{
  "best_metric": 6.879824638366699,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.03702104029123218,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004936138705497624,
      "grad_norm": 0.1294831931591034,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.9388,
      "step": 1
    },
    {
      "epoch": 0.0004936138705497624,
      "eval_loss": 6.934586048126221,
      "eval_runtime": 0.0792,
      "eval_samples_per_second": 631.199,
      "eval_steps_per_second": 164.112,
      "step": 1
    },
    {
      "epoch": 0.0009872277410995249,
      "grad_norm": 0.1353587508201599,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.9381,
      "step": 2
    },
    {
      "epoch": 0.0014808416116492873,
      "grad_norm": 0.14798350632190704,
      "learning_rate": 0.0001,
      "loss": 6.9389,
      "step": 3
    },
    {
      "epoch": 0.0019744554821990497,
      "grad_norm": 0.14640209078788757,
      "learning_rate": 9.997376600647783e-05,
      "loss": 6.9363,
      "step": 4
    },
    {
      "epoch": 0.002468069352748812,
      "grad_norm": 0.14401522278785706,
      "learning_rate": 9.989509461357426e-05,
      "loss": 6.938,
      "step": 5
    },
    {
      "epoch": 0.0029616832232985746,
      "grad_norm": 0.14567096531391144,
      "learning_rate": 9.976407754861426e-05,
      "loss": 6.9357,
      "step": 6
    },
    {
      "epoch": 0.003455297093848337,
      "grad_norm": 0.1365479975938797,
      "learning_rate": 9.958086757163489e-05,
      "loss": 6.9338,
      "step": 7
    },
    {
      "epoch": 0.0039489109643980995,
      "grad_norm": 0.13593412935733795,
      "learning_rate": 9.934567829727386e-05,
      "loss": 6.9351,
      "step": 8
    },
    {
      "epoch": 0.004442524834947862,
      "grad_norm": 0.13452042639255524,
      "learning_rate": 9.905878394570453e-05,
      "loss": 6.933,
      "step": 9
    },
    {
      "epoch": 0.004936138705497624,
      "grad_norm": 0.1374937891960144,
      "learning_rate": 9.872051902290737e-05,
      "loss": 6.9336,
      "step": 10
    },
    {
      "epoch": 0.005429752576047387,
      "grad_norm": 0.13684473931789398,
      "learning_rate": 9.833127793065098e-05,
      "loss": 6.9338,
      "step": 11
    },
    {
      "epoch": 0.005923366446597149,
      "grad_norm": 0.14771386981010437,
      "learning_rate": 9.789151450663723e-05,
      "loss": 6.9308,
      "step": 12
    },
    {
      "epoch": 0.006416980317146912,
      "grad_norm": 0.1428656429052353,
      "learning_rate": 9.740174149534693e-05,
      "loss": 6.931,
      "step": 13
    },
    {
      "epoch": 0.006910594187696674,
      "grad_norm": 0.14314448833465576,
      "learning_rate": 9.686252995020249e-05,
      "loss": 6.9295,
      "step": 14
    },
    {
      "epoch": 0.007404208058246437,
      "grad_norm": 0.1460285633802414,
      "learning_rate": 9.627450856774539e-05,
      "loss": 6.9304,
      "step": 15
    },
    {
      "epoch": 0.007897821928796199,
      "grad_norm": 0.14801424741744995,
      "learning_rate": 9.563836295460398e-05,
      "loss": 6.9296,
      "step": 16
    },
    {
      "epoch": 0.008391435799345962,
      "grad_norm": 0.15197831392288208,
      "learning_rate": 9.495483482810688e-05,
      "loss": 6.9251,
      "step": 17
    },
    {
      "epoch": 0.008885049669895725,
      "grad_norm": 0.14863520860671997,
      "learning_rate": 9.422472115147382e-05,
      "loss": 6.9282,
      "step": 18
    },
    {
      "epoch": 0.009378663540445486,
      "grad_norm": 0.13960832357406616,
      "learning_rate": 9.3448873204592e-05,
      "loss": 6.9281,
      "step": 19
    },
    {
      "epoch": 0.009872277410995249,
      "grad_norm": 0.1437833458185196,
      "learning_rate": 9.2628195591462e-05,
      "loss": 6.9249,
      "step": 20
    },
    {
      "epoch": 0.010365891281545012,
      "grad_norm": 0.1537475436925888,
      "learning_rate": 9.176364518546989e-05,
      "loss": 6.9223,
      "step": 21
    },
    {
      "epoch": 0.010859505152094774,
      "grad_norm": 0.1554909348487854,
      "learning_rate": 9.08562300137157e-05,
      "loss": 6.9201,
      "step": 22
    },
    {
      "epoch": 0.011353119022644536,
      "grad_norm": 0.15719279646873474,
      "learning_rate": 8.990700808169889e-05,
      "loss": 6.9213,
      "step": 23
    },
    {
      "epoch": 0.011846732893194298,
      "grad_norm": 0.15599289536476135,
      "learning_rate": 8.891708613973126e-05,
      "loss": 6.9211,
      "step": 24
    },
    {
      "epoch": 0.012340346763744061,
      "grad_norm": 0.16797839105129242,
      "learning_rate": 8.788761839251559e-05,
      "loss": 6.9162,
      "step": 25
    },
    {
      "epoch": 0.012340346763744061,
      "eval_loss": 6.91409969329834,
      "eval_runtime": 0.0843,
      "eval_samples_per_second": 593.267,
      "eval_steps_per_second": 154.249,
      "step": 25
    },
    {
      "epoch": 0.012833960634293824,
      "grad_norm": 0.15400898456573486,
      "learning_rate": 8.681980515339464e-05,
      "loss": 6.92,
      "step": 26
    },
    {
      "epoch": 0.013327574504843585,
      "grad_norm": 0.16461063921451569,
      "learning_rate": 8.571489144483944e-05,
      "loss": 6.9187,
      "step": 27
    },
    {
      "epoch": 0.013821188375393348,
      "grad_norm": 0.15997587144374847,
      "learning_rate": 8.457416554680877e-05,
      "loss": 6.9185,
      "step": 28
    },
    {
      "epoch": 0.014314802245943111,
      "grad_norm": 0.17501673102378845,
      "learning_rate": 8.339895749467238e-05,
      "loss": 6.915,
      "step": 29
    },
    {
      "epoch": 0.014808416116492874,
      "grad_norm": 0.16417518258094788,
      "learning_rate": 8.219063752844926e-05,
      "loss": 6.9176,
      "step": 30
    },
    {
      "epoch": 0.015302029987042635,
      "grad_norm": 0.17748786509037018,
      "learning_rate": 8.095061449516903e-05,
      "loss": 6.9119,
      "step": 31
    },
    {
      "epoch": 0.015795643857592398,
      "grad_norm": 0.17625170946121216,
      "learning_rate": 7.968033420621935e-05,
      "loss": 6.9124,
      "step": 32
    },
    {
      "epoch": 0.01628925772814216,
      "grad_norm": 0.16539260745048523,
      "learning_rate": 7.838127775159452e-05,
      "loss": 6.914,
      "step": 33
    },
    {
      "epoch": 0.016782871598691924,
      "grad_norm": 0.18232646584510803,
      "learning_rate": 7.705495977301078e-05,
      "loss": 6.9073,
      "step": 34
    },
    {
      "epoch": 0.017276485469241685,
      "grad_norm": 0.17349576950073242,
      "learning_rate": 7.570292669790186e-05,
      "loss": 6.9101,
      "step": 35
    },
    {
      "epoch": 0.01777009933979145,
      "grad_norm": 0.1874023824930191,
      "learning_rate": 7.43267549363537e-05,
      "loss": 6.9062,
      "step": 36
    },
    {
      "epoch": 0.01826371321034121,
      "grad_norm": 0.17965620756149292,
      "learning_rate": 7.292804904308087e-05,
      "loss": 6.905,
      "step": 37
    },
    {
      "epoch": 0.01875732708089097,
      "grad_norm": 0.17918899655342102,
      "learning_rate": 7.150843984658754e-05,
      "loss": 6.9092,
      "step": 38
    },
    {
      "epoch": 0.019250940951440736,
      "grad_norm": 0.18893581628799438,
      "learning_rate": 7.006958254769438e-05,
      "loss": 6.9072,
      "step": 39
    },
    {
      "epoch": 0.019744554821990497,
      "grad_norm": 0.189700648188591,
      "learning_rate": 6.861315478964841e-05,
      "loss": 6.9048,
      "step": 40
    },
    {
      "epoch": 0.020238168692540262,
      "grad_norm": 0.19713561236858368,
      "learning_rate": 6.714085470206609e-05,
      "loss": 6.9022,
      "step": 41
    },
    {
      "epoch": 0.020731782563090023,
      "grad_norm": 0.18430104851722717,
      "learning_rate": 6.56543989209901e-05,
      "loss": 6.9024,
      "step": 42
    },
    {
      "epoch": 0.021225396433639784,
      "grad_norm": 0.18701981008052826,
      "learning_rate": 6.415552058736854e-05,
      "loss": 6.903,
      "step": 43
    },
    {
      "epoch": 0.02171901030418955,
      "grad_norm": 0.18464837968349457,
      "learning_rate": 6.264596732629e-05,
      "loss": 6.902,
      "step": 44
    },
    {
      "epoch": 0.02221262417473931,
      "grad_norm": 0.18956860899925232,
      "learning_rate": 6.112749920933111e-05,
      "loss": 6.8958,
      "step": 45
    },
    {
      "epoch": 0.02270623804528907,
      "grad_norm": 0.18333902955055237,
      "learning_rate": 5.960188670239154e-05,
      "loss": 6.9006,
      "step": 46
    },
    {
      "epoch": 0.023199851915838836,
      "grad_norm": 0.17345166206359863,
      "learning_rate": 5.80709086014102e-05,
      "loss": 6.8991,
      "step": 47
    },
    {
      "epoch": 0.023693465786388597,
      "grad_norm": 0.17997267842292786,
      "learning_rate": 5.653634995836856e-05,
      "loss": 6.9001,
      "step": 48
    },
    {
      "epoch": 0.02418707965693836,
      "grad_norm": 0.18579334020614624,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.8974,
      "step": 49
    },
    {
      "epoch": 0.024680693527488123,
      "grad_norm": 0.1840241253376007,
      "learning_rate": 5.346365004163145e-05,
      "loss": 6.8931,
      "step": 50
    },
    {
      "epoch": 0.024680693527488123,
      "eval_loss": 6.8887457847595215,
      "eval_runtime": 0.0853,
      "eval_samples_per_second": 586.013,
      "eval_steps_per_second": 152.363,
      "step": 50
    },
    {
      "epoch": 0.025174307398037884,
      "grad_norm": 0.1739850789308548,
      "learning_rate": 5.192909139858981e-05,
      "loss": 6.8971,
      "step": 51
    },
    {
      "epoch": 0.02566792126858765,
      "grad_norm": 0.1729678362607956,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 6.8957,
      "step": 52
    },
    {
      "epoch": 0.02616153513913741,
      "grad_norm": 0.178720623254776,
      "learning_rate": 4.887250079066892e-05,
      "loss": 6.8935,
      "step": 53
    },
    {
      "epoch": 0.02665514900968717,
      "grad_norm": 0.1674613654613495,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 6.8948,
      "step": 54
    },
    {
      "epoch": 0.027148762880236935,
      "grad_norm": 0.15328410267829895,
      "learning_rate": 4.584447941263149e-05,
      "loss": 6.8912,
      "step": 55
    },
    {
      "epoch": 0.027642376750786696,
      "grad_norm": 0.16422665119171143,
      "learning_rate": 4.43456010790099e-05,
      "loss": 6.8897,
      "step": 56
    },
    {
      "epoch": 0.02813599062133646,
      "grad_norm": 0.1450253576040268,
      "learning_rate": 4.285914529793391e-05,
      "loss": 6.8908,
      "step": 57
    },
    {
      "epoch": 0.028629604491886222,
      "grad_norm": 0.15350405871868134,
      "learning_rate": 4.13868452103516e-05,
      "loss": 6.8917,
      "step": 58
    },
    {
      "epoch": 0.029123218362435983,
      "grad_norm": 0.16251219809055328,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 6.8909,
      "step": 59
    },
    {
      "epoch": 0.029616832232985748,
      "grad_norm": 0.1406952440738678,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 6.8922,
      "step": 60
    },
    {
      "epoch": 0.03011044610353551,
      "grad_norm": 0.15078043937683105,
      "learning_rate": 3.707195095691913e-05,
      "loss": 6.8862,
      "step": 61
    },
    {
      "epoch": 0.03060405997408527,
      "grad_norm": 0.15306660532951355,
      "learning_rate": 3.567324506364632e-05,
      "loss": 6.8878,
      "step": 62
    },
    {
      "epoch": 0.031097673844635035,
      "grad_norm": 0.14538978040218353,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 6.8888,
      "step": 63
    },
    {
      "epoch": 0.031591287715184796,
      "grad_norm": 0.1452692747116089,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 6.8895,
      "step": 64
    },
    {
      "epoch": 0.03208490158573456,
      "grad_norm": 0.14324979484081268,
      "learning_rate": 3.16187222484055e-05,
      "loss": 6.8897,
      "step": 65
    },
    {
      "epoch": 0.03257851545628432,
      "grad_norm": 0.1350090503692627,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 6.8859,
      "step": 66
    },
    {
      "epoch": 0.033072129326834086,
      "grad_norm": 0.12386202067136765,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 6.8881,
      "step": 67
    },
    {
      "epoch": 0.03356574319738385,
      "grad_norm": 0.12516862154006958,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 6.8903,
      "step": 68
    },
    {
      "epoch": 0.03405935706793361,
      "grad_norm": 0.1329328715801239,
      "learning_rate": 2.660104250532764e-05,
      "loss": 6.888,
      "step": 69
    },
    {
      "epoch": 0.03455297093848337,
      "grad_norm": 0.12640073895454407,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 6.8854,
      "step": 70
    },
    {
      "epoch": 0.03504658480903313,
      "grad_norm": 0.13168954849243164,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 6.8887,
      "step": 71
    },
    {
      "epoch": 0.0355401986795829,
      "grad_norm": 0.13239482045173645,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 6.8874,
      "step": 72
    },
    {
      "epoch": 0.03603381255013266,
      "grad_norm": 0.11545424908399582,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 6.8883,
      "step": 73
    },
    {
      "epoch": 0.03652742642068242,
      "grad_norm": 0.12295694649219513,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 6.8867,
      "step": 74
    },
    {
      "epoch": 0.03702104029123218,
      "grad_norm": 0.13138267397880554,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 6.885,
      "step": 75
    },
    {
      "epoch": 0.03702104029123218,
      "eval_loss": 6.879824638366699,
      "eval_runtime": 0.0753,
      "eval_samples_per_second": 663.996,
      "eval_steps_per_second": 172.639,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8558936064000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}