{
  "best_metric": 1.0061397552490234,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.010664960273022984,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021329920546045967,
      "grad_norm": 0.4889717996120453,
      "learning_rate": 5e-06,
      "loss": 1.1541,
      "step": 1
    },
    {
      "epoch": 0.00021329920546045967,
      "eval_loss": 1.3311876058578491,
      "eval_runtime": 193.5704,
      "eval_samples_per_second": 40.791,
      "eval_steps_per_second": 20.396,
      "step": 1
    },
    {
      "epoch": 0.00042659841092091935,
      "grad_norm": 0.45240214467048645,
      "learning_rate": 1e-05,
      "loss": 1.3002,
      "step": 2
    },
    {
      "epoch": 0.0006398976163813789,
      "grad_norm": 0.4729762077331543,
      "learning_rate": 1.5e-05,
      "loss": 1.2334,
      "step": 3
    },
    {
      "epoch": 0.0008531968218418387,
      "grad_norm": 0.48300838470458984,
      "learning_rate": 2e-05,
      "loss": 1.2363,
      "step": 4
    },
    {
      "epoch": 0.0010664960273022983,
      "grad_norm": 0.46940040588378906,
      "learning_rate": 2.5e-05,
      "loss": 1.156,
      "step": 5
    },
    {
      "epoch": 0.0012797952327627579,
      "grad_norm": 0.4578542709350586,
      "learning_rate": 3e-05,
      "loss": 1.2202,
      "step": 6
    },
    {
      "epoch": 0.0014930944382232176,
      "grad_norm": 0.46893829107284546,
      "learning_rate": 3.5e-05,
      "loss": 1.3289,
      "step": 7
    },
    {
      "epoch": 0.0017063936436836774,
      "grad_norm": 0.4128904938697815,
      "learning_rate": 4e-05,
      "loss": 1.331,
      "step": 8
    },
    {
      "epoch": 0.001919692849144137,
      "grad_norm": 0.5264115929603577,
      "learning_rate": 4.5e-05,
      "loss": 1.2029,
      "step": 9
    },
    {
      "epoch": 0.0021329920546045967,
      "grad_norm": 0.5400672554969788,
      "learning_rate": 5e-05,
      "loss": 1.244,
      "step": 10
    },
    {
      "epoch": 0.002346291260065056,
      "grad_norm": 0.5268250703811646,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.3097,
      "step": 11
    },
    {
      "epoch": 0.0025595904655255157,
      "grad_norm": 0.4096634089946747,
      "learning_rate": 6e-05,
      "loss": 1.1846,
      "step": 12
    },
    {
      "epoch": 0.0027728896709859757,
      "grad_norm": 0.3764404058456421,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.0895,
      "step": 13
    },
    {
      "epoch": 0.0029861888764464353,
      "grad_norm": 0.4485396146774292,
      "learning_rate": 7e-05,
      "loss": 1.1241,
      "step": 14
    },
    {
      "epoch": 0.003199488081906895,
      "grad_norm": 0.3677101731300354,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.05,
      "step": 15
    },
    {
      "epoch": 0.0034127872873673548,
      "grad_norm": 0.31273096799850464,
      "learning_rate": 8e-05,
      "loss": 1.0426,
      "step": 16
    },
    {
      "epoch": 0.0036260864928278143,
      "grad_norm": 0.33157649636268616,
      "learning_rate": 8.5e-05,
      "loss": 1.072,
      "step": 17
    },
    {
      "epoch": 0.003839385698288274,
      "grad_norm": 0.3081548810005188,
      "learning_rate": 9e-05,
      "loss": 1.1552,
      "step": 18
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 0.30431386828422546,
      "learning_rate": 9.5e-05,
      "loss": 1.1341,
      "step": 19
    },
    {
      "epoch": 0.004265984109209193,
      "grad_norm": 0.3565789461135864,
      "learning_rate": 0.0001,
      "loss": 1.2314,
      "step": 20
    },
    {
      "epoch": 0.004479283314669653,
      "grad_norm": 0.30596891045570374,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.0621,
      "step": 21
    },
    {
      "epoch": 0.004692582520130112,
      "grad_norm": 0.3264557719230652,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.0075,
      "step": 22
    },
    {
      "epoch": 0.004905881725590572,
      "grad_norm": 0.2670353055000305,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.8905,
      "step": 23
    },
    {
      "epoch": 0.0051191809310510315,
      "grad_norm": 0.35703352093696594,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1189,
      "step": 24
    },
    {
      "epoch": 0.005332480136511492,
      "grad_norm": 0.32691025733947754,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.9613,
      "step": 25
    },
    {
      "epoch": 0.0055457793419719514,
      "grad_norm": 0.31508925557136536,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.0339,
      "step": 26
    },
    {
      "epoch": 0.005759078547432411,
      "grad_norm": 0.2960086464881897,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.0747,
      "step": 27
    },
    {
      "epoch": 0.0059723777528928705,
      "grad_norm": 0.3089136779308319,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1023,
      "step": 28
    },
    {
      "epoch": 0.00618567695835333,
      "grad_norm": 0.33887767791748047,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.075,
      "step": 29
    },
    {
      "epoch": 0.00639897616381379,
      "grad_norm": 0.3024013042449951,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0643,
      "step": 30
    },
    {
      "epoch": 0.006612275369274249,
      "grad_norm": 0.26423823833465576,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.984,
      "step": 31
    },
    {
      "epoch": 0.0068255745747347095,
      "grad_norm": 0.3321572542190552,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9507,
      "step": 32
    },
    {
      "epoch": 0.007038873780195169,
      "grad_norm": 0.33192047476768494,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.1432,
      "step": 33
    },
    {
      "epoch": 0.007252172985655629,
      "grad_norm": 0.2856525778770447,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.9586,
      "step": 34
    },
    {
      "epoch": 0.007465472191116088,
      "grad_norm": 0.3510894775390625,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0734,
      "step": 35
    },
    {
      "epoch": 0.007678771396576548,
      "grad_norm": 0.3441113531589508,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1277,
      "step": 36
    },
    {
      "epoch": 0.007892070602037008,
      "grad_norm": 0.33906152844429016,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.946,
      "step": 37
    },
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 0.2947957217693329,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9868,
      "step": 38
    },
    {
      "epoch": 0.008318669012957927,
      "grad_norm": 0.3095934987068176,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.1242,
      "step": 39
    },
    {
      "epoch": 0.008531968218418387,
      "grad_norm": 0.29008540511131287,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0002,
      "step": 40
    },
    {
      "epoch": 0.008745267423878846,
      "grad_norm": 0.3008119761943817,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.9385,
      "step": 41
    },
    {
      "epoch": 0.008958566629339306,
      "grad_norm": 0.3274795114994049,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.1308,
      "step": 42
    },
    {
      "epoch": 0.009171865834799765,
      "grad_norm": 0.30111584067344666,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.8305,
      "step": 43
    },
    {
      "epoch": 0.009385165040260225,
      "grad_norm": 0.32425105571746826,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0669,
      "step": 44
    },
    {
      "epoch": 0.009598464245720684,
      "grad_norm": 0.3228484094142914,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.0983,
      "step": 45
    },
    {
      "epoch": 0.009811763451181144,
      "grad_norm": 0.31862518191337585,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.0798,
      "step": 46
    },
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 0.31603214144706726,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.0202,
      "step": 47
    },
    {
      "epoch": 0.010238361862102063,
      "grad_norm": 0.34538108110427856,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.0098,
      "step": 48
    },
    {
      "epoch": 0.010451661067562523,
      "grad_norm": 0.3631366491317749,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.0367,
      "step": 49
    },
    {
      "epoch": 0.010664960273022984,
      "grad_norm": 0.47178760170936584,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9188,
      "step": 50
    },
    {
      "epoch": 0.010664960273022984,
      "eval_loss": 1.0061397552490234,
      "eval_runtime": 195.5718,
      "eval_samples_per_second": 40.374,
      "eval_steps_per_second": 20.187,
      "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": 1254629342969856.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}