{
  "best_metric": 1.7665985822677612,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 81,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 3.0762956142425537,
      "learning_rate": 7e-06,
      "loss": 2.8658,
      "step": 1
    },
    {
      "epoch": 0.037037037037037035,
      "eval_loss": 3.5639960765838623,
      "eval_runtime": 3.2908,
      "eval_samples_per_second": 13.978,
      "eval_steps_per_second": 3.647,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 3.893179416656494,
      "learning_rate": 1.4e-05,
      "loss": 3.6387,
      "step": 2
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.5411174297332764,
      "learning_rate": 2.1e-05,
      "loss": 3.4665,
      "step": 3
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 3.4620625972747803,
      "learning_rate": 2.8e-05,
      "loss": 3.4607,
      "step": 4
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 2.918036460876465,
      "learning_rate": 3.5e-05,
      "loss": 3.4412,
      "step": 5
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.1347150802612305,
      "learning_rate": 4.2e-05,
      "loss": 3.4438,
      "step": 6
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 2.0844814777374268,
      "learning_rate": 4.899999999999999e-05,
      "loss": 2.9182,
      "step": 7
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.5144269466400146,
      "learning_rate": 5.6e-05,
      "loss": 2.7481,
      "step": 8
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.326944351196289,
      "learning_rate": 6.3e-05,
      "loss": 2.8674,
      "step": 9
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.9930708408355713,
      "learning_rate": 7e-05,
      "loss": 2.5017,
      "step": 10
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 3.013411045074463,
      "learning_rate": 6.996574292819907e-05,
      "loss": 2.485,
      "step": 11
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.9861669540405273,
      "learning_rate": 6.986303877262306e-05,
      "loss": 2.0643,
      "step": 12
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 1.5490922927856445,
      "learning_rate": 6.969208858147951e-05,
      "loss": 1.8952,
      "step": 13
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.5672123432159424,
      "learning_rate": 6.945322699779538e-05,
      "loss": 1.8413,
      "step": 14
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.6187469959259033,
      "learning_rate": 6.914692160433773e-05,
      "loss": 1.8835,
      "step": 15
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.6432483196258545,
      "learning_rate": 6.877377200829835e-05,
      "loss": 1.981,
      "step": 16
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 1.4468789100646973,
      "learning_rate": 6.83345086675346e-05,
      "loss": 1.9871,
      "step": 17
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4680477380752563,
      "learning_rate": 6.782999146066386e-05,
      "loss": 1.9639,
      "step": 18
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 1.1646554470062256,
      "learning_rate": 6.726120800381073e-05,
      "loss": 1.825,
      "step": 19
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.0831339359283447,
      "learning_rate": 6.662927171730213e-05,
      "loss": 1.645,
      "step": 20
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.171111822128296,
      "learning_rate": 6.593541964609463e-05,
      "loss": 1.6865,
      "step": 21
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.1838645935058594,
      "learning_rate": 6.518101003820097e-05,
      "loss": 1.7186,
      "step": 22
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 1.165795087814331,
      "learning_rate": 6.43675196858557e-05,
      "loss": 1.9583,
      "step": 23
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.2042009830474854,
      "learning_rate": 6.34965410346251e-05,
      "loss": 2.0201,
      "step": 24
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.0208855867385864,
      "learning_rate": 6.256977906612013e-05,
      "loss": 1.6992,
      "step": 25
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.0845801830291748,
      "learning_rate": 6.158904796041496e-05,
      "loss": 1.8454,
      "step": 26
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2094794511795044,
      "learning_rate": 6.05562675447042e-05,
      "loss": 1.5763,
      "step": 27
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.9708940386772156,
      "learning_rate": 5.947345953515099e-05,
      "loss": 1.343,
      "step": 28
    },
    {
      "epoch": 1.074074074074074,
      "grad_norm": 1.04697585105896,
      "learning_rate": 5.834274357928277e-05,
      "loss": 1.4841,
      "step": 29
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 1.1268396377563477,
      "learning_rate": 5.7166333106681644e-05,
      "loss": 1.7666,
      "step": 30
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 1.0179731845855713,
      "learning_rate": 5.594653099609201e-05,
      "loss": 1.6149,
      "step": 31
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 1.0401766300201416,
      "learning_rate": 5.468572506742732e-05,
      "loss": 1.4658,
      "step": 32
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 1.0923527479171753,
      "learning_rate": 5.338638340750045e-05,
      "loss": 1.5151,
      "step": 33
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 1.327430009841919,
      "learning_rate": 5.205104953862787e-05,
      "loss": 1.4007,
      "step": 34
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 1.1446799039840698,
      "learning_rate": 5.068233743956524e-05,
      "loss": 1.6688,
      "step": 35
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.2676280736923218,
      "learning_rate": 4.9282926428521266e-05,
      "loss": 1.8306,
      "step": 36
    },
    {
      "epoch": 1.3703703703703702,
      "grad_norm": 1.1416800022125244,
      "learning_rate": 4.785555591826649e-05,
      "loss": 1.4489,
      "step": 37
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": 1.2351667881011963,
      "learning_rate": 4.640302005360411e-05,
      "loss": 1.6123,
      "step": 38
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 1.3364763259887695,
      "learning_rate": 4.492816224170038e-05,
      "loss": 1.7015,
      "step": 39
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 1.1775413751602173,
      "learning_rate": 4.34338695859815e-05,
      "loss": 1.3681,
      "step": 40
    },
    {
      "epoch": 1.5185185185185186,
      "grad_norm": 1.271789312362671,
      "learning_rate": 4.1923067234493104e-05,
      "loss": 1.4819,
      "step": 41
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 1.2430049180984497,
      "learning_rate": 4.0398712653785575e-05,
      "loss": 1.4588,
      "step": 42
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 1.2405871152877808,
      "learning_rate": 3.8863789839534444e-05,
      "loss": 1.4588,
      "step": 43
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 1.6753511428833008,
      "learning_rate": 3.7321303475228634e-05,
      "loss": 1.4858,
      "step": 44
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.3085812330245972,
      "learning_rate": 3.577427305036154e-05,
      "loss": 1.4578,
      "step": 45
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": 1.2051222324371338,
      "learning_rate": 3.4225726949638464e-05,
      "loss": 1.3037,
      "step": 46
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 1.1844594478607178,
      "learning_rate": 3.2678696524771367e-05,
      "loss": 1.3121,
      "step": 47
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.3920973539352417,
      "learning_rate": 3.113621016046556e-05,
      "loss": 1.5805,
      "step": 48
    },
    {
      "epoch": 1.8148148148148149,
      "grad_norm": 1.3390107154846191,
      "learning_rate": 2.960128734621441e-05,
      "loss": 1.2356,
      "step": 49
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 1.55970299243927,
      "learning_rate": 2.8076932765506893e-05,
      "loss": 1.445,
      "step": 50
    },
    {
      "epoch": 1.8518518518518519,
      "eval_loss": 1.7665985822677612,
      "eval_runtime": 3.3723,
      "eval_samples_per_second": 13.64,
      "eval_steps_per_second": 3.558,
      "step": 50
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 1.49898099899292,
      "learning_rate": 2.6566130414018495e-05,
      "loss": 1.427,
      "step": 51
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 1.2517292499542236,
      "learning_rate": 2.5071837758299613e-05,
      "loss": 1.124,
      "step": 52
    },
    {
      "epoch": 1.9629629629629628,
      "grad_norm": 1.6222271919250488,
      "learning_rate": 2.359697994639589e-05,
      "loss": 1.318,
      "step": 53
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.829454779624939,
      "learning_rate": 2.2144444081733517e-05,
      "loss": 1.7384,
      "step": 54
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 1.2274819612503052,
      "learning_rate": 2.071707357147872e-05,
      "loss": 0.9252,
      "step": 55
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 1.5283606052398682,
      "learning_rate": 1.931766256043475e-05,
      "loss": 1.0436,
      "step": 56
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 1.5208336114883423,
      "learning_rate": 1.7948950461372128e-05,
      "loss": 1.2807,
      "step": 57
    },
    {
      "epoch": 2.148148148148148,
      "grad_norm": 1.5189377069473267,
      "learning_rate": 1.6613616592499547e-05,
      "loss": 0.9818,
      "step": 58
    },
    {
      "epoch": 2.185185185185185,
      "grad_norm": 1.881172776222229,
      "learning_rate": 1.5314274932572676e-05,
      "loss": 1.1691,
      "step": 59
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 1.8424291610717773,
      "learning_rate": 1.4053469003907992e-05,
      "loss": 1.246,
      "step": 60
    },
    {
      "epoch": 2.259259259259259,
      "grad_norm": 1.9025232791900635,
      "learning_rate": 1.2833666893318349e-05,
      "loss": 1.0384,
      "step": 61
    },
    {
      "epoch": 2.2962962962962963,
      "grad_norm": 1.7848095893859863,
      "learning_rate": 1.165725642071722e-05,
      "loss": 1.0459,
      "step": 62
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 1.7614284753799438,
      "learning_rate": 1.0526540464849008e-05,
      "loss": 1.1616,
      "step": 63
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 2.083524465560913,
      "learning_rate": 9.443732455295803e-06,
      "loss": 1.2212,
      "step": 64
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 2.120060682296753,
      "learning_rate": 8.410952039585034e-06,
      "loss": 1.2193,
      "step": 65
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 1.8416856527328491,
      "learning_rate": 7.430220933879868e-06,
      "loss": 1.0275,
      "step": 66
    },
    {
      "epoch": 2.4814814814814814,
      "grad_norm": 1.6970349550247192,
      "learning_rate": 6.503458965374907e-06,
      "loss": 0.9866,
      "step": 67
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 1.7311978340148926,
      "learning_rate": 5.632480314144302e-06,
      "loss": 1.1222,
      "step": 68
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 1.8647996187210083,
      "learning_rate": 4.818989961799024e-06,
      "loss": 1.1971,
      "step": 69
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 1.8562637567520142,
      "learning_rate": 4.064580353905361e-06,
      "loss": 1.0966,
      "step": 70
    },
    {
      "epoch": 2.6296296296296298,
      "grad_norm": 2.1647939682006836,
      "learning_rate": 3.3707282826978684e-06,
      "loss": 1.2084,
      "step": 71
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 2.267409563064575,
      "learning_rate": 2.7387919961892603e-06,
      "loss": 1.2536,
      "step": 72
    },
    {
      "epoch": 2.7037037037037037,
      "grad_norm": 1.875108003616333,
      "learning_rate": 2.170008539336139e-06,
      "loss": 1.0385,
      "step": 73
    },
    {
      "epoch": 2.7407407407407405,
      "grad_norm": 1.690350890159607,
      "learning_rate": 1.665491332465404e-06,
      "loss": 0.9002,
      "step": 74
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 1.8636929988861084,
      "learning_rate": 1.2262279917016548e-06,
      "loss": 1.1853,
      "step": 75
    },
    {
      "epoch": 2.814814814814815,
      "grad_norm": 1.7024513483047485,
      "learning_rate": 8.530783956622628e-07,
      "loss": 1.1387,
      "step": 76
    },
    {
      "epoch": 2.851851851851852,
      "grad_norm": 1.7570838928222656,
      "learning_rate": 5.467730022046046e-07,
      "loss": 0.9747,
      "step": 77
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 1.8747435808181763,
      "learning_rate": 3.0791141852049006e-07,
      "loss": 1.1896,
      "step": 78
    },
    {
      "epoch": 2.925925925925926,
      "grad_norm": 1.7294906377792358,
      "learning_rate": 1.369612273769316e-07,
      "loss": 0.9973,
      "step": 79
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 1.958431363105774,
      "learning_rate": 3.4257071800923855e-08,
      "loss": 1.2993,
      "step": 80
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.917493462562561,
      "learning_rate": 0.0,
      "loss": 1.2325,
      "step": 81
    }
  ],
  "logging_steps": 1,
  "max_steps": 81,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": 1.2072723618988032e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}