trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3733,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1339405304045004,
      "grad_norm": 20.019311904907227,
      "learning_rate": 1.925573087228342e-05,
      "loss": 0.6476,
      "step": 500
    },
    {
      "epoch": 0.2678810608090008,
      "grad_norm": 15.345267295837402,
      "learning_rate": 1.627865436141709e-05,
      "loss": 0.4459,
      "step": 1000
    },
    {
      "epoch": 0.4018215912135012,
      "grad_norm": 10.613130569458008,
      "learning_rate": 1.330157785055076e-05,
      "loss": 0.3806,
      "step": 1500
    },
    {
      "epoch": 0.5357621216180016,
      "grad_norm": 6.42950439453125,
      "learning_rate": 1.0324501339684432e-05,
      "loss": 0.356,
      "step": 2000
    },
    {
      "epoch": 0.669702652022502,
      "grad_norm": 11.147576332092285,
      "learning_rate": 7.347424828818102e-06,
      "loss": 0.3135,
      "step": 2500
    },
    {
      "epoch": 0.8036431824270024,
      "grad_norm": 6.7693047523498535,
      "learning_rate": 4.370348317951772e-06,
      "loss": 0.304,
      "step": 3000
    },
    {
      "epoch": 0.9375837128315028,
      "grad_norm": 8.816291809082031,
      "learning_rate": 1.3932718070854423e-06,
      "loss": 0.2765,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 3733,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}