{
  "best_metric": 11.929627418518066,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.030503304524656837,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010167768174885613,
      "eval_loss": 11.931282997131348,
      "eval_runtime": 12.1282,
      "eval_samples_per_second": 34.218,
      "eval_steps_per_second": 17.15,
      "step": 1
    },
    {
      "epoch": 0.003050330452465684,
      "grad_norm": 0.034024111926555634,
      "learning_rate": 6e-05,
      "loss": 11.9303,
      "step": 3
    },
    {
      "epoch": 0.005083884087442806,
      "eval_loss": 11.931171417236328,
      "eval_runtime": 12.2651,
      "eval_samples_per_second": 33.836,
      "eval_steps_per_second": 16.959,
      "step": 5
    },
    {
      "epoch": 0.006100660904931368,
      "grad_norm": 0.03859293833374977,
      "learning_rate": 0.00012,
      "loss": 11.9311,
      "step": 6
    },
    {
      "epoch": 0.009150991357397052,
      "grad_norm": 0.028728436678647995,
      "learning_rate": 0.00018,
      "loss": 11.9335,
      "step": 9
    },
    {
      "epoch": 0.010167768174885612,
      "eval_loss": 11.93080997467041,
      "eval_runtime": 12.0381,
      "eval_samples_per_second": 34.474,
      "eval_steps_per_second": 17.278,
      "step": 10
    },
    {
      "epoch": 0.012201321809862735,
      "grad_norm": 0.03001631423830986,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.9301,
      "step": 12
    },
    {
      "epoch": 0.015251652262328419,
      "grad_norm": 0.05156728997826576,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.9283,
      "step": 15
    },
    {
      "epoch": 0.015251652262328419,
      "eval_loss": 11.930292129516602,
      "eval_runtime": 12.0367,
      "eval_samples_per_second": 34.478,
      "eval_steps_per_second": 17.28,
      "step": 15
    },
    {
      "epoch": 0.018301982714794104,
      "grad_norm": 0.04535188153386116,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9301,
      "step": 18
    },
    {
      "epoch": 0.020335536349771224,
      "eval_loss": 11.929884910583496,
      "eval_runtime": 12.3097,
      "eval_samples_per_second": 33.713,
      "eval_steps_per_second": 16.897,
      "step": 20
    },
    {
      "epoch": 0.021352313167259787,
      "grad_norm": 0.03429163247346878,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9307,
      "step": 21
    },
    {
      "epoch": 0.02440264361972547,
      "grad_norm": 0.02444632537662983,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.9311,
      "step": 24
    },
    {
      "epoch": 0.02541942043721403,
      "eval_loss": 11.929669380187988,
      "eval_runtime": 12.3353,
      "eval_samples_per_second": 33.643,
      "eval_steps_per_second": 16.862,
      "step": 25
    },
    {
      "epoch": 0.027452974072191154,
      "grad_norm": 0.03801164776086807,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.9294,
      "step": 27
    },
    {
      "epoch": 0.030503304524656837,
      "grad_norm": 0.027243835851550102,
      "learning_rate": 0.0,
      "loss": 11.9301,
      "step": 30
    },
    {
      "epoch": 0.030503304524656837,
      "eval_loss": 11.929627418518066,
      "eval_runtime": 12.1453,
      "eval_samples_per_second": 34.17,
      "eval_steps_per_second": 17.126,
      "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": 16956751872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}