{
  "best_metric": 0.6084063053131104,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.1444564824846515,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001444564824846515,
      "grad_norm": 16.361541748046875,
      "learning_rate": 1e-05,
      "loss": 3.9012,
      "step": 1
    },
    {
      "epoch": 0.001444564824846515,
      "eval_loss": 1.3323529958724976,
      "eval_runtime": 130.472,
      "eval_samples_per_second": 8.937,
      "eval_steps_per_second": 2.238,
      "step": 1
    },
    {
      "epoch": 0.00288912964969303,
      "grad_norm": 17.223962783813477,
      "learning_rate": 2e-05,
      "loss": 4.3025,
      "step": 2
    },
    {
      "epoch": 0.004333694474539545,
      "grad_norm": 11.914349555969238,
      "learning_rate": 3e-05,
      "loss": 3.9574,
      "step": 3
    },
    {
      "epoch": 0.00577825929938606,
      "grad_norm": 7.502524375915527,
      "learning_rate": 4e-05,
      "loss": 3.4755,
      "step": 4
    },
    {
      "epoch": 0.007222824124232575,
      "grad_norm": 8.291370391845703,
      "learning_rate": 5e-05,
      "loss": 3.2739,
      "step": 5
    },
    {
      "epoch": 0.00866738894907909,
      "grad_norm": 5.763211727142334,
      "learning_rate": 6e-05,
      "loss": 3.3542,
      "step": 6
    },
    {
      "epoch": 0.010111953773925604,
      "grad_norm": 4.348060607910156,
      "learning_rate": 7e-05,
      "loss": 3.4148,
      "step": 7
    },
    {
      "epoch": 0.01155651859877212,
      "grad_norm": 4.385978698730469,
      "learning_rate": 8e-05,
      "loss": 3.272,
      "step": 8
    },
    {
      "epoch": 0.013001083423618635,
      "grad_norm": 5.313387393951416,
      "learning_rate": 9e-05,
      "loss": 3.3586,
      "step": 9
    },
    {
      "epoch": 0.01444564824846515,
      "grad_norm": 3.8400723934173584,
      "learning_rate": 0.0001,
      "loss": 2.8071,
      "step": 10
    },
    {
      "epoch": 0.015890213073311666,
      "grad_norm": 3.9980530738830566,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.0573,
      "step": 11
    },
    {
      "epoch": 0.01733477789815818,
      "grad_norm": 3.494262933731079,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.9222,
      "step": 12
    },
    {
      "epoch": 0.018779342723004695,
      "grad_norm": 3.459137201309204,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.8361,
      "step": 13
    },
    {
      "epoch": 0.020223907547851208,
      "grad_norm": 3.226391077041626,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.886,
      "step": 14
    },
    {
      "epoch": 0.021668472372697724,
      "grad_norm": 3.5243947505950928,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.6985,
      "step": 15
    },
    {
      "epoch": 0.02311303719754424,
      "grad_norm": 2.652158260345459,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.4968,
      "step": 16
    },
    {
      "epoch": 0.024557602022390754,
      "grad_norm": 3.0979390144348145,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.5622,
      "step": 17
    },
    {
      "epoch": 0.02600216684723727,
      "grad_norm": 2.7068538665771484,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.5086,
      "step": 18
    },
    {
      "epoch": 0.027446731672083786,
      "grad_norm": 2.9226999282836914,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.4883,
      "step": 19
    },
    {
      "epoch": 0.0288912964969303,
      "grad_norm": 2.653764009475708,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.6347,
      "step": 20
    },
    {
      "epoch": 0.030335861321776816,
      "grad_norm": 2.486294984817505,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.1697,
      "step": 21
    },
    {
      "epoch": 0.03178042614662333,
      "grad_norm": 2.477294445037842,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.721,
      "step": 22
    },
    {
      "epoch": 0.033224990971469845,
      "grad_norm": 2.8305273056030273,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.4226,
      "step": 23
    },
    {
      "epoch": 0.03466955579631636,
      "grad_norm": 2.611548900604248,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.4349,
      "step": 24
    },
    {
      "epoch": 0.03611412062116288,
      "grad_norm": 2.581512451171875,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.4936,
      "step": 25
    },
    {
      "epoch": 0.03755868544600939,
      "grad_norm": 2.717400312423706,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.1803,
      "step": 26
    },
    {
      "epoch": 0.0390032502708559,
      "grad_norm": 2.3485753536224365,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.1241,
      "step": 27
    },
    {
      "epoch": 0.040447815095702416,
      "grad_norm": 3.051213264465332,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.3048,
      "step": 28
    },
    {
      "epoch": 0.041892379920548936,
      "grad_norm": 3.0653040409088135,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8214,
      "step": 29
    },
    {
      "epoch": 0.04333694474539545,
      "grad_norm": 5.2764129638671875,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.3896,
      "step": 30
    },
    {
      "epoch": 0.04478150957024196,
      "grad_norm": 3.2993524074554443,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.8715,
      "step": 31
    },
    {
      "epoch": 0.04622607439508848,
      "grad_norm": 3.6438353061676025,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.7842,
      "step": 32
    },
    {
      "epoch": 0.047670639219934995,
      "grad_norm": 3.4112958908081055,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.5711,
      "step": 33
    },
    {
      "epoch": 0.04911520404478151,
      "grad_norm": 3.6442129611968994,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.5648,
      "step": 34
    },
    {
      "epoch": 0.05055976886962803,
      "grad_norm": 3.5792927742004395,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.6949,
      "step": 35
    },
    {
      "epoch": 0.05200433369447454,
      "grad_norm": 3.691844940185547,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.5631,
      "step": 36
    },
    {
      "epoch": 0.05344889851932105,
      "grad_norm": 3.7965307235717773,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.978,
      "step": 37
    },
    {
      "epoch": 0.05489346334416757,
      "grad_norm": 3.610480785369873,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.9458,
      "step": 38
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 4.116268157958984,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.9296,
      "step": 39
    },
    {
      "epoch": 0.0577825929938606,
      "grad_norm": 4.377668380737305,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.0599,
      "step": 40
    },
    {
      "epoch": 0.05922715781870711,
      "grad_norm": 4.640693664550781,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.1757,
      "step": 41
    },
    {
      "epoch": 0.06067172264355363,
      "grad_norm": 6.292191505432129,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.1289,
      "step": 42
    },
    {
      "epoch": 0.062116287468400144,
      "grad_norm": 5.429113388061523,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.2564,
      "step": 43
    },
    {
      "epoch": 0.06356085229324666,
      "grad_norm": 7.226019382476807,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.8515,
      "step": 44
    },
    {
      "epoch": 0.06500541711809317,
      "grad_norm": 11.428001403808594,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.7185,
      "step": 45
    },
    {
      "epoch": 0.06644998194293969,
      "grad_norm": 13.498456954956055,
      "learning_rate": 9.140044155740101e-05,
      "loss": 4.7712,
      "step": 46
    },
    {
      "epoch": 0.06789454676778621,
      "grad_norm": 11.203150749206543,
      "learning_rate": 9.093124073433463e-05,
      "loss": 4.3562,
      "step": 47
    },
    {
      "epoch": 0.06933911159263272,
      "grad_norm": 18.002939224243164,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.7091,
      "step": 48
    },
    {
      "epoch": 0.07078367641747924,
      "grad_norm": 14.366482734680176,
      "learning_rate": 8.995939984474624e-05,
      "loss": 5.1619,
      "step": 49
    },
    {
      "epoch": 0.07222824124232576,
      "grad_norm": 25.771150588989258,
      "learning_rate": 8.945702546981969e-05,
      "loss": 7.0849,
      "step": 50
    },
    {
      "epoch": 0.07222824124232576,
      "eval_loss": 0.7910234928131104,
      "eval_runtime": 131.8556,
      "eval_samples_per_second": 8.843,
      "eval_steps_per_second": 2.215,
      "step": 50
    },
    {
      "epoch": 0.07367280606717226,
      "grad_norm": 10.92339038848877,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.896,
      "step": 51
    },
    {
      "epoch": 0.07511737089201878,
      "grad_norm": 4.852169990539551,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.614,
      "step": 52
    },
    {
      "epoch": 0.0765619357168653,
      "grad_norm": 3.439312219619751,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.4682,
      "step": 53
    },
    {
      "epoch": 0.0780065005417118,
      "grad_norm": 2.424557685852051,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.6748,
      "step": 54
    },
    {
      "epoch": 0.07945106536655833,
      "grad_norm": 2.1135504245758057,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.0125,
      "step": 55
    },
    {
      "epoch": 0.08089563019140483,
      "grad_norm": 2.3444604873657227,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.3545,
      "step": 56
    },
    {
      "epoch": 0.08234019501625135,
      "grad_norm": 2.220395088195801,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3434,
      "step": 57
    },
    {
      "epoch": 0.08378475984109787,
      "grad_norm": 2.29278564453125,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.0731,
      "step": 58
    },
    {
      "epoch": 0.08522932466594438,
      "grad_norm": 2.278346061706543,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.4211,
      "step": 59
    },
    {
      "epoch": 0.0866738894907909,
      "grad_norm": 2.0982675552368164,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.7617,
      "step": 60
    },
    {
      "epoch": 0.08811845431563742,
      "grad_norm": 2.262214183807373,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.022,
      "step": 61
    },
    {
      "epoch": 0.08956301914048392,
      "grad_norm": 2.122612714767456,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.0926,
      "step": 62
    },
    {
      "epoch": 0.09100758396533044,
      "grad_norm": 2.29144287109375,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.093,
      "step": 63
    },
    {
      "epoch": 0.09245214879017696,
      "grad_norm": 2.253896474838257,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.9666,
      "step": 64
    },
    {
      "epoch": 0.09389671361502347,
      "grad_norm": 2.204949140548706,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.2943,
      "step": 65
    },
    {
      "epoch": 0.09534127843986999,
      "grad_norm": 2.1490232944488525,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.9285,
      "step": 66
    },
    {
      "epoch": 0.09678584326471651,
      "grad_norm": 2.109954833984375,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.161,
      "step": 67
    },
    {
      "epoch": 0.09823040808956301,
      "grad_norm": 2.0772545337677,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.787,
      "step": 68
    },
    {
      "epoch": 0.09967497291440953,
      "grad_norm": 2.3547136783599854,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.0184,
      "step": 69
    },
    {
      "epoch": 0.10111953773925605,
      "grad_norm": 2.1117351055145264,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.9861,
      "step": 70
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.4485626220703125,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.2225,
      "step": 71
    },
    {
      "epoch": 0.10400866738894908,
      "grad_norm": 2.093348503112793,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.0359,
      "step": 72
    },
    {
      "epoch": 0.1054532322137956,
      "grad_norm": 2.024015188217163,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.7762,
      "step": 73
    },
    {
      "epoch": 0.1068977970386421,
      "grad_norm": 2.1689019203186035,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.6212,
      "step": 74
    },
    {
      "epoch": 0.10834236186348863,
      "grad_norm": 2.0198400020599365,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.8681,
      "step": 75
    },
    {
      "epoch": 0.10978692668833515,
      "grad_norm": 2.089298725128174,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.1604,
      "step": 76
    },
    {
      "epoch": 0.11123149151318165,
      "grad_norm": 2.336698532104492,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.1222,
      "step": 77
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 2.329235076904297,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.0341,
      "step": 78
    },
    {
      "epoch": 0.11412062116287468,
      "grad_norm": 2.9682834148406982,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.196,
      "step": 79
    },
    {
      "epoch": 0.1155651859877212,
      "grad_norm": 2.6919736862182617,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.1352,
      "step": 80
    },
    {
      "epoch": 0.11700975081256772,
      "grad_norm": 2.4734435081481934,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.8077,
      "step": 81
    },
    {
      "epoch": 0.11845431563741422,
      "grad_norm": 2.6794533729553223,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.2776,
      "step": 82
    },
    {
      "epoch": 0.11989888046226074,
      "grad_norm": 2.8582587242126465,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.1036,
      "step": 83
    },
    {
      "epoch": 0.12134344528710726,
      "grad_norm": 3.296032190322876,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.4848,
      "step": 84
    },
    {
      "epoch": 0.12278801011195377,
      "grad_norm": 3.1677138805389404,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.4112,
      "step": 85
    },
    {
      "epoch": 0.12423257493680029,
      "grad_norm": 3.2526278495788574,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.4407,
      "step": 86
    },
    {
      "epoch": 0.1256771397616468,
      "grad_norm": 3.802973508834839,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.5273,
      "step": 87
    },
    {
      "epoch": 0.12712170458649333,
      "grad_norm": 3.6186423301696777,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.1346,
      "step": 88
    },
    {
      "epoch": 0.12856626941133983,
      "grad_norm": 4.2363200187683105,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.6065,
      "step": 89
    },
    {
      "epoch": 0.13001083423618634,
      "grad_norm": 4.081016540527344,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.6405,
      "step": 90
    },
    {
      "epoch": 0.13145539906103287,
      "grad_norm": 5.950720310211182,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.1082,
      "step": 91
    },
    {
      "epoch": 0.13289996388587938,
      "grad_norm": 4.650112152099609,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.6436,
      "step": 92
    },
    {
      "epoch": 0.13434452871072589,
      "grad_norm": 4.918834686279297,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.8926,
      "step": 93
    },
    {
      "epoch": 0.13578909353557242,
      "grad_norm": 5.376173973083496,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.0728,
      "step": 94
    },
    {
      "epoch": 0.13723365836041893,
      "grad_norm": 6.745965480804443,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.4414,
      "step": 95
    },
    {
      "epoch": 0.13867822318526543,
      "grad_norm": 10.788195610046387,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.6239,
      "step": 96
    },
    {
      "epoch": 0.14012278801011196,
      "grad_norm": 10.470982551574707,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.8976,
      "step": 97
    },
    {
      "epoch": 0.14156735283495847,
      "grad_norm": 10.752097129821777,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.6363,
      "step": 98
    },
    {
      "epoch": 0.14301191765980498,
      "grad_norm": 12.399551391601562,
      "learning_rate": 5.495227651252315e-05,
      "loss": 4.3399,
      "step": 99
    },
    {
      "epoch": 0.1444564824846515,
      "grad_norm": 20.386749267578125,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 6.0517,
      "step": 100
    },
    {
      "epoch": 0.1444564824846515,
      "eval_loss": 0.6084063053131104,
      "eval_runtime": 131.5687,
      "eval_samples_per_second": 8.862,
      "eval_steps_per_second": 2.219,
      "step": 100
    }
  ],
  "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": 2.2001619151355904e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}