{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 754,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13262599469496023,
      "grad_norm": 21.097429275512695,
      "learning_rate": 1.73474801061008e-05,
      "loss": 0.0817,
      "step": 100
    },
    {
      "epoch": 0.13262599469496023,
      "eval_accuracy": 0.869792531120332,
      "eval_exact_match": 0.7966805100440979,
      "eval_f1": 0.8265865023267873,
      "eval_loss": 0.8273831605911255,
      "eval_runtime": 77.717,
      "eval_samples_per_second": 155.05,
      "eval_steps_per_second": 2.432,
      "step": 100
    },
    {
      "epoch": 0.26525198938992045,
      "grad_norm": 8.12032699584961,
      "learning_rate": 1.4694960212201592e-05,
      "loss": 0.6049,
      "step": 200
    },
    {
      "epoch": 0.26525198938992045,
      "eval_accuracy": 0.8897095435684648,
      "eval_exact_match": 0.8233194947242737,
      "eval_f1": 0.8582754375863904,
      "eval_loss": 0.46533215045928955,
      "eval_runtime": 77.7446,
      "eval_samples_per_second": 154.995,
      "eval_steps_per_second": 2.431,
      "step": 200
    },
    {
      "epoch": 0.3978779840848806,
      "grad_norm": 8.341373443603516,
      "learning_rate": 1.2042440318302389e-05,
      "loss": 0.5368,
      "step": 300
    },
    {
      "epoch": 0.3978779840848806,
      "eval_accuracy": 0.8922821576763486,
      "eval_exact_match": 0.8272199034690857,
      "eval_f1": 0.8665420024034713,
      "eval_loss": 0.4373999834060669,
      "eval_runtime": 77.7756,
      "eval_samples_per_second": 154.933,
      "eval_steps_per_second": 2.43,
      "step": 300
    },
    {
      "epoch": 0.5305039787798409,
      "grad_norm": 7.795539379119873,
      "learning_rate": 9.389920424403184e-06,
      "loss": 0.4667,
      "step": 400
    },
    {
      "epoch": 0.5305039787798409,
      "eval_accuracy": 0.8947717842323651,
      "eval_exact_match": 0.8323651552200317,
      "eval_f1": 0.8640837391100382,
      "eval_loss": 0.42141905426979065,
      "eval_runtime": 77.8395,
      "eval_samples_per_second": 154.806,
      "eval_steps_per_second": 2.428,
      "step": 400
    },
    {
      "epoch": 0.6631299734748011,
      "grad_norm": 7.433889389038086,
      "learning_rate": 6.737400530503979e-06,
      "loss": 0.4562,
      "step": 500
    },
    {
      "epoch": 0.6631299734748011,
      "eval_accuracy": 0.9021576763485477,
      "eval_exact_match": 0.8416597247123718,
      "eval_f1": 0.8720677794061028,
      "eval_loss": 0.40394431352615356,
      "eval_runtime": 77.7908,
      "eval_samples_per_second": 154.903,
      "eval_steps_per_second": 2.43,
      "step": 500
    },
    {
      "epoch": 0.7957559681697612,
      "grad_norm": 7.736847877502441,
      "learning_rate": 4.084880636604775e-06,
      "loss": 0.4531,
      "step": 600
    },
    {
      "epoch": 0.7957559681697612,
      "eval_accuracy": 0.9040663900414938,
      "eval_exact_match": 0.8449792265892029,
      "eval_f1": 0.8772518788024197,
      "eval_loss": 0.39679694175720215,
      "eval_runtime": 77.7628,
      "eval_samples_per_second": 154.958,
      "eval_steps_per_second": 2.43,
      "step": 600
    },
    {
      "epoch": 0.9283819628647215,
      "grad_norm": 9.126861572265625,
      "learning_rate": 1.4323607427055705e-06,
      "loss": 0.4251,
      "step": 700
    },
    {
      "epoch": 0.9283819628647215,
      "eval_accuracy": 0.9044813278008299,
      "eval_exact_match": 0.8445643186569214,
      "eval_f1": 0.8783158736794041,
      "eval_loss": 0.39353764057159424,
      "eval_runtime": 77.7653,
      "eval_samples_per_second": 154.953,
      "eval_steps_per_second": 2.43,
      "step": 700
    }
  ],
  "logging_steps": 100,
  "max_steps": 754,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2594242377918464e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}