trainer_state.json

{
  "best_metric": 0.1700817346572876,
  "best_model_checkpoint": "./models/results_unfun_me_693/checkpoint-15",
  "epoch": 0.7643312101910829,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "eval_accuracy": 0.5977653631284916,
      "eval_f1": 0.0,
      "eval_loss": 0.49542680382728577,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.6005,
      "eval_samples_per_second": 111.84,
      "eval_steps_per_second": 14.37,
      "step": 5
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.8947368421052634e-05,
      "loss": 0.5957,
      "step": 8
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.8994413407821229,
      "eval_f1": 0.888888888888889,
      "eval_loss": 0.23239067196846008,
      "eval_precision": 0.8,
      "eval_recall": 1.0,
      "eval_runtime": 1.6096,
      "eval_samples_per_second": 111.21,
      "eval_steps_per_second": 14.29,
      "step": 10
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.9162011173184358,
      "eval_f1": 0.9056603773584906,
      "eval_loss": 0.1700817346572876,
      "eval_precision": 0.8275862068965517,
      "eval_recall": 1.0,
      "eval_runtime": 1.6469,
      "eval_samples_per_second": 108.686,
      "eval_steps_per_second": 13.965,
      "step": 15
    }
  ],
  "max_steps": 19,
  "num_train_epochs": 1,
  "total_flos": 34039992787200.0,
  "trial_name": null,
  "trial_params": null
}