trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 1.3545468190942493,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.5496,
      "mean_token_accuracy": 0.8319763600826263,
      "num_tokens": 818989.0,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.1667092027460337,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.5682,
      "mean_token_accuracy": 0.8255345612764359,
      "num_tokens": 1639216.0,
      "step": 20
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.1097172351640952,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.5692,
      "mean_token_accuracy": 0.8248896270990371,
      "num_tokens": 2463909.0,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.063402063268306,
      "learning_rate": 0.0,
      "loss": 0.5601,
      "mean_token_accuracy": 0.8281995952129364,
      "num_tokens": 3286234.0,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8214189834240.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}