{
  "best_metric": 1.4071842432022095,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0024681201151789387,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.227067050596462e-05,
      "eval_loss": 1.5133055448532104,
      "eval_runtime": 207.9858,
      "eval_samples_per_second": 24.607,
      "eval_steps_per_second": 12.304,
      "step": 1
    },
    {
      "epoch": 0.00024681201151789385,
      "grad_norm": 3.4121687412261963,
      "learning_rate": 6e-05,
      "loss": 6.2253,
      "step": 3
    },
    {
      "epoch": 0.00041135335252982314,
      "eval_loss": 1.4851385354995728,
      "eval_runtime": 208.391,
      "eval_samples_per_second": 24.56,
      "eval_steps_per_second": 12.28,
      "step": 5
    },
    {
      "epoch": 0.0004936240230357877,
      "grad_norm": 3.0287251472473145,
      "learning_rate": 0.00012,
      "loss": 6.0201,
      "step": 6
    },
    {
      "epoch": 0.0007404360345536817,
      "grad_norm": 2.988588571548462,
      "learning_rate": 0.00018,
      "loss": 6.2595,
      "step": 9
    },
    {
      "epoch": 0.0008227067050596463,
      "eval_loss": 1.4425612688064575,
      "eval_runtime": 208.2339,
      "eval_samples_per_second": 24.578,
      "eval_steps_per_second": 12.289,
      "step": 10
    },
    {
      "epoch": 0.0009872480460715754,
      "grad_norm": 3.4223175048828125,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.4238,
      "step": 12
    },
    {
      "epoch": 0.0012340600575894694,
      "grad_norm": 3.620543956756592,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.9195,
      "step": 15
    },
    {
      "epoch": 0.0012340600575894694,
      "eval_loss": 1.4251627922058105,
      "eval_runtime": 208.572,
      "eval_samples_per_second": 24.538,
      "eval_steps_per_second": 12.269,
      "step": 15
    },
    {
      "epoch": 0.0014808720691073633,
      "grad_norm": 2.249208688735962,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.7577,
      "step": 18
    },
    {
      "epoch": 0.0016454134101192926,
      "eval_loss": 1.4145777225494385,
      "eval_runtime": 208.5441,
      "eval_samples_per_second": 24.542,
      "eval_steps_per_second": 12.271,
      "step": 20
    },
    {
      "epoch": 0.001727684080625257,
      "grad_norm": 3.4575071334838867,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.1962,
      "step": 21
    },
    {
      "epoch": 0.001974496092143151,
      "grad_norm": 2.291224479675293,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.9208,
      "step": 24
    },
    {
      "epoch": 0.0020567667626491155,
      "eval_loss": 1.4084250926971436,
      "eval_runtime": 208.4803,
      "eval_samples_per_second": 24.549,
      "eval_steps_per_second": 12.275,
      "step": 25
    },
    {
      "epoch": 0.002221308103661045,
      "grad_norm": 2.2885515689849854,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.5707,
      "step": 27
    },
    {
      "epoch": 0.0024681201151789387,
      "grad_norm": 2.3244194984436035,
      "learning_rate": 0.0,
      "loss": 5.6968,
      "step": 30
    },
    {
      "epoch": 0.0024681201151789387,
      "eval_loss": 1.4071842432022095,
      "eval_runtime": 208.401,
      "eval_samples_per_second": 24.558,
      "eval_steps_per_second": 12.279,
      "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": 2088510475468800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}