trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4444444444444444,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 14.32094669342041,
      "learning_rate": 9.734513274336284e-06,
      "loss": 6.813,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 16.18659210205078,
      "learning_rate": 9.43952802359882e-06,
      "loss": 6.5747,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 6.325502395629883,
      "learning_rate": 9.144542772861357e-06,
      "loss": 6.1611,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 8.064691543579102,
      "learning_rate": 8.849557522123895e-06,
      "loss": 6.0259,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 5.3117876052856445,
      "learning_rate": 8.554572271386432e-06,
      "loss": 5.7028,
      "step": 50
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 5.456820011138916,
      "eval_runtime": 193.0,
      "eval_samples_per_second": 0.518,
      "eval_steps_per_second": 0.259,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 339,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 435235061760000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}