trainer_state.json

{
  "best_metric": 0.8544235229492188,
  "best_model_checkpoint": "beto-SDS-long-esp-mchoice/checkpoint-5547",
  "epoch": 1.0,
  "global_step": 5547,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 4.774652965566974e-05,
      "loss": 0.7789,
      "step": 500
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.549305931133946e-05,
      "loss": 0.6927,
      "step": 1000
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.32395889670092e-05,
      "loss": 0.6155,
      "step": 1500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.0986118622678924e-05,
      "loss": 0.6213,
      "step": 2000
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.873264827834866e-05,
      "loss": 0.5896,
      "step": 2500
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.647917793401839e-05,
      "loss": 0.5446,
      "step": 3000
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.422570758968812e-05,
      "loss": 0.5276,
      "step": 3500
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.197223724535785e-05,
      "loss": 0.5183,
      "step": 4000
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.9718766901027585e-05,
      "loss": 0.5084,
      "step": 4500
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.746529655669732e-05,
      "loss": 0.5032,
      "step": 5000
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5211826212367046e-05,
      "loss": 0.4839,
      "step": 5500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8544235229492188,
      "eval_loss": 0.4278242290019989,
      "eval_runtime": 63.6742,
      "eval_samples_per_second": 72.604,
      "eval_steps_per_second": 12.109,
      "step": 5547
    }
  ],
  "max_steps": 11094,
  "num_train_epochs": 2,
  "total_flos": 4307533300198464.0,
  "trial_name": null,
  "trial_params": null
}