{
  "best_metric": 0.933211624622345,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.09000900090009001,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009000900090009,
      "grad_norm": 5.405413627624512,
      "learning_rate": 1e-06,
      "loss": 2.6833,
      "step": 1
    },
    {
      "epoch": 0.0009000900090009,
      "eval_loss": 1.522924780845642,
      "eval_runtime": 106.2023,
      "eval_samples_per_second": 4.407,
      "eval_steps_per_second": 1.102,
      "step": 1
    },
    {
      "epoch": 0.0018001800180018,
      "grad_norm": 6.125265121459961,
      "learning_rate": 2e-06,
      "loss": 2.7378,
      "step": 2
    },
    {
      "epoch": 0.0027002700270027003,
      "grad_norm": 5.993320465087891,
      "learning_rate": 3e-06,
      "loss": 2.9158,
      "step": 3
    },
    {
      "epoch": 0.0036003600360036,
      "grad_norm": 6.266770362854004,
      "learning_rate": 4e-06,
      "loss": 2.7044,
      "step": 4
    },
    {
      "epoch": 0.004500450045004501,
      "grad_norm": 6.800923824310303,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 2.8806,
      "step": 5
    },
    {
      "epoch": 0.0054005400540054005,
      "grad_norm": 6.074341297149658,
      "learning_rate": 6e-06,
      "loss": 2.7618,
      "step": 6
    },
    {
      "epoch": 0.0063006300630063005,
      "grad_norm": 5.479096412658691,
      "learning_rate": 7e-06,
      "loss": 2.5574,
      "step": 7
    },
    {
      "epoch": 0.0072007200720072,
      "grad_norm": 3.8990819454193115,
      "learning_rate": 8e-06,
      "loss": 2.425,
      "step": 8
    },
    {
      "epoch": 0.008100810081008101,
      "grad_norm": 3.068220376968384,
      "learning_rate": 9e-06,
      "loss": 2.6252,
      "step": 9
    },
    {
      "epoch": 0.009000900090009001,
      "grad_norm": 3.1901001930236816,
      "learning_rate": 9.999999999999999e-06,
      "loss": 2.4851,
      "step": 10
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 3.36604380607605,
      "learning_rate": 1.1e-05,
      "loss": 2.4045,
      "step": 11
    },
    {
      "epoch": 0.010801080108010801,
      "grad_norm": 2.9655489921569824,
      "learning_rate": 1.2e-05,
      "loss": 2.5242,
      "step": 12
    },
    {
      "epoch": 0.011701170117011701,
      "grad_norm": 2.827815532684326,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.6771,
      "step": 13
    },
    {
      "epoch": 0.012601260126012601,
      "grad_norm": 2.3643851280212402,
      "learning_rate": 1.4e-05,
      "loss": 2.5468,
      "step": 14
    },
    {
      "epoch": 0.013501350135013501,
      "grad_norm": 2.146620273590088,
      "learning_rate": 1.5e-05,
      "loss": 2.2051,
      "step": 15
    },
    {
      "epoch": 0.0144014401440144,
      "grad_norm": 2.0729222297668457,
      "learning_rate": 1.6e-05,
      "loss": 2.5173,
      "step": 16
    },
    {
      "epoch": 0.0153015301530153,
      "grad_norm": 1.7945488691329956,
      "learning_rate": 1.7e-05,
      "loss": 2.0158,
      "step": 17
    },
    {
      "epoch": 0.016201620162016202,
      "grad_norm": 1.7809333801269531,
      "learning_rate": 1.8e-05,
      "loss": 2.3056,
      "step": 18
    },
    {
      "epoch": 0.017101710171017102,
      "grad_norm": 1.6572290658950806,
      "learning_rate": 1.9e-05,
      "loss": 2.4406,
      "step": 19
    },
    {
      "epoch": 0.018001800180018002,
      "grad_norm": 1.8199654817581177,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 2.3008,
      "step": 20
    },
    {
      "epoch": 0.018901890189018902,
      "grad_norm": 1.445672869682312,
      "learning_rate": 2.1e-05,
      "loss": 2.4013,
      "step": 21
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 1.3299720287322998,
      "learning_rate": 2.2e-05,
      "loss": 2.5153,
      "step": 22
    },
    {
      "epoch": 0.020702070207020702,
      "grad_norm": 1.3345452547073364,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.9483,
      "step": 23
    },
    {
      "epoch": 0.021602160216021602,
      "grad_norm": 1.339888334274292,
      "learning_rate": 2.4e-05,
      "loss": 2.2493,
      "step": 24
    },
    {
      "epoch": 0.022502250225022502,
      "grad_norm": 1.1863774061203003,
      "learning_rate": 2.5e-05,
      "loss": 2.0514,
      "step": 25
    },
    {
      "epoch": 0.023402340234023402,
      "grad_norm": 1.347615361213684,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.1209,
      "step": 26
    },
    {
      "epoch": 0.024302430243024302,
      "grad_norm": 1.3726738691329956,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 2.08,
      "step": 27
    },
    {
      "epoch": 0.025202520252025202,
      "grad_norm": 1.4481537342071533,
      "learning_rate": 2.8e-05,
      "loss": 2.1589,
      "step": 28
    },
    {
      "epoch": 0.026102610261026102,
      "grad_norm": 1.3069828748703003,
      "learning_rate": 2.9e-05,
      "loss": 2.0717,
      "step": 29
    },
    {
      "epoch": 0.027002700270027002,
      "grad_norm": 1.3439555168151855,
      "learning_rate": 3e-05,
      "loss": 2.3236,
      "step": 30
    },
    {
      "epoch": 0.0279027902790279,
      "grad_norm": 1.3758991956710815,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 2.3634,
      "step": 31
    },
    {
      "epoch": 0.0288028802880288,
      "grad_norm": 1.342500925064087,
      "learning_rate": 2.993961440992859e-05,
      "loss": 2.4211,
      "step": 32
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 1.2951146364212036,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 2.0738,
      "step": 33
    },
    {
      "epoch": 0.0306030603060306,
      "grad_norm": 1.210880994796753,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 2.3646,
      "step": 34
    },
    {
      "epoch": 0.0315031503150315,
      "grad_norm": 1.453122854232788,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 2.1522,
      "step": 35
    },
    {
      "epoch": 0.032403240324032405,
      "grad_norm": 1.259437084197998,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 2.5665,
      "step": 36
    },
    {
      "epoch": 0.0333033303330333,
      "grad_norm": 1.358750581741333,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 2.101,
      "step": 37
    },
    {
      "epoch": 0.034203420342034205,
      "grad_norm": 1.1546375751495361,
      "learning_rate": 2.904352305959606e-05,
      "loss": 2.0149,
      "step": 38
    },
    {
      "epoch": 0.0351035103510351,
      "grad_norm": 1.28835928440094,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 2.9375,
      "step": 39
    },
    {
      "epoch": 0.036003600360036005,
      "grad_norm": 1.1649773120880127,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 2.2544,
      "step": 40
    },
    {
      "epoch": 0.0369036903690369,
      "grad_norm": 1.1442354917526245,
      "learning_rate": 2.820893297785107e-05,
      "loss": 2.6504,
      "step": 41
    },
    {
      "epoch": 0.037803780378037805,
      "grad_norm": 1.11664617061615,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 2.8791,
      "step": 42
    },
    {
      "epoch": 0.0387038703870387,
      "grad_norm": 1.0840619802474976,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 2.6283,
      "step": 43
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 1.1481599807739258,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 2.7925,
      "step": 44
    },
    {
      "epoch": 0.0405040504050405,
      "grad_norm": 1.1215124130249023,
      "learning_rate": 2.672747223702045e-05,
      "loss": 3.1867,
      "step": 45
    },
    {
      "epoch": 0.041404140414041404,
      "grad_norm": 1.1518648862838745,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 2.9494,
      "step": 46
    },
    {
      "epoch": 0.0423042304230423,
      "grad_norm": 1.0652910470962524,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 3.5141,
      "step": 47
    },
    {
      "epoch": 0.043204320432043204,
      "grad_norm": 1.111494541168213,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 3.3104,
      "step": 48
    },
    {
      "epoch": 0.04410441044104411,
      "grad_norm": 1.044433832168579,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 2.6152,
      "step": 49
    },
    {
      "epoch": 0.045004500450045004,
      "grad_norm": 0.9503619074821472,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 2.9733,
      "step": 50
    },
    {
      "epoch": 0.045004500450045004,
      "eval_loss": 0.9813548922538757,
      "eval_runtime": 107.9014,
      "eval_samples_per_second": 4.337,
      "eval_steps_per_second": 1.084,
      "step": 50
    },
    {
      "epoch": 0.04590459045904591,
      "grad_norm": 5.705034255981445,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 1.3283,
      "step": 51
    },
    {
      "epoch": 0.046804680468046804,
      "grad_norm": 3.1250901222229004,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 1.1372,
      "step": 52
    },
    {
      "epoch": 0.04770477047704771,
      "grad_norm": 3.5653185844421387,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 1.1422,
      "step": 53
    },
    {
      "epoch": 0.048604860486048604,
      "grad_norm": 2.5940499305725098,
      "learning_rate": 2.210802993709498e-05,
      "loss": 1.0782,
      "step": 54
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 1.700508713722229,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 0.8352,
      "step": 55
    },
    {
      "epoch": 0.050405040504050404,
      "grad_norm": 1.5756418704986572,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 1.3823,
      "step": 56
    },
    {
      "epoch": 0.05130513051305131,
      "grad_norm": 1.4209038019180298,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 1.1883,
      "step": 57
    },
    {
      "epoch": 0.052205220522052204,
      "grad_norm": 1.3939372301101685,
      "learning_rate": 1.963525491562421e-05,
      "loss": 1.0329,
      "step": 58
    },
    {
      "epoch": 0.05310531053105311,
      "grad_norm": 1.2505179643630981,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 1.2086,
      "step": 59
    },
    {
      "epoch": 0.054005400540054004,
      "grad_norm": 1.3785752058029175,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 1.0227,
      "step": 60
    },
    {
      "epoch": 0.05490549054905491,
      "grad_norm": 1.367503046989441,
      "learning_rate": 1.767835342197955e-05,
      "loss": 1.609,
      "step": 61
    },
    {
      "epoch": 0.0558055805580558,
      "grad_norm": 1.2117955684661865,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 1.3177,
      "step": 62
    },
    {
      "epoch": 0.05670567056705671,
      "grad_norm": 1.0135844945907593,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 1.4245,
      "step": 63
    },
    {
      "epoch": 0.0576057605760576,
      "grad_norm": 1.1287009716033936,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 1.5013,
      "step": 64
    },
    {
      "epoch": 0.05850585058505851,
      "grad_norm": 1.2982141971588135,
      "learning_rate": 1.5e-05,
      "loss": 1.5079,
      "step": 65
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 1.1244807243347168,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 2.046,
      "step": 66
    },
    {
      "epoch": 0.06030603060306031,
      "grad_norm": 0.9998478293418884,
      "learning_rate": 1.36554103664485e-05,
      "loss": 1.3912,
      "step": 67
    },
    {
      "epoch": 0.0612061206120612,
      "grad_norm": 1.026103138923645,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 1.6617,
      "step": 68
    },
    {
      "epoch": 0.062106210621062106,
      "grad_norm": 1.0572633743286133,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 1.7724,
      "step": 69
    },
    {
      "epoch": 0.063006300630063,
      "grad_norm": 1.105764389038086,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 1.4844,
      "step": 70
    },
    {
      "epoch": 0.0639063906390639,
      "grad_norm": 0.9881569147109985,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 1.5753,
      "step": 71
    },
    {
      "epoch": 0.06480648064806481,
      "grad_norm": 0.9760916829109192,
      "learning_rate": 1.036474508437579e-05,
      "loss": 1.7407,
      "step": 72
    },
    {
      "epoch": 0.06570657065706571,
      "grad_norm": 0.998174250125885,
      "learning_rate": 9.729377638779859e-06,
      "loss": 1.734,
      "step": 73
    },
    {
      "epoch": 0.0666066606660666,
      "grad_norm": 0.9511818289756775,
      "learning_rate": 9.104624525191147e-06,
      "loss": 1.6426,
      "step": 74
    },
    {
      "epoch": 0.0675067506750675,
      "grad_norm": 0.995963454246521,
      "learning_rate": 8.491743913236629e-06,
      "loss": 1.8299,
      "step": 75
    },
    {
      "epoch": 0.06840684068406841,
      "grad_norm": 0.9901272058486938,
      "learning_rate": 7.89197006290502e-06,
      "loss": 1.8434,
      "step": 76
    },
    {
      "epoch": 0.06930693069306931,
      "grad_norm": 1.0815800428390503,
      "learning_rate": 7.30651083891141e-06,
      "loss": 2.1484,
      "step": 77
    },
    {
      "epoch": 0.0702070207020702,
      "grad_norm": 1.1151647567749023,
      "learning_rate": 6.736545278218464e-06,
      "loss": 2.0096,
      "step": 78
    },
    {
      "epoch": 0.0711071107110711,
      "grad_norm": 0.9471780061721802,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 1.8158,
      "step": 79
    },
    {
      "epoch": 0.07200720072007201,
      "grad_norm": 0.8763648271560669,
      "learning_rate": 5.647652972118998e-06,
      "loss": 1.5679,
      "step": 80
    },
    {
      "epoch": 0.07290729072907291,
      "grad_norm": 1.0473607778549194,
      "learning_rate": 5.130919110904311e-06,
      "loss": 1.9162,
      "step": 81
    },
    {
      "epoch": 0.0738073807380738,
      "grad_norm": 0.9801396727561951,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 1.95,
      "step": 82
    },
    {
      "epoch": 0.0747074707470747,
      "grad_norm": 1.2046276330947876,
      "learning_rate": 4.158077042589129e-06,
      "loss": 2.0275,
      "step": 83
    },
    {
      "epoch": 0.07560756075607561,
      "grad_norm": 1.0073298215866089,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 1.8993,
      "step": 84
    },
    {
      "epoch": 0.07650765076507651,
      "grad_norm": 0.9107989072799683,
      "learning_rate": 3.272527762979553e-06,
      "loss": 1.8347,
      "step": 85
    },
    {
      "epoch": 0.0774077407740774,
      "grad_norm": 1.0077648162841797,
      "learning_rate": 2.86474508437579e-06,
      "loss": 2.1918,
      "step": 86
    },
    {
      "epoch": 0.0783078307830783,
      "grad_norm": 0.9970296621322632,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 2.0114,
      "step": 87
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.9443178176879883,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 1.8943,
      "step": 88
    },
    {
      "epoch": 0.08010801080108011,
      "grad_norm": 1.1723785400390625,
      "learning_rate": 1.79106702214893e-06,
      "loss": 2.5215,
      "step": 89
    },
    {
      "epoch": 0.081008100810081,
      "grad_norm": 1.1029690504074097,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 2.9212,
      "step": 90
    },
    {
      "epoch": 0.0819081908190819,
      "grad_norm": 0.8593942523002625,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 1.9948,
      "step": 91
    },
    {
      "epoch": 0.08280828082808281,
      "grad_norm": 1.2536730766296387,
      "learning_rate": 9.56476940403942e-07,
      "loss": 2.9596,
      "step": 92
    },
    {
      "epoch": 0.08370837083708371,
      "grad_norm": 1.1047546863555908,
      "learning_rate": 7.341522555726971e-07,
      "loss": 3.2272,
      "step": 93
    },
    {
      "epoch": 0.0846084608460846,
      "grad_norm": 1.0855673551559448,
      "learning_rate": 5.405570895622014e-07,
      "loss": 3.1168,
      "step": 94
    },
    {
      "epoch": 0.0855085508550855,
      "grad_norm": 1.0301321744918823,
      "learning_rate": 3.760813172726457e-07,
      "loss": 2.7688,
      "step": 95
    },
    {
      "epoch": 0.08640864086408641,
      "grad_norm": 0.9736518859863281,
      "learning_rate": 2.41056171020555e-07,
      "loss": 2.6513,
      "step": 96
    },
    {
      "epoch": 0.08730873087308731,
      "grad_norm": 1.150550365447998,
      "learning_rate": 1.357535734809795e-07,
      "loss": 3.3847,
      "step": 97
    },
    {
      "epoch": 0.08820882088208822,
      "grad_norm": 1.075913906097412,
      "learning_rate": 6.038559007141397e-08,
      "loss": 2.7569,
      "step": 98
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 1.1728016138076782,
      "learning_rate": 1.510400188028116e-08,
      "loss": 2.8988,
      "step": 99
    },
    {
      "epoch": 0.09000900090009001,
      "grad_norm": 1.0802109241485596,
      "learning_rate": 0.0,
      "loss": 2.9239,
      "step": 100
    },
    {
      "epoch": 0.09000900090009001,
      "eval_loss": 0.933211624622345,
      "eval_runtime": 107.8918,
      "eval_samples_per_second": 4.338,
      "eval_steps_per_second": 1.084,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.6422040428544e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}