{
  "best_metric": 1.3760838508605957,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.009540467482906663,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003180155827635554,
      "eval_loss": 2.397944688796997,
      "eval_runtime": 141.6356,
      "eval_samples_per_second": 18.696,
      "eval_steps_per_second": 4.674,
      "step": 1
    },
    {
      "epoch": 0.0009540467482906663,
      "grad_norm": 1.3596196174621582,
      "learning_rate": 0.00012,
      "loss": 6.9414,
      "step": 3
    },
    {
      "epoch": 0.0015900779138177772,
      "eval_loss": 2.150930643081665,
      "eval_runtime": 141.7488,
      "eval_samples_per_second": 18.681,
      "eval_steps_per_second": 4.67,
      "step": 5
    },
    {
      "epoch": 0.0019080934965813325,
      "grad_norm": 1.8086575269699097,
      "learning_rate": 0.0001992114701314478,
      "loss": 7.0836,
      "step": 6
    },
    {
      "epoch": 0.0028621402448719985,
      "grad_norm": 2.4983463287353516,
      "learning_rate": 0.00018763066800438636,
      "loss": 6.4925,
      "step": 9
    },
    {
      "epoch": 0.0031801558276355543,
      "eval_loss": 1.8019968271255493,
      "eval_runtime": 141.2678,
      "eval_samples_per_second": 18.745,
      "eval_steps_per_second": 4.686,
      "step": 10
    },
    {
      "epoch": 0.003816186993162665,
      "grad_norm": 1.5523895025253296,
      "learning_rate": 0.000163742398974869,
      "loss": 6.559,
      "step": 12
    },
    {
      "epoch": 0.0047702337414533315,
      "grad_norm": 1.4192075729370117,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.2157,
      "step": 15
    },
    {
      "epoch": 0.0047702337414533315,
      "eval_loss": 1.5555007457733154,
      "eval_runtime": 142.2994,
      "eval_samples_per_second": 18.609,
      "eval_steps_per_second": 4.652,
      "step": 15
    },
    {
      "epoch": 0.005724280489743997,
      "grad_norm": 1.7687486410140991,
      "learning_rate": 9.372094804706867e-05,
      "loss": 5.7934,
      "step": 18
    },
    {
      "epoch": 0.006360311655271109,
      "eval_loss": 1.425671935081482,
      "eval_runtime": 141.2734,
      "eval_samples_per_second": 18.744,
      "eval_steps_per_second": 4.686,
      "step": 20
    },
    {
      "epoch": 0.0066783272380346636,
      "grad_norm": 1.4714587926864624,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 5.9333,
      "step": 21
    },
    {
      "epoch": 0.00763237398632533,
      "grad_norm": 1.673614263534546,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.1225,
      "step": 24
    },
    {
      "epoch": 0.007950389569088886,
      "eval_loss": 1.3837761878967285,
      "eval_runtime": 141.5893,
      "eval_samples_per_second": 18.702,
      "eval_steps_per_second": 4.675,
      "step": 25
    },
    {
      "epoch": 0.008586420734615996,
      "grad_norm": 1.7184377908706665,
      "learning_rate": 7.022351411174866e-06,
      "loss": 5.6696,
      "step": 27
    },
    {
      "epoch": 0.009540467482906663,
      "grad_norm": 1.8490729331970215,
      "learning_rate": 0.0,
      "loss": 5.6566,
      "step": 30
    },
    {
      "epoch": 0.009540467482906663,
      "eval_loss": 1.3760838508605957,
      "eval_runtime": 142.0308,
      "eval_samples_per_second": 18.644,
      "eval_steps_per_second": 4.661,
      "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": 1.1605176502714368e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}