{
  "best_metric": 0.21203623712062836,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.27229407760381213,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010891763104152484,
      "grad_norm": 28.75968360900879,
      "learning_rate": 5e-05,
      "loss": 12.5864,
      "step": 1
    },
    {
      "epoch": 0.010891763104152484,
      "eval_loss": 12.764678001403809,
      "eval_runtime": 12.7735,
      "eval_samples_per_second": 48.46,
      "eval_steps_per_second": 6.106,
      "step": 1
    },
    {
      "epoch": 0.021783526208304968,
      "grad_norm": 28.662094116210938,
      "learning_rate": 0.0001,
      "loss": 12.7415,
      "step": 2
    },
    {
      "epoch": 0.03267528931245745,
      "grad_norm": 29.574182510375977,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.8154,
      "step": 3
    },
    {
      "epoch": 0.043567052416609936,
      "grad_norm": 17.31101417541504,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.6392,
      "step": 4
    },
    {
      "epoch": 0.05445881552076242,
      "grad_norm": 13.541991233825684,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.1811,
      "step": 5
    },
    {
      "epoch": 0.0653505786249149,
      "grad_norm": 11.794838905334473,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.5217,
      "step": 6
    },
    {
      "epoch": 0.0762423417290674,
      "grad_norm": 7.424805641174316,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.5871,
      "step": 7
    },
    {
      "epoch": 0.08713410483321987,
      "grad_norm": 6.943188190460205,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0732,
      "step": 8
    },
    {
      "epoch": 0.09802586793737236,
      "grad_norm": 20.18202018737793,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.9517,
      "step": 9
    },
    {
      "epoch": 0.10891763104152484,
      "grad_norm": 8.790501594543457,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.695,
      "step": 10
    },
    {
      "epoch": 0.11980939414567733,
      "grad_norm": 3.5396814346313477,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.6084,
      "step": 11
    },
    {
      "epoch": 0.1307011572498298,
      "grad_norm": 2.165926456451416,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6215,
      "step": 12
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 1.313301682472229,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.5894,
      "step": 13
    },
    {
      "epoch": 0.1524846834581348,
      "grad_norm": 1.1743314266204834,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5612,
      "step": 14
    },
    {
      "epoch": 0.16337644656228728,
      "grad_norm": 1.1539360284805298,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5283,
      "step": 15
    },
    {
      "epoch": 0.17426820966643974,
      "grad_norm": 1.2591698169708252,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5093,
      "step": 16
    },
    {
      "epoch": 0.18515997277059223,
      "grad_norm": 2.5328752994537354,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4869,
      "step": 17
    },
    {
      "epoch": 0.19605173587474473,
      "grad_norm": 2.8118677139282227,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4226,
      "step": 18
    },
    {
      "epoch": 0.20694349897889722,
      "grad_norm": 3.584213972091675,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.3765,
      "step": 19
    },
    {
      "epoch": 0.21783526208304968,
      "grad_norm": 4.752110004425049,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3473,
      "step": 20
    },
    {
      "epoch": 0.22872702518720217,
      "grad_norm": 2.8016960620880127,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3038,
      "step": 21
    },
    {
      "epoch": 0.23961878829135466,
      "grad_norm": 2.771104574203491,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3159,
      "step": 22
    },
    {
      "epoch": 0.25051055139550715,
      "grad_norm": 2.1360843181610107,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.2692,
      "step": 23
    },
    {
      "epoch": 0.2614023144996596,
      "grad_norm": 1.6023329496383667,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.2478,
      "step": 24
    },
    {
      "epoch": 0.27229407760381213,
      "grad_norm": 1.636376142501831,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.1794,
      "step": 25
    },
    {
      "epoch": 0.27229407760381213,
      "eval_loss": 0.21203623712062836,
      "eval_runtime": 12.7659,
      "eval_samples_per_second": 48.488,
      "eval_steps_per_second": 6.11,
      "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": 8.1240447254528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}