{
  "best_metric": 0.30729740858078003,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.005825808330905913,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011651616661811826,
      "grad_norm": 5.975294589996338,
      "learning_rate": 1e-05,
      "loss": 1.4886,
      "step": 1
    },
    {
      "epoch": 0.00011651616661811826,
      "eval_loss": 0.7362678647041321,
      "eval_runtime": 1251.5529,
      "eval_samples_per_second": 11.55,
      "eval_steps_per_second": 2.888,
      "step": 1
    },
    {
      "epoch": 0.00023303233323623653,
      "grad_norm": 7.621860027313232,
      "learning_rate": 2e-05,
      "loss": 2.022,
      "step": 2
    },
    {
      "epoch": 0.0003495484998543548,
      "grad_norm": 10.003783226013184,
      "learning_rate": 3e-05,
      "loss": 2.6357,
      "step": 3
    },
    {
      "epoch": 0.00046606466647247305,
      "grad_norm": 7.267496585845947,
      "learning_rate": 4e-05,
      "loss": 2.8787,
      "step": 4
    },
    {
      "epoch": 0.0005825808330905913,
      "grad_norm": 8.449346542358398,
      "learning_rate": 5e-05,
      "loss": 3.2433,
      "step": 5
    },
    {
      "epoch": 0.0006990969997087095,
      "grad_norm": 7.849472522735596,
      "learning_rate": 6e-05,
      "loss": 2.7579,
      "step": 6
    },
    {
      "epoch": 0.0008156131663268278,
      "grad_norm": 9.259416580200195,
      "learning_rate": 7e-05,
      "loss": 2.8856,
      "step": 7
    },
    {
      "epoch": 0.0009321293329449461,
      "grad_norm": 9.022052764892578,
      "learning_rate": 8e-05,
      "loss": 2.5201,
      "step": 8
    },
    {
      "epoch": 0.0010486454995630643,
      "grad_norm": 10.637661933898926,
      "learning_rate": 9e-05,
      "loss": 2.4325,
      "step": 9
    },
    {
      "epoch": 0.0011651616661811825,
      "grad_norm": 20.810359954833984,
      "learning_rate": 0.0001,
      "loss": 3.6425,
      "step": 10
    },
    {
      "epoch": 0.0012816778327993008,
      "grad_norm": 22.364402770996094,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2994,
      "step": 11
    },
    {
      "epoch": 0.001398193999417419,
      "grad_norm": 21.3902645111084,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9994,
      "step": 12
    },
    {
      "epoch": 0.0015147101660355374,
      "grad_norm": 20.095746994018555,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4923,
      "step": 13
    },
    {
      "epoch": 0.0016312263326536556,
      "grad_norm": 19.705101013183594,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.3813,
      "step": 14
    },
    {
      "epoch": 0.001747742499271774,
      "grad_norm": 10.08316421508789,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8004,
      "step": 15
    },
    {
      "epoch": 0.0018642586658898922,
      "grad_norm": 6.992054462432861,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6966,
      "step": 16
    },
    {
      "epoch": 0.0019807748325080107,
      "grad_norm": 7.983057022094727,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6435,
      "step": 17
    },
    {
      "epoch": 0.0020972909991261285,
      "grad_norm": 10.571928024291992,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3488,
      "step": 18
    },
    {
      "epoch": 0.002213807165744247,
      "grad_norm": 7.997575759887695,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0088,
      "step": 19
    },
    {
      "epoch": 0.002330323332362365,
      "grad_norm": 7.503167629241943,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8738,
      "step": 20
    },
    {
      "epoch": 0.0024468394989804834,
      "grad_norm": 6.179886341094971,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7921,
      "step": 21
    },
    {
      "epoch": 0.0025633556655986016,
      "grad_norm": 6.789474010467529,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7108,
      "step": 22
    },
    {
      "epoch": 0.00267987183221672,
      "grad_norm": 6.373968601226807,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6128,
      "step": 23
    },
    {
      "epoch": 0.002796387998834838,
      "grad_norm": 5.637046813964844,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5566,
      "step": 24
    },
    {
      "epoch": 0.0029129041654529565,
      "grad_norm": 7.8370184898376465,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5593,
      "step": 25
    },
    {
      "epoch": 0.0030294203320710747,
      "grad_norm": 5.988832950592041,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.559,
      "step": 26
    },
    {
      "epoch": 0.003145936498689193,
      "grad_norm": 7.165755271911621,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2816,
      "step": 27
    },
    {
      "epoch": 0.0032624526653073113,
      "grad_norm": 4.786063194274902,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4154,
      "step": 28
    },
    {
      "epoch": 0.0033789688319254296,
      "grad_norm": 4.706677436828613,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3299,
      "step": 29
    },
    {
      "epoch": 0.003495484998543548,
      "grad_norm": 4.422995090484619,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4687,
      "step": 30
    },
    {
      "epoch": 0.003612001165161666,
      "grad_norm": 4.65325403213501,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4085,
      "step": 31
    },
    {
      "epoch": 0.0037285173317797844,
      "grad_norm": 5.4333882331848145,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3464,
      "step": 32
    },
    {
      "epoch": 0.0038450334983979027,
      "grad_norm": 72.83003997802734,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6495,
      "step": 33
    },
    {
      "epoch": 0.003961549665016021,
      "grad_norm": 6.982298851013184,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.703,
      "step": 34
    },
    {
      "epoch": 0.00407806583163414,
      "grad_norm": 6.191880226135254,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2861,
      "step": 35
    },
    {
      "epoch": 0.004194581998252257,
      "grad_norm": 6.210261344909668,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.4421,
      "step": 36
    },
    {
      "epoch": 0.004311098164870375,
      "grad_norm": 3.793665647506714,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2314,
      "step": 37
    },
    {
      "epoch": 0.004427614331488494,
      "grad_norm": 3.907691717147827,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.2664,
      "step": 38
    },
    {
      "epoch": 0.004544130498106612,
      "grad_norm": 3.6872928142547607,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3018,
      "step": 39
    },
    {
      "epoch": 0.00466064666472473,
      "grad_norm": 5.131813049316406,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3065,
      "step": 40
    },
    {
      "epoch": 0.0047771628313428485,
      "grad_norm": 6.162957191467285,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5872,
      "step": 41
    },
    {
      "epoch": 0.004893678997960967,
      "grad_norm": 5.168027877807617,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4656,
      "step": 42
    },
    {
      "epoch": 0.005010195164579085,
      "grad_norm": 5.235057830810547,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3406,
      "step": 43
    },
    {
      "epoch": 0.005126711331197203,
      "grad_norm": 3.2103614807128906,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2492,
      "step": 44
    },
    {
      "epoch": 0.0052432274978153216,
      "grad_norm": 4.117974281311035,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4447,
      "step": 45
    },
    {
      "epoch": 0.00535974366443344,
      "grad_norm": 4.725550174713135,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3768,
      "step": 46
    },
    {
      "epoch": 0.005476259831051558,
      "grad_norm": 3.656212091445923,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3273,
      "step": 47
    },
    {
      "epoch": 0.005592775997669676,
      "grad_norm": 3.0423667430877686,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1449,
      "step": 48
    },
    {
      "epoch": 0.005709292164287795,
      "grad_norm": 5.057799339294434,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3125,
      "step": 49
    },
    {
      "epoch": 0.005825808330905913,
      "grad_norm": 4.145799160003662,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2972,
      "step": 50
    },
    {
      "epoch": 0.005825808330905913,
      "eval_loss": 0.30729740858078003,
      "eval_runtime": 1259.5242,
      "eval_samples_per_second": 11.477,
      "eval_steps_per_second": 2.869,
      "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": 8.62176300415058e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}