{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.2118003025718609,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024205748865355523,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 8047.6182,
      "step": 1
    },
    {
      "epoch": 0.024205748865355523,
      "eval_loss": NaN,
      "eval_runtime": 1.5106,
      "eval_samples_per_second": 33.099,
      "eval_steps_per_second": 8.606,
      "step": 1
    },
    {
      "epoch": 0.048411497730711045,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.07261724659606657,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.09682299546142209,
      "grad_norm": NaN,
      "learning_rate": 9.99571699711836e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.12102874432677761,
      "grad_norm": NaN,
      "learning_rate": 9.982876141412856e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.14523449319213314,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.16944024205748864,
      "grad_norm": NaN,
      "learning_rate": 9.931634888554937e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.19364599092284418,
      "grad_norm": NaN,
      "learning_rate": 9.893332032039701e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.2178517397881997,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.24205748865355523,
      "grad_norm": NaN,
      "learning_rate": 9.791726278367022e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.26626323751891073,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.29046898638426627,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.3146747352496218,
      "grad_norm": NaN,
      "learning_rate": 9.578385041664925e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.3388804841149773,
      "grad_norm": NaN,
      "learning_rate": 9.491548749301997e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.3630862329803328,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.38729198184568836,
      "grad_norm": NaN,
      "learning_rate": 9.295261506157986e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.4114977307110439,
      "grad_norm": NaN,
      "learning_rate": 9.186184199300464e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.4357034795763994,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.4599092284417549,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.48411497730711045,
      "grad_norm": NaN,
      "learning_rate": 8.817748015645558e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.5083207261724659,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.5325264750378215,
      "grad_norm": NaN,
      "learning_rate": 8.540155934270471e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.556732223903177,
      "grad_norm": NaN,
      "learning_rate": 8.392544243589427e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.5809379727685325,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.6051437216338881,
      "grad_norm": NaN,
      "learning_rate": 8.081093963579707e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.6051437216338881,
      "eval_loss": NaN,
      "eval_runtime": 0.6667,
      "eval_samples_per_second": 74.996,
      "eval_steps_per_second": 19.499,
      "step": 25
    },
    {
      "epoch": 0.6293494704992436,
      "grad_norm": NaN,
      "learning_rate": 7.917848237560709e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.653555219364599,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.6777609682299546,
      "grad_norm": NaN,
      "learning_rate": 7.577868759557654e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.7019667170953101,
      "grad_norm": NaN,
      "learning_rate": 7.401782177833148e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.7261724659606656,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.7503782148260212,
      "grad_norm": NaN,
      "learning_rate": 7.03909064496551e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.7745839636913767,
      "grad_norm": NaN,
      "learning_rate": 6.853176097769229e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.7987897125567323,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.8229954614220878,
      "grad_norm": NaN,
      "learning_rate": 6.473978262721463e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.8472012102874432,
      "grad_norm": NaN,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.8714069591527988,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.8956127080181543,
      "grad_norm": NaN,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.9198184568835098,
      "grad_norm": NaN,
      "learning_rate": 5.696287243144013e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.9440242057488654,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.9682299546142209,
      "grad_norm": NaN,
      "learning_rate": 5.303712756855988e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.9924357034795764,
      "grad_norm": NaN,
      "learning_rate": 5.107799157635538e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 1.0181543116490166,
      "grad_norm": NaN,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 1.0423600605143721,
      "grad_norm": NaN,
      "learning_rate": 4.718583200498814e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 1.0665658093797277,
      "grad_norm": NaN,
      "learning_rate": 4.526021737278538e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 1.0907715582450832,
      "grad_norm": NaN,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 1.1149773071104387,
      "grad_norm": NaN,
      "learning_rate": 4.146823902230772e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 1.1391830559757943,
      "grad_norm": NaN,
      "learning_rate": 3.960909355034491e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 1.1633888048411498,
      "grad_norm": NaN,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 1.1875945537065054,
      "grad_norm": NaN,
      "learning_rate": 3.598217822166854e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 1.2118003025718609,
      "grad_norm": NaN,
      "learning_rate": 3.422131240442349e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 1.2118003025718609,
      "eval_loss": NaN,
      "eval_runtime": 0.6669,
      "eval_samples_per_second": 74.968,
      "eval_steps_per_second": 19.492,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.104401093707694e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}