{
  "best_metric": 1.9288491010665894,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.043875685557586835,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014625228519195613,
      "eval_loss": 4.080230712890625,
      "eval_runtime": 28.8774,
      "eval_samples_per_second": 19.946,
      "eval_steps_per_second": 4.987,
      "step": 1
    },
    {
      "epoch": 0.0043875685557586835,
      "grad_norm": 1.2262245416641235,
      "learning_rate": 0.00012,
      "loss": 2.7363,
      "step": 3
    },
    {
      "epoch": 0.007312614259597806,
      "eval_loss": 3.627354621887207,
      "eval_runtime": 28.9404,
      "eval_samples_per_second": 19.903,
      "eval_steps_per_second": 4.976,
      "step": 5
    },
    {
      "epoch": 0.008775137111517367,
      "grad_norm": 2.2417445182800293,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.0584,
      "step": 6
    },
    {
      "epoch": 0.01316270566727605,
      "grad_norm": 1.9625098705291748,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.6714,
      "step": 9
    },
    {
      "epoch": 0.014625228519195612,
      "eval_loss": 2.6835503578186035,
      "eval_runtime": 28.9032,
      "eval_samples_per_second": 19.929,
      "eval_steps_per_second": 4.982,
      "step": 10
    },
    {
      "epoch": 0.017550274223034734,
      "grad_norm": 2.024289846420288,
      "learning_rate": 0.000163742398974869,
      "loss": 2.4231,
      "step": 12
    },
    {
      "epoch": 0.021937842778793418,
      "grad_norm": 2.3763327598571777,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2555,
      "step": 15
    },
    {
      "epoch": 0.021937842778793418,
      "eval_loss": 2.221853017807007,
      "eval_runtime": 28.9865,
      "eval_samples_per_second": 19.871,
      "eval_steps_per_second": 4.968,
      "step": 15
    },
    {
      "epoch": 0.0263254113345521,
      "grad_norm": 1.9897043704986572,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.0195,
      "step": 18
    },
    {
      "epoch": 0.029250457038391225,
      "eval_loss": 2.021346092224121,
      "eval_runtime": 28.9621,
      "eval_samples_per_second": 19.888,
      "eval_steps_per_second": 4.972,
      "step": 20
    },
    {
      "epoch": 0.030712979890310785,
      "grad_norm": 2.345966100692749,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.1036,
      "step": 21
    },
    {
      "epoch": 0.03510054844606947,
      "grad_norm": 2.4038145542144775,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.0068,
      "step": 24
    },
    {
      "epoch": 0.03656307129798903,
      "eval_loss": 1.946331262588501,
      "eval_runtime": 28.9445,
      "eval_samples_per_second": 19.9,
      "eval_steps_per_second": 4.975,
      "step": 25
    },
    {
      "epoch": 0.03948811700182815,
      "grad_norm": 2.389855146408081,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8486,
      "step": 27
    },
    {
      "epoch": 0.043875685557586835,
      "grad_norm": 2.1546502113342285,
      "learning_rate": 0.0,
      "loss": 1.8765,
      "step": 30
    },
    {
      "epoch": 0.043875685557586835,
      "eval_loss": 1.9288491010665894,
      "eval_runtime": 28.9156,
      "eval_samples_per_second": 19.92,
      "eval_steps_per_second": 4.98,
      "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": 2.114592047313715e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}