{
  "best_metric": 1.7419980764389038,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.05405405405405406,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018018018018018018,
      "eval_loss": 8.1071138381958,
      "eval_runtime": 7.5703,
      "eval_samples_per_second": 61.821,
      "eval_steps_per_second": 15.455,
      "step": 1
    },
    {
      "epoch": 0.005405405405405406,
      "grad_norm": 33.437171936035156,
      "learning_rate": 0.00012,
      "loss": 5.3075,
      "step": 3
    },
    {
      "epoch": 0.009009009009009009,
      "eval_loss": 3.6301381587982178,
      "eval_runtime": 7.5717,
      "eval_samples_per_second": 61.809,
      "eval_steps_per_second": 15.452,
      "step": 5
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 7.13177490234375,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.0468,
      "step": 6
    },
    {
      "epoch": 0.016216216216216217,
      "grad_norm": 2.9952075481414795,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.7418,
      "step": 9
    },
    {
      "epoch": 0.018018018018018018,
      "eval_loss": 2.52937388420105,
      "eval_runtime": 7.5432,
      "eval_samples_per_second": 62.043,
      "eval_steps_per_second": 15.511,
      "step": 10
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 3.121565818786621,
      "learning_rate": 0.000163742398974869,
      "loss": 2.4953,
      "step": 12
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 5.132299423217773,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2275,
      "step": 15
    },
    {
      "epoch": 0.02702702702702703,
      "eval_loss": 2.072098970413208,
      "eval_runtime": 7.7108,
      "eval_samples_per_second": 60.694,
      "eval_steps_per_second": 15.174,
      "step": 15
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 6.874202728271484,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1091,
      "step": 18
    },
    {
      "epoch": 0.036036036036036036,
      "eval_loss": 1.864715337753296,
      "eval_runtime": 7.5729,
      "eval_samples_per_second": 61.8,
      "eval_steps_per_second": 15.45,
      "step": 20
    },
    {
      "epoch": 0.03783783783783784,
      "grad_norm": 2.82894229888916,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.9228,
      "step": 21
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 5.222259044647217,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.8717,
      "step": 24
    },
    {
      "epoch": 0.04504504504504504,
      "eval_loss": 1.7659335136413574,
      "eval_runtime": 7.7119,
      "eval_samples_per_second": 60.685,
      "eval_steps_per_second": 15.171,
      "step": 25
    },
    {
      "epoch": 0.04864864864864865,
      "grad_norm": 1.8492400646209717,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8215,
      "step": 27
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 3.2856228351593018,
      "learning_rate": 0.0,
      "loss": 1.7748,
      "step": 30
    },
    {
      "epoch": 0.05405405405405406,
      "eval_loss": 1.7419980764389038,
      "eval_runtime": 7.57,
      "eval_samples_per_second": 61.823,
      "eval_steps_per_second": 15.456,
      "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": 3088106316103680.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}