{
  "best_metric": 2.900310754776001,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.1205836247437598,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002411672494875196,
      "eval_loss": 3.066455364227295,
      "eval_runtime": 626.091,
      "eval_samples_per_second": 11.155,
      "eval_steps_per_second": 2.789,
      "step": 1
    },
    {
      "epoch": 0.012058362474375979,
      "grad_norm": 26.8266658782959,
      "learning_rate": 0.000105,
      "loss": 34.4762,
      "step": 50
    },
    {
      "epoch": 0.024116724948751958,
      "grad_norm": 17.117137908935547,
      "learning_rate": 0.00021,
      "loss": 27.3809,
      "step": 100
    },
    {
      "epoch": 0.03617508742312794,
      "grad_norm": 19.39618492126465,
      "learning_rate": 0.0002020073509136851,
      "loss": 25.8381,
      "step": 150
    },
    {
      "epoch": 0.048233449897503916,
      "grad_norm": 12.715009689331055,
      "learning_rate": 0.0001792462120245875,
      "loss": 25.3802,
      "step": 200
    },
    {
      "epoch": 0.0602918123718799,
      "grad_norm": 14.577338218688965,
      "learning_rate": 0.00014518176039833445,
      "loss": 25.0877,
      "step": 250
    },
    {
      "epoch": 0.07235017484625587,
      "grad_norm": 16.010438919067383,
      "learning_rate": 0.000105,
      "loss": 24.8455,
      "step": 300
    },
    {
      "epoch": 0.08440853732063186,
      "grad_norm": 14.42565631866455,
      "learning_rate": 6.481823960166558e-05,
      "loss": 24.8311,
      "step": 350
    },
    {
      "epoch": 0.09646689979500783,
      "grad_norm": 13.525891304016113,
      "learning_rate": 3.0753787975412515e-05,
      "loss": 24.5001,
      "step": 400
    },
    {
      "epoch": 0.10852526226938382,
      "grad_norm": 12.025201797485352,
      "learning_rate": 7.992649086314893e-06,
      "loss": 24.4302,
      "step": 450
    },
    {
      "epoch": 0.1205836247437598,
      "grad_norm": 13.995806694030762,
      "learning_rate": 0.0,
      "loss": 24.4398,
      "step": 500
    },
    {
      "epoch": 0.1205836247437598,
      "eval_loss": 2.900310754776001,
      "eval_runtime": 625.5359,
      "eval_samples_per_second": 11.165,
      "eval_steps_per_second": 2.791,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.816288866442936e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}