{
  "best_metric": 0.039619311690330505,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.9133421014175069,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014613473622680112,
      "eval_loss": 1.079929232597351,
      "eval_runtime": 120.3442,
      "eval_samples_per_second": 14.965,
      "eval_steps_per_second": 3.0,
      "step": 1
    },
    {
      "epoch": 0.07306736811340056,
      "grad_norm": 0.8063929677009583,
      "learning_rate": 0.0001068,
      "loss": 0.2017,
      "step": 50
    },
    {
      "epoch": 0.14613473622680112,
      "grad_norm": 0.5706304907798767,
      "learning_rate": 0.0002136,
      "loss": 0.0961,
      "step": 100
    },
    {
      "epoch": 0.21920210434020165,
      "grad_norm": 0.5012636184692383,
      "learning_rate": 0.0002653563934694509,
      "loss": 0.0841,
      "step": 150
    },
    {
      "epoch": 0.29226947245360224,
      "grad_norm": 0.28799599409103394,
      "learning_rate": 0.0002524493709791471,
      "loss": 0.1039,
      "step": 200
    },
    {
      "epoch": 0.3653368405670028,
      "grad_norm": 1.3303046226501465,
      "learning_rate": 0.00022789875528840406,
      "loss": 0.0776,
      "step": 250
    },
    {
      "epoch": 0.4384042086804033,
      "grad_norm": 0.5361071825027466,
      "learning_rate": 0.00019410773171522948,
      "loss": 0.0642,
      "step": 300
    },
    {
      "epoch": 0.5114715767938038,
      "grad_norm": 0.10300945490598679,
      "learning_rate": 0.00015438400108287083,
      "loss": 0.0564,
      "step": 350
    },
    {
      "epoch": 0.5845389449072045,
      "grad_norm": 0.33445683121681213,
      "learning_rate": 0.00011261599891712914,
      "loss": 0.0519,
      "step": 400
    },
    {
      "epoch": 0.657606313020605,
      "grad_norm": 0.13534684479236603,
      "learning_rate": 7.28922682847705e-05,
      "loss": 0.0438,
      "step": 450
    },
    {
      "epoch": 0.7306736811340055,
      "grad_norm": 0.07572776079177856,
      "learning_rate": 3.9101244711595914e-05,
      "loss": 0.0404,
      "step": 500
    },
    {
      "epoch": 0.7306736811340055,
      "eval_loss": 0.039619311690330505,
      "eval_runtime": 119.8958,
      "eval_samples_per_second": 15.021,
      "eval_steps_per_second": 3.011,
      "step": 500
    },
    {
      "epoch": 0.8037410492474061,
      "grad_norm": 0.11217395961284637,
      "learning_rate": 1.45506290208529e-05,
      "loss": 0.0382,
      "step": 550
    },
    {
      "epoch": 0.8768084173608066,
      "grad_norm": 0.057221416383981705,
      "learning_rate": 1.6436065305491224e-06,
      "loss": 0.036,
      "step": 600
    }
  ],
  "logging_steps": 50,
  "max_steps": 625,
  "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": 1.85151356928e+18,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}