{
  "best_metric": 1.2798569202423096,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.005578333751708364,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001115666750341673,
      "grad_norm": 1.8212274312973022,
      "learning_rate": 1e-05,
      "loss": 2.3379,
      "step": 1
    },
    {
      "epoch": 0.0001115666750341673,
      "eval_loss": 2.0897305011749268,
      "eval_runtime": 459.6053,
      "eval_samples_per_second": 32.848,
      "eval_steps_per_second": 8.214,
      "step": 1
    },
    {
      "epoch": 0.0002231333500683346,
      "grad_norm": 1.4086194038391113,
      "learning_rate": 2e-05,
      "loss": 2.01,
      "step": 2
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": 1.7514138221740723,
      "learning_rate": 3e-05,
      "loss": 2.0344,
      "step": 3
    },
    {
      "epoch": 0.0004462667001366692,
      "grad_norm": 1.4951744079589844,
      "learning_rate": 4e-05,
      "loss": 2.0691,
      "step": 4
    },
    {
      "epoch": 0.0005578333751708364,
      "grad_norm": 2.0470707416534424,
      "learning_rate": 5e-05,
      "loss": 1.8823,
      "step": 5
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": 1.2319015264511108,
      "learning_rate": 6e-05,
      "loss": 1.669,
      "step": 6
    },
    {
      "epoch": 0.000780966725239171,
      "grad_norm": 1.0491044521331787,
      "learning_rate": 7e-05,
      "loss": 1.8064,
      "step": 7
    },
    {
      "epoch": 0.0008925334002733384,
      "grad_norm": 0.8125782608985901,
      "learning_rate": 8e-05,
      "loss": 1.5541,
      "step": 8
    },
    {
      "epoch": 0.0010041000753075056,
      "grad_norm": 0.7733227610588074,
      "learning_rate": 9e-05,
      "loss": 1.4467,
      "step": 9
    },
    {
      "epoch": 0.0011156667503416729,
      "grad_norm": 0.7457000613212585,
      "learning_rate": 0.0001,
      "loss": 1.6052,
      "step": 10
    },
    {
      "epoch": 0.0012272334253758403,
      "grad_norm": 0.8214192986488342,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3595,
      "step": 11
    },
    {
      "epoch": 0.0013388001004100076,
      "grad_norm": 0.8121744990348816,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5238,
      "step": 12
    },
    {
      "epoch": 0.0014503667754441748,
      "grad_norm": 0.8887802958488464,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4391,
      "step": 13
    },
    {
      "epoch": 0.001561933450478342,
      "grad_norm": 0.8478315472602844,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5244,
      "step": 14
    },
    {
      "epoch": 0.0016735001255125093,
      "grad_norm": 0.7322865128517151,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4157,
      "step": 15
    },
    {
      "epoch": 0.0017850668005466768,
      "grad_norm": 0.6391441822052002,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5161,
      "step": 16
    },
    {
      "epoch": 0.001896633475580844,
      "grad_norm": 0.6411845684051514,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4755,
      "step": 17
    },
    {
      "epoch": 0.0020082001506150113,
      "grad_norm": 0.6023644804954529,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3029,
      "step": 18
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.6136645674705505,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3007,
      "step": 19
    },
    {
      "epoch": 0.0022313335006833458,
      "grad_norm": 0.6210187077522278,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2692,
      "step": 20
    },
    {
      "epoch": 0.002342900175717513,
      "grad_norm": 0.6014333963394165,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4677,
      "step": 21
    },
    {
      "epoch": 0.0024544668507516807,
      "grad_norm": 0.6709775328636169,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4501,
      "step": 22
    },
    {
      "epoch": 0.0025660335257858477,
      "grad_norm": 0.6392071843147278,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4234,
      "step": 23
    },
    {
      "epoch": 0.002677600200820015,
      "grad_norm": 0.6098843216896057,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3298,
      "step": 24
    },
    {
      "epoch": 0.002789166875854182,
      "grad_norm": 0.5846989750862122,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2984,
      "step": 25
    },
    {
      "epoch": 0.0029007335508883497,
      "grad_norm": 0.6030681729316711,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3124,
      "step": 26
    },
    {
      "epoch": 0.003012300225922517,
      "grad_norm": 0.6540078520774841,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4155,
      "step": 27
    },
    {
      "epoch": 0.003123866900956684,
      "grad_norm": 0.6274188160896301,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3318,
      "step": 28
    },
    {
      "epoch": 0.0032354335759908516,
      "grad_norm": 0.6784371137619019,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4022,
      "step": 29
    },
    {
      "epoch": 0.0033470002510250186,
      "grad_norm": 0.6410314440727234,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1663,
      "step": 30
    },
    {
      "epoch": 0.003458566926059186,
      "grad_norm": 0.6650882959365845,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3205,
      "step": 31
    },
    {
      "epoch": 0.0035701336010933536,
      "grad_norm": 0.6392965912818909,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2732,
      "step": 32
    },
    {
      "epoch": 0.0036817002761275206,
      "grad_norm": 0.6518154144287109,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2392,
      "step": 33
    },
    {
      "epoch": 0.003793266951161688,
      "grad_norm": 0.6471737623214722,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2403,
      "step": 34
    },
    {
      "epoch": 0.0039048336261958555,
      "grad_norm": 0.7046892642974854,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.277,
      "step": 35
    },
    {
      "epoch": 0.0040164003012300225,
      "grad_norm": 0.7445775866508484,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.181,
      "step": 36
    },
    {
      "epoch": 0.0041279669762641896,
      "grad_norm": 0.6786828637123108,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1956,
      "step": 37
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 0.7013096213340759,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2562,
      "step": 38
    },
    {
      "epoch": 0.0043511003263325245,
      "grad_norm": 0.7101519703865051,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1892,
      "step": 39
    },
    {
      "epoch": 0.0044626670013666915,
      "grad_norm": 0.7629431486129761,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1483,
      "step": 40
    },
    {
      "epoch": 0.004574233676400859,
      "grad_norm": 0.7780884504318237,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.265,
      "step": 41
    },
    {
      "epoch": 0.004685800351435026,
      "grad_norm": 0.7125723958015442,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.101,
      "step": 42
    },
    {
      "epoch": 0.0047973670264691935,
      "grad_norm": 0.7452905774116516,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2251,
      "step": 43
    },
    {
      "epoch": 0.004908933701503361,
      "grad_norm": 0.7337647080421448,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1975,
      "step": 44
    },
    {
      "epoch": 0.005020500376537528,
      "grad_norm": 0.7240177989006042,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.275,
      "step": 45
    },
    {
      "epoch": 0.005132067051571695,
      "grad_norm": 0.8364499807357788,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.2254,
      "step": 46
    },
    {
      "epoch": 0.005243633726605862,
      "grad_norm": 0.8767226934432983,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.3331,
      "step": 47
    },
    {
      "epoch": 0.00535520040164003,
      "grad_norm": 0.9071653485298157,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1337,
      "step": 48
    },
    {
      "epoch": 0.005466767076674197,
      "grad_norm": 0.8514352440834045,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0207,
      "step": 49
    },
    {
      "epoch": 0.005578333751708364,
      "grad_norm": 0.9976662993431091,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0039,
      "step": 50
    },
    {
      "epoch": 0.005578333751708364,
      "eval_loss": 1.2798569202423096,
      "eval_runtime": 460.1544,
      "eval_samples_per_second": 32.809,
      "eval_steps_per_second": 8.204,
      "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": 1.39474174476288e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}