{
  "best_metric": 1.1134846210479736,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.026549847338377803,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010619938935351122,
      "grad_norm": 50.445369720458984,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 43.7219,
      "step": 1
    },
    {
      "epoch": 0.0010619938935351122,
      "eval_loss": 1.3181114196777344,
      "eval_runtime": 4.7962,
      "eval_samples_per_second": 10.425,
      "eval_steps_per_second": 2.71,
      "step": 1
    },
    {
      "epoch": 0.0021239877870702245,
      "grad_norm": 22.956039428710938,
      "learning_rate": 6.666666666666667e-05,
      "loss": 40.9591,
      "step": 2
    },
    {
      "epoch": 0.0031859816806053365,
      "grad_norm": 66.04405975341797,
      "learning_rate": 0.0001,
      "loss": 70.2201,
      "step": 3
    },
    {
      "epoch": 0.004247975574140449,
      "grad_norm": 46.3990592956543,
      "learning_rate": 9.99571699711836e-05,
      "loss": 51.5672,
      "step": 4
    },
    {
      "epoch": 0.005309969467675561,
      "grad_norm": 30.05483055114746,
      "learning_rate": 9.982876141412856e-05,
      "loss": 43.201,
      "step": 5
    },
    {
      "epoch": 0.006371963361210673,
      "grad_norm": 24.478403091430664,
      "learning_rate": 9.961501876182148e-05,
      "loss": 38.8057,
      "step": 6
    },
    {
      "epoch": 0.007433957254745785,
      "grad_norm": 24.022966384887695,
      "learning_rate": 9.931634888554937e-05,
      "loss": 37.9515,
      "step": 7
    },
    {
      "epoch": 0.008495951148280898,
      "grad_norm": 21.067651748657227,
      "learning_rate": 9.893332032039701e-05,
      "loss": 41.8724,
      "step": 8
    },
    {
      "epoch": 0.009557945041816009,
      "grad_norm": 17.71038818359375,
      "learning_rate": 9.846666218300807e-05,
      "loss": 38.8532,
      "step": 9
    },
    {
      "epoch": 0.010619938935351122,
      "grad_norm": 23.2802791595459,
      "learning_rate": 9.791726278367022e-05,
      "loss": 44.3834,
      "step": 10
    },
    {
      "epoch": 0.011681932828886235,
      "grad_norm": 25.220415115356445,
      "learning_rate": 9.728616793536588e-05,
      "loss": 43.2465,
      "step": 11
    },
    {
      "epoch": 0.012743926722421346,
      "grad_norm": 30.065141677856445,
      "learning_rate": 9.657457896300791e-05,
      "loss": 42.4665,
      "step": 12
    },
    {
      "epoch": 0.013805920615956459,
      "grad_norm": 47.5212287902832,
      "learning_rate": 9.578385041664925e-05,
      "loss": 50.1018,
      "step": 13
    },
    {
      "epoch": 0.01486791450949157,
      "grad_norm": 34.7642936706543,
      "learning_rate": 9.491548749301997e-05,
      "loss": 40.72,
      "step": 14
    },
    {
      "epoch": 0.01592990840302668,
      "grad_norm": 23.62519073486328,
      "learning_rate": 9.397114317029975e-05,
      "loss": 42.3325,
      "step": 15
    },
    {
      "epoch": 0.016991902296561796,
      "grad_norm": 42.359012603759766,
      "learning_rate": 9.295261506157986e-05,
      "loss": 54.7568,
      "step": 16
    },
    {
      "epoch": 0.018053896190096907,
      "grad_norm": 21.744274139404297,
      "learning_rate": 9.186184199300464e-05,
      "loss": 36.6027,
      "step": 17
    },
    {
      "epoch": 0.019115890083632018,
      "grad_norm": 17.517501831054688,
      "learning_rate": 9.070090031310558e-05,
      "loss": 33.6735,
      "step": 18
    },
    {
      "epoch": 0.020177883977167133,
      "grad_norm": 13.376629829406738,
      "learning_rate": 8.947199994035401e-05,
      "loss": 34.858,
      "step": 19
    },
    {
      "epoch": 0.021239877870702244,
      "grad_norm": 16.480670928955078,
      "learning_rate": 8.817748015645558e-05,
      "loss": 35.9226,
      "step": 20
    },
    {
      "epoch": 0.022301871764237355,
      "grad_norm": 14.814435958862305,
      "learning_rate": 8.681980515339464e-05,
      "loss": 36.5462,
      "step": 21
    },
    {
      "epoch": 0.02336386565777247,
      "grad_norm": 15.242733001708984,
      "learning_rate": 8.540155934270471e-05,
      "loss": 38.7139,
      "step": 22
    },
    {
      "epoch": 0.02442585955130758,
      "grad_norm": 16.00188636779785,
      "learning_rate": 8.392544243589427e-05,
      "loss": 39.0224,
      "step": 23
    },
    {
      "epoch": 0.025487853444842692,
      "grad_norm": 16.244796752929688,
      "learning_rate": 8.239426430539243e-05,
      "loss": 38.5783,
      "step": 24
    },
    {
      "epoch": 0.026549847338377803,
      "grad_norm": 26.823301315307617,
      "learning_rate": 8.081093963579707e-05,
      "loss": 38.7784,
      "step": 25
    },
    {
      "epoch": 0.026549847338377803,
      "eval_loss": 1.1134846210479736,
      "eval_runtime": 5.1844,
      "eval_samples_per_second": 9.644,
      "eval_steps_per_second": 2.508,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 6.017220982551347e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}