{
  "best_metric": 1.8223572969436646,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.042034468263976464,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016813787305590584,
      "grad_norm": 9.957021713256836,
      "learning_rate": 2e-05,
      "loss": 2.9782,
      "step": 1
    },
    {
      "epoch": 0.0016813787305590584,
      "eval_loss": 3.21144437789917,
      "eval_runtime": 53.0784,
      "eval_samples_per_second": 18.878,
      "eval_steps_per_second": 2.374,
      "step": 1
    },
    {
      "epoch": 0.003362757461118117,
      "grad_norm": 13.708298683166504,
      "learning_rate": 4e-05,
      "loss": 3.1329,
      "step": 2
    },
    {
      "epoch": 0.005044136191677175,
      "grad_norm": 12.74589729309082,
      "learning_rate": 6e-05,
      "loss": 3.1098,
      "step": 3
    },
    {
      "epoch": 0.006725514922236234,
      "grad_norm": 9.0891752243042,
      "learning_rate": 8e-05,
      "loss": 2.8129,
      "step": 4
    },
    {
      "epoch": 0.008406893652795292,
      "grad_norm": 7.467917442321777,
      "learning_rate": 0.0001,
      "loss": 2.5554,
      "step": 5
    },
    {
      "epoch": 0.01008827238335435,
      "grad_norm": 7.4391961097717285,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2017,
      "step": 6
    },
    {
      "epoch": 0.011769651113913409,
      "grad_norm": 7.036105632781982,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.3765,
      "step": 7
    },
    {
      "epoch": 0.013451029844472467,
      "grad_norm": 11.589292526245117,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.1577,
      "step": 8
    },
    {
      "epoch": 0.015132408575031526,
      "grad_norm": 7.228753566741943,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.9935,
      "step": 9
    },
    {
      "epoch": 0.016813787305590584,
      "grad_norm": 8.207776069641113,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8316,
      "step": 10
    },
    {
      "epoch": 0.018495166036149643,
      "grad_norm": 7.985312461853027,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.8113,
      "step": 11
    },
    {
      "epoch": 0.0201765447667087,
      "grad_norm": 7.26406192779541,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.8366,
      "step": 12
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 6.2105631828308105,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.7943,
      "step": 13
    },
    {
      "epoch": 0.023539302227826818,
      "grad_norm": 8.026552200317383,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8496,
      "step": 14
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 6.089547634124756,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4218,
      "step": 15
    },
    {
      "epoch": 0.026902059688944935,
      "grad_norm": 6.291636943817139,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.4374,
      "step": 16
    },
    {
      "epoch": 0.028583438419503993,
      "grad_norm": 13.020359992980957,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.9619,
      "step": 17
    },
    {
      "epoch": 0.03026481715006305,
      "grad_norm": 7.324967861175537,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7719,
      "step": 18
    },
    {
      "epoch": 0.031946195880622114,
      "grad_norm": 6.144652843475342,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.8435,
      "step": 19
    },
    {
      "epoch": 0.03362757461118117,
      "grad_norm": 4.967810153961182,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4193,
      "step": 20
    },
    {
      "epoch": 0.03530895334174023,
      "grad_norm": 4.567094802856445,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.5105,
      "step": 21
    },
    {
      "epoch": 0.036990332072299285,
      "grad_norm": 4.7514328956604,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6116,
      "step": 22
    },
    {
      "epoch": 0.03867171080285835,
      "grad_norm": 4.926995277404785,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6433,
      "step": 23
    },
    {
      "epoch": 0.0403530895334174,
      "grad_norm": 5.670762538909912,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8285,
      "step": 24
    },
    {
      "epoch": 0.042034468263976464,
      "grad_norm": 4.81981897354126,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5872,
      "step": 25
    },
    {
      "epoch": 0.042034468263976464,
      "eval_loss": 1.8223572969436646,
      "eval_runtime": 53.8519,
      "eval_samples_per_second": 18.607,
      "eval_steps_per_second": 2.34,
      "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": 3.02966221307904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}