checkpoint-1/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.6138832569122314,
      "learning_rate": 0.0001,
      "loss": 2.6929,
      "memory/device_reserved (GiB)": 23.52,
      "memory/max_active (GiB)": 22.98,
      "memory/max_allocated (GiB)": 22.98,
      "step": 1,
      "tokens_per_second_per_gpu": 360.33
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 54457376440320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}