{
  "best_metric": 2.6144490242004395,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.8213552361396304,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.6311900019645691,
      "learning_rate": 5e-05,
      "loss": 2.2234,
      "step": 1
    },
    {
      "epoch": 0.03285420944558522,
      "eval_loss": 2.9316341876983643,
      "eval_runtime": 5.9386,
      "eval_samples_per_second": 34.52,
      "eval_steps_per_second": 4.378,
      "step": 1
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.9081849455833435,
      "learning_rate": 0.0001,
      "loss": 2.5157,
      "step": 2
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.875443160533905,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.9443,
      "step": 3
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.681532084941864,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.8083,
      "step": 4
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.7546427249908447,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.7923,
      "step": 5
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.7163383960723877,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.6759,
      "step": 6
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 0.7841737866401672,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.7357,
      "step": 7
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 0.5721498131752014,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1194,
      "step": 8
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.5235785245895386,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.3936,
      "step": 9
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.5043471455574036,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.5788,
      "step": 10
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.49539726972579956,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.6342,
      "step": 11
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 0.5420206189155579,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.6928,
      "step": 12
    },
    {
      "epoch": 0.4271047227926078,
      "grad_norm": 0.5541395545005798,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.7383,
      "step": 13
    },
    {
      "epoch": 0.459958932238193,
      "grad_norm": 0.6163436770439148,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6837,
      "step": 14
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 0.9190883636474609,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.7666,
      "step": 15
    },
    {
      "epoch": 0.5256673511293635,
      "grad_norm": 0.38201871514320374,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.1146,
      "step": 16
    },
    {
      "epoch": 0.5585215605749486,
      "grad_norm": 0.48645922541618347,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.5198,
      "step": 17
    },
    {
      "epoch": 0.5913757700205339,
      "grad_norm": 0.4911983609199524,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.5752,
      "step": 18
    },
    {
      "epoch": 0.6242299794661191,
      "grad_norm": 0.5300045609474182,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.6961,
      "step": 19
    },
    {
      "epoch": 0.6570841889117043,
      "grad_norm": 0.5103335380554199,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.5715,
      "step": 20
    },
    {
      "epoch": 0.6899383983572895,
      "grad_norm": 0.5545403361320496,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.5873,
      "step": 21
    },
    {
      "epoch": 0.7227926078028748,
      "grad_norm": 0.6748920679092407,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.6207,
      "step": 22
    },
    {
      "epoch": 0.75564681724846,
      "grad_norm": 0.3921031355857849,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.0321,
      "step": 23
    },
    {
      "epoch": 0.7885010266940452,
      "grad_norm": 0.4426540434360504,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.2132,
      "step": 24
    },
    {
      "epoch": 0.8213552361396304,
      "grad_norm": 0.4701845347881317,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.5561,
      "step": 25
    },
    {
      "epoch": 0.8213552361396304,
      "eval_loss": 2.6144490242004395,
      "eval_runtime": 5.9393,
      "eval_samples_per_second": 34.516,
      "eval_steps_per_second": 4.378,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.822877455843328e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}