{
  "best_metric": 0.09381499141454697,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.5827505827505828,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011655011655011655,
      "eval_loss": 0.7416201233863831,
      "eval_runtime": 293.8057,
      "eval_samples_per_second": 4.918,
      "eval_steps_per_second": 1.232,
      "step": 1
    },
    {
      "epoch": 0.05827505827505827,
      "grad_norm": 0.10827689617872238,
      "learning_rate": 0.000109,
      "loss": 0.3523,
      "step": 50
    },
    {
      "epoch": 0.11655011655011654,
      "grad_norm": 0.0924234688282013,
      "learning_rate": 0.000218,
      "loss": 0.1255,
      "step": 100
    },
    {
      "epoch": 0.17482517482517482,
      "grad_norm": 0.08200813084840775,
      "learning_rate": 0.00020970286904373027,
      "loss": 0.1145,
      "step": 150
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 0.07190132141113281,
      "learning_rate": 0.00018607463914933369,
      "loss": 0.1077,
      "step": 200
    },
    {
      "epoch": 0.2913752913752914,
      "grad_norm": 0.07174722105264664,
      "learning_rate": 0.0001507124941277948,
      "loss": 0.1029,
      "step": 250
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 0.06725361943244934,
      "learning_rate": 0.000109,
      "loss": 0.101,
      "step": 300
    },
    {
      "epoch": 0.40792540792540793,
      "grad_norm": 0.07163528352975845,
      "learning_rate": 6.728750587220522e-05,
      "loss": 0.097,
      "step": 350
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 0.06800274550914764,
      "learning_rate": 3.192536085066633e-05,
      "loss": 0.0948,
      "step": 400
    },
    {
      "epoch": 0.5244755244755245,
      "grad_norm": 0.07512625306844711,
      "learning_rate": 8.297130956269746e-06,
      "loss": 0.0932,
      "step": 450
    },
    {
      "epoch": 0.5827505827505828,
      "grad_norm": 0.07177788019180298,
      "learning_rate": 0.0,
      "loss": 0.0934,
      "step": 500
    },
    {
      "epoch": 0.5827505827505828,
      "eval_loss": 0.09381499141454697,
      "eval_runtime": 293.9054,
      "eval_samples_per_second": 4.917,
      "eval_steps_per_second": 1.232,
      "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": 1.330508659163136e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}