{
  "best_metric": 0.7829228043556213,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.024387269845140835,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048774539690281675,
      "grad_norm": 0.42755216360092163,
      "learning_rate": 1e-05,
      "loss": 0.8209,
      "step": 1
    },
    {
      "epoch": 0.00048774539690281675,
      "eval_loss": 1.4778821468353271,
      "eval_runtime": 249.3288,
      "eval_samples_per_second": 13.849,
      "eval_steps_per_second": 3.465,
      "step": 1
    },
    {
      "epoch": 0.0009754907938056335,
      "grad_norm": 0.4249762296676636,
      "learning_rate": 2e-05,
      "loss": 0.8839,
      "step": 2
    },
    {
      "epoch": 0.0014632361907084503,
      "grad_norm": 0.46692362427711487,
      "learning_rate": 3e-05,
      "loss": 0.8946,
      "step": 3
    },
    {
      "epoch": 0.001950981587611267,
      "grad_norm": 0.42918190360069275,
      "learning_rate": 4e-05,
      "loss": 0.891,
      "step": 4
    },
    {
      "epoch": 0.0024387269845140835,
      "grad_norm": 0.4296896755695343,
      "learning_rate": 5e-05,
      "loss": 0.8432,
      "step": 5
    },
    {
      "epoch": 0.0029264723814169005,
      "grad_norm": 0.5116732716560364,
      "learning_rate": 6e-05,
      "loss": 0.8429,
      "step": 6
    },
    {
      "epoch": 0.003414217778319717,
      "grad_norm": 0.54510098695755,
      "learning_rate": 7e-05,
      "loss": 0.8155,
      "step": 7
    },
    {
      "epoch": 0.003901963175222534,
      "grad_norm": 0.497958242893219,
      "learning_rate": 8e-05,
      "loss": 0.9446,
      "step": 8
    },
    {
      "epoch": 0.0043897085721253505,
      "grad_norm": 0.5095407366752625,
      "learning_rate": 9e-05,
      "loss": 0.7652,
      "step": 9
    },
    {
      "epoch": 0.004877453969028167,
      "grad_norm": 0.6286997199058533,
      "learning_rate": 0.0001,
      "loss": 0.8051,
      "step": 10
    },
    {
      "epoch": 0.005365199365930984,
      "grad_norm": 0.551766037940979,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.84,
      "step": 11
    },
    {
      "epoch": 0.005852944762833801,
      "grad_norm": 0.48569273948669434,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7634,
      "step": 12
    },
    {
      "epoch": 0.0063406901597366176,
      "grad_norm": 0.5907832980155945,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8695,
      "step": 13
    },
    {
      "epoch": 0.006828435556639434,
      "grad_norm": 0.5869553089141846,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7659,
      "step": 14
    },
    {
      "epoch": 0.007316180953542251,
      "grad_norm": 0.5571699142456055,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7572,
      "step": 15
    },
    {
      "epoch": 0.007803926350445068,
      "grad_norm": 0.682612419128418,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7622,
      "step": 16
    },
    {
      "epoch": 0.008291671747347884,
      "grad_norm": 0.6647069454193115,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8033,
      "step": 17
    },
    {
      "epoch": 0.008779417144250701,
      "grad_norm": 0.7218847870826721,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.749,
      "step": 18
    },
    {
      "epoch": 0.009267162541153518,
      "grad_norm": 0.6879798173904419,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6535,
      "step": 19
    },
    {
      "epoch": 0.009754907938056334,
      "grad_norm": 0.6669095158576965,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6185,
      "step": 20
    },
    {
      "epoch": 0.010242653334959152,
      "grad_norm": 0.7336055040359497,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7455,
      "step": 21
    },
    {
      "epoch": 0.010730398731861967,
      "grad_norm": 0.7467696070671082,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6521,
      "step": 22
    },
    {
      "epoch": 0.011218144128764785,
      "grad_norm": 0.7632023096084595,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7245,
      "step": 23
    },
    {
      "epoch": 0.011705889525667602,
      "grad_norm": 0.8390482068061829,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7136,
      "step": 24
    },
    {
      "epoch": 0.012193634922570418,
      "grad_norm": 0.8675934076309204,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6735,
      "step": 25
    },
    {
      "epoch": 0.012681380319473235,
      "grad_norm": 0.9683317542076111,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7933,
      "step": 26
    },
    {
      "epoch": 0.013169125716376053,
      "grad_norm": 1.026005744934082,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8079,
      "step": 27
    },
    {
      "epoch": 0.013656871113278868,
      "grad_norm": 1.0004651546478271,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7579,
      "step": 28
    },
    {
      "epoch": 0.014144616510181686,
      "grad_norm": 0.9923139214515686,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6652,
      "step": 29
    },
    {
      "epoch": 0.014632361907084501,
      "grad_norm": 1.1677155494689941,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7852,
      "step": 30
    },
    {
      "epoch": 0.015120107303987319,
      "grad_norm": 1.1109479665756226,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7314,
      "step": 31
    },
    {
      "epoch": 0.015607852700890136,
      "grad_norm": 1.178887963294983,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6344,
      "step": 32
    },
    {
      "epoch": 0.016095598097792953,
      "grad_norm": 1.1039280891418457,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8052,
      "step": 33
    },
    {
      "epoch": 0.016583343494695767,
      "grad_norm": 0.9677231907844543,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6957,
      "step": 34
    },
    {
      "epoch": 0.017071088891598585,
      "grad_norm": 1.3303396701812744,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7921,
      "step": 35
    },
    {
      "epoch": 0.017558834288501402,
      "grad_norm": 1.3315911293029785,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8033,
      "step": 36
    },
    {
      "epoch": 0.01804657968540422,
      "grad_norm": 1.4298336505889893,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8131,
      "step": 37
    },
    {
      "epoch": 0.018534325082307037,
      "grad_norm": 1.2538775205612183,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7601,
      "step": 38
    },
    {
      "epoch": 0.01902207047920985,
      "grad_norm": 1.2895811796188354,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7014,
      "step": 39
    },
    {
      "epoch": 0.01950981587611267,
      "grad_norm": 1.301110863685608,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7467,
      "step": 40
    },
    {
      "epoch": 0.019997561273015486,
      "grad_norm": 1.4002180099487305,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7049,
      "step": 41
    },
    {
      "epoch": 0.020485306669918303,
      "grad_norm": 1.42429518699646,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6995,
      "step": 42
    },
    {
      "epoch": 0.02097305206682112,
      "grad_norm": 1.5314632654190063,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6996,
      "step": 43
    },
    {
      "epoch": 0.021460797463723934,
      "grad_norm": 1.3588933944702148,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6915,
      "step": 44
    },
    {
      "epoch": 0.021948542860626752,
      "grad_norm": 1.8157392740249634,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7544,
      "step": 45
    },
    {
      "epoch": 0.02243628825752957,
      "grad_norm": 1.422425389289856,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.665,
      "step": 46
    },
    {
      "epoch": 0.022924033654432387,
      "grad_norm": 1.61789870262146,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7163,
      "step": 47
    },
    {
      "epoch": 0.023411779051335204,
      "grad_norm": 1.9989192485809326,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8351,
      "step": 48
    },
    {
      "epoch": 0.02389952444823802,
      "grad_norm": 1.481856346130371,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4612,
      "step": 49
    },
    {
      "epoch": 0.024387269845140835,
      "grad_norm": 5.016469478607178,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2368,
      "step": 50
    },
    {
      "epoch": 0.024387269845140835,
      "eval_loss": 0.7829228043556213,
      "eval_runtime": 251.0575,
      "eval_samples_per_second": 13.754,
      "eval_steps_per_second": 3.441,
      "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": 7.28717951238144e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}