{
  "best_metric": 0.3110412061214447,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.015844094113919037,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031688188227838076,
      "grad_norm": 0.288943886756897,
      "learning_rate": 1e-05,
      "loss": 0.4815,
      "step": 1
    },
    {
      "epoch": 0.00031688188227838076,
      "eval_loss": 1.0073962211608887,
      "eval_runtime": 388.2204,
      "eval_samples_per_second": 13.691,
      "eval_steps_per_second": 3.423,
      "step": 1
    },
    {
      "epoch": 0.0006337637645567615,
      "grad_norm": 0.34678709506988525,
      "learning_rate": 2e-05,
      "loss": 0.6068,
      "step": 2
    },
    {
      "epoch": 0.0009506456468351422,
      "grad_norm": 0.34489861130714417,
      "learning_rate": 3e-05,
      "loss": 0.5999,
      "step": 3
    },
    {
      "epoch": 0.001267527529113523,
      "grad_norm": 0.3450894355773926,
      "learning_rate": 4e-05,
      "loss": 0.6676,
      "step": 4
    },
    {
      "epoch": 0.0015844094113919036,
      "grad_norm": 0.31017449498176575,
      "learning_rate": 5e-05,
      "loss": 0.6433,
      "step": 5
    },
    {
      "epoch": 0.0019012912936702843,
      "grad_norm": 0.3006879985332489,
      "learning_rate": 6e-05,
      "loss": 0.607,
      "step": 6
    },
    {
      "epoch": 0.0022181731759486653,
      "grad_norm": 0.2969091534614563,
      "learning_rate": 7e-05,
      "loss": 0.6448,
      "step": 7
    },
    {
      "epoch": 0.002535055058227046,
      "grad_norm": 0.24432115256786346,
      "learning_rate": 8e-05,
      "loss": 0.533,
      "step": 8
    },
    {
      "epoch": 0.002851936940505427,
      "grad_norm": 0.24627213180065155,
      "learning_rate": 9e-05,
      "loss": 0.5425,
      "step": 9
    },
    {
      "epoch": 0.003168818822783807,
      "grad_norm": 0.24130110442638397,
      "learning_rate": 0.0001,
      "loss": 0.5446,
      "step": 10
    },
    {
      "epoch": 0.003485700705062188,
      "grad_norm": 0.2302355170249939,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5384,
      "step": 11
    },
    {
      "epoch": 0.0038025825873405686,
      "grad_norm": 0.2180791199207306,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.489,
      "step": 12
    },
    {
      "epoch": 0.004119464469618949,
      "grad_norm": 0.20865923166275024,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5058,
      "step": 13
    },
    {
      "epoch": 0.004436346351897331,
      "grad_norm": 0.22682811319828033,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4016,
      "step": 14
    },
    {
      "epoch": 0.004753228234175711,
      "grad_norm": 0.18705151975154877,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.466,
      "step": 15
    },
    {
      "epoch": 0.005070110116454092,
      "grad_norm": 0.21964482963085175,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4538,
      "step": 16
    },
    {
      "epoch": 0.005386991998732472,
      "grad_norm": 0.21100586652755737,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3919,
      "step": 17
    },
    {
      "epoch": 0.005703873881010854,
      "grad_norm": 0.1652364581823349,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.3553,
      "step": 18
    },
    {
      "epoch": 0.006020755763289234,
      "grad_norm": 0.17498663067817688,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4155,
      "step": 19
    },
    {
      "epoch": 0.006337637645567614,
      "grad_norm": 0.20370839536190033,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4282,
      "step": 20
    },
    {
      "epoch": 0.0066545195278459954,
      "grad_norm": 0.17204949259757996,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3919,
      "step": 21
    },
    {
      "epoch": 0.006971401410124376,
      "grad_norm": 0.1701580435037613,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3842,
      "step": 22
    },
    {
      "epoch": 0.007288283292402757,
      "grad_norm": 0.1702832579612732,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3708,
      "step": 23
    },
    {
      "epoch": 0.007605165174681137,
      "grad_norm": 0.1734638214111328,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4457,
      "step": 24
    },
    {
      "epoch": 0.007922047056959518,
      "grad_norm": 0.17348387837409973,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.3987,
      "step": 25
    },
    {
      "epoch": 0.008238928939237899,
      "grad_norm": 0.15915273129940033,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3546,
      "step": 26
    },
    {
      "epoch": 0.008555810821516279,
      "grad_norm": 0.17628248035907745,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.3845,
      "step": 27
    },
    {
      "epoch": 0.008872692703794661,
      "grad_norm": 0.17458303272724152,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3812,
      "step": 28
    },
    {
      "epoch": 0.009189574586073041,
      "grad_norm": 0.1784602254629135,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3656,
      "step": 29
    },
    {
      "epoch": 0.009506456468351422,
      "grad_norm": 0.16332803666591644,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3481,
      "step": 30
    },
    {
      "epoch": 0.009823338350629802,
      "grad_norm": 0.1699024736881256,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3658,
      "step": 31
    },
    {
      "epoch": 0.010140220232908184,
      "grad_norm": 0.17193962633609772,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3438,
      "step": 32
    },
    {
      "epoch": 0.010457102115186565,
      "grad_norm": 0.17559102177619934,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.346,
      "step": 33
    },
    {
      "epoch": 0.010773983997464945,
      "grad_norm": 0.1714521050453186,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3722,
      "step": 34
    },
    {
      "epoch": 0.011090865879743325,
      "grad_norm": 0.19045782089233398,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3926,
      "step": 35
    },
    {
      "epoch": 0.011407747762021707,
      "grad_norm": 0.18003332614898682,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3513,
      "step": 36
    },
    {
      "epoch": 0.011724629644300088,
      "grad_norm": 0.1978747546672821,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3949,
      "step": 37
    },
    {
      "epoch": 0.012041511526578468,
      "grad_norm": 0.19634827971458435,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3866,
      "step": 38
    },
    {
      "epoch": 0.012358393408856848,
      "grad_norm": 0.21444833278656006,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4006,
      "step": 39
    },
    {
      "epoch": 0.012675275291135229,
      "grad_norm": 0.1893952488899231,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3924,
      "step": 40
    },
    {
      "epoch": 0.01299215717341361,
      "grad_norm": 0.18121342360973358,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3769,
      "step": 41
    },
    {
      "epoch": 0.013309039055691991,
      "grad_norm": 0.17903916537761688,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3801,
      "step": 42
    },
    {
      "epoch": 0.013625920937970371,
      "grad_norm": 0.17503075301647186,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3669,
      "step": 43
    },
    {
      "epoch": 0.013942802820248752,
      "grad_norm": 0.19540923833847046,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3888,
      "step": 44
    },
    {
      "epoch": 0.014259684702527134,
      "grad_norm": 0.19996744394302368,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3779,
      "step": 45
    },
    {
      "epoch": 0.014576566584805514,
      "grad_norm": 0.20995080471038818,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3893,
      "step": 46
    },
    {
      "epoch": 0.014893448467083894,
      "grad_norm": 0.21569843590259552,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3882,
      "step": 47
    },
    {
      "epoch": 0.015210330349362275,
      "grad_norm": 0.2168152928352356,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4067,
      "step": 48
    },
    {
      "epoch": 0.015527212231640657,
      "grad_norm": 0.2293938845396042,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4036,
      "step": 49
    },
    {
      "epoch": 0.015844094113919037,
      "grad_norm": 0.27539652585983276,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4517,
      "step": 50
    },
    {
      "epoch": 0.015844094113919037,
      "eval_loss": 0.3110412061214447,
      "eval_runtime": 391.0829,
      "eval_samples_per_second": 13.59,
      "eval_steps_per_second": 3.398,
      "step": 50
    }
  ],
  "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": 6.719068728773837e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}