{
  "best_metric": 0.704846203327179,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0285714285714285,
  "eval_steps": 10,
  "global_step": 53,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.3966389298439026,
      "learning_rate": 1e-05,
      "loss": 0.9692,
      "step": 1
    },
    {
      "epoch": 0.05714285714285714,
      "eval_loss": 1.0108790397644043,
      "eval_runtime": 2.0492,
      "eval_samples_per_second": 7.32,
      "eval_steps_per_second": 1.952,
      "step": 1
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.3902052640914917,
      "learning_rate": 2e-05,
      "loss": 0.9505,
      "step": 2
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3335510790348053,
      "learning_rate": 3e-05,
      "loss": 1.0194,
      "step": 3
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.36140090227127075,
      "learning_rate": 4e-05,
      "loss": 0.9429,
      "step": 4
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.375689297914505,
      "learning_rate": 5e-05,
      "loss": 1.0009,
      "step": 5
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3948005139827728,
      "learning_rate": 6e-05,
      "loss": 0.8756,
      "step": 6
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4350300133228302,
      "learning_rate": 7e-05,
      "loss": 1.0427,
      "step": 7
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.36623847484588623,
      "learning_rate": 8e-05,
      "loss": 0.9048,
      "step": 8
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3320309817790985,
      "learning_rate": 9e-05,
      "loss": 0.8974,
      "step": 9
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.32206276059150696,
      "learning_rate": 0.0001,
      "loss": 0.8542,
      "step": 10
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 0.9411152005195618,
      "eval_runtime": 2.0837,
      "eval_samples_per_second": 7.199,
      "eval_steps_per_second": 1.92,
      "step": 10
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.33402150869369507,
      "learning_rate": 9.986661418317759e-05,
      "loss": 0.8844,
      "step": 11
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.31261247396469116,
      "learning_rate": 9.946716840375551e-05,
      "loss": 0.8441,
      "step": 12
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 0.33552902936935425,
      "learning_rate": 9.880379387779637e-05,
      "loss": 0.8498,
      "step": 13
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.33501139283180237,
      "learning_rate": 9.78800299954203e-05,
      "loss": 0.8905,
      "step": 14
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.33641278743743896,
      "learning_rate": 9.67008054366274e-05,
      "loss": 0.8753,
      "step": 15
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.3439123332500458,
      "learning_rate": 9.527241187465734e-05,
      "loss": 0.8292,
      "step": 16
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 0.3387420177459717,
      "learning_rate": 9.360247040719039e-05,
      "loss": 0.8047,
      "step": 17
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 0.35765647888183594,
      "learning_rate": 9.16998908944939e-05,
      "loss": 0.8683,
      "step": 18
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.33680498600006104,
      "learning_rate": 8.957482442146272e-05,
      "loss": 0.7337,
      "step": 19
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.32664304971694946,
      "learning_rate": 8.72386091371891e-05,
      "loss": 0.7241,
      "step": 20
    },
    {
      "epoch": 1.1428571428571428,
      "eval_loss": 0.784389317035675,
      "eval_runtime": 2.086,
      "eval_samples_per_second": 7.191,
      "eval_steps_per_second": 1.918,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.35325202345848083,
      "learning_rate": 8.47037097610317e-05,
      "loss": 0.7718,
      "step": 21
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.30332982540130615,
      "learning_rate": 8.198365107794457e-05,
      "loss": 0.6796,
      "step": 22
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 0.365041047334671,
      "learning_rate": 7.909294577789766e-05,
      "loss": 0.7059,
      "step": 23
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 0.2987039387226105,
      "learning_rate": 7.604701702439651e-05,
      "loss": 0.6808,
      "step": 24
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3556249141693115,
      "learning_rate": 7.286211616523193e-05,
      "loss": 0.7061,
      "step": 25
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 0.37903037667274475,
      "learning_rate": 6.95552360245078e-05,
      "loss": 0.736,
      "step": 26
    },
    {
      "epoch": 1.5428571428571427,
      "grad_norm": 0.36219486594200134,
      "learning_rate": 6.614402023857232e-05,
      "loss": 0.7291,
      "step": 27
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.31098002195358276,
      "learning_rate": 6.264666911958404e-05,
      "loss": 0.6836,
      "step": 28
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 0.3429687023162842,
      "learning_rate": 5.908184254897182e-05,
      "loss": 0.7052,
      "step": 29
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.3376871645450592,
      "learning_rate": 5.546856041889373e-05,
      "loss": 0.678,
      "step": 30
    },
    {
      "epoch": 1.7142857142857144,
      "eval_loss": 0.7271688580513,
      "eval_runtime": 2.0876,
      "eval_samples_per_second": 7.185,
      "eval_steps_per_second": 1.916,
      "step": 30
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.29218417406082153,
      "learning_rate": 5.182610115288295e-05,
      "loss": 0.6656,
      "step": 31
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 0.30864810943603516,
      "learning_rate": 4.817389884711705e-05,
      "loss": 0.7106,
      "step": 32
    },
    {
      "epoch": 1.8857142857142857,
      "grad_norm": 0.3442583382129669,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 0.7097,
      "step": 33
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.32284116744995117,
      "learning_rate": 4.0918157451028185e-05,
      "loss": 0.7053,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2941528856754303,
      "learning_rate": 3.735333088041596e-05,
      "loss": 0.5891,
      "step": 35
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 0.3290832042694092,
      "learning_rate": 3.38559797614277e-05,
      "loss": 0.7012,
      "step": 36
    },
    {
      "epoch": 2.1142857142857143,
      "grad_norm": 0.29661279916763306,
      "learning_rate": 3.0444763975492208e-05,
      "loss": 0.6034,
      "step": 37
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.30858200788497925,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 0.6878,
      "step": 38
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 0.2789033353328705,
      "learning_rate": 2.3952982975603496e-05,
      "loss": 0.7019,
      "step": 39
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.2946871519088745,
      "learning_rate": 2.090705422210237e-05,
      "loss": 0.6679,
      "step": 40
    },
    {
      "epoch": 2.2857142857142856,
      "eval_loss": 0.7075809240341187,
      "eval_runtime": 2.087,
      "eval_samples_per_second": 7.187,
      "eval_steps_per_second": 1.917,
      "step": 40
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.30310121178627014,
      "learning_rate": 1.801634892205545e-05,
      "loss": 0.633,
      "step": 41
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.3069086968898773,
      "learning_rate": 1.5296290238968303e-05,
      "loss": 0.7029,
      "step": 42
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 0.2964320182800293,
      "learning_rate": 1.2761390862810907e-05,
      "loss": 0.7385,
      "step": 43
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.28013864159584045,
      "learning_rate": 1.0425175578537299e-05,
      "loss": 0.6347,
      "step": 44
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.29106035828590393,
      "learning_rate": 8.30010910550611e-06,
      "loss": 0.6346,
      "step": 45
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 0.28448185324668884,
      "learning_rate": 6.397529592809614e-06,
      "loss": 0.6148,
      "step": 46
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.2868902087211609,
      "learning_rate": 4.727588125342669e-06,
      "loss": 0.5431,
      "step": 47
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 0.28776589035987854,
      "learning_rate": 3.299194563372604e-06,
      "loss": 0.6296,
      "step": 48
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.2633899748325348,
      "learning_rate": 2.1199700045797077e-06,
      "loss": 0.6345,
      "step": 49
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.2832770049571991,
      "learning_rate": 1.196206122203647e-06,
      "loss": 0.6468,
      "step": 50
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 0.704846203327179,
      "eval_runtime": 2.0892,
      "eval_samples_per_second": 7.18,
      "eval_steps_per_second": 1.915,
      "step": 50
    },
    {
      "epoch": 2.914285714285714,
      "grad_norm": 0.2923741936683655,
      "learning_rate": 5.328315962444874e-07,
      "loss": 0.6826,
      "step": 51
    },
    {
      "epoch": 2.9714285714285715,
      "grad_norm": 0.29426372051239014,
      "learning_rate": 1.333858168224178e-07,
      "loss": 0.6043,
      "step": 52
    },
    {
      "epoch": 3.0285714285714285,
      "grad_norm": 0.29648035764694214,
      "learning_rate": 0.0,
      "loss": 0.6566,
      "step": 53
    }
  ],
  "logging_steps": 1,
  "max_steps": 53,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0398259709149184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}