{
  "best_metric": 2.406879425048828,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0052514113167913875,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017504704389304627,
      "eval_loss": 2.599263906478882,
      "eval_runtime": 29.6592,
      "eval_samples_per_second": 81.122,
      "eval_steps_per_second": 40.561,
      "step": 1
    },
    {
      "epoch": 0.0005251411316791387,
      "grad_norm": 1.3951877355575562,
      "learning_rate": 0.00012,
      "loss": 9.9456,
      "step": 3
    },
    {
      "epoch": 0.0008752352194652313,
      "eval_loss": 2.5780935287475586,
      "eval_runtime": 29.8289,
      "eval_samples_per_second": 80.66,
      "eval_steps_per_second": 40.33,
      "step": 5
    },
    {
      "epoch": 0.0010502822633582775,
      "grad_norm": 1.2411249876022339,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.1858,
      "step": 6
    },
    {
      "epoch": 0.0015754233950374162,
      "grad_norm": 0.9938393831253052,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.5193,
      "step": 9
    },
    {
      "epoch": 0.0017504704389304626,
      "eval_loss": 2.4776437282562256,
      "eval_runtime": 29.9977,
      "eval_samples_per_second": 80.206,
      "eval_steps_per_second": 40.103,
      "step": 10
    },
    {
      "epoch": 0.002100564526716555,
      "grad_norm": 0.5660353899002075,
      "learning_rate": 0.000163742398974869,
      "loss": 9.1216,
      "step": 12
    },
    {
      "epoch": 0.0026257056583956937,
      "grad_norm": 0.7864254713058472,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.4294,
      "step": 15
    },
    {
      "epoch": 0.0026257056583956937,
      "eval_loss": 2.4329674243927,
      "eval_runtime": 29.8474,
      "eval_samples_per_second": 80.61,
      "eval_steps_per_second": 40.305,
      "step": 15
    },
    {
      "epoch": 0.0031508467900748325,
      "grad_norm": 0.8525682687759399,
      "learning_rate": 9.372094804706867e-05,
      "loss": 9.1762,
      "step": 18
    },
    {
      "epoch": 0.003500940877860925,
      "eval_loss": 2.4166924953460693,
      "eval_runtime": 29.7208,
      "eval_samples_per_second": 80.953,
      "eval_steps_per_second": 40.477,
      "step": 20
    },
    {
      "epoch": 0.0036759879217539712,
      "grad_norm": 1.8014469146728516,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.2091,
      "step": 21
    },
    {
      "epoch": 0.00420112905343311,
      "grad_norm": 0.7783241271972656,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.8708,
      "step": 24
    },
    {
      "epoch": 0.0043761760973261565,
      "eval_loss": 2.4078986644744873,
      "eval_runtime": 29.6893,
      "eval_samples_per_second": 81.039,
      "eval_steps_per_second": 40.52,
      "step": 25
    },
    {
      "epoch": 0.004726270185112249,
      "grad_norm": 1.095931887626648,
      "learning_rate": 7.022351411174866e-06,
      "loss": 10.1005,
      "step": 27
    },
    {
      "epoch": 0.0052514113167913875,
      "grad_norm": 0.9916987419128418,
      "learning_rate": 0.0,
      "loss": 10.183,
      "step": 30
    },
    {
      "epoch": 0.0052514113167913875,
      "eval_loss": 2.406879425048828,
      "eval_runtime": 29.5806,
      "eval_samples_per_second": 81.337,
      "eval_steps_per_second": 40.669,
      "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": 149764618321920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}