{
  "best_metric": 0.8604340553283691,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07467330429371499,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002489110143123833,
      "eval_loss": 1.072034239768982,
      "eval_runtime": 11.4235,
      "eval_samples_per_second": 14.882,
      "eval_steps_per_second": 7.441,
      "step": 1
    },
    {
      "epoch": 0.0074673304293715,
      "grad_norm": 1.2329739332199097,
      "learning_rate": 6e-05,
      "loss": 4.1544,
      "step": 3
    },
    {
      "epoch": 0.012445550715619166,
      "eval_loss": 1.0362956523895264,
      "eval_runtime": 11.4791,
      "eval_samples_per_second": 14.81,
      "eval_steps_per_second": 7.405,
      "step": 5
    },
    {
      "epoch": 0.014934660858743,
      "grad_norm": 1.251894235610962,
      "learning_rate": 0.00012,
      "loss": 4.1252,
      "step": 6
    },
    {
      "epoch": 0.0224019912881145,
      "grad_norm": 1.2535237073898315,
      "learning_rate": 0.00018,
      "loss": 3.923,
      "step": 9
    },
    {
      "epoch": 0.024891101431238332,
      "eval_loss": 0.9608532190322876,
      "eval_runtime": 11.4914,
      "eval_samples_per_second": 14.794,
      "eval_steps_per_second": 7.397,
      "step": 10
    },
    {
      "epoch": 0.029869321717486,
      "grad_norm": 1.6997766494750977,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.7935,
      "step": 12
    },
    {
      "epoch": 0.037336652146857496,
      "grad_norm": 1.376512050628662,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.5661,
      "step": 15
    },
    {
      "epoch": 0.037336652146857496,
      "eval_loss": 0.8920488953590393,
      "eval_runtime": 11.5125,
      "eval_samples_per_second": 14.767,
      "eval_steps_per_second": 7.383,
      "step": 15
    },
    {
      "epoch": 0.044803982576229,
      "grad_norm": 1.3809574842453003,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.4827,
      "step": 18
    },
    {
      "epoch": 0.049782202862476664,
      "eval_loss": 0.8709966540336609,
      "eval_runtime": 11.5089,
      "eval_samples_per_second": 14.771,
      "eval_steps_per_second": 7.386,
      "step": 20
    },
    {
      "epoch": 0.0522713130056005,
      "grad_norm": 1.4493108987808228,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.5754,
      "step": 21
    },
    {
      "epoch": 0.059738643434972,
      "grad_norm": 1.3764252662658691,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.4635,
      "step": 24
    },
    {
      "epoch": 0.06222775357809583,
      "eval_loss": 0.8631235361099243,
      "eval_runtime": 11.5249,
      "eval_samples_per_second": 14.751,
      "eval_steps_per_second": 7.375,
      "step": 25
    },
    {
      "epoch": 0.0672059738643435,
      "grad_norm": 1.310421347618103,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.4281,
      "step": 27
    },
    {
      "epoch": 0.07467330429371499,
      "grad_norm": 1.4106675386428833,
      "learning_rate": 0.0,
      "loss": 3.3246,
      "step": 30
    },
    {
      "epoch": 0.07467330429371499,
      "eval_loss": 0.8604340553283691,
      "eval_runtime": 11.5063,
      "eval_samples_per_second": 14.774,
      "eval_steps_per_second": 7.387,
      "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": 1.71516213854208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}