{
  "best_metric": 8.605793952941895,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0017435778216901082,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.81192607230036e-05,
      "eval_loss": 9.679449081420898,
      "eval_runtime": 151.0403,
      "eval_samples_per_second": 95.935,
      "eval_steps_per_second": 23.987,
      "step": 1
    },
    {
      "epoch": 0.0001743577821690108,
      "grad_norm": 3.528407573699951,
      "learning_rate": 0.00012,
      "loss": 10.4592,
      "step": 3
    },
    {
      "epoch": 0.000290596303615018,
      "eval_loss": 9.54148006439209,
      "eval_runtime": 150.4404,
      "eval_samples_per_second": 96.317,
      "eval_steps_per_second": 24.083,
      "step": 5
    },
    {
      "epoch": 0.0003487155643380216,
      "grad_norm": 3.3199355602264404,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.1961,
      "step": 6
    },
    {
      "epoch": 0.0005230733465070325,
      "grad_norm": 3.0173420906066895,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.6324,
      "step": 9
    },
    {
      "epoch": 0.000581192607230036,
      "eval_loss": 9.164874076843262,
      "eval_runtime": 150.7889,
      "eval_samples_per_second": 96.095,
      "eval_steps_per_second": 24.027,
      "step": 10
    },
    {
      "epoch": 0.0006974311286760432,
      "grad_norm": 2.844165563583374,
      "learning_rate": 0.000163742398974869,
      "loss": 9.4022,
      "step": 12
    },
    {
      "epoch": 0.0008717889108450541,
      "grad_norm": 2.6431076526641846,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.3523,
      "step": 15
    },
    {
      "epoch": 0.0008717889108450541,
      "eval_loss": 8.866779327392578,
      "eval_runtime": 151.2566,
      "eval_samples_per_second": 95.797,
      "eval_steps_per_second": 23.953,
      "step": 15
    },
    {
      "epoch": 0.001046146693014065,
      "grad_norm": 2.6509759426116943,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.9539,
      "step": 18
    },
    {
      "epoch": 0.001162385214460072,
      "eval_loss": 8.694866180419922,
      "eval_runtime": 150.5717,
      "eval_samples_per_second": 96.233,
      "eval_steps_per_second": 24.062,
      "step": 20
    },
    {
      "epoch": 0.0012205044751830757,
      "grad_norm": 2.4120562076568604,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 8.39,
      "step": 21
    },
    {
      "epoch": 0.0013948622573520864,
      "grad_norm": 2.093318223953247,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.5658,
      "step": 24
    },
    {
      "epoch": 0.00145298151807509,
      "eval_loss": 8.619199752807617,
      "eval_runtime": 150.7975,
      "eval_samples_per_second": 96.089,
      "eval_steps_per_second": 24.026,
      "step": 25
    },
    {
      "epoch": 0.0015692200395210972,
      "grad_norm": 2.264380693435669,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.4889,
      "step": 27
    },
    {
      "epoch": 0.0017435778216901082,
      "grad_norm": 2.35832142829895,
      "learning_rate": 0.0,
      "loss": 8.2069,
      "step": 30
    },
    {
      "epoch": 0.0017435778216901082,
      "eval_loss": 8.605793952941895,
      "eval_runtime": 151.1869,
      "eval_samples_per_second": 95.842,
      "eval_steps_per_second": 23.964,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 8484225024000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}