{
  "best_metric": 2.4635510444641113,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0064524454768357204,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001290489095367144,
      "grad_norm": 1.8824232816696167,
      "learning_rate": 1e-05,
      "loss": 8.9881,
      "step": 1
    },
    {
      "epoch": 0.0001290489095367144,
      "eval_loss": 2.636259078979492,
      "eval_runtime": 1413.0548,
      "eval_samples_per_second": 9.236,
      "eval_steps_per_second": 2.309,
      "step": 1
    },
    {
      "epoch": 0.0002580978190734288,
      "grad_norm": 2.8287086486816406,
      "learning_rate": 2e-05,
      "loss": 9.2454,
      "step": 2
    },
    {
      "epoch": 0.00038714672861014324,
      "grad_norm": 2.5714402198791504,
      "learning_rate": 3e-05,
      "loss": 9.0849,
      "step": 3
    },
    {
      "epoch": 0.0005161956381468576,
      "grad_norm": 2.7806339263916016,
      "learning_rate": 4e-05,
      "loss": 9.4978,
      "step": 4
    },
    {
      "epoch": 0.0006452445476835721,
      "grad_norm": 2.4504265785217285,
      "learning_rate": 5e-05,
      "loss": 9.7492,
      "step": 5
    },
    {
      "epoch": 0.0007742934572202865,
      "grad_norm": 2.520981550216675,
      "learning_rate": 6e-05,
      "loss": 8.8263,
      "step": 6
    },
    {
      "epoch": 0.0009033423667570009,
      "grad_norm": 2.629502534866333,
      "learning_rate": 7e-05,
      "loss": 9.3517,
      "step": 7
    },
    {
      "epoch": 0.0010323912762937152,
      "grad_norm": 2.9892454147338867,
      "learning_rate": 8e-05,
      "loss": 9.6262,
      "step": 8
    },
    {
      "epoch": 0.0011614401858304297,
      "grad_norm": 2.9270966053009033,
      "learning_rate": 9e-05,
      "loss": 9.0262,
      "step": 9
    },
    {
      "epoch": 0.0012904890953671442,
      "grad_norm": 3.554283618927002,
      "learning_rate": 0.0001,
      "loss": 9.1454,
      "step": 10
    },
    {
      "epoch": 0.0014195380049038585,
      "grad_norm": 2.9322144985198975,
      "learning_rate": 9.999316524962345e-05,
      "loss": 9.189,
      "step": 11
    },
    {
      "epoch": 0.001548586914440573,
      "grad_norm": 2.8467869758605957,
      "learning_rate": 9.997266286704631e-05,
      "loss": 9.13,
      "step": 12
    },
    {
      "epoch": 0.0016776358239772875,
      "grad_norm": 2.985856294631958,
      "learning_rate": 9.993849845741524e-05,
      "loss": 9.3862,
      "step": 13
    },
    {
      "epoch": 0.0018066847335140017,
      "grad_norm": 2.986755132675171,
      "learning_rate": 9.989068136093873e-05,
      "loss": 9.3611,
      "step": 14
    },
    {
      "epoch": 0.0019357336430507162,
      "grad_norm": 2.891209840774536,
      "learning_rate": 9.98292246503335e-05,
      "loss": 8.9278,
      "step": 15
    },
    {
      "epoch": 0.0020647825525874305,
      "grad_norm": 3.200324535369873,
      "learning_rate": 9.975414512725057e-05,
      "loss": 9.3208,
      "step": 16
    },
    {
      "epoch": 0.002193831462124145,
      "grad_norm": 3.082493782043457,
      "learning_rate": 9.966546331768191e-05,
      "loss": 9.3286,
      "step": 17
    },
    {
      "epoch": 0.0023228803716608595,
      "grad_norm": 2.9336154460906982,
      "learning_rate": 9.956320346634876e-05,
      "loss": 9.1107,
      "step": 18
    },
    {
      "epoch": 0.0024519292811975737,
      "grad_norm": 2.870712995529175,
      "learning_rate": 9.944739353007344e-05,
      "loss": 9.2296,
      "step": 19
    },
    {
      "epoch": 0.0025809781907342884,
      "grad_norm": 3.229865789413452,
      "learning_rate": 9.931806517013612e-05,
      "loss": 9.0709,
      "step": 20
    },
    {
      "epoch": 0.0027100271002710027,
      "grad_norm": 2.955902576446533,
      "learning_rate": 9.917525374361912e-05,
      "loss": 9.1987,
      "step": 21
    },
    {
      "epoch": 0.002839076009807717,
      "grad_norm": 3.0389182567596436,
      "learning_rate": 9.901899829374047e-05,
      "loss": 8.9725,
      "step": 22
    },
    {
      "epoch": 0.0029681249193444317,
      "grad_norm": 4.6783766746521,
      "learning_rate": 9.884934153917997e-05,
      "loss": 9.3348,
      "step": 23
    },
    {
      "epoch": 0.003097173828881146,
      "grad_norm": 3.08036208152771,
      "learning_rate": 9.86663298624003e-05,
      "loss": 9.3108,
      "step": 24
    },
    {
      "epoch": 0.0032262227384178602,
      "grad_norm": 3.42242693901062,
      "learning_rate": 9.847001329696653e-05,
      "loss": 9.0909,
      "step": 25
    },
    {
      "epoch": 0.003355271647954575,
      "grad_norm": 3.5331575870513916,
      "learning_rate": 9.826044551386744e-05,
      "loss": 9.3532,
      "step": 26
    },
    {
      "epoch": 0.003484320557491289,
      "grad_norm": 7.4575581550598145,
      "learning_rate": 9.803768380684242e-05,
      "loss": 9.2112,
      "step": 27
    },
    {
      "epoch": 0.0036133694670280035,
      "grad_norm": 3.2820820808410645,
      "learning_rate": 9.780178907671789e-05,
      "loss": 9.4624,
      "step": 28
    },
    {
      "epoch": 0.003742418376564718,
      "grad_norm": 3.459367275238037,
      "learning_rate": 9.755282581475769e-05,
      "loss": 9.2565,
      "step": 29
    },
    {
      "epoch": 0.0038714672861014324,
      "grad_norm": 3.8929476737976074,
      "learning_rate": 9.729086208503174e-05,
      "loss": 9.669,
      "step": 30
    },
    {
      "epoch": 0.004000516195638147,
      "grad_norm": 3.531162738800049,
      "learning_rate": 9.701596950580806e-05,
      "loss": 9.2843,
      "step": 31
    },
    {
      "epoch": 0.004129565105174861,
      "grad_norm": 3.5504400730133057,
      "learning_rate": 9.672822322997305e-05,
      "loss": 9.5244,
      "step": 32
    },
    {
      "epoch": 0.004258614014711576,
      "grad_norm": 3.8479762077331543,
      "learning_rate": 9.642770192448536e-05,
      "loss": 9.287,
      "step": 33
    },
    {
      "epoch": 0.00438766292424829,
      "grad_norm": 3.660515308380127,
      "learning_rate": 9.611448774886924e-05,
      "loss": 9.1514,
      "step": 34
    },
    {
      "epoch": 0.004516711833785004,
      "grad_norm": 3.883052110671997,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.7452,
      "step": 35
    },
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 3.631749153137207,
      "learning_rate": 9.545032675245813e-05,
      "loss": 8.7108,
      "step": 36
    },
    {
      "epoch": 0.004774809652858434,
      "grad_norm": 4.567019939422607,
      "learning_rate": 9.509956150664796e-05,
      "loss": 9.0823,
      "step": 37
    },
    {
      "epoch": 0.0049038585623951475,
      "grad_norm": 3.8664674758911133,
      "learning_rate": 9.473646649103818e-05,
      "loss": 9.0209,
      "step": 38
    },
    {
      "epoch": 0.005032907471931862,
      "grad_norm": 3.753689765930176,
      "learning_rate": 9.43611409721806e-05,
      "loss": 9.1999,
      "step": 39
    },
    {
      "epoch": 0.005161956381468577,
      "grad_norm": 4.090752124786377,
      "learning_rate": 9.397368756032445e-05,
      "loss": 9.5598,
      "step": 40
    },
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 5.097810745239258,
      "learning_rate": 9.357421218136386e-05,
      "loss": 9.3718,
      "step": 41
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 4.1418232917785645,
      "learning_rate": 9.316282404787871e-05,
      "loss": 9.2399,
      "step": 42
    },
    {
      "epoch": 0.00554910311007872,
      "grad_norm": 4.791266918182373,
      "learning_rate": 9.273963562927695e-05,
      "loss": 9.6049,
      "step": 43
    },
    {
      "epoch": 0.005678152019615434,
      "grad_norm": 5.000885486602783,
      "learning_rate": 9.230476262104677e-05,
      "loss": 9.2656,
      "step": 44
    },
    {
      "epoch": 0.005807200929152149,
      "grad_norm": 4.691623210906982,
      "learning_rate": 9.185832391312644e-05,
      "loss": 9.0675,
      "step": 45
    },
    {
      "epoch": 0.005936249838688863,
      "grad_norm": 8.883625030517578,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.0689,
      "step": 46
    },
    {
      "epoch": 0.006065298748225577,
      "grad_norm": 7.350927829742432,
      "learning_rate": 9.093124073433463e-05,
      "loss": 9.5976,
      "step": 47
    },
    {
      "epoch": 0.006194347657762292,
      "grad_norm": 5.843919277191162,
      "learning_rate": 9.045084971874738e-05,
      "loss": 9.7173,
      "step": 48
    },
    {
      "epoch": 0.006323396567299007,
      "grad_norm": 5.78486967086792,
      "learning_rate": 8.995939984474624e-05,
      "loss": 9.5343,
      "step": 49
    },
    {
      "epoch": 0.0064524454768357204,
      "grad_norm": 7.93582820892334,
      "learning_rate": 8.945702546981969e-05,
      "loss": 9.6716,
      "step": 50
    },
    {
      "epoch": 0.0064524454768357204,
      "eval_loss": 2.4635510444641113,
      "eval_runtime": 1423.6372,
      "eval_samples_per_second": 9.167,
      "eval_steps_per_second": 2.292,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1662573078315008e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}