{
  "best_metric": 0.7696604439217992,
  "best_model_checkpoint": "./hatebert_finetuned_v5/checkpoint-1000",
  "epoch": 0.12532898859506203,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06266449429753101,
      "grad_norm": 2.7858245372772217,
      "learning_rate": 4.160401002506266e-06,
      "loss": 0.5658,
      "step": 500
    },
    {
      "epoch": 0.12532898859506203,
      "grad_norm": 0.6836428642272949,
      "learning_rate": 8.320802005012531e-06,
      "loss": 0.3394,
      "step": 1000
    },
    {
      "epoch": 0.12532898859506203,
      "eval_accuracy": 0.9509008303305656,
      "eval_f1": 0.7696604439217992,
      "eval_loss": 0.3321492373943329,
      "eval_optimal_threshold": 0.7856788039207458,
      "eval_runtime": 24.5664,
      "eval_samples_per_second": 1299.13,
      "eval_steps_per_second": 40.625,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 23937,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}