.8973,
      "step": 45
    },
    {
      "epoch": 0.00822566945326121,
      "grad_norm": 2.08626127243042,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9699,
      "step": 46
    },
    {
      "epoch": 0.008404488354419062,
      "grad_norm": 1.9656062126159668,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.035,
      "step": 47
    },
    {
      "epoch": 0.008583307255576914,
      "grad_norm": 1.7307604551315308,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8978,
      "step": 48
    },
    {
      "epoch": 0.008762126156734766,
      "grad_norm": 1.9000718593597412,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.9207,
      "step": 49
    },
    {
      "epoch": 0.00894094505789262,
      "grad_norm": 2.231043577194214,
      "learning_rate": 0.0,
      "loss": 1.0866,
      "step": 50
    },
    {
      "epoch": 0.00894094505789262,
      "eval_loss": 0.9053548574447632,
      "eval_runtime": 559.2119,
      "eval_samples_per_second": 67.37,
      "eval_steps_per_second": 8.423,
      "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}