trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2247,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.67,
      "grad_norm": 19.199373245239258,
      "learning_rate": 3.887405429461504e-05,
      "loss": 5.3472,
      "step": 500
    },
    {
      "epoch": 1.34,
      "grad_norm": 3.351874589920044,
      "learning_rate": 2.774810858923009e-05,
      "loss": 3.2429,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.8240840435028076,
      "learning_rate": 1.6622162883845125e-05,
      "loss": 2.4001,
      "step": 1500
    },
    {
      "epoch": 2.67,
      "grad_norm": 3.5159881114959717,
      "learning_rate": 5.4962171784601695e-06,
      "loss": 1.7989,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "step": 2247,
      "total_flos": 6.282668952178917e+18,
      "train_loss": 3.034465251628908,
      "train_runtime": 6532.7764,
      "train_samples_per_second": 21.994,
      "train_steps_per_second": 0.344
    }
  ],
  "logging_steps": 500,
  "max_steps": 2247,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 6.282668952178917e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}