checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 16.068714141845703,
      "learning_rate": 1.9749279121818235e-05,
      "loss": 3.8588,
      "mean_token_accuracy": 0.4894747719168663,
      "num_tokens": 9055.0,
      "step": 5
    },
    {
      "epoch": 1.0,
      "grad_norm": 9.082130432128906,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 3.7874,
      "mean_token_accuracy": 0.48474713787436485,
      "num_tokens": 15888.0,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.2974560260772705,
      "eval_mean_token_accuracy": 0.5215695897738138,
      "eval_num_tokens": 15888.0,
      "eval_runtime": 0.4278,
      "eval_samples_per_second": 49.086,
      "eval_steps_per_second": 7.012,
      "step": 10
    }
  ],
  "logging_steps": 5,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 9925838106624.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}