{
  "best_metric": 0.0023557350505143404,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.04589261128958238,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018357044515832951,
      "grad_norm": 0.28899645805358887,
      "learning_rate": 5e-05,
      "loss": 0.1753,
      "step": 1
    },
    {
      "epoch": 0.0018357044515832951,
      "eval_loss": 0.38865751028060913,
      "eval_runtime": 41.8533,
      "eval_samples_per_second": 87.687,
      "eval_steps_per_second": 10.967,
      "step": 1
    },
    {
      "epoch": 0.0036714089031665903,
      "grad_norm": 0.42189186811447144,
      "learning_rate": 0.0001,
      "loss": 0.248,
      "step": 2
    },
    {
      "epoch": 0.005507113354749885,
      "grad_norm": 0.6095991730690002,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.2594,
      "step": 3
    },
    {
      "epoch": 0.0073428178063331805,
      "grad_norm": 0.7982662916183472,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2334,
      "step": 4
    },
    {
      "epoch": 0.009178522257916476,
      "grad_norm": 0.7745523452758789,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1986,
      "step": 5
    },
    {
      "epoch": 0.01101422670949977,
      "grad_norm": 0.9550557136535645,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.1547,
      "step": 6
    },
    {
      "epoch": 0.012849931161083065,
      "grad_norm": 1.1150208711624146,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0993,
      "step": 7
    },
    {
      "epoch": 0.014685635612666361,
      "grad_norm": 0.5300053358078003,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0317,
      "step": 8
    },
    {
      "epoch": 0.016521340064249657,
      "grad_norm": 0.554506242275238,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0284,
      "step": 9
    },
    {
      "epoch": 0.018357044515832952,
      "grad_norm": 0.22338461875915527,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0165,
      "step": 10
    },
    {
      "epoch": 0.020192748967416244,
      "grad_norm": 0.22608879208564758,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0133,
      "step": 11
    },
    {
      "epoch": 0.02202845341899954,
      "grad_norm": 0.19878767430782318,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.011,
      "step": 12
    },
    {
      "epoch": 0.023864157870582835,
      "grad_norm": 0.21398384869098663,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0085,
      "step": 13
    },
    {
      "epoch": 0.02569986232216613,
      "grad_norm": 0.10816192626953125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0073,
      "step": 14
    },
    {
      "epoch": 0.027535566773749427,
      "grad_norm": 0.08344914764165878,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0035,
      "step": 15
    },
    {
      "epoch": 0.029371271225332722,
      "grad_norm": 0.1762116253376007,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0052,
      "step": 16
    },
    {
      "epoch": 0.031206975676916018,
      "grad_norm": 0.11861647665500641,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0046,
      "step": 17
    },
    {
      "epoch": 0.03304268012849931,
      "grad_norm": 0.07198595255613327,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0042,
      "step": 18
    },
    {
      "epoch": 0.034878384580082605,
      "grad_norm": 0.12151943147182465,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0043,
      "step": 19
    },
    {
      "epoch": 0.036714089031665904,
      "grad_norm": 0.08527624607086182,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0031,
      "step": 20
    },
    {
      "epoch": 0.038549793483249196,
      "grad_norm": 0.11344439536333084,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0052,
      "step": 21
    },
    {
      "epoch": 0.04038549793483249,
      "grad_norm": 0.025957219302654266,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0011,
      "step": 22
    },
    {
      "epoch": 0.04222120238641579,
      "grad_norm": 0.10967632383108139,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0023,
      "step": 23
    },
    {
      "epoch": 0.04405690683799908,
      "grad_norm": 0.027078542858362198,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0015,
      "step": 24
    },
    {
      "epoch": 0.04589261128958238,
      "grad_norm": 0.16326873004436493,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0056,
      "step": 25
    },
    {
      "epoch": 0.04589261128958238,
      "eval_loss": 0.0023557350505143404,
      "eval_runtime": 41.8035,
      "eval_samples_per_second": 87.792,
      "eval_steps_per_second": 10.98,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 5.300992813406618e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}