trainer_state.json

{
  "best_metric": 0.9583333333333334,
  "best_model_checkpoint": "JoseVilla/cfe-telmex-classification-finetuned-v3/checkpoint-17",
  "epoch": 2.8235294117647056,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.94,
      "eval_accuracy": 0.8166666666666667,
      "eval_loss": 0.4386190176010132,
      "eval_runtime": 6.5765,
      "eval_samples_per_second": 18.247,
      "eval_steps_per_second": 0.608,
      "step": 8
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6716,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9583333333333334,
      "eval_loss": 0.20470969378948212,
      "eval_runtime": 6.5683,
      "eval_samples_per_second": 18.27,
      "eval_steps_per_second": 0.609,
      "step": 17
    },
    {
      "epoch": 2.35,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.1864,
      "step": 20
    },
    {
      "epoch": 2.82,
      "eval_accuracy": 0.9583333333333334,
      "eval_loss": 0.1664045751094818,
      "eval_runtime": 5.3954,
      "eval_samples_per_second": 22.241,
      "eval_steps_per_second": 0.741,
      "step": 24
    },
    {
      "epoch": 2.82,
      "step": 24,
      "total_flos": 7.58128847422464e+16,
      "train_loss": 0.3779665194451809,
      "train_runtime": 203.0983,
      "train_samples_per_second": 15.909,
      "train_steps_per_second": 0.118
    }
  ],
  "max_steps": 24,
  "num_train_epochs": 3,
  "total_flos": 7.58128847422464e+16,
  "trial_name": null,
  "trial_params": null
}