trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.1016042232513428,
      "learning_rate": 9.957496810072027e-05,
      "loss": 2.6639,
      "step": 33
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.501771330833435,
      "learning_rate": 9.476474187102033e-05,
      "loss": 0.9859,
      "step": 66
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.1652584075927734,
      "learning_rate": 8.508819268854713e-05,
      "loss": 0.6134,
      "step": 99
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.9725931882858276,
      "learning_rate": 7.204877166108152e-05,
      "loss": 0.3789,
      "step": 132
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.272465229034424,
      "learning_rate": 5.625670365982332e-05,
      "loss": 0.2299,
      "step": 165
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.3849730491638184,
      "learning_rate": 3.9784476690683085e-05,
      "loss": 0.1512,
      "step": 198
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5065215229988098,
      "learning_rate": 2.4422767362814043e-05,
      "loss": 0.0885,
      "step": 231
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.9854081273078918,
      "learning_rate": 1.184152920597028e-05,
      "loss": 0.0634,
      "step": 264
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.8770450353622437,
      "learning_rate": 3.4084539672271764e-06,
      "loss": 0.0461,
      "step": 297
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.49316543340682983,
      "learning_rate": 4.029143406262259e-08,
      "loss": 0.0412,
      "step": 330
    }
  ],
  "logging_steps": 500,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 920382499768320.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}