{
  "best_metric": 11.932905197143555,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.002196916993152942,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.32305664384314e-05,
      "eval_loss": 11.933247566223145,
      "eval_runtime": 93.9585,
      "eval_samples_per_second": 61.197,
      "eval_steps_per_second": 30.599,
      "step": 1
    },
    {
      "epoch": 0.0002196916993152942,
      "grad_norm": 0.01346541941165924,
      "learning_rate": 6e-05,
      "loss": 11.9324,
      "step": 3
    },
    {
      "epoch": 0.000366152832192157,
      "eval_loss": 11.933225631713867,
      "eval_runtime": 94.5233,
      "eval_samples_per_second": 60.832,
      "eval_steps_per_second": 30.416,
      "step": 5
    },
    {
      "epoch": 0.0004393833986305884,
      "grad_norm": 0.013578471727669239,
      "learning_rate": 0.00012,
      "loss": 11.9338,
      "step": 6
    },
    {
      "epoch": 0.0006590750979458826,
      "grad_norm": 0.011808818206191063,
      "learning_rate": 0.00018,
      "loss": 11.9324,
      "step": 9
    },
    {
      "epoch": 0.000732305664384314,
      "eval_loss": 11.933143615722656,
      "eval_runtime": 94.4176,
      "eval_samples_per_second": 60.9,
      "eval_steps_per_second": 30.45,
      "step": 10
    },
    {
      "epoch": 0.0008787667972611768,
      "grad_norm": 0.0106218745931983,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.9332,
      "step": 12
    },
    {
      "epoch": 0.001098458496576471,
      "grad_norm": 0.00903626624494791,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.9314,
      "step": 15
    },
    {
      "epoch": 0.001098458496576471,
      "eval_loss": 11.933040618896484,
      "eval_runtime": 94.0048,
      "eval_samples_per_second": 61.167,
      "eval_steps_per_second": 30.584,
      "step": 15
    },
    {
      "epoch": 0.0013181501958917652,
      "grad_norm": 0.016062667593359947,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9332,
      "step": 18
    },
    {
      "epoch": 0.001464611328768628,
      "eval_loss": 11.93295669555664,
      "eval_runtime": 94.3686,
      "eval_samples_per_second": 60.931,
      "eval_steps_per_second": 30.466,
      "step": 20
    },
    {
      "epoch": 0.0015378418952070594,
      "grad_norm": 0.011252116411924362,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9329,
      "step": 21
    },
    {
      "epoch": 0.0017575335945223536,
      "grad_norm": 0.013713706284761429,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.932,
      "step": 24
    },
    {
      "epoch": 0.001830764160960785,
      "eval_loss": 11.932912826538086,
      "eval_runtime": 93.9864,
      "eval_samples_per_second": 61.179,
      "eval_steps_per_second": 30.59,
      "step": 25
    },
    {
      "epoch": 0.0019772252938376478,
      "grad_norm": 0.015976207330822945,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.9334,
      "step": 27
    },
    {
      "epoch": 0.002196916993152942,
      "grad_norm": 0.014109929092228413,
      "learning_rate": 0.0,
      "loss": 11.9354,
      "step": 30
    },
    {
      "epoch": 0.002196916993152942,
      "eval_loss": 11.932905197143555,
      "eval_runtime": 94.2996,
      "eval_samples_per_second": 60.976,
      "eval_steps_per_second": 30.488,
      "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": 11429412864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}