{
  "best_metric": 1.7330271005630493,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 2.9958847736625516,
  "eval_steps": 50,
  "global_step": 182,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01646090534979424,
      "eval_loss": 2.5531206130981445,
      "eval_runtime": 2.5108,
      "eval_samples_per_second": 162.894,
      "eval_steps_per_second": 5.178,
      "step": 1
    },
    {
      "epoch": 0.823045267489712,
      "grad_norm": 0.3033908009529114,
      "learning_rate": 0.0002003,
      "loss": 2.0429,
      "step": 50
    },
    {
      "epoch": 0.823045267489712,
      "eval_loss": 1.874566912651062,
      "eval_runtime": 2.4985,
      "eval_samples_per_second": 163.7,
      "eval_steps_per_second": 5.203,
      "step": 50
    },
    {
      "epoch": 1.646090534979424,
      "grad_norm": 0.21998366713523865,
      "learning_rate": 0.0002003,
      "loss": 1.8267,
      "step": 100
    },
    {
      "epoch": 1.646090534979424,
      "eval_loss": 1.7729922533035278,
      "eval_runtime": 2.5071,
      "eval_samples_per_second": 163.139,
      "eval_steps_per_second": 5.185,
      "step": 100
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 0.35732659697532654,
      "learning_rate": 0.0002003,
      "loss": 1.7302,
      "step": 150
    },
    {
      "epoch": 2.4691358024691357,
      "eval_loss": 1.7330271005630493,
      "eval_runtime": 2.5058,
      "eval_samples_per_second": 163.222,
      "eval_steps_per_second": 5.188,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 182,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "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": 2.743044113891328e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}