{
  "best_metric": 2.9646615982055664,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.1426872770511296,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0047562425683709865,
      "eval_loss": 3.103335380554199,
      "eval_runtime": 2.4888,
      "eval_samples_per_second": 71.52,
      "eval_steps_per_second": 18.081,
      "step": 1
    },
    {
      "epoch": 0.014268727705112961,
      "grad_norm": 14.646588325500488,
      "learning_rate": 0.00012,
      "loss": 10.2719,
      "step": 3
    },
    {
      "epoch": 0.023781212841854936,
      "eval_loss": 3.07517671585083,
      "eval_runtime": 1.6135,
      "eval_samples_per_second": 110.322,
      "eval_steps_per_second": 27.89,
      "step": 5
    },
    {
      "epoch": 0.028537455410225922,
      "grad_norm": 15.306797981262207,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.8924,
      "step": 6
    },
    {
      "epoch": 0.04280618311533888,
      "grad_norm": 20.227991104125977,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.0889,
      "step": 9
    },
    {
      "epoch": 0.04756242568370987,
      "eval_loss": 3.0353667736053467,
      "eval_runtime": 1.6434,
      "eval_samples_per_second": 108.309,
      "eval_steps_per_second": 27.382,
      "step": 10
    },
    {
      "epoch": 0.057074910820451845,
      "grad_norm": 23.035850524902344,
      "learning_rate": 0.000163742398974869,
      "loss": 11.4774,
      "step": 12
    },
    {
      "epoch": 0.0713436385255648,
      "grad_norm": 21.357481002807617,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.6186,
      "step": 15
    },
    {
      "epoch": 0.0713436385255648,
      "eval_loss": 3.0080606937408447,
      "eval_runtime": 1.6384,
      "eval_samples_per_second": 108.642,
      "eval_steps_per_second": 27.466,
      "step": 15
    },
    {
      "epoch": 0.08561236623067776,
      "grad_norm": 26.94682502746582,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.9721,
      "step": 18
    },
    {
      "epoch": 0.09512485136741974,
      "eval_loss": 2.9805502891540527,
      "eval_runtime": 2.0766,
      "eval_samples_per_second": 85.715,
      "eval_steps_per_second": 21.67,
      "step": 20
    },
    {
      "epoch": 0.09988109393579073,
      "grad_norm": 24.07295036315918,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.5067,
      "step": 21
    },
    {
      "epoch": 0.11414982164090369,
      "grad_norm": 23.57462501525879,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.9897,
      "step": 24
    },
    {
      "epoch": 0.11890606420927467,
      "eval_loss": 2.96132493019104,
      "eval_runtime": 1.6292,
      "eval_samples_per_second": 109.253,
      "eval_steps_per_second": 27.62,
      "step": 25
    },
    {
      "epoch": 0.12841854934601665,
      "grad_norm": 25.987632751464844,
      "learning_rate": 7.022351411174866e-06,
      "loss": 11.3795,
      "step": 27
    },
    {
      "epoch": 0.1426872770511296,
      "grad_norm": 27.918235778808594,
      "learning_rate": 0.0,
      "loss": 12.4756,
      "step": 30
    },
    {
      "epoch": 0.1426872770511296,
      "eval_loss": 2.9646615982055664,
      "eval_runtime": 1.6445,
      "eval_samples_per_second": 108.241,
      "eval_steps_per_second": 27.364,
      "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": 1106270748672000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}