{
  "best_metric": 2.5658836364746094,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0931098696461825,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00186219739292365,
      "grad_norm": 1.178178310394287,
      "learning_rate": 5e-06,
      "loss": 2.6211,
      "step": 1
    },
    {
      "epoch": 0.00186219739292365,
      "eval_loss": 3.3070647716522217,
      "eval_runtime": 21.7175,
      "eval_samples_per_second": 41.672,
      "eval_steps_per_second": 20.859,
      "step": 1
    },
    {
      "epoch": 0.0037243947858473,
      "grad_norm": 2.1356124877929688,
      "learning_rate": 1e-05,
      "loss": 2.7551,
      "step": 2
    },
    {
      "epoch": 0.00558659217877095,
      "grad_norm": 1.9746735095977783,
      "learning_rate": 1.5e-05,
      "loss": 3.0001,
      "step": 3
    },
    {
      "epoch": 0.0074487895716946,
      "grad_norm": 1.9692213535308838,
      "learning_rate": 2e-05,
      "loss": 2.8061,
      "step": 4
    },
    {
      "epoch": 0.00931098696461825,
      "grad_norm": 2.3928768634796143,
      "learning_rate": 2.5e-05,
      "loss": 2.6685,
      "step": 5
    },
    {
      "epoch": 0.0111731843575419,
      "grad_norm": 2.2253520488739014,
      "learning_rate": 3e-05,
      "loss": 2.6104,
      "step": 6
    },
    {
      "epoch": 0.01303538175046555,
      "grad_norm": 2.323080539703369,
      "learning_rate": 3.5e-05,
      "loss": 2.689,
      "step": 7
    },
    {
      "epoch": 0.0148975791433892,
      "grad_norm": 2.3765766620635986,
      "learning_rate": 4e-05,
      "loss": 2.9615,
      "step": 8
    },
    {
      "epoch": 0.01675977653631285,
      "grad_norm": 2.05714750289917,
      "learning_rate": 4.5e-05,
      "loss": 2.723,
      "step": 9
    },
    {
      "epoch": 0.0186219739292365,
      "grad_norm": 2.683811902999878,
      "learning_rate": 5e-05,
      "loss": 2.5645,
      "step": 10
    },
    {
      "epoch": 0.020484171322160148,
      "grad_norm": 2.434372663497925,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.6508,
      "step": 11
    },
    {
      "epoch": 0.0223463687150838,
      "grad_norm": 2.7041714191436768,
      "learning_rate": 6e-05,
      "loss": 2.5503,
      "step": 12
    },
    {
      "epoch": 0.024208566108007448,
      "grad_norm": 2.5691897869110107,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.6562,
      "step": 13
    },
    {
      "epoch": 0.0260707635009311,
      "grad_norm": 3.0065274238586426,
      "learning_rate": 7e-05,
      "loss": 2.6278,
      "step": 14
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 2.199162244796753,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2827,
      "step": 15
    },
    {
      "epoch": 0.0297951582867784,
      "grad_norm": 2.762291431427002,
      "learning_rate": 8e-05,
      "loss": 2.2615,
      "step": 16
    },
    {
      "epoch": 0.03165735567970205,
      "grad_norm": 2.3539557456970215,
      "learning_rate": 8.5e-05,
      "loss": 2.3974,
      "step": 17
    },
    {
      "epoch": 0.0335195530726257,
      "grad_norm": 2.7445669174194336,
      "learning_rate": 9e-05,
      "loss": 2.2605,
      "step": 18
    },
    {
      "epoch": 0.035381750465549346,
      "grad_norm": 2.828781843185425,
      "learning_rate": 9.5e-05,
      "loss": 2.4178,
      "step": 19
    },
    {
      "epoch": 0.037243947858473,
      "grad_norm": 2.554708480834961,
      "learning_rate": 0.0001,
      "loss": 2.1424,
      "step": 20
    },
    {
      "epoch": 0.03910614525139665,
      "grad_norm": 2.6451961994171143,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.1344,
      "step": 21
    },
    {
      "epoch": 0.040968342644320296,
      "grad_norm": 2.7068910598754883,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.2556,
      "step": 22
    },
    {
      "epoch": 0.04283054003724395,
      "grad_norm": 2.764464855194092,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.3873,
      "step": 23
    },
    {
      "epoch": 0.0446927374301676,
      "grad_norm": 2.798506021499634,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2367,
      "step": 24
    },
    {
      "epoch": 0.04655493482309125,
      "grad_norm": 2.565629243850708,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.4074,
      "step": 25
    },
    {
      "epoch": 0.048417132216014895,
      "grad_norm": 2.5067367553710938,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.0703,
      "step": 26
    },
    {
      "epoch": 0.05027932960893855,
      "grad_norm": 3.635667562484741,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.1721,
      "step": 27
    },
    {
      "epoch": 0.0521415270018622,
      "grad_norm": 3.774707317352295,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.1216,
      "step": 28
    },
    {
      "epoch": 0.054003724394785846,
      "grad_norm": 2.8153574466705322,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.2958,
      "step": 29
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 3.2285168170928955,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.3483,
      "step": 30
    },
    {
      "epoch": 0.05772811918063315,
      "grad_norm": 4.216028690338135,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.566,
      "step": 31
    },
    {
      "epoch": 0.0595903165735568,
      "grad_norm": 3.771660804748535,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.1817,
      "step": 32
    },
    {
      "epoch": 0.061452513966480445,
      "grad_norm": 3.534721851348877,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.2499,
      "step": 33
    },
    {
      "epoch": 0.0633147113594041,
      "grad_norm": 2.9690186977386475,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.243,
      "step": 34
    },
    {
      "epoch": 0.06517690875232775,
      "grad_norm": 3.739225149154663,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.3059,
      "step": 35
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": 3.2151126861572266,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.3284,
      "step": 36
    },
    {
      "epoch": 0.06890130353817504,
      "grad_norm": 3.2973902225494385,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.8754,
      "step": 37
    },
    {
      "epoch": 0.07076350093109869,
      "grad_norm": 3.0244390964508057,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.6087,
      "step": 38
    },
    {
      "epoch": 0.07262569832402235,
      "grad_norm": 3.9037907123565674,
      "learning_rate": 9.727592877996585e-05,
      "loss": 2.3161,
      "step": 39
    },
    {
      "epoch": 0.074487895716946,
      "grad_norm": 3.0399837493896484,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.9208,
      "step": 40
    },
    {
      "epoch": 0.07635009310986965,
      "grad_norm": 2.6149749755859375,
      "learning_rate": 9.667902132486009e-05,
      "loss": 2.7519,
      "step": 41
    },
    {
      "epoch": 0.0782122905027933,
      "grad_norm": 2.8330459594726562,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.002,
      "step": 42
    },
    {
      "epoch": 0.08007448789571694,
      "grad_norm": 3.024914264678955,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.7255,
      "step": 43
    },
    {
      "epoch": 0.08193668528864059,
      "grad_norm": 3.103067398071289,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.9374,
      "step": 44
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 4.024307727813721,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.4808,
      "step": 45
    },
    {
      "epoch": 0.0856610800744879,
      "grad_norm": 3.7541255950927734,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.9799,
      "step": 46
    },
    {
      "epoch": 0.08752327746741155,
      "grad_norm": 3.815789222717285,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.0052,
      "step": 47
    },
    {
      "epoch": 0.0893854748603352,
      "grad_norm": 4.527659893035889,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.3865,
      "step": 48
    },
    {
      "epoch": 0.09124767225325885,
      "grad_norm": 4.477816581726074,
      "learning_rate": 9.373098535696979e-05,
      "loss": 3.0642,
      "step": 49
    },
    {
      "epoch": 0.0931098696461825,
      "grad_norm": 5.919867515563965,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.1839,
      "step": 50
    },
    {
      "epoch": 0.0931098696461825,
      "eval_loss": 2.5658836364746094,
      "eval_runtime": 21.709,
      "eval_samples_per_second": 41.688,
      "eval_steps_per_second": 20.867,
      "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": 1.010975272599552e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}