{
  "best_metric": 1.3339548110961914,
  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-1220",
  "epoch": 4.996045413955862,
  "eval_steps": 500,
  "global_step": 1220,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9960454139558618,
      "grad_norm": 0.04875887930393219,
      "learning_rate": 0.0009833333333333332,
      "loss": 1.3837,
      "step": 244
    },
    {
      "epoch": 0.9960454139558618,
      "eval_loss": 1.3716533184051514,
      "eval_runtime": 25.1667,
      "eval_samples_per_second": 32.821,
      "eval_steps_per_second": 16.411,
      "step": 244
    },
    {
      "epoch": 1.9960454139558617,
      "grad_norm": 0.10088465362787247,
      "learning_rate": 0.0009666666666666667,
      "loss": 1.373,
      "step": 488
    },
    {
      "epoch": 1.9960454139558617,
      "eval_loss": 1.3613533973693848,
      "eval_runtime": 25.126,
      "eval_samples_per_second": 32.874,
      "eval_steps_per_second": 16.437,
      "step": 488
    },
    {
      "epoch": 2.9960454139558617,
      "grad_norm": 0.07232648879289627,
      "learning_rate": 0.00095,
      "loss": 1.3631,
      "step": 732
    },
    {
      "epoch": 2.9960454139558617,
      "eval_loss": 1.3529444932937622,
      "eval_runtime": 25.1711,
      "eval_samples_per_second": 32.815,
      "eval_steps_per_second": 16.408,
      "step": 732
    },
    {
      "epoch": 3.9960454139558617,
      "grad_norm": 0.13273808360099792,
      "learning_rate": 0.0009333333333333333,
      "loss": 1.3542,
      "step": 976
    },
    {
      "epoch": 3.9960454139558617,
      "eval_loss": 1.3419935703277588,
      "eval_runtime": 25.2204,
      "eval_samples_per_second": 32.751,
      "eval_steps_per_second": 16.376,
      "step": 976
    },
    {
      "epoch": 4.996045413955862,
      "grad_norm": 0.16875308752059937,
      "learning_rate": 0.0009166666666666666,
      "loss": 1.3448,
      "step": 1220
    },
    {
      "epoch": 4.996045413955862,
      "eval_loss": 1.3339548110961914,
      "eval_runtime": 25.1789,
      "eval_samples_per_second": 32.805,
      "eval_steps_per_second": 16.403,
      "step": 1220
    }
  ],
  "logging_steps": 500,
  "max_steps": 14640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 60,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}