trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.57,
      "grad_norm": 0.6077275276184082,
      "learning_rate": 1.948074025402493e-05,
      "loss": 0.5215,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "step": 1750,
      "total_flos": 3.3565659451244544e+17,
      "train_loss": 0.5047183837890625,
      "train_runtime": 18395.9977,
      "train_samples_per_second": 0.381,
      "train_steps_per_second": 0.095
    }
  ],
  "logging_steps": 1000,
  "max_steps": 1750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 3.3565659451244544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}