{
  "best_metric": 0.508665144443512,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.023515579071134628,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009406231628453851,
      "grad_norm": 9.278800010681152,
      "learning_rate": 5e-05,
      "loss": 1.0665,
      "step": 1
    },
    {
      "epoch": 0.0009406231628453851,
      "eval_loss": 1.3672261238098145,
      "eval_runtime": 357.1528,
      "eval_samples_per_second": 20.053,
      "eval_steps_per_second": 2.509,
      "step": 1
    },
    {
      "epoch": 0.0018812463256907702,
      "grad_norm": 9.454571723937988,
      "learning_rate": 0.0001,
      "loss": 1.1219,
      "step": 2
    },
    {
      "epoch": 0.0028218694885361554,
      "grad_norm": 3.554928779602051,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.8661,
      "step": 3
    },
    {
      "epoch": 0.0037624926513815404,
      "grad_norm": 8.035897254943848,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.864,
      "step": 4
    },
    {
      "epoch": 0.004703115814226925,
      "grad_norm": 1.914970874786377,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.6396,
      "step": 5
    },
    {
      "epoch": 0.005643738977072311,
      "grad_norm": 1.7866945266723633,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.6384,
      "step": 6
    },
    {
      "epoch": 0.006584362139917695,
      "grad_norm": 1.609639286994934,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.6046,
      "step": 7
    },
    {
      "epoch": 0.007524985302763081,
      "grad_norm": 1.64801824092865,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5935,
      "step": 8
    },
    {
      "epoch": 0.008465608465608466,
      "grad_norm": 1.6314135789871216,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6356,
      "step": 9
    },
    {
      "epoch": 0.00940623162845385,
      "grad_norm": 1.4281870126724243,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5954,
      "step": 10
    },
    {
      "epoch": 0.010346854791299235,
      "grad_norm": 1.4309544563293457,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5273,
      "step": 11
    },
    {
      "epoch": 0.011287477954144622,
      "grad_norm": 1.7998919486999512,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5526,
      "step": 12
    },
    {
      "epoch": 0.012228101116990006,
      "grad_norm": 1.4200043678283691,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.5697,
      "step": 13
    },
    {
      "epoch": 0.01316872427983539,
      "grad_norm": 1.0186113119125366,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5172,
      "step": 14
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 1.1935527324676514,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5575,
      "step": 15
    },
    {
      "epoch": 0.015049970605526162,
      "grad_norm": 1.1734066009521484,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5612,
      "step": 16
    },
    {
      "epoch": 0.015990593768371548,
      "grad_norm": 1.0498110055923462,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5582,
      "step": 17
    },
    {
      "epoch": 0.016931216931216932,
      "grad_norm": 1.109232783317566,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5777,
      "step": 18
    },
    {
      "epoch": 0.017871840094062317,
      "grad_norm": 1.086000919342041,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5232,
      "step": 19
    },
    {
      "epoch": 0.0188124632569077,
      "grad_norm": 1.0963627099990845,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4975,
      "step": 20
    },
    {
      "epoch": 0.019753086419753086,
      "grad_norm": 1.3133893013000488,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.5509,
      "step": 21
    },
    {
      "epoch": 0.02069370958259847,
      "grad_norm": 1.212689995765686,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5253,
      "step": 22
    },
    {
      "epoch": 0.021634332745443855,
      "grad_norm": 1.15071439743042,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5126,
      "step": 23
    },
    {
      "epoch": 0.022574955908289243,
      "grad_norm": 1.2678868770599365,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.516,
      "step": 24
    },
    {
      "epoch": 0.023515579071134628,
      "grad_norm": 1.3126546144485474,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4731,
      "step": 25
    },
    {
      "epoch": 0.023515579071134628,
      "eval_loss": 0.508665144443512,
      "eval_runtime": 315.5228,
      "eval_samples_per_second": 22.699,
      "eval_steps_per_second": 2.84,
      "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": 2.829012279754752e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}