{
  "best_metric": 1.7303435802459717,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.28328611898017,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 0.33666571974754333,
      "learning_rate": 2e-05,
      "loss": 1.7268,
      "step": 1
    },
    {
      "epoch": 0.0113314447592068,
      "eval_loss": 1.8638567924499512,
      "eval_runtime": 1.406,
      "eval_samples_per_second": 105.975,
      "eval_steps_per_second": 13.514,
      "step": 1
    },
    {
      "epoch": 0.0226628895184136,
      "grad_norm": 0.34872931241989136,
      "learning_rate": 4e-05,
      "loss": 1.7041,
      "step": 2
    },
    {
      "epoch": 0.0339943342776204,
      "grad_norm": 0.32515448331832886,
      "learning_rate": 6e-05,
      "loss": 1.6899,
      "step": 3
    },
    {
      "epoch": 0.0453257790368272,
      "grad_norm": 0.39392638206481934,
      "learning_rate": 8e-05,
      "loss": 1.771,
      "step": 4
    },
    {
      "epoch": 0.056657223796033995,
      "grad_norm": 0.32078537344932556,
      "learning_rate": 0.0001,
      "loss": 1.7116,
      "step": 5
    },
    {
      "epoch": 0.0679886685552408,
      "grad_norm": 0.3297460675239563,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.7778,
      "step": 6
    },
    {
      "epoch": 0.07932011331444759,
      "grad_norm": 0.2444680780172348,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6437,
      "step": 7
    },
    {
      "epoch": 0.0906515580736544,
      "grad_norm": 0.25901690125465393,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7814,
      "step": 8
    },
    {
      "epoch": 0.10198300283286119,
      "grad_norm": 0.2574293911457062,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.76,
      "step": 9
    },
    {
      "epoch": 0.11331444759206799,
      "grad_norm": 0.22195817530155182,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.7619,
      "step": 10
    },
    {
      "epoch": 0.12464589235127478,
      "grad_norm": 0.25635820627212524,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7202,
      "step": 11
    },
    {
      "epoch": 0.1359773371104816,
      "grad_norm": 0.25191575288772583,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7746,
      "step": 12
    },
    {
      "epoch": 0.14730878186968838,
      "grad_norm": 0.2583252489566803,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.7015,
      "step": 13
    },
    {
      "epoch": 0.15864022662889518,
      "grad_norm": 0.2822646498680115,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7986,
      "step": 14
    },
    {
      "epoch": 0.16997167138810199,
      "grad_norm": 0.27486222982406616,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7921,
      "step": 15
    },
    {
      "epoch": 0.1813031161473088,
      "grad_norm": 0.2897486090660095,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.68,
      "step": 16
    },
    {
      "epoch": 0.19263456090651557,
      "grad_norm": 0.2819582223892212,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.9592,
      "step": 17
    },
    {
      "epoch": 0.20396600566572237,
      "grad_norm": 0.3186541199684143,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8444,
      "step": 18
    },
    {
      "epoch": 0.21529745042492918,
      "grad_norm": 0.32152897119522095,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.9009,
      "step": 19
    },
    {
      "epoch": 0.22662889518413598,
      "grad_norm": 0.33151161670684814,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8928,
      "step": 20
    },
    {
      "epoch": 0.23796033994334279,
      "grad_norm": 0.33403679728507996,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9462,
      "step": 21
    },
    {
      "epoch": 0.24929178470254956,
      "grad_norm": 0.37862664461135864,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.8694,
      "step": 22
    },
    {
      "epoch": 0.26062322946175637,
      "grad_norm": 0.20253029465675354,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6101,
      "step": 23
    },
    {
      "epoch": 0.2719546742209632,
      "grad_norm": 0.18948052823543549,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6217,
      "step": 24
    },
    {
      "epoch": 0.28328611898017,
      "grad_norm": 0.19364707171916962,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5635,
      "step": 25
    },
    {
      "epoch": 0.28328611898017,
      "eval_loss": 1.7303435802459717,
      "eval_runtime": 1.3795,
      "eval_samples_per_second": 108.007,
      "eval_steps_per_second": 13.773,
      "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": 618044011315200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}