{
  "best_metric": 1.0437217950820923,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.02386634844868735,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002386634844868735,
      "grad_norm": 1.13600492477417,
      "learning_rate": 2e-05,
      "loss": 1.612,
      "step": 1
    },
    {
      "epoch": 0.002386634844868735,
      "eval_loss": 1.3748971223831177,
      "eval_runtime": 52.3445,
      "eval_samples_per_second": 3.381,
      "eval_steps_per_second": 1.7,
      "step": 1
    },
    {
      "epoch": 0.00477326968973747,
      "grad_norm": 0.5665156245231628,
      "learning_rate": 4e-05,
      "loss": 0.8491,
      "step": 2
    },
    {
      "epoch": 0.007159904534606206,
      "grad_norm": 0.6333050727844238,
      "learning_rate": 6e-05,
      "loss": 1.1232,
      "step": 3
    },
    {
      "epoch": 0.00954653937947494,
      "grad_norm": 0.7455923557281494,
      "learning_rate": 8e-05,
      "loss": 1.3785,
      "step": 4
    },
    {
      "epoch": 0.011933174224343675,
      "grad_norm": 0.7020689845085144,
      "learning_rate": 0.0001,
      "loss": 1.1252,
      "step": 5
    },
    {
      "epoch": 0.011933174224343675,
      "eval_loss": 1.3356304168701172,
      "eval_runtime": 53.3626,
      "eval_samples_per_second": 3.317,
      "eval_steps_per_second": 1.668,
      "step": 5
    },
    {
      "epoch": 0.014319809069212411,
      "grad_norm": 1.1946194171905518,
      "learning_rate": 0.00012,
      "loss": 1.4196,
      "step": 6
    },
    {
      "epoch": 0.016706443914081145,
      "grad_norm": 0.7819809913635254,
      "learning_rate": 0.00014,
      "loss": 1.1684,
      "step": 7
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 0.698846161365509,
      "learning_rate": 0.00016,
      "loss": 1.1637,
      "step": 8
    },
    {
      "epoch": 0.021479713603818614,
      "grad_norm": 0.8251622915267944,
      "learning_rate": 0.00018,
      "loss": 1.284,
      "step": 9
    },
    {
      "epoch": 0.02386634844868735,
      "grad_norm": 0.3362489640712738,
      "learning_rate": 0.0002,
      "loss": 0.3899,
      "step": 10
    },
    {
      "epoch": 0.02386634844868735,
      "eval_loss": 1.0437217950820923,
      "eval_runtime": 52.5447,
      "eval_samples_per_second": 3.369,
      "eval_steps_per_second": 1.694,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5637488844472320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}