checkpoint-354/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 354,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42462845010615713,
      "grad_norm": 0.7648019194602966,
      "learning_rate": 4.307909604519774e-05,
      "loss": 4.6549,
      "step": 50
    },
    {
      "epoch": 0.8492569002123143,
      "grad_norm": 0.2843627333641052,
      "learning_rate": 3.601694915254237e-05,
      "loss": 0.2552,
      "step": 100
    },
    {
      "epoch": 1.2717622080679405,
      "grad_norm": 0.31124347448349,
      "learning_rate": 2.895480225988701e-05,
      "loss": 0.2166,
      "step": 150
    },
    {
      "epoch": 1.6963906581740975,
      "grad_norm": 0.323591411113739,
      "learning_rate": 2.189265536723164e-05,
      "loss": 0.2091,
      "step": 200
    },
    {
      "epoch": 2.118895966029724,
      "grad_norm": 0.34488922357559204,
      "learning_rate": 1.4830508474576272e-05,
      "loss": 0.1913,
      "step": 250
    },
    {
      "epoch": 2.543524416135881,
      "grad_norm": 0.37014636397361755,
      "learning_rate": 7.768361581920905e-06,
      "loss": 0.1855,
      "step": 300
    },
    {
      "epoch": 2.968152866242038,
      "grad_norm": 0.3245241940021515,
      "learning_rate": 7.062146892655367e-07,
      "loss": 0.1882,
      "step": 350
    }
  ],
  "logging_steps": 50,
  "max_steps": 354,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7663655067844608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}