{
  "best_metric": 1.9676353931427002,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 1.9002375296912115,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025336500395882817,
      "grad_norm": 2.2324469089508057,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.8506,
      "step": 1
    },
    {
      "epoch": 0.025336500395882817,
      "eval_loss": 3.2235260009765625,
      "eval_runtime": 4.4309,
      "eval_samples_per_second": 11.284,
      "eval_steps_per_second": 2.934,
      "step": 1
    },
    {
      "epoch": 0.050673000791765635,
      "grad_norm": 2.381058692932129,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.0093,
      "step": 2
    },
    {
      "epoch": 0.07600950118764846,
      "grad_norm": 2.3582041263580322,
      "learning_rate": 0.0001,
      "loss": 3.181,
      "step": 3
    },
    {
      "epoch": 0.10134600158353127,
      "grad_norm": 1.9811993837356567,
      "learning_rate": 9.99571699711836e-05,
      "loss": 2.8749,
      "step": 4
    },
    {
      "epoch": 0.12668250197941408,
      "grad_norm": 1.3407419919967651,
      "learning_rate": 9.982876141412856e-05,
      "loss": 2.5471,
      "step": 5
    },
    {
      "epoch": 0.15201900237529692,
      "grad_norm": 1.2031052112579346,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.5596,
      "step": 6
    },
    {
      "epoch": 0.17735550277117973,
      "grad_norm": 1.1195051670074463,
      "learning_rate": 9.931634888554937e-05,
      "loss": 2.3508,
      "step": 7
    },
    {
      "epoch": 0.20269200316706254,
      "grad_norm": 1.1609400510787964,
      "learning_rate": 9.893332032039701e-05,
      "loss": 2.4024,
      "step": 8
    },
    {
      "epoch": 0.22802850356294538,
      "grad_norm": 0.922203540802002,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.3731,
      "step": 9
    },
    {
      "epoch": 0.25336500395882816,
      "grad_norm": 0.9324221611022949,
      "learning_rate": 9.791726278367022e-05,
      "loss": 2.2997,
      "step": 10
    },
    {
      "epoch": 0.278701504354711,
      "grad_norm": 0.8938511610031128,
      "learning_rate": 9.728616793536588e-05,
      "loss": 1.9322,
      "step": 11
    },
    {
      "epoch": 0.30403800475059384,
      "grad_norm": 0.8871761560440063,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.1083,
      "step": 12
    },
    {
      "epoch": 0.32937450514647665,
      "grad_norm": 0.8015140295028687,
      "learning_rate": 9.578385041664925e-05,
      "loss": 2.1816,
      "step": 13
    },
    {
      "epoch": 0.35471100554235946,
      "grad_norm": 0.6659315228462219,
      "learning_rate": 9.491548749301997e-05,
      "loss": 2.0578,
      "step": 14
    },
    {
      "epoch": 0.38004750593824227,
      "grad_norm": 0.677569568157196,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.2049,
      "step": 15
    },
    {
      "epoch": 0.4053840063341251,
      "grad_norm": 0.6852902173995972,
      "learning_rate": 9.295261506157986e-05,
      "loss": 2.1755,
      "step": 16
    },
    {
      "epoch": 0.4307205067300079,
      "grad_norm": 0.6610775589942932,
      "learning_rate": 9.186184199300464e-05,
      "loss": 2.1688,
      "step": 17
    },
    {
      "epoch": 0.45605700712589076,
      "grad_norm": 0.7055267691612244,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.2208,
      "step": 18
    },
    {
      "epoch": 0.48139350752177357,
      "grad_norm": 0.7409207820892334,
      "learning_rate": 8.947199994035401e-05,
      "loss": 2.0766,
      "step": 19
    },
    {
      "epoch": 0.5067300079176563,
      "grad_norm": 0.8099169135093689,
      "learning_rate": 8.817748015645558e-05,
      "loss": 2.0201,
      "step": 20
    },
    {
      "epoch": 0.5320665083135392,
      "grad_norm": 0.7952609658241272,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.9931,
      "step": 21
    },
    {
      "epoch": 0.557403008709422,
      "grad_norm": 0.6881078481674194,
      "learning_rate": 8.540155934270471e-05,
      "loss": 2.0588,
      "step": 22
    },
    {
      "epoch": 0.5827395091053048,
      "grad_norm": 0.629474401473999,
      "learning_rate": 8.392544243589427e-05,
      "loss": 1.9601,
      "step": 23
    },
    {
      "epoch": 0.6080760095011877,
      "grad_norm": 0.6908378005027771,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.0348,
      "step": 24
    },
    {
      "epoch": 0.6334125098970704,
      "grad_norm": 0.6623687148094177,
      "learning_rate": 8.081093963579707e-05,
      "loss": 1.9823,
      "step": 25
    },
    {
      "epoch": 0.6334125098970704,
      "eval_loss": 2.0515553951263428,
      "eval_runtime": 4.475,
      "eval_samples_per_second": 11.173,
      "eval_steps_per_second": 2.905,
      "step": 25
    },
    {
      "epoch": 0.6587490102929533,
      "grad_norm": 0.6521803140640259,
      "learning_rate": 7.917848237560709e-05,
      "loss": 2.1157,
      "step": 26
    },
    {
      "epoch": 0.684085510688836,
      "grad_norm": 0.704856812953949,
      "learning_rate": 7.75e-05,
      "loss": 2.0327,
      "step": 27
    },
    {
      "epoch": 0.7094220110847189,
      "grad_norm": 0.7150166034698486,
      "learning_rate": 7.577868759557654e-05,
      "loss": 2.0704,
      "step": 28
    },
    {
      "epoch": 0.7347585114806018,
      "grad_norm": 0.7469585537910461,
      "learning_rate": 7.401782177833148e-05,
      "loss": 2.1531,
      "step": 29
    },
    {
      "epoch": 0.7600950118764845,
      "grad_norm": 0.8201628923416138,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.9451,
      "step": 30
    },
    {
      "epoch": 0.7854315122723674,
      "grad_norm": 0.8757390975952148,
      "learning_rate": 7.03909064496551e-05,
      "loss": 1.9914,
      "step": 31
    },
    {
      "epoch": 0.8107680126682502,
      "grad_norm": 0.7520741820335388,
      "learning_rate": 6.853176097769229e-05,
      "loss": 2.0039,
      "step": 32
    },
    {
      "epoch": 0.836104513064133,
      "grad_norm": 0.6872738599777222,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.0456,
      "step": 33
    },
    {
      "epoch": 0.8614410134600158,
      "grad_norm": 0.6908338665962219,
      "learning_rate": 6.473978262721463e-05,
      "loss": 1.9938,
      "step": 34
    },
    {
      "epoch": 0.8867775138558986,
      "grad_norm": 0.6956162452697754,
      "learning_rate": 6.281416799501188e-05,
      "loss": 1.8879,
      "step": 35
    },
    {
      "epoch": 0.9121140142517815,
      "grad_norm": 0.7513056397438049,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.8482,
      "step": 36
    },
    {
      "epoch": 0.9374505146476643,
      "grad_norm": 0.7429540753364563,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 2.041,
      "step": 37
    },
    {
      "epoch": 0.9627870150435471,
      "grad_norm": 0.7829824090003967,
      "learning_rate": 5.696287243144013e-05,
      "loss": 2.0959,
      "step": 38
    },
    {
      "epoch": 0.9881235154394299,
      "grad_norm": 0.8197765350341797,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.1425,
      "step": 39
    },
    {
      "epoch": 1.0134600158353126,
      "grad_norm": 1.0817195177078247,
      "learning_rate": 5.303712756855988e-05,
      "loss": 2.9087,
      "step": 40
    },
    {
      "epoch": 1.0387965162311956,
      "grad_norm": 0.6091715693473816,
      "learning_rate": 5.107799157635538e-05,
      "loss": 1.7902,
      "step": 41
    },
    {
      "epoch": 1.0641330166270784,
      "grad_norm": 0.6952990293502808,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.9021,
      "step": 42
    },
    {
      "epoch": 1.0894695170229611,
      "grad_norm": 0.685823917388916,
      "learning_rate": 4.718583200498814e-05,
      "loss": 1.8873,
      "step": 43
    },
    {
      "epoch": 1.114806017418844,
      "grad_norm": 0.6813154816627502,
      "learning_rate": 4.526021737278538e-05,
      "loss": 1.9176,
      "step": 44
    },
    {
      "epoch": 1.1401425178147269,
      "grad_norm": 0.6047990918159485,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.8264,
      "step": 45
    },
    {
      "epoch": 1.1654790182106096,
      "grad_norm": 0.6644649505615234,
      "learning_rate": 4.146823902230772e-05,
      "loss": 1.8149,
      "step": 46
    },
    {
      "epoch": 1.1908155186064926,
      "grad_norm": 0.6789914965629578,
      "learning_rate": 3.960909355034491e-05,
      "loss": 1.8527,
      "step": 47
    },
    {
      "epoch": 1.2161520190023754,
      "grad_norm": 0.7495952248573303,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.8789,
      "step": 48
    },
    {
      "epoch": 1.241488519398258,
      "grad_norm": 0.7526772022247314,
      "learning_rate": 3.598217822166854e-05,
      "loss": 1.9336,
      "step": 49
    },
    {
      "epoch": 1.2668250197941409,
      "grad_norm": 0.6890441179275513,
      "learning_rate": 3.422131240442349e-05,
      "loss": 1.6726,
      "step": 50
    },
    {
      "epoch": 1.2668250197941409,
      "eval_loss": 1.9965410232543945,
      "eval_runtime": 4.3615,
      "eval_samples_per_second": 11.464,
      "eval_steps_per_second": 2.981,
      "step": 50
    },
    {
      "epoch": 1.2921615201900236,
      "grad_norm": 0.6857823729515076,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.9029,
      "step": 51
    },
    {
      "epoch": 1.3174980205859066,
      "grad_norm": 0.6684339642524719,
      "learning_rate": 3.082151762439293e-05,
      "loss": 1.7395,
      "step": 52
    },
    {
      "epoch": 1.3428345209817893,
      "grad_norm": 0.6476242542266846,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 1.8194,
      "step": 53
    },
    {
      "epoch": 1.3681710213776723,
      "grad_norm": 0.6561811566352844,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.8019,
      "step": 54
    },
    {
      "epoch": 1.393507521773555,
      "grad_norm": 0.655868649482727,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 1.6997,
      "step": 55
    },
    {
      "epoch": 1.4188440221694378,
      "grad_norm": 0.6722643375396729,
      "learning_rate": 2.459844065729529e-05,
      "loss": 1.926,
      "step": 56
    },
    {
      "epoch": 1.4441805225653206,
      "grad_norm": 0.6922515034675598,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.9037,
      "step": 57
    },
    {
      "epoch": 1.4695170229612033,
      "grad_norm": 0.7588927149772644,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 1.9156,
      "step": 58
    },
    {
      "epoch": 1.4948535233570863,
      "grad_norm": 0.6962288618087769,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 1.835,
      "step": 59
    },
    {
      "epoch": 1.520190023752969,
      "grad_norm": 0.7170149683952332,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.7774,
      "step": 60
    },
    {
      "epoch": 1.545526524148852,
      "grad_norm": 0.677159309387207,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 1.8,
      "step": 61
    },
    {
      "epoch": 1.5708630245447348,
      "grad_norm": 0.7060984969139099,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 1.8481,
      "step": 62
    },
    {
      "epoch": 1.5961995249406176,
      "grad_norm": 0.8111439943313599,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.772,
      "step": 63
    },
    {
      "epoch": 1.6215360253365003,
      "grad_norm": 0.6780772805213928,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 1.7634,
      "step": 64
    },
    {
      "epoch": 1.646872525732383,
      "grad_norm": 0.6579707860946655,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 1.8308,
      "step": 65
    },
    {
      "epoch": 1.672209026128266,
      "grad_norm": 0.6961445808410645,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.8009,
      "step": 66
    },
    {
      "epoch": 1.6975455265241488,
      "grad_norm": 0.7140675187110901,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 1.7937,
      "step": 67
    },
    {
      "epoch": 1.7228820269200318,
      "grad_norm": 0.817320704460144,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 1.7937,
      "step": 68
    },
    {
      "epoch": 1.7482185273159145,
      "grad_norm": 0.6845941543579102,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.699,
      "step": 69
    },
    {
      "epoch": 1.7735550277117973,
      "grad_norm": 0.6956932544708252,
      "learning_rate": 1.1066679679603e-05,
      "loss": 1.8236,
      "step": 70
    },
    {
      "epoch": 1.79889152810768,
      "grad_norm": 0.6442613005638123,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 1.7499,
      "step": 71
    },
    {
      "epoch": 1.8242280285035628,
      "grad_norm": 0.7191362380981445,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.8782,
      "step": 72
    },
    {
      "epoch": 1.8495645288994458,
      "grad_norm": 0.697597324848175,
      "learning_rate": 1.017123858587145e-05,
      "loss": 1.8019,
      "step": 73
    },
    {
      "epoch": 1.8749010292953285,
      "grad_norm": 0.7081029415130615,
      "learning_rate": 1.00428300288164e-05,
      "loss": 1.8513,
      "step": 74
    },
    {
      "epoch": 1.9002375296912115,
      "grad_norm": 0.6932956576347351,
      "learning_rate": 1e-05,
      "loss": 1.7828,
      "step": 75
    },
    {
      "epoch": 1.9002375296912115,
      "eval_loss": 1.9676353931427002,
      "eval_runtime": 4.4978,
      "eval_samples_per_second": 11.116,
      "eval_steps_per_second": 2.89,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 8.952125425975296e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}