checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.1020408163265305,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7943333333333333,
      "eval_f1": 0.7930526774486847,
      "eval_loss": 0.5377587080001831,
      "eval_runtime": 3.0956,
      "eval_samples_per_second": 969.112,
      "eval_steps_per_second": 3.876,
      "step": 98
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.838,
      "eval_f1": 0.8378349608143602,
      "eval_loss": 0.47621798515319824,
      "eval_runtime": 3.0912,
      "eval_samples_per_second": 970.483,
      "eval_steps_per_second": 3.882,
      "step": 196
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.851,
      "eval_f1": 0.8511510805118198,
      "eval_loss": 0.4523032605648041,
      "eval_runtime": 3.1117,
      "eval_samples_per_second": 964.094,
      "eval_steps_per_second": 3.856,
      "step": 294
    },
    {
      "epoch": 3.98,
      "learning_rate": 3.344671201814059e-05,
      "loss": 0.3853,
      "step": 390
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8576666666666667,
      "eval_f1": 0.8573781508901815,
      "eval_loss": 0.4846896529197693,
      "eval_runtime": 3.0975,
      "eval_samples_per_second": 968.515,
      "eval_steps_per_second": 3.874,
      "step": 392
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8583333333333333,
      "eval_f1": 0.8581937288721457,
      "eval_loss": 0.5415525436401367,
      "eval_runtime": 3.0931,
      "eval_samples_per_second": 969.891,
      "eval_steps_per_second": 3.88,
      "step": 490
    }
  ],
  "logging_steps": 390,
  "max_steps": 980,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6554710240470000.0,
  "trial_name": null,
  "trial_params": null
}