{
  "best_metric": 1.122968316078186,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.10217113665389528,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005108556832694764,
      "eval_loss": 1.2817872762680054,
      "eval_runtime": 43.0727,
      "eval_samples_per_second": 3.831,
      "eval_steps_per_second": 0.975,
      "step": 1
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 0.15897178649902344,
      "learning_rate": 0.00012,
      "loss": 1.1005,
      "step": 3
    },
    {
      "epoch": 0.02554278416347382,
      "eval_loss": 1.2362875938415527,
      "eval_runtime": 43.7766,
      "eval_samples_per_second": 3.769,
      "eval_steps_per_second": 0.959,
      "step": 5
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 0.2071477323770523,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.0994,
      "step": 6
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 0.12776418030261993,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.9775,
      "step": 9
    },
    {
      "epoch": 0.05108556832694764,
      "eval_loss": 1.1640980243682861,
      "eval_runtime": 42.8759,
      "eval_samples_per_second": 3.848,
      "eval_steps_per_second": 0.98,
      "step": 10
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 0.1395108997821808,
      "learning_rate": 0.000163742398974869,
      "loss": 0.9864,
      "step": 12
    },
    {
      "epoch": 0.07662835249042145,
      "grad_norm": 0.14121867716312408,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.985,
      "step": 15
    },
    {
      "epoch": 0.07662835249042145,
      "eval_loss": 1.148338794708252,
      "eval_runtime": 41.99,
      "eval_samples_per_second": 3.93,
      "eval_steps_per_second": 1.0,
      "step": 15
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.13990887999534607,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.9709,
      "step": 18
    },
    {
      "epoch": 0.10217113665389528,
      "eval_loss": 1.122968316078186,
      "eval_runtime": 44.6271,
      "eval_samples_per_second": 3.697,
      "eval_steps_per_second": 0.941,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.715327779995648e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}