{
  "best_metric": 0.9847307801246643,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.04642525533890436,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018570102135561746,
      "grad_norm": 0.47194573283195496,
      "learning_rate": 2e-05,
      "loss": 0.9088,
      "step": 1
    },
    {
      "epoch": 0.0018570102135561746,
      "eval_loss": 1.4481745958328247,
      "eval_runtime": 33.9472,
      "eval_samples_per_second": 26.718,
      "eval_steps_per_second": 3.358,
      "step": 1
    },
    {
      "epoch": 0.003714020427112349,
      "grad_norm": 0.49819284677505493,
      "learning_rate": 4e-05,
      "loss": 1.0455,
      "step": 2
    },
    {
      "epoch": 0.005571030640668524,
      "grad_norm": 0.5030564069747925,
      "learning_rate": 6e-05,
      "loss": 1.0282,
      "step": 3
    },
    {
      "epoch": 0.007428040854224698,
      "grad_norm": 0.517458975315094,
      "learning_rate": 8e-05,
      "loss": 1.068,
      "step": 4
    },
    {
      "epoch": 0.009285051067780872,
      "grad_norm": 0.5054612755775452,
      "learning_rate": 0.0001,
      "loss": 1.0048,
      "step": 5
    },
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 0.5697569251060486,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9944,
      "step": 6
    },
    {
      "epoch": 0.012999071494893221,
      "grad_norm": 0.34437480568885803,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8405,
      "step": 7
    },
    {
      "epoch": 0.014856081708449397,
      "grad_norm": 0.3470451533794403,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9741,
      "step": 8
    },
    {
      "epoch": 0.016713091922005572,
      "grad_norm": 0.42112597823143005,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9068,
      "step": 9
    },
    {
      "epoch": 0.018570102135561744,
      "grad_norm": 0.3286053538322449,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8783,
      "step": 10
    },
    {
      "epoch": 0.02042711234911792,
      "grad_norm": 0.33338308334350586,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0133,
      "step": 11
    },
    {
      "epoch": 0.022284122562674095,
      "grad_norm": 0.32179006934165955,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9356,
      "step": 12
    },
    {
      "epoch": 0.02414113277623027,
      "grad_norm": 0.3683066964149475,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.0115,
      "step": 13
    },
    {
      "epoch": 0.025998142989786442,
      "grad_norm": 0.3992704749107361,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1339,
      "step": 14
    },
    {
      "epoch": 0.027855153203342618,
      "grad_norm": 0.3542136549949646,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.947,
      "step": 15
    },
    {
      "epoch": 0.029712163416898793,
      "grad_norm": 0.3169046938419342,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.968,
      "step": 16
    },
    {
      "epoch": 0.031569173630454965,
      "grad_norm": 0.34261420369148254,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.0831,
      "step": 17
    },
    {
      "epoch": 0.033426183844011144,
      "grad_norm": 0.3178490698337555,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.0376,
      "step": 18
    },
    {
      "epoch": 0.035283194057567316,
      "grad_norm": 0.31970250606536865,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.1084,
      "step": 19
    },
    {
      "epoch": 0.03714020427112349,
      "grad_norm": 0.3838099241256714,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9999,
      "step": 20
    },
    {
      "epoch": 0.03899721448467967,
      "grad_norm": 0.3478296995162964,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1841,
      "step": 21
    },
    {
      "epoch": 0.04085422469823584,
      "grad_norm": 0.32308429479599,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9192,
      "step": 22
    },
    {
      "epoch": 0.04271123491179202,
      "grad_norm": 0.38567522168159485,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0335,
      "step": 23
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 0.3469473719596863,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0549,
      "step": 24
    },
    {
      "epoch": 0.04642525533890436,
      "grad_norm": 0.3284890353679657,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0766,
      "step": 25
    },
    {
      "epoch": 0.04642525533890436,
      "eval_loss": 0.9847307801246643,
      "eval_runtime": 34.4301,
      "eval_samples_per_second": 26.343,
      "eval_steps_per_second": 3.311,
      "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": 5,
        "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": 1.884002508079104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}