trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.179245283018868,
      "grad_norm": 28.103540420532227,
      "learning_rate": 2.410377358490566e-05,
      "loss": 2.2352,
      "step": 500
    },
    {
      "epoch": 2.358490566037736,
      "grad_norm": 16.953514099121094,
      "learning_rate": 1.8207547169811322e-05,
      "loss": 1.5029,
      "step": 1000
    },
    {
      "epoch": 3.5377358490566038,
      "grad_norm": 31.308820724487305,
      "learning_rate": 1.2311320754716983e-05,
      "loss": 1.1127,
      "step": 1500
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 26.33289337158203,
      "learning_rate": 6.415094339622642e-06,
      "loss": 0.7052,
      "step": 2000
    },
    {
      "epoch": 5.89622641509434,
      "grad_norm": 106.1405258178711,
      "learning_rate": 5.188679245283019e-07,
      "loss": 0.2618,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "step": 2544,
      "total_flos": 9479673213373440.0,
      "train_loss": 1.1461569756831762,
      "train_runtime": 6870.8994,
      "train_samples_per_second": 11.828,
      "train_steps_per_second": 0.37
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9479673213373440.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}