{
  "best_metric": 10.359004020690918,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.028557829604950024,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009519276534983341,
      "eval_loss": 10.37730598449707,
      "eval_runtime": 1.8963,
      "eval_samples_per_second": 466.709,
      "eval_steps_per_second": 117.073,
      "step": 1
    },
    {
      "epoch": 0.0028557829604950024,
      "grad_norm": 0.20045891404151917,
      "learning_rate": 0.00012,
      "loss": 10.3757,
      "step": 3
    },
    {
      "epoch": 0.00475963826749167,
      "eval_loss": 10.37522029876709,
      "eval_runtime": 1.9434,
      "eval_samples_per_second": 455.382,
      "eval_steps_per_second": 114.232,
      "step": 5
    },
    {
      "epoch": 0.005711565920990005,
      "grad_norm": 0.2182302474975586,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.3756,
      "step": 6
    },
    {
      "epoch": 0.008567348881485007,
      "grad_norm": 0.21302692592144012,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.3731,
      "step": 9
    },
    {
      "epoch": 0.00951927653498334,
      "eval_loss": 10.36978530883789,
      "eval_runtime": 1.9159,
      "eval_samples_per_second": 461.916,
      "eval_steps_per_second": 115.87,
      "step": 10
    },
    {
      "epoch": 0.01142313184198001,
      "grad_norm": 0.22757567465305328,
      "learning_rate": 0.000163742398974869,
      "loss": 10.3681,
      "step": 12
    },
    {
      "epoch": 0.014278914802475012,
      "grad_norm": 0.21294520795345306,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.366,
      "step": 15
    },
    {
      "epoch": 0.014278914802475012,
      "eval_loss": 10.364806175231934,
      "eval_runtime": 1.9501,
      "eval_samples_per_second": 453.815,
      "eval_steps_per_second": 113.838,
      "step": 15
    },
    {
      "epoch": 0.017134697762970014,
      "grad_norm": 0.24626882374286652,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.3634,
      "step": 18
    },
    {
      "epoch": 0.01903855306996668,
      "eval_loss": 10.361103057861328,
      "eval_runtime": 1.9432,
      "eval_samples_per_second": 455.442,
      "eval_steps_per_second": 114.246,
      "step": 20
    },
    {
      "epoch": 0.019990480723465015,
      "grad_norm": 0.2671791613101959,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 10.3624,
      "step": 21
    },
    {
      "epoch": 0.02284626368396002,
      "grad_norm": 0.279178649187088,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 10.3612,
      "step": 24
    },
    {
      "epoch": 0.023798191337458353,
      "eval_loss": 10.359330177307129,
      "eval_runtime": 1.9488,
      "eval_samples_per_second": 454.12,
      "eval_steps_per_second": 113.915,
      "step": 25
    },
    {
      "epoch": 0.02570204664445502,
      "grad_norm": 0.2777588367462158,
      "learning_rate": 7.022351411174866e-06,
      "loss": 10.3575,
      "step": 27
    },
    {
      "epoch": 0.028557829604950024,
      "grad_norm": 0.28034502267837524,
      "learning_rate": 0.0,
      "loss": 10.3584,
      "step": 30
    },
    {
      "epoch": 0.028557829604950024,
      "eval_loss": 10.359004020690918,
      "eval_runtime": 1.9773,
      "eval_samples_per_second": 447.578,
      "eval_steps_per_second": 112.274,
      "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": 1569073397760.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}