{
  "best_metric": 1.2199846506118774,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.2700877785280216,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027008777852802163,
      "grad_norm": 0.3624476194381714,
      "learning_rate": 1e-05,
      "loss": 1.4218,
      "step": 1
    },
    {
      "epoch": 0.0027008777852802163,
      "eval_loss": 1.4606833457946777,
      "eval_runtime": 15.6141,
      "eval_samples_per_second": 39.964,
      "eval_steps_per_second": 9.991,
      "step": 1
    },
    {
      "epoch": 0.0054017555705604325,
      "grad_norm": 0.3938450813293457,
      "learning_rate": 2e-05,
      "loss": 1.3709,
      "step": 2
    },
    {
      "epoch": 0.008102633355840648,
      "grad_norm": 0.39943069219589233,
      "learning_rate": 3e-05,
      "loss": 1.4067,
      "step": 3
    },
    {
      "epoch": 0.010803511141120865,
      "grad_norm": 0.40101104974746704,
      "learning_rate": 4e-05,
      "loss": 1.4221,
      "step": 4
    },
    {
      "epoch": 0.01350438892640108,
      "grad_norm": 0.36832377314567566,
      "learning_rate": 5e-05,
      "loss": 1.4441,
      "step": 5
    },
    {
      "epoch": 0.016205266711681297,
      "grad_norm": 0.41918250918388367,
      "learning_rate": 6e-05,
      "loss": 1.4905,
      "step": 6
    },
    {
      "epoch": 0.018906144496961513,
      "grad_norm": 0.4318130612373352,
      "learning_rate": 7e-05,
      "loss": 1.3951,
      "step": 7
    },
    {
      "epoch": 0.02160702228224173,
      "grad_norm": 0.524061381816864,
      "learning_rate": 8e-05,
      "loss": 1.3791,
      "step": 8
    },
    {
      "epoch": 0.024307900067521943,
      "grad_norm": 0.5278139710426331,
      "learning_rate": 9e-05,
      "loss": 1.3826,
      "step": 9
    },
    {
      "epoch": 0.02700877785280216,
      "grad_norm": 0.5666940808296204,
      "learning_rate": 0.0001,
      "loss": 1.3379,
      "step": 10
    },
    {
      "epoch": 0.029709655638082377,
      "grad_norm": 0.5191312432289124,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1892,
      "step": 11
    },
    {
      "epoch": 0.03241053342336259,
      "grad_norm": 0.430105596780777,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1462,
      "step": 12
    },
    {
      "epoch": 0.035111411208642807,
      "grad_norm": 0.4412747621536255,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.2241,
      "step": 13
    },
    {
      "epoch": 0.03781228899392303,
      "grad_norm": 0.4131179451942444,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2011,
      "step": 14
    },
    {
      "epoch": 0.04051316677920324,
      "grad_norm": 0.4340050518512726,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1766,
      "step": 15
    },
    {
      "epoch": 0.04321404456448346,
      "grad_norm": 0.42998600006103516,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.2414,
      "step": 16
    },
    {
      "epoch": 0.04591492234976367,
      "grad_norm": 0.42034226655960083,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.0788,
      "step": 17
    },
    {
      "epoch": 0.048615800135043886,
      "grad_norm": 0.5337233543395996,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1981,
      "step": 18
    },
    {
      "epoch": 0.05131667792032411,
      "grad_norm": 0.4583562910556793,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2196,
      "step": 19
    },
    {
      "epoch": 0.05401755570560432,
      "grad_norm": 0.49332761764526367,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1968,
      "step": 20
    },
    {
      "epoch": 0.05671843349088454,
      "grad_norm": 0.48594799637794495,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1309,
      "step": 21
    },
    {
      "epoch": 0.05941931127616475,
      "grad_norm": 0.5126538276672363,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1186,
      "step": 22
    },
    {
      "epoch": 0.062120189061444966,
      "grad_norm": 0.47921475768089294,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0795,
      "step": 23
    },
    {
      "epoch": 0.06482106684672519,
      "grad_norm": 0.4876593053340912,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0949,
      "step": 24
    },
    {
      "epoch": 0.0675219446320054,
      "grad_norm": 0.536691427230835,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0373,
      "step": 25
    },
    {
      "epoch": 0.07022282241728561,
      "grad_norm": 0.6566392779350281,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2434,
      "step": 26
    },
    {
      "epoch": 0.07292370020256583,
      "grad_norm": 0.5158787369728088,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.1554,
      "step": 27
    },
    {
      "epoch": 0.07562457798784605,
      "grad_norm": 0.5759814977645874,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3289,
      "step": 28
    },
    {
      "epoch": 0.07832545577312626,
      "grad_norm": 0.5752044320106506,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1889,
      "step": 29
    },
    {
      "epoch": 0.08102633355840648,
      "grad_norm": 0.6152178645133972,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1266,
      "step": 30
    },
    {
      "epoch": 0.0837272113436867,
      "grad_norm": 0.6457420587539673,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1839,
      "step": 31
    },
    {
      "epoch": 0.08642808912896692,
      "grad_norm": 0.6329084038734436,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.234,
      "step": 32
    },
    {
      "epoch": 0.08912896691424713,
      "grad_norm": 0.6863877773284912,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2342,
      "step": 33
    },
    {
      "epoch": 0.09182984469952735,
      "grad_norm": 0.6431719660758972,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.177,
      "step": 34
    },
    {
      "epoch": 0.09453072248480757,
      "grad_norm": 0.6808779835700989,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3163,
      "step": 35
    },
    {
      "epoch": 0.09723160027008777,
      "grad_norm": 0.7064206600189209,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3071,
      "step": 36
    },
    {
      "epoch": 0.099932478055368,
      "grad_norm": 0.7828763723373413,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3091,
      "step": 37
    },
    {
      "epoch": 0.10263335584064821,
      "grad_norm": 0.8526866436004639,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2666,
      "step": 38
    },
    {
      "epoch": 0.10533423362592843,
      "grad_norm": 0.7964354157447815,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4333,
      "step": 39
    },
    {
      "epoch": 0.10803511141120864,
      "grad_norm": 0.8185365796089172,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.3689,
      "step": 40
    },
    {
      "epoch": 0.11073598919648886,
      "grad_norm": 0.8150967955589294,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.3536,
      "step": 41
    },
    {
      "epoch": 0.11343686698176908,
      "grad_norm": 0.8503111004829407,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3862,
      "step": 42
    },
    {
      "epoch": 0.11613774476704929,
      "grad_norm": 0.8694619536399841,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3512,
      "step": 43
    },
    {
      "epoch": 0.1188386225523295,
      "grad_norm": 1.0029643774032593,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2742,
      "step": 44
    },
    {
      "epoch": 0.12153950033760973,
      "grad_norm": 1.017909049987793,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4303,
      "step": 45
    },
    {
      "epoch": 0.12424037812288993,
      "grad_norm": 1.519902229309082,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4151,
      "step": 46
    },
    {
      "epoch": 0.12694125590817015,
      "grad_norm": 1.4137510061264038,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.4488,
      "step": 47
    },
    {
      "epoch": 0.12964213369345037,
      "grad_norm": 1.4305354356765747,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3568,
      "step": 48
    },
    {
      "epoch": 0.1323430114787306,
      "grad_norm": 1.5225553512573242,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.2391,
      "step": 49
    },
    {
      "epoch": 0.1350438892640108,
      "grad_norm": 2.4049932956695557,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.4481,
      "step": 50
    },
    {
      "epoch": 0.1350438892640108,
      "eval_loss": 1.2866495847702026,
      "eval_runtime": 15.5441,
      "eval_samples_per_second": 40.144,
      "eval_steps_per_second": 10.036,
      "step": 50
    },
    {
      "epoch": 0.137744767049291,
      "grad_norm": 0.6834385395050049,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.4087,
      "step": 51
    },
    {
      "epoch": 0.14044564483457123,
      "grad_norm": 0.6383047699928284,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.4105,
      "step": 52
    },
    {
      "epoch": 0.14314652261985145,
      "grad_norm": 0.4831598997116089,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4986,
      "step": 53
    },
    {
      "epoch": 0.14584740040513167,
      "grad_norm": 0.42735621333122253,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.3571,
      "step": 54
    },
    {
      "epoch": 0.1485482781904119,
      "grad_norm": 0.3566948473453522,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.3558,
      "step": 55
    },
    {
      "epoch": 0.1512491559756921,
      "grad_norm": 0.37861260771751404,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2901,
      "step": 56
    },
    {
      "epoch": 0.15395003376097233,
      "grad_norm": 0.3618011176586151,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2906,
      "step": 57
    },
    {
      "epoch": 0.15665091154625252,
      "grad_norm": 0.42364272475242615,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.2269,
      "step": 58
    },
    {
      "epoch": 0.15935178933153274,
      "grad_norm": 0.39519202709198,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3802,
      "step": 59
    },
    {
      "epoch": 0.16205266711681296,
      "grad_norm": 0.39644855260849,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2644,
      "step": 60
    },
    {
      "epoch": 0.16475354490209318,
      "grad_norm": 0.4740903973579407,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.4338,
      "step": 61
    },
    {
      "epoch": 0.1674544226873734,
      "grad_norm": 0.40571337938308716,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0527,
      "step": 62
    },
    {
      "epoch": 0.17015530047265362,
      "grad_norm": 0.37622109055519104,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.2377,
      "step": 63
    },
    {
      "epoch": 0.17285617825793384,
      "grad_norm": 0.3867974579334259,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.1328,
      "step": 64
    },
    {
      "epoch": 0.17555705604321403,
      "grad_norm": 0.3665173649787903,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0941,
      "step": 65
    },
    {
      "epoch": 0.17825793382849425,
      "grad_norm": 0.3812106251716614,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.1682,
      "step": 66
    },
    {
      "epoch": 0.18095881161377447,
      "grad_norm": 0.396047979593277,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0769,
      "step": 67
    },
    {
      "epoch": 0.1836596893990547,
      "grad_norm": 0.4016658663749695,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2621,
      "step": 68
    },
    {
      "epoch": 0.1863605671843349,
      "grad_norm": 0.42150306701660156,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0641,
      "step": 69
    },
    {
      "epoch": 0.18906144496961513,
      "grad_norm": 0.4154197573661804,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.0688,
      "step": 70
    },
    {
      "epoch": 0.19176232275489535,
      "grad_norm": 0.43228766322135925,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0701,
      "step": 71
    },
    {
      "epoch": 0.19446320054017555,
      "grad_norm": 0.5811237096786499,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1266,
      "step": 72
    },
    {
      "epoch": 0.19716407832545577,
      "grad_norm": 0.4404866397380829,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0782,
      "step": 73
    },
    {
      "epoch": 0.199864956110736,
      "grad_norm": 0.5220156908035278,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.1294,
      "step": 74
    },
    {
      "epoch": 0.2025658338960162,
      "grad_norm": 0.5216073989868164,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1765,
      "step": 75
    },
    {
      "epoch": 0.20526671168129643,
      "grad_norm": 0.5543369054794312,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0467,
      "step": 76
    },
    {
      "epoch": 0.20796758946657665,
      "grad_norm": 0.4874238669872284,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.164,
      "step": 77
    },
    {
      "epoch": 0.21066846725185687,
      "grad_norm": 0.5671214461326599,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0665,
      "step": 78
    },
    {
      "epoch": 0.21336934503713706,
      "grad_norm": 0.5563834309577942,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1413,
      "step": 79
    },
    {
      "epoch": 0.21607022282241728,
      "grad_norm": 0.5251386761665344,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0943,
      "step": 80
    },
    {
      "epoch": 0.2187711006076975,
      "grad_norm": 0.6318755745887756,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0754,
      "step": 81
    },
    {
      "epoch": 0.22147197839297772,
      "grad_norm": 0.6159390211105347,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.2784,
      "step": 82
    },
    {
      "epoch": 0.22417285617825794,
      "grad_norm": 0.6226337552070618,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2542,
      "step": 83
    },
    {
      "epoch": 0.22687373396353816,
      "grad_norm": 0.6405479311943054,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.2991,
      "step": 84
    },
    {
      "epoch": 0.22957461174881835,
      "grad_norm": 0.5985673069953918,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2481,
      "step": 85
    },
    {
      "epoch": 0.23227548953409857,
      "grad_norm": 0.6607664823532104,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1372,
      "step": 86
    },
    {
      "epoch": 0.2349763673193788,
      "grad_norm": 0.6545572280883789,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2627,
      "step": 87
    },
    {
      "epoch": 0.237677245104659,
      "grad_norm": 0.7357593774795532,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1535,
      "step": 88
    },
    {
      "epoch": 0.24037812288993923,
      "grad_norm": 0.7484399676322937,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.3262,
      "step": 89
    },
    {
      "epoch": 0.24307900067521945,
      "grad_norm": 0.7360692024230957,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.2027,
      "step": 90
    },
    {
      "epoch": 0.24577987846049967,
      "grad_norm": 0.7954505681991577,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.3984,
      "step": 91
    },
    {
      "epoch": 0.24848075624577987,
      "grad_norm": 0.8479906320571899,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.3639,
      "step": 92
    },
    {
      "epoch": 0.2511816340310601,
      "grad_norm": 0.9463720917701721,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2841,
      "step": 93
    },
    {
      "epoch": 0.2538825118163403,
      "grad_norm": 1.0730533599853516,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3653,
      "step": 94
    },
    {
      "epoch": 0.2565833896016205,
      "grad_norm": 0.95060795545578,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.3841,
      "step": 95
    },
    {
      "epoch": 0.25928426738690075,
      "grad_norm": 1.2638509273529053,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.3912,
      "step": 96
    },
    {
      "epoch": 0.26198514517218097,
      "grad_norm": 1.0868135690689087,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.4162,
      "step": 97
    },
    {
      "epoch": 0.2646860229574612,
      "grad_norm": 1.3574937582015991,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.2467,
      "step": 98
    },
    {
      "epoch": 0.2673869007427414,
      "grad_norm": 1.4365593194961548,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.1534,
      "step": 99
    },
    {
      "epoch": 0.2700877785280216,
      "grad_norm": 2.1243996620178223,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2386,
      "step": 100
    },
    {
      "epoch": 0.2700877785280216,
      "eval_loss": 1.2199846506118774,
      "eval_runtime": 15.5244,
      "eval_samples_per_second": 40.195,
      "eval_steps_per_second": 10.049,
      "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": 2.8915377635328e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}