last-checkpoint/trainer_state.json

{
  "best_metric": 4.000585079193115,
  "best_model_checkpoint": "./ES_corlec/checkpoint-4000",
  "epoch": 0.7930214115781126,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 9.914549390452318e-07,
      "loss": 4.6573,
      "step": 500
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.77213170787285e-07,
      "loss": 4.1911,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.62971402529338e-07,
      "loss": 4.1368,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.487296342713911e-07,
      "loss": 4.0957,
      "step": 2000
    },
    {
      "epoch": 0.4,
      "eval_loss": 4.06580114364624,
      "eval_runtime": 962.1135,
      "eval_samples_per_second": 42.075,
      "eval_steps_per_second": 2.631,
      "step": 2000
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.344878660134443e-07,
      "loss": 4.0586,
      "step": 2500
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.202460977554973e-07,
      "loss": 4.022,
      "step": 3000
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.060043294975503e-07,
      "loss": 4.0038,
      "step": 3500
    },
    {
      "epoch": 0.79,
      "learning_rate": 8.917625612396035e-07,
      "loss": 3.9852,
      "step": 4000
    },
    {
      "epoch": 0.79,
      "eval_loss": 4.000585079193115,
      "eval_runtime": 962.3175,
      "eval_samples_per_second": 42.066,
      "eval_steps_per_second": 2.63,
      "step": 4000
    }
  ],
  "max_steps": 35308,
  "num_train_epochs": 7,
  "total_flos": 4899225600000000.0,
  "trial_name": null,
  "trial_params": null
}