trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 7,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": NaN,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 2.1348,
      "eval_samples_per_second": 0.468,
      "eval_steps_per_second": 0.468,
      "step": 7
    },
    {
      "epoch": 1.0,
      "step": 7,
      "total_flos": 54979878453248.0,
      "train_loss": 0.0,
      "train_runtime": 98.4374,
      "train_samples_per_second": 1.016,
      "train_steps_per_second": 0.071
    }
  ],
  "logging_steps": 1,
  "max_steps": 7,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 54979878453248.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}