checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.251414204902577,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 8.985917667125256e-06,
      "loss": 0.4081,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.943758807211778e-06,
      "loss": 0.2059,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.873787284747973e-06,
      "loss": 0.1613,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.776441038520995e-06,
      "loss": 0.1359,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.652329340639053e-06,
      "loss": 0.1794,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.502228983210244e-06,
      "loss": 0.1471,
      "step": 60
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.327079416544763e-06,
      "loss": 0.1173,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.127976869309567e-06,
      "loss": 0.1016,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.906167487436374e-06,
      "loss": 0.1486,
      "step": 90
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.663039534725309e-06,
      "loss": 0.1029,
      "step": 100
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1548028089336526e-09,
      "eval_runtime": 31.6494,
      "eval_samples_per_second": 89.354,
      "eval_steps_per_second": 11.185,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 397,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}