checkpoint-25/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.9920000000000002e-05,
      "loss": 2.3122,
      "step": 1
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.896e-05,
      "loss": 2.2992,
      "step": 13
    },
    {
      "epoch": 0.52,
      "eval_accuracy": 0.1,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.785266876220703,
      "eval_f1": 0.018181818181818184,
      "eval_gpu_ram_allocated": 2.091515064239502,
      "eval_gpu_ram_cached": 24.6484375,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 50,
      "eval_loss": 2.303118944168091,
      "eval_precision": 0.01,
      "eval_recall": 0.1,
      "eval_runtime": 0.3632,
      "eval_samples_per_second": 550.672,
      "eval_steps_per_second": 19.274,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 3.9340057373046875,
      "step": 13
    }
  ],
  "max_steps": 250,
  "num_train_epochs": 10,
  "total_flos": 54485323206528.0,
  "trial_name": null,
  "trial_params": null
}