{
  "best_metric": 4.053124904632568,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.009029345372460496,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009029345372460496,
      "grad_norm": 0.5397587418556213,
      "learning_rate": 2e-05,
      "loss": 4.8343,
      "step": 1
    },
    {
      "epoch": 0.0009029345372460496,
      "eval_loss": 4.486961841583252,
      "eval_runtime": 74.5945,
      "eval_samples_per_second": 6.261,
      "eval_steps_per_second": 3.137,
      "step": 1
    },
    {
      "epoch": 0.0018058690744920992,
      "grad_norm": 0.5734784007072449,
      "learning_rate": 4e-05,
      "loss": 4.6517,
      "step": 2
    },
    {
      "epoch": 0.002708803611738149,
      "grad_norm": 0.516501247882843,
      "learning_rate": 6e-05,
      "loss": 4.1793,
      "step": 3
    },
    {
      "epoch": 0.0036117381489841984,
      "grad_norm": 0.5289381146430969,
      "learning_rate": 8e-05,
      "loss": 4.0826,
      "step": 4
    },
    {
      "epoch": 0.004514672686230248,
      "grad_norm": 0.5648006796836853,
      "learning_rate": 0.0001,
      "loss": 4.4783,
      "step": 5
    },
    {
      "epoch": 0.004514672686230248,
      "eval_loss": 4.469165325164795,
      "eval_runtime": 73.412,
      "eval_samples_per_second": 6.361,
      "eval_steps_per_second": 3.187,
      "step": 5
    },
    {
      "epoch": 0.005417607223476298,
      "grad_norm": 0.6955599784851074,
      "learning_rate": 0.00012,
      "loss": 4.7307,
      "step": 6
    },
    {
      "epoch": 0.006320541760722348,
      "grad_norm": 0.6882440447807312,
      "learning_rate": 0.00014,
      "loss": 4.3198,
      "step": 7
    },
    {
      "epoch": 0.007223476297968397,
      "grad_norm": 0.7614045143127441,
      "learning_rate": 0.00016,
      "loss": 4.3397,
      "step": 8
    },
    {
      "epoch": 0.008126410835214447,
      "grad_norm": 0.9158193469047546,
      "learning_rate": 0.00018,
      "loss": 4.5137,
      "step": 9
    },
    {
      "epoch": 0.009029345372460496,
      "grad_norm": 1.0128803253173828,
      "learning_rate": 0.0002,
      "loss": 4.35,
      "step": 10
    },
    {
      "epoch": 0.009029345372460496,
      "eval_loss": 4.053124904632568,
      "eval_runtime": 72.7097,
      "eval_samples_per_second": 6.423,
      "eval_steps_per_second": 3.218,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1873333749547008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}