{
  "best_metric": 1.5424069166183472,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.28153153153153154,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005630630630630631,
      "eval_loss": 3.883523464202881,
      "eval_runtime": 401.3191,
      "eval_samples_per_second": 7.455,
      "eval_steps_per_second": 1.864,
      "step": 1
    },
    {
      "epoch": 0.028153153153153154,
      "grad_norm": 1.086362361907959,
      "learning_rate": 0.000106,
      "loss": 3.0977,
      "step": 50
    },
    {
      "epoch": 0.05630630630630631,
      "grad_norm": 1.337011456489563,
      "learning_rate": 0.000212,
      "loss": 2.0647,
      "step": 100
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.0307221412658691,
      "learning_rate": 0.0002039312304461964,
      "loss": 2.0058,
      "step": 150
    },
    {
      "epoch": 0.11261261261261261,
      "grad_norm": 0.895391583442688,
      "learning_rate": 0.00018095331880577404,
      "loss": 1.84,
      "step": 200
    },
    {
      "epoch": 0.14076576576576577,
      "grad_norm": 1.0741695165634155,
      "learning_rate": 0.00014656444383069953,
      "loss": 1.8431,
      "step": 250
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 0.9879794120788574,
      "learning_rate": 0.000106,
      "loss": 1.7352,
      "step": 300
    },
    {
      "epoch": 0.19707207207207209,
      "grad_norm": 1.1784024238586426,
      "learning_rate": 6.543555616930049e-05,
      "loss": 1.7086,
      "step": 350
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 0.9603841304779053,
      "learning_rate": 3.104668119422597e-05,
      "loss": 1.6924,
      "step": 400
    },
    {
      "epoch": 0.2533783783783784,
      "grad_norm": 1.6870561838150024,
      "learning_rate": 8.068769553803605e-06,
      "loss": 1.5726,
      "step": 450
    },
    {
      "epoch": 0.28153153153153154,
      "grad_norm": 1.2599513530731201,
      "learning_rate": 0.0,
      "loss": 1.5307,
      "step": 500
    },
    {
      "epoch": 0.28153153153153154,
      "eval_loss": 1.5424069166183472,
      "eval_runtime": 402.0469,
      "eval_samples_per_second": 7.442,
      "eval_steps_per_second": 1.86,
      "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": 8.942681325400228e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}