checkpoint-250/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.999466666666667e-05,
      "loss": 2.308,
      "step": 1
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8997333333333335e-05,
      "loss": 1.6916,
      "step": 188
    },
    {
      "epoch": 0.75,
      "eval_accuracy": 0.6755,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.806385040283203,
      "eval_f1": 0.6708054417489328,
      "eval_gpu_ram_allocated": 2.089780330657959,
      "eval_gpu_ram_cached": 25.85546875,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 50,
      "eval_loss": 1.1062816381454468,
      "eval_precision": 0.690043017889279,
      "eval_recall": 0.6755,
      "eval_runtime": 2.3912,
      "eval_samples_per_second": 836.398,
      "eval_steps_per_second": 26.347,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 4.019077301025391,
      "step": 188
    }
  ],
  "max_steps": 3750,
  "num_train_epochs": 15,
  "total_flos": 478954442421888.0,
  "trial_name": null,
  "trial_params": null
}