{
  "best_metric": 2.9403679370880127,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005820552370419952,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9401841234733175e-05,
      "eval_loss": 3.109846830368042,
      "eval_runtime": 2024.7504,
      "eval_samples_per_second": 10.718,
      "eval_steps_per_second": 5.359,
      "step": 1
    },
    {
      "epoch": 5.820552370419953e-05,
      "grad_norm": 0.19847838580608368,
      "learning_rate": 6e-05,
      "loss": 2.9343,
      "step": 3
    },
    {
      "epoch": 9.700920617366589e-05,
      "eval_loss": 3.0984432697296143,
      "eval_runtime": 2027.1501,
      "eval_samples_per_second": 10.706,
      "eval_steps_per_second": 5.353,
      "step": 5
    },
    {
      "epoch": 0.00011641104740839906,
      "grad_norm": 0.25328367948532104,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.9184,
      "step": 6
    },
    {
      "epoch": 0.0001746165711125986,
      "grad_norm": 0.23369625210762024,
      "learning_rate": 9.381533400219318e-05,
      "loss": 3.0195,
      "step": 9
    },
    {
      "epoch": 0.00019401841234733177,
      "eval_loss": 3.0252015590667725,
      "eval_runtime": 2024.6928,
      "eval_samples_per_second": 10.719,
      "eval_steps_per_second": 5.359,
      "step": 10
    },
    {
      "epoch": 0.00023282209481679812,
      "grad_norm": 0.4297844171524048,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.8714,
      "step": 12
    },
    {
      "epoch": 0.0002910276185209976,
      "grad_norm": 0.3757598400115967,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.8659,
      "step": 15
    },
    {
      "epoch": 0.0002910276185209976,
      "eval_loss": 2.9789626598358154,
      "eval_runtime": 2026.1573,
      "eval_samples_per_second": 10.711,
      "eval_steps_per_second": 5.355,
      "step": 15
    },
    {
      "epoch": 0.0003492331422251972,
      "grad_norm": 0.35646551847457886,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.8937,
      "step": 18
    },
    {
      "epoch": 0.00038803682469466355,
      "eval_loss": 2.954017400741577,
      "eval_runtime": 2027.9112,
      "eval_samples_per_second": 10.702,
      "eval_steps_per_second": 5.351,
      "step": 20
    },
    {
      "epoch": 0.0004074386659293967,
      "grad_norm": 0.40540552139282227,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 3.0663,
      "step": 21
    },
    {
      "epoch": 0.00046564418963359624,
      "grad_norm": 0.3658403158187866,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.9409,
      "step": 24
    },
    {
      "epoch": 0.0004850460308683294,
      "eval_loss": 2.942352056503296,
      "eval_runtime": 2026.1692,
      "eval_samples_per_second": 10.711,
      "eval_steps_per_second": 5.355,
      "step": 25
    },
    {
      "epoch": 0.0005238497133377958,
      "grad_norm": 0.6082600951194763,
      "learning_rate": 3.511175705587433e-06,
      "loss": 3.0562,
      "step": 27
    },
    {
      "epoch": 0.0005820552370419952,
      "grad_norm": 0.45390358567237854,
      "learning_rate": 0.0,
      "loss": 2.8248,
      "step": 30
    },
    {
      "epoch": 0.0005820552370419952,
      "eval_loss": 2.9403679370880127,
      "eval_runtime": 2027.2099,
      "eval_samples_per_second": 10.705,
      "eval_steps_per_second": 5.353,
      "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": 3915159982571520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}