{
  "best_metric": 3.3031609058380127,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.000383136869260929,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 3.761971950531006,
      "eval_runtime": 495.2638,
      "eval_samples_per_second": 66.569,
      "eval_steps_per_second": 33.285,
      "step": 1
    },
    {
      "epoch": 3.8313686926092896e-05,
      "grad_norm": 1.6783641576766968,
      "learning_rate": 0.00012,
      "loss": 15.0748,
      "step": 3
    },
    {
      "epoch": 6.38561448768215e-05,
      "eval_loss": 3.731351852416992,
      "eval_runtime": 495.902,
      "eval_samples_per_second": 66.483,
      "eval_steps_per_second": 33.242,
      "step": 5
    },
    {
      "epoch": 7.662737385218579e-05,
      "grad_norm": 1.7251548767089844,
      "learning_rate": 0.0001992114701314478,
      "loss": 14.8657,
      "step": 6
    },
    {
      "epoch": 0.0001149410607782787,
      "grad_norm": 2.13313364982605,
      "learning_rate": 0.00018763066800438636,
      "loss": 14.9604,
      "step": 9
    },
    {
      "epoch": 0.000127712289753643,
      "eval_loss": 3.5326249599456787,
      "eval_runtime": 494.84,
      "eval_samples_per_second": 66.626,
      "eval_steps_per_second": 33.314,
      "step": 10
    },
    {
      "epoch": 0.00015325474770437158,
      "grad_norm": 1.8235368728637695,
      "learning_rate": 0.000163742398974869,
      "loss": 14.243,
      "step": 12
    },
    {
      "epoch": 0.0001915684346304645,
      "grad_norm": 2.1185615062713623,
      "learning_rate": 0.00013090169943749476,
      "loss": 13.4274,
      "step": 15
    },
    {
      "epoch": 0.0001915684346304645,
      "eval_loss": 3.4010062217712402,
      "eval_runtime": 494.8886,
      "eval_samples_per_second": 66.619,
      "eval_steps_per_second": 33.311,
      "step": 15
    },
    {
      "epoch": 0.0002298821215565574,
      "grad_norm": 2.2047791481018066,
      "learning_rate": 9.372094804706867e-05,
      "loss": 13.6264,
      "step": 18
    },
    {
      "epoch": 0.000255424579507286,
      "eval_loss": 3.337207555770874,
      "eval_runtime": 495.0413,
      "eval_samples_per_second": 66.598,
      "eval_steps_per_second": 33.3,
      "step": 20
    },
    {
      "epoch": 0.0002681958084826503,
      "grad_norm": 2.2516863346099854,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 13.2387,
      "step": 21
    },
    {
      "epoch": 0.00030650949540874317,
      "grad_norm": 2.9069862365722656,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 13.1951,
      "step": 24
    },
    {
      "epoch": 0.00031928072438410746,
      "eval_loss": 3.3083837032318115,
      "eval_runtime": 494.7436,
      "eval_samples_per_second": 66.639,
      "eval_steps_per_second": 33.32,
      "step": 25
    },
    {
      "epoch": 0.0003448231823348361,
      "grad_norm": 2.1830813884735107,
      "learning_rate": 7.022351411174866e-06,
      "loss": 13.1907,
      "step": 27
    },
    {
      "epoch": 0.000383136869260929,
      "grad_norm": 2.640789270401001,
      "learning_rate": 0.0,
      "loss": 13.069,
      "step": 30
    },
    {
      "epoch": 0.000383136869260929,
      "eval_loss": 3.3031609058380127,
      "eval_runtime": 494.7185,
      "eval_samples_per_second": 66.642,
      "eval_steps_per_second": 33.322,
      "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": 129293195673600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}