{
  "best_metric": 0.8532171581769437,
  "best_model_checkpoint": "deberta-classification-chatrag/checkpoint-4228",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6342,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24,
      "learning_rate": 9.211605171870073e-06,
      "loss": 0.4251,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.423210343740146e-06,
      "loss": 0.3842,
      "step": 1000
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.634815515610218e-06,
      "loss": 0.3502,
      "step": 1500
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.846420687480291e-06,
      "loss": 0.334,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8458445040214477,
      "eval_f1": 0.8458445040214477,
      "eval_loss": 0.37406206130981445,
      "eval_roc_auc": 0.846812946081549,
      "eval_runtime": 22.7345,
      "eval_samples_per_second": 65.627,
      "eval_steps_per_second": 8.225,
      "step": 2114
    },
    {
      "epoch": 1.18,
      "learning_rate": 6.058025859350363e-06,
      "loss": 0.3267,
      "step": 2500
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.269631031220436e-06,
      "loss": 0.3134,
      "step": 3000
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.4812362030905085e-06,
      "loss": 0.3171,
      "step": 3500
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.6928413749605807e-06,
      "loss": 0.3197,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8532171581769437,
      "eval_f1": 0.8532171581769437,
      "eval_loss": 0.42327263951301575,
      "eval_roc_auc": 0.8199641368101195,
      "eval_runtime": 22.432,
      "eval_samples_per_second": 66.512,
      "eval_steps_per_second": 8.336,
      "step": 4228
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.904446546830653e-06,
      "loss": 0.3166,
      "step": 4500
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.1160517187007253e-06,
      "loss": 0.2854,
      "step": 5000
    },
    {
      "epoch": 2.6,
      "learning_rate": 1.3276568905707978e-06,
      "loss": 0.29,
      "step": 5500
    },
    {
      "epoch": 2.84,
      "learning_rate": 5.392620624408705e-07,
      "loss": 0.2915,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8525469168900804,
      "eval_f1": 0.8525469168900803,
      "eval_loss": 0.4641505181789398,
      "eval_roc_auc": 0.8244735354391916,
      "eval_runtime": 22.4686,
      "eval_samples_per_second": 66.404,
      "eval_steps_per_second": 8.323,
      "step": 6342
    }
  ],
  "logging_steps": 500,
  "max_steps": 6342,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.3345375348952064e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}