{
  "best_metric": 1.4065148830413818,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.17135023989033585,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003427004797806717,
      "eval_loss": 2.133542537689209,
      "eval_runtime": 277.6973,
      "eval_samples_per_second": 17.699,
      "eval_steps_per_second": 4.426,
      "step": 1
    },
    {
      "epoch": 0.017135023989033583,
      "grad_norm": 2.3972327709198,
      "learning_rate": 0.0001015,
      "loss": 1.9134,
      "step": 50
    },
    {
      "epoch": 0.03427004797806717,
      "grad_norm": 2.3598361015319824,
      "learning_rate": 0.000203,
      "loss": 1.7653,
      "step": 100
    },
    {
      "epoch": 0.05140507196710076,
      "grad_norm": 2.0902371406555176,
      "learning_rate": 0.0001952737725498956,
      "loss": 1.6237,
      "step": 150
    },
    {
      "epoch": 0.06854009595613433,
      "grad_norm": 1.998542308807373,
      "learning_rate": 0.00017327133829043458,
      "loss": 1.5722,
      "step": 200
    },
    {
      "epoch": 0.08567511994516792,
      "grad_norm": 1.9381009340286255,
      "learning_rate": 0.00014034236838505662,
      "loss": 1.5449,
      "step": 250
    },
    {
      "epoch": 0.10281014393420151,
      "grad_norm": 2.0616586208343506,
      "learning_rate": 0.0001015,
      "loss": 1.5526,
      "step": 300
    },
    {
      "epoch": 0.11994516792323509,
      "grad_norm": 2.2782583236694336,
      "learning_rate": 6.265763161494339e-05,
      "loss": 1.4466,
      "step": 350
    },
    {
      "epoch": 0.13708019191226867,
      "grad_norm": 2.050510883331299,
      "learning_rate": 2.972866170956543e-05,
      "loss": 1.4486,
      "step": 400
    },
    {
      "epoch": 0.15421521590130227,
      "grad_norm": 2.100144624710083,
      "learning_rate": 7.726227450104397e-06,
      "loss": 1.4349,
      "step": 450
    },
    {
      "epoch": 0.17135023989033585,
      "grad_norm": 1.9951103925704956,
      "learning_rate": 0.0,
      "loss": 1.4296,
      "step": 500
    },
    {
      "epoch": 0.17135023989033585,
      "eval_loss": 1.4065148830413818,
      "eval_runtime": 277.7278,
      "eval_samples_per_second": 17.697,
      "eval_steps_per_second": 4.425,
      "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": 2.334765779653755e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}