{
  "best_metric": 0.14771892130374908,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.009848820603732702,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019697641207465407,
      "grad_norm": 3.348949670791626,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.0606,
      "step": 1
    },
    {
      "epoch": 0.00019697641207465407,
      "eval_loss": 0.360129714012146,
      "eval_runtime": 10.5317,
      "eval_samples_per_second": 4.748,
      "eval_steps_per_second": 0.665,
      "step": 1
    },
    {
      "epoch": 0.00039395282414930814,
      "grad_norm": 3.371903657913208,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.0354,
      "step": 2
    },
    {
      "epoch": 0.0005909292362239622,
      "grad_norm": 2.8037610054016113,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.9175,
      "step": 3
    },
    {
      "epoch": 0.0007879056482986163,
      "grad_norm": 1.5464385747909546,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.5709,
      "step": 4
    },
    {
      "epoch": 0.0009848820603732703,
      "grad_norm": 1.5053009986877441,
      "learning_rate": 0.00015,
      "loss": 0.5139,
      "step": 5
    },
    {
      "epoch": 0.0011818584724479244,
      "grad_norm": 1.4200072288513184,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.5191,
      "step": 6
    },
    {
      "epoch": 0.0013788348845225785,
      "grad_norm": 1.2713923454284668,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.5693,
      "step": 7
    },
    {
      "epoch": 0.0015758112965972325,
      "grad_norm": 2.9913175106048584,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.4701,
      "step": 8
    },
    {
      "epoch": 0.0017727877086718866,
      "grad_norm": 3.1078169345855713,
      "learning_rate": 0.00027,
      "loss": 0.4946,
      "step": 9
    },
    {
      "epoch": 0.0019697641207465405,
      "grad_norm": 1.0796478986740112,
      "learning_rate": 0.0003,
      "loss": 0.552,
      "step": 10
    },
    {
      "epoch": 0.0021667405328211946,
      "grad_norm": 0.8546186685562134,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.4502,
      "step": 11
    },
    {
      "epoch": 0.0023637169448958487,
      "grad_norm": 1.210360050201416,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.4655,
      "step": 12
    },
    {
      "epoch": 0.002560693356970503,
      "grad_norm": 1.6150785684585571,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.4661,
      "step": 13
    },
    {
      "epoch": 0.002757669769045157,
      "grad_norm": 0.7436849474906921,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.366,
      "step": 14
    },
    {
      "epoch": 0.002954646181119811,
      "grad_norm": 0.7962251901626587,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.4605,
      "step": 15
    },
    {
      "epoch": 0.003151622593194465,
      "grad_norm": 0.9352697134017944,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.382,
      "step": 16
    },
    {
      "epoch": 0.003348599005269119,
      "grad_norm": 0.9323279857635498,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.5812,
      "step": 17
    },
    {
      "epoch": 0.0035455754173437733,
      "grad_norm": 0.8441579937934875,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.4787,
      "step": 18
    },
    {
      "epoch": 0.003742551829418427,
      "grad_norm": 1.0008450746536255,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.3968,
      "step": 19
    },
    {
      "epoch": 0.003939528241493081,
      "grad_norm": 0.7684171199798584,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.3796,
      "step": 20
    },
    {
      "epoch": 0.004136504653567736,
      "grad_norm": 1.0816248655319214,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.4181,
      "step": 21
    },
    {
      "epoch": 0.004333481065642389,
      "grad_norm": 0.8110284209251404,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.3604,
      "step": 22
    },
    {
      "epoch": 0.004530457477717044,
      "grad_norm": 2.4406509399414062,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.4562,
      "step": 23
    },
    {
      "epoch": 0.004727433889791697,
      "grad_norm": 1.13535475730896,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.4112,
      "step": 24
    },
    {
      "epoch": 0.004924410301866351,
      "grad_norm": 0.845367968082428,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.4399,
      "step": 25
    },
    {
      "epoch": 0.004924410301866351,
      "eval_loss": 0.11439956724643707,
      "eval_runtime": 12.8261,
      "eval_samples_per_second": 3.898,
      "eval_steps_per_second": 0.546,
      "step": 25
    },
    {
      "epoch": 0.005121386713941006,
      "grad_norm": 0.7668648362159729,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.4863,
      "step": 26
    },
    {
      "epoch": 0.005318363126015659,
      "grad_norm": 0.8414048552513123,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.4708,
      "step": 27
    },
    {
      "epoch": 0.005515339538090314,
      "grad_norm": 0.9618905782699585,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.4237,
      "step": 28
    },
    {
      "epoch": 0.0057123159501649675,
      "grad_norm": 0.7617946267127991,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.3429,
      "step": 29
    },
    {
      "epoch": 0.005909292362239622,
      "grad_norm": 1.3151721954345703,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.5637,
      "step": 30
    },
    {
      "epoch": 0.006106268774314276,
      "grad_norm": 1.2373560667037964,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.4711,
      "step": 31
    },
    {
      "epoch": 0.00630324518638893,
      "grad_norm": 0.9699512124061584,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.3827,
      "step": 32
    },
    {
      "epoch": 0.006500221598463584,
      "grad_norm": 1.1460570096969604,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.4132,
      "step": 33
    },
    {
      "epoch": 0.006697198010538238,
      "grad_norm": 1.2482142448425293,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.4066,
      "step": 34
    },
    {
      "epoch": 0.006894174422612892,
      "grad_norm": 1.0130342245101929,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.4401,
      "step": 35
    },
    {
      "epoch": 0.007091150834687547,
      "grad_norm": 1.153891921043396,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.3825,
      "step": 36
    },
    {
      "epoch": 0.0072881272467622,
      "grad_norm": 1.4242093563079834,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.3514,
      "step": 37
    },
    {
      "epoch": 0.007485103658836854,
      "grad_norm": 0.8260576725006104,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.38,
      "step": 38
    },
    {
      "epoch": 0.007682080070911508,
      "grad_norm": 1.6134790182113647,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.3237,
      "step": 39
    },
    {
      "epoch": 0.007879056482986162,
      "grad_norm": 1.4775500297546387,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.503,
      "step": 40
    },
    {
      "epoch": 0.008076032895060816,
      "grad_norm": 1.2248170375823975,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.3367,
      "step": 41
    },
    {
      "epoch": 0.008273009307135471,
      "grad_norm": 5.347848415374756,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.3759,
      "step": 42
    },
    {
      "epoch": 0.008469985719210125,
      "grad_norm": 1.2572146654129028,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.3936,
      "step": 43
    },
    {
      "epoch": 0.008666962131284778,
      "grad_norm": 1.1421171426773071,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.2144,
      "step": 44
    },
    {
      "epoch": 0.008863938543359432,
      "grad_norm": 0.9987139701843262,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.217,
      "step": 45
    },
    {
      "epoch": 0.009060914955434088,
      "grad_norm": 1.9025821685791016,
      "learning_rate": 0.000274201324672203,
      "loss": 0.2224,
      "step": 46
    },
    {
      "epoch": 0.009257891367508741,
      "grad_norm": 0.7751299738883972,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.1837,
      "step": 47
    },
    {
      "epoch": 0.009454867779583395,
      "grad_norm": 2.193005084991455,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.1896,
      "step": 48
    },
    {
      "epoch": 0.009651844191658049,
      "grad_norm": 1.596818447113037,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.2651,
      "step": 49
    },
    {
      "epoch": 0.009848820603732702,
      "grad_norm": 10.099899291992188,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.4042,
      "step": 50
    },
    {
      "epoch": 0.009848820603732702,
      "eval_loss": 0.14771892130374908,
      "eval_runtime": 10.3847,
      "eval_samples_per_second": 4.815,
      "eval_steps_per_second": 0.674,
      "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": 1,
        "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": 8.778132335099904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}